chore: v4.0.3

Currently translated at 98.4% (1108 of 1126 strings)

Co-authored-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translation: InvokeAI/Web UI

.github/actions/install-frontend-deps/action.yml

@@ -0,0 +1,33 @@
+name: install frontend dependencies
+description: Installs frontend dependencies with pnpm, with caching
+runs:
+  using: 'composite'
+  steps:
+    - name: setup node 18
+      uses: actions/setup-node@v4
+      with:
+        node-version: '18'
+
+    - name: setup pnpm
+      uses: pnpm/action-setup@v2
+      with:
+        version: 8
+        run_install: false
+
+    - name: get pnpm store directory
+      shell: bash
+      run: |
+        echo "STORE_PATH=$(pnpm store path --silent)" >> $GITHUB_ENV
+
+    - name: setup cache
+      uses: actions/cache@v4
+      with:
+        path: ${{ env.STORE_PATH }}
+        key: ${{ runner.os }}-pnpm-store-${{ hashFiles('**/pnpm-lock.yaml') }}
+        restore-keys: |
+          ${{ runner.os }}-pnpm-store-
+
+    - name: install frontend dependencies
+      run: pnpm install --prefer-frozen-lockfile
+      shell: bash
+      working-directory: invokeai/frontend/web

.github/pr_labels.yml

@@ -1,59 +1,59 @@
-Root:
+root:
 - changed-files:
   - any-glob-to-any-file: '*'
 
-PythonDeps:
+python-deps:
 - changed-files:
   - any-glob-to-any-file: 'pyproject.toml'
 
-Python:
+python:
 - changed-files:
   - all-globs-to-any-file: 
     - 'invokeai/**'
     - '!invokeai/frontend/web/**'
 
-PythonTests:
+python-tests:
 - changed-files:
   - any-glob-to-any-file: 'tests/**'
 
-CICD:
+ci-cd:
 - changed-files:
   - any-glob-to-any-file: .github/**
 
-Docker:
+docker:
 - changed-files:
   - any-glob-to-any-file: docker/**
 
-Installer:
+installer:
 - changed-files:
   - any-glob-to-any-file: installer/**
 
-Documentation:
+docs:
 - changed-files:
   - any-glob-to-any-file: docs/**
 
-Invocations:
+invocations:
 - changed-files:
   - any-glob-to-any-file: 'invokeai/app/invocations/**'
 
-Backend:
+backend:
 - changed-files:
   - any-glob-to-any-file: 'invokeai/backend/**'
 
-Api:
+api:
 - changed-files:
   - any-glob-to-any-file: 'invokeai/app/api/**'
 
-Services:
+services:
 - changed-files:
   - any-glob-to-any-file: 'invokeai/app/services/**'
 
-FrontendDeps:
+frontend-deps:
 - changed-files:
   - any-glob-to-any-file:
     - '**/*/package.json'
     - '**/*/pnpm-lock.yaml'
 
-Frontend:
+frontend:
 - changed-files:
   - any-glob-to-any-file: 'invokeai/frontend/web/**'

.github/pull_request_template.md

@@ -1,66 +1,21 @@
-## What type of PR is this? (check all applicable)
+## Summary
 
-- [ ] Refactor
-- [ ] Feature
-- [ ] Bug Fix
-- [ ] Optimization
-- [ ] Documentation Update
-- [ ] Community Node Submission
+<!--A description of the changes in this PR. Include the kind of change (fix, feature, docs, etc), the "why" and the "how". Screenshots or videos are useful for frontend changes.-->
 
+## Related Issues / Discussions
 
-## Have you discussed this change with the InvokeAI team?
-- [ ] Yes
-- [ ] No, because:
+<!--WHEN APPLICABLE: List any related issues or discussions on github or discord. If this PR closes an issue, please use the "Closes #1234" format, so that the issue will be automatically closed when the PR merges.-->
 
-      
-## Have you updated all relevant documentation?
-- [ ] Yes
-- [ ] No
+## QA Instructions
 
-
-## Description
-
-
-## Related Tickets & Documents
-
-<!--
-For pull requests that relate or close an issue, please include them
-below. 
-
-For example having the text: "closes #1234" would connect the current pull
-request to issue 1234.  And when we merge the pull request, Github will
-automatically close the issue.
--->
-
-- Related Issue #
-- Closes #
-
-## QA Instructions, Screenshots, Recordings
-
-<!-- 
-Please provide steps on how to test changes, any hardware or 
-software specifications as well as any other pertinent information. 
--->
+<!--WHEN APPLICABLE: Describe how we can test the changes in this PR.-->
 
 ## Merge Plan
 
-<!--
-A merge plan describes how this PR should be handled after it is approved.
+<!--WHEN APPLICABLE: Large PRs, or PRs that touch sensitive things like DB schemas, may need some care when merging. For example, a careful rebase by the change author, timing to not interfere with a pending release, or a message to contributors on discord after merging.-->
 
-Example merge plans:
-- "This PR can be merged when approved"
-- "This must be squash-merged when approved"
-- "DO NOT MERGE - I will rebase and tidy commits before merging"
-- "#dev-chat on discord needs to be advised of this change when it is merged"
+## Checklist
 
-A merge plan is particularly important for large PRs or PRs that touch the
-database in any way.
--->
-
-## Added/updated tests?
-
-- [ ] Yes
-- [ ] No : _please replace this line with details on why tests
-      have not been included_
-
-## [optional] Are there any post deployment tasks we need to perform?
+- [ ] _The PR has a short but descriptive title, suitable for a changelog_
+- [ ] _Tests added / updated (if applicable)_
+- [ ] _Documentation added / updated (if applicable)_

.github/workflows/build-container.yml

@@ -11,7 +11,7 @@ on:
       - 'docker/docker-entrypoint.sh'
       - 'workflows/build-container.yml'
     tags:
-      - 'v*'
+      - 'v*.*.*'
   workflow_dispatch:
 
 permissions:

.github/workflows/build-installer.yml

@@ -0,0 +1,45 @@
+# Builds and uploads the installer and python build artifacts.
+
+name: build installer
+
+on:
+  workflow_dispatch:
+  workflow_call:
+
+jobs:
+  build-installer:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5 # expected run time: <2 min
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: setup python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          cache: pip
+          cache-dependency-path: pyproject.toml
+
+      - name: install pypa/build
+        run: pip install --upgrade build
+
+      - name: setup frontend
+        uses: ./.github/actions/install-frontend-deps
+
+      - name: create installer
+        id: create_installer
+        run: ./create_installer.sh
+        working-directory: installer
+
+      - name: upload python distribution artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: ${{ steps.create_installer.outputs.DIST_PATH }}
+
+      - name: upload installer artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: installer
+          path: ${{ steps.create_installer.outputs.INSTALLER_PATH }}

.github/workflows/frontend-checks.yml

@@ -0,0 +1,80 @@
+# Runs frontend code quality checks.
+#
+# Checks for changes to frontend files before running the checks.
+# If always_run is true, always runs the checks.
+
+name: 'frontend checks'
+
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+    inputs:
+      always_run:
+        description: 'Always run the checks'
+        required: true
+        type: boolean
+        default: true
+  workflow_call:
+    inputs:
+      always_run:
+        description: 'Always run the checks'
+        required: true
+        type: boolean
+        default: true
+
+defaults:
+  run:
+    working-directory: invokeai/frontend/web
+
+jobs:
+  frontend-checks:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10 # expected run time: <2 min
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: check for changed frontend files
+        if: ${{ inputs.always_run != true }}
+        id: changed-files
+        uses: tj-actions/changed-files@v42
+        with:
+          files_yaml: |
+            frontend:
+              - 'invokeai/frontend/web/**'
+
+      - name: install dependencies
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        uses: ./.github/actions/install-frontend-deps
+
+      - name: tsc
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:tsc'
+        shell: bash
+
+      - name: dpdm
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:dpdm'
+        shell: bash
+
+      - name: eslint
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:eslint'
+        shell: bash
+
+      - name: prettier
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:prettier'
+        shell: bash
+
+      - name: knip
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:knip'
+        shell: bash

.github/workflows/frontend-tests.yml

@@ -0,0 +1,60 @@
+# Runs frontend tests.
+#
+# Checks for changes to frontend files before running the tests.
+# If always_run is true, always runs the tests.
+
+name: 'frontend tests'
+
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+    inputs:
+      always_run:
+        description: 'Always run the tests'
+        required: true
+        type: boolean
+        default: true
+  workflow_call:
+    inputs:
+      always_run:
+        description: 'Always run the tests'
+        required: true
+        type: boolean
+        default: true
+
+defaults:
+  run:
+    working-directory: invokeai/frontend/web
+
+jobs:
+  frontend-tests:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10 # expected run time: <2 min
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: check for changed frontend files
+        if: ${{ inputs.always_run != true }}
+        id: changed-files
+        uses: tj-actions/changed-files@v42
+        with:
+          files_yaml: |
+            frontend:
+              - 'invokeai/frontend/web/**'
+
+      - name: install dependencies
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        uses: ./.github/actions/install-frontend-deps
+
+      - name: vitest
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm test:no-watch'
+        shell: bash

.github/workflows/label-pr.yml

@@ -1,6 +1,6 @@
-name: "Pull Request Labeler"
+name: 'label PRs'
 on:
-- pull_request_target
+  - pull_request_target
 
 jobs:
   labeler:
@@ -9,8 +9,10 @@ jobs:
       pull-requests: write
     runs-on: ubuntu-latest
     steps:
-      - name: Checkout
+      - name: checkout
         uses: actions/checkout@v4
-      - uses: actions/labeler@v5
+
+      - name: label PRs
+        uses: actions/labeler@v5
         with:
-          configuration-path: .github/pr_labels.yml
+          configuration-path: .github/pr_labels.yml

.github/workflows/lint-frontend.yml

@@ -1,43 +0,0 @@
-name: Lint frontend
-
-on:
-  pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  push:
-    branches:
-      - 'main'
-  merge_group:
-  workflow_dispatch:
-
-defaults:
-  run:
-    working-directory: invokeai/frontend/web
-
-jobs:
-  lint-frontend:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-22.04
-    steps:
-      - name: Setup Node 18
-        uses: actions/setup-node@v4
-        with:
-          node-version: '18'
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Setup pnpm
-        uses: pnpm/action-setup@v2
-        with:
-          version: '8.12.1'
-      - name: Install dependencies
-        run: 'pnpm install --prefer-frozen-lockfile'
-      - name: Typescript
-        run: 'pnpm run lint:tsc'
-      - name: Madge
-        run: 'pnpm run lint:madge'
-      - name: ESLint
-        run: 'pnpm run lint:eslint'
-      - name: Prettier
-        run: 'pnpm run lint:prettier'

.github/workflows/mkdocs-material.yml

@@ -1,51 +1,49 @@
-name: mkdocs-material
+# This is a mostly a copy-paste from https://github.com/squidfunk/mkdocs-material/blob/master/docs/publishing-your-site.md
+
+name: mkdocs
+
 on:
   push:
     branches:
-      - 'refs/heads/main'
+      - main
+  workflow_dispatch:
 
 permissions:
-    contents: write
+  contents: write
 
 jobs:
-  mkdocs-material:
+  deploy:
     if: github.event.pull_request.draft == false
     runs-on: ubuntu-latest
     env:
       REPO_URL: '${{ github.server_url }}/${{ github.repository }}'
       REPO_NAME: '${{ github.repository }}'
       SITE_URL: 'https://${{ github.repository_owner }}.github.io/InvokeAI'
+
     steps:
-      - name: checkout sources
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
+      - name: checkout
+        uses: actions/checkout@v4
 
       - name: setup python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: '3.10'
           cache: pip
           cache-dependency-path: pyproject.toml
 
-      - name: install requirements
-        env:
-          PIP_USE_PEP517: 1
-        run: |
-          python -m \
-            pip install ".[docs]"
+      - name: set cache id
+        run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
 
-      - name: confirm buildability
-        run: |
-          python -m \
-            mkdocs build \
-            --clean \
-            --verbose
+      - name: use cache
+        uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
 
-      - name: deploy to gh-pages
-        if: ${{ github.ref == 'refs/heads/main' }}
-        run: |
-          python -m \
-            mkdocs gh-deploy \
-            --clean \
-            --force
+      - name: install dependencies
+        run: python -m pip install ".[docs]"
+
+      - name: build & deploy
+        run: mkdocs gh-deploy --force

.github/workflows/pypi-release.yml

@@ -1,67 +0,0 @@
-name: PyPI Release
-
-on:
-  workflow_dispatch:
-    inputs:
-      publish_package:
-        description: 'Publish build on PyPi? [true/false]'
-        required: true
-        default: 'false'
-
-jobs:
-  build-and-release:
-    if: github.repository == 'invoke-ai/InvokeAI'
-    runs-on: ubuntu-22.04
-    env:
-      TWINE_USERNAME: __token__
-      TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
-      TWINE_NON_INTERACTIVE: 1
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Setup Node 18
-        uses: actions/setup-node@v4
-        with:
-          node-version: '18'
-
-      - name: Setup pnpm
-        uses: pnpm/action-setup@v2
-        with:
-          version: '8.12.1'
-
-      - name: Install frontend dependencies
-        run: pnpm install --prefer-frozen-lockfile
-        working-directory: invokeai/frontend/web
-
-      - name: Build frontend
-        run: pnpm run build
-        working-directory: invokeai/frontend/web
-
-      - name: Install python dependencies
-        run: pip install --upgrade build twine
-
-      - name: Build python package
-        run: python3 -m build
-
-      - name: Upload build as workflow artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: dist
-          path: dist
-
-      - name: Check distribution
-        run: twine check dist/*
-
-      - name: Check PyPI versions
-        if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
-        run: |
-          pip install --upgrade requests
-          python -c "\
-          import scripts.pypi_helper; \
-          EXISTS=scripts.pypi_helper.local_on_pypi(); \
-          print(f'PACKAGE_EXISTS={EXISTS}')" >> $GITHUB_ENV
-
-      - name: Publish build on PyPi
-        if: env.PACKAGE_EXISTS == 'False' && env.TWINE_PASSWORD != '' && github.event.inputs.publish_package == 'true'
-        run: twine upload dist/*

.github/workflows/python-checks.yml

@@ -0,0 +1,76 @@
+# Runs python code quality checks.
+#
+# Checks for changes to python files before running the checks.
+# If always_run is true, always runs the checks.
+#
+# TODO: Add mypy or pyright to the checks.
+
+name: 'python checks'
+
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+    inputs:
+      always_run:
+        description: 'Always run the checks'
+        required: true
+        type: boolean
+        default: true
+  workflow_call:
+    inputs:
+      always_run:
+        description: 'Always run the checks'
+        required: true
+        type: boolean
+        default: true
+
+jobs:
+  python-checks:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5 # expected run time: <1 min
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: check for changed python files
+        if: ${{ inputs.always_run != true }}
+        id: changed-files
+        uses: tj-actions/changed-files@v42
+        with:
+          files_yaml: |
+            python:
+              - 'pyproject.toml'
+              - 'invokeai/**'
+              - '!invokeai/frontend/web/**'
+              - 'tests/**'
+
+      - name: setup python
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          cache: pip
+          cache-dependency-path: pyproject.toml
+
+      - name: install ruff
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        run: pip install ruff
+        shell: bash
+
+      - name: ruff check
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        run: ruff check --output-format=github .
+        shell: bash
+
+      - name: ruff format
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        run: ruff format --check .
+        shell: bash

.github/workflows/python-tests.yml

@@ -0,0 +1,106 @@
+# Runs python tests on a matrix of python versions and platforms.
+#
+# Checks for changes to python files before running the tests.
+# If always_run is true, always runs the tests.
+
+name: 'python tests'
+
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+    inputs:
+      always_run:
+        description: 'Always run the tests'
+        required: true
+        type: boolean
+        default: true
+  workflow_call:
+    inputs:
+      always_run:
+        description: 'Always run the tests'
+        required: true
+        type: boolean
+        default: true
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  matrix:
+    strategy:
+      matrix:
+        python-version:
+          - '3.10'
+          - '3.11'
+        platform:
+          - linux-cuda-11_7
+          - linux-rocm-5_2
+          - linux-cpu
+          - macos-default
+          - windows-cpu
+        include:
+          - platform: linux-cuda-11_7
+            os: ubuntu-22.04
+            github-env: $GITHUB_ENV
+          - platform: linux-rocm-5_2
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
+            github-env: $GITHUB_ENV
+          - platform: linux-cpu
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/cpu'
+            github-env: $GITHUB_ENV
+          - platform: macos-default
+            os: macOS-12
+            github-env: $GITHUB_ENV
+          - platform: windows-cpu
+            os: windows-2022
+            github-env: $env:GITHUB_ENV
+    name: 'py${{ matrix.python-version }}: ${{ matrix.platform }}'
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 15 # expected run time: 2-6 min, depending on platform
+    env:
+      PIP_USE_PEP517: '1'
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: check for changed python files
+        if: ${{ inputs.always_run != true }}
+        id: changed-files
+        uses: tj-actions/changed-files@v42
+        with:
+          files_yaml: |
+            python:
+              - 'pyproject.toml'
+              - 'invokeai/**'
+              - '!invokeai/frontend/web/**'
+              - 'tests/**'
+
+      - name: setup python
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+          cache-dependency-path: pyproject.toml
+
+      - name: install dependencies
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        env:
+          PIP_EXTRA_INDEX_URL: ${{ matrix.extra-index-url }}
+        run: >
+          pip3 install --editable=".[test]"
+
+      - name: run pytest
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        run: pytest

.github/workflows/release.yml

@@ -0,0 +1,108 @@
+# Main release workflow. Triggered on tag push or manual trigger.
+#
+# - Runs all code checks and tests
+# - Verifies the app version matches the tag version.
+# - Builds the installer and build, uploading them as artifacts.
+# - Publishes to TestPyPI and PyPI. Both are conditional on the previous steps passing and require a manual approval.
+#
+# See docs/RELEASE.md for more information on the release process.
+
+name: release
+
+on:
+  push:
+    tags:
+      - 'v*'
+  workflow_dispatch:
+
+jobs:
+  check-version:
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: check python version
+        uses: samuelcolvin/check-python-version@v4
+        id: check-python-version
+        with:
+          version_file_path: invokeai/version/invokeai_version.py
+
+  frontend-checks:
+    uses: ./.github/workflows/frontend-checks.yml
+    with:
+      always_run: true
+
+  frontend-tests:
+    uses: ./.github/workflows/frontend-tests.yml
+    with:
+      always_run: true
+
+  python-checks:
+    uses: ./.github/workflows/python-checks.yml
+    with:
+      always_run: true
+
+  python-tests:
+    uses: ./.github/workflows/python-tests.yml
+    with:
+      always_run: true
+
+  build:
+    uses: ./.github/workflows/build-installer.yml
+
+  publish-testpypi:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5 # expected run time: <1 min
+    needs:
+      [
+        check-version,
+        frontend-checks,
+        frontend-tests,
+        python-checks,
+        python-tests,
+        build,
+      ]
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/invokeai
+    permissions:
+      id-token: write
+    steps:
+      - name: download distribution from build job
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: publish distribution to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+
+  publish-pypi:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5 # expected run time: <1 min
+    needs:
+      [
+        check-version,
+        frontend-checks,
+        frontend-tests,
+        python-checks,
+        python-tests,
+        build,
+      ]
+    environment:
+      name: pypi
+      url: https://pypi.org/p/invokeai
+    permissions:
+      id-token: write
+    steps:
+      - name: download distribution from build job
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: publish distribution to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/style-checks.yml

@@ -1,24 +0,0 @@
-name: style checks
-
-on:
-  pull_request:
-  push:
-    branches: main
-
-jobs:
-  ruff:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Setup Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.10'
-
-      - name: Install dependencies with pip
-        run: |
-          pip install ruff
-
-      - run: ruff check --output-format=github .
-      - run: ruff format --check .

.github/workflows/test-invoke-pip.yml

@@ -1,129 +0,0 @@
-name: Test invoke.py pip
-on:
-  push:
-    branches:
-      - 'main'
-  pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  merge_group:
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  matrix:
-    if: github.event.pull_request.draft == false
-    strategy:
-      matrix:
-        python-version:
-          # - '3.9'
-          - '3.10'
-        pytorch:
-          - linux-cuda-11_7
-          - linux-rocm-5_2
-          - linux-cpu
-          - macos-default
-          - windows-cpu
-        include:
-          - pytorch: linux-cuda-11_7
-            os: ubuntu-22.04
-            github-env: $GITHUB_ENV
-          - pytorch: linux-rocm-5_2
-            os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
-            github-env: $GITHUB_ENV
-          - pytorch: linux-cpu
-            os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/cpu'
-            github-env: $GITHUB_ENV
-          - pytorch: macos-default
-            os: macOS-12
-            github-env: $GITHUB_ENV
-          - pytorch: windows-cpu
-            os: windows-2022
-            github-env: $env:GITHUB_ENV
-    name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
-    runs-on: ${{ matrix.os }}
-    env:
-      PIP_USE_PEP517: '1'
-    steps:
-      - name: Checkout sources
-        id: checkout-sources
-        uses: actions/checkout@v3
-
-      - name: Check for changed python files
-        id: changed-files
-        uses: tj-actions/changed-files@v41
-        with:
-          files_yaml: |
-            python:
-              - 'pyproject.toml'
-              - 'invokeai/**'
-              - '!invokeai/frontend/web/**'
-              - 'tests/**'
-
-      - name: set test prompt to main branch validation
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
-
-      - name: setup python
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: pip
-          cache-dependency-path: pyproject.toml
-
-      - name: install invokeai
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        env:
-          PIP_EXTRA_INDEX_URL: ${{ matrix.extra-index-url }}
-        run: >
-          pip3 install
-          --editable=".[test]"
-
-      - name: run pytest
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        id: run-pytest
-        run: pytest
-
-      # - name: run invokeai-configure
-      #   env:
-      #     HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
-      #   run: >
-      #     invokeai-configure
-      #     --yes
-      #     --default_only
-      #     --full-precision
-      #   # can't use fp16 weights without a GPU
-
-      # - name: run invokeai
-      #   id: run-invokeai
-      #   env:
-      #     # Set offline mode to make sure configure preloaded successfully.
-      #     HF_HUB_OFFLINE: 1
-      #     HF_DATASETS_OFFLINE: 1
-      #     TRANSFORMERS_OFFLINE: 1
-      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-      #   run: >
-      #     invokeai
-      #     --no-patchmatch
-      #     --no-nsfw_checker
-      #     --precision=float32
-      #     --always_use_cpu
-      #     --use_memory_db
-      #     --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
-      #     --from_file ${{ env.TEST_PROMPTS }}
-
-      # - name: Archive results
-      #   env:
-      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-      #   uses: actions/upload-artifact@v3
-      #   with:
-      #     name: results
-      #     path: ${{ env.INVOKEAI_OUTDIR }}

.prettierrc.yaml

@@ -7,7 +7,7 @@ embeddedLanguageFormatting: auto
 overrides:
   - files: '*.md'
     options:
-      proseWrap: always
+      proseWrap: preserve
       printWidth: 80
       parser: markdown
       cursorOffset: -1

Makefile

@@ -6,33 +6,50 @@ default: help
 help:
 	@echo Developer commands:
 	@echo
-	@echo "ruff           Run ruff, fixing any safely-fixable errors and formatting"
-	@echo "ruff-unsafe    Run ruff, fixing all fixable errors and formatting"
-	@echo "mypy           Run mypy using the config in pyproject.toml to identify type mismatches and other coding errors"
-	@echo "mypy-all       Run mypy ignoring the config in pyproject.tom but still ignoring missing imports"
-	@echo "frontend-build Build the frontend in order to run on localhost:9090"
-	@echo "frontend-dev   Run the frontend in developer mode on localhost:5173"
-	@echo "installer-zip  Build the installer .zip file for the current version"
-	@echo "tag-release    Tag the GitHub repository with the current version (use at release time only!)"
+	@echo "ruff                     Run ruff, fixing any safely-fixable errors and formatting"
+	@echo "ruff-unsafe              Run ruff, fixing all fixable errors and formatting"
+	@echo "mypy                     Run mypy using the config in pyproject.toml to identify type mismatches and other coding errors"
+	@echo "mypy-all                 Run mypy ignoring the config in pyproject.tom but still ignoring missing imports"
+	@echo "test                     Run the unit tests."
+	@echo "update-config-docstring  Update the app's config docstring so mkdocs can autogenerate it correctly."
+	@echo "frontend-install         Install the pnpm modules needed for the front end"
+	@echo "frontend-build           Build the frontend in order to run on localhost:9090"
+	@echo "frontend-dev             Run the frontend in developer mode on localhost:5173"
+	@echo "frontend-typegen         Generate types for the frontend from the OpenAPI schema"
+	@echo "installer-zip            Build the installer .zip file for the current version"
+	@echo "tag-release              Tag the GitHub repository with the current version (use at release time only!)"
 
 # Runs ruff, fixing any safely-fixable errors and formatting
 ruff:
-		ruff check . --fix
-		ruff format .
+	ruff check . --fix
+	ruff format .
 
 # Runs ruff, fixing all errors it can fix and formatting
 ruff-unsafe:
-		ruff check . --fix --unsafe-fixes
-		ruff format .
+	ruff check . --fix --unsafe-fixes
+	ruff format .
 
 # Runs mypy, using the config in pyproject.toml
 mypy:
-		mypy scripts/invokeai-web.py
+	mypy scripts/invokeai-web.py
 
 # Runs mypy, ignoring the config in pyproject.toml but still ignoring missing (untyped) imports
 # (many files are ignored by the config, so this is useful for checking all files)
 mypy-all:
-		mypy scripts/invokeai-web.py --config-file= --ignore-missing-imports
+	mypy scripts/invokeai-web.py --config-file= --ignore-missing-imports
+
+# Run the unit tests
+test:
+	pytest ./tests
+
+# Update config docstring
+update-config-docstring:
+	python scripts/update_config_docstring.py
+
+# Install the pnpm modules needed for the front end
+frontend-install:
+	rm -rf invokeai/frontend/web/node_modules
+	cd invokeai/frontend/web && pnpm install
 
 # Build the frontend
 frontend-build:
@@ -42,6 +59,9 @@ frontend-build:
 frontend-dev:
 	cd invokeai/frontend/web && pnpm dev
 
+frontend-typegen:
+	cd invokeai/frontend/web && python ../../../scripts/generate_openapi_schema.py | pnpm typegen
+
 # Installer zip file
 installer-zip:
 	cd installer && ./create_installer.sh

README.md

@@ -395,9 +395,9 @@ For our latest changes, view our [Release
 Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
 [CHANGELOG](docs/CHANGELOG.md).
 
-### Troubleshooting
+### Troubleshooting / FAQ
 
-Please check out our **[Troubleshooting Guide](https://invoke-ai.github.io/InvokeAI/installation/010_INSTALL_AUTOMATED/#troubleshooting)** to get solutions for common installation
+Please check out our **[FAQ](https://invoke-ai.github.io/InvokeAI/help/FAQ/)** to get solutions for common installation
 problems and other issues. For more help, please join our [Discord][discord link]
 
 ## Contributing

docker/.env.sample

@@ -2,17 +2,25 @@
 ## Any environment variables supported by InvokeAI can be specified here,
 ## in addition to the examples below.
 
-# HOST_INVOKEAI_ROOT is the path on the docker host's filesystem where InvokeAI will store data.
-# Outputs will also be stored here by default.
-# If relative, it will be relative to the docker directory in which the docker-compose.yml file is located
-#HOST_INVOKEAI_ROOT=../../invokeai-data
-
-# INVOKEAI_ROOT is the path to the root of the InvokeAI repository within the container.
+## INVOKEAI_ROOT is the path *on the host system* where Invoke will store its data.
+## It is mounted into the container and allows both containerized and non-containerized usage of Invoke.
+# Usually this is the only variable you need to set. It can be relative or absolute.
 # INVOKEAI_ROOT=~/invokeai
 
-# Get this value from your HuggingFace account settings page.
-# HUGGING_FACE_HUB_TOKEN=
+## HOST_INVOKEAI_ROOT and CONTAINER_INVOKEAI_ROOT can be used to control the on-host
+## and in-container paths separately, if needed.
+## HOST_INVOKEAI_ROOT is the path on the docker host's filesystem where Invoke will store data.
+## If relative, it will be relative to the docker directory in which the docker-compose.yml file is located
+## CONTAINER_INVOKEAI_ROOT is the path within the container where Invoke will expect to find the runtime directory.
+## It MUST be absolute. There is usually no need to change this.
+# HOST_INVOKEAI_ROOT=../../invokeai-data
+# CONTAINER_INVOKEAI_ROOT=/invokeai
 
-## optional variables specific to the docker setup.
+## INVOKEAI_PORT is the port on which the InvokeAI web interface will be available
+# INVOKEAI_PORT=9090
+
+## GPU_DRIVER can be set to either `nvidia` or `rocm` to enable GPU support in the container accordingly.
 # GPU_DRIVER=nvidia #| rocm
+
+## CONTAINER_UID can be set to the UID of the user on the host system that should own the files in the container.
 # CONTAINER_UID=1000

docker/Dockerfile

@@ -18,8 +18,6 @@ ENV INVOKEAI_SRC=/opt/invokeai
 ENV VIRTUAL_ENV=/opt/venv/invokeai
 
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-ARG TORCH_VERSION=2.1.2
-ARG TORCHVISION_VERSION=0.16.2
 ARG GPU_DRIVER=cuda
 ARG TARGETPLATFORM="linux/amd64"
 # unused but available
@@ -27,7 +25,12 @@ ARG BUILDPLATFORM
 
 WORKDIR ${INVOKEAI_SRC}
 
-# Install pytorch before all other pip packages
+COPY invokeai ./invokeai
+COPY pyproject.toml ./
+
+# Editable mode helps use the same image for development:
+# the local working copy can be bind-mounted into the image
+# at path defined by ${INVOKEAI_SRC}
 # NOTE: there are no pytorch builds for arm64 + cuda, only cpu
 # x86_64/CUDA is default
 RUN --mount=type=cache,target=/root/.cache/pip \
@@ -39,20 +42,10 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     else \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
     fi &&\
-    pip install $extra_index_url_arg \
-        torch==$TORCH_VERSION \
-        torchvision==$TORCHVISION_VERSION
 
-# Install the local package.
-# Editable mode helps use the same image for development:
-# the local working copy can be bind-mounted into the image
-# at path defined by ${INVOKEAI_SRC}
-COPY invokeai ./invokeai
-COPY pyproject.toml ./
-RUN --mount=type=cache,target=/root/.cache/pip \
     # xformers + triton fails to install on arm64
     if [ "$GPU_DRIVER" = "cuda" ] && [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
-        pip install -e ".[xformers]"; \
+        pip install $extra_index_url_arg -e ".[xformers]"; \
     else \
         pip install $extra_index_url_arg -e "."; \
     fi
@@ -101,6 +94,8 @@ RUN apt update && apt install -y --no-install-recommends \
 ENV INVOKEAI_SRC=/opt/invokeai
 ENV VIRTUAL_ENV=/opt/venv/invokeai
 ENV INVOKEAI_ROOT=/invokeai
+ENV INVOKEAI_HOST=0.0.0.0
+ENV INVOKEAI_PORT=9090
 ENV PATH="$VIRTUAL_ENV/bin:$INVOKEAI_SRC:$PATH"
 ENV CONTAINER_UID=${CONTAINER_UID:-1000}
 ENV CONTAINER_GID=${CONTAINER_GID:-1000}
@@ -125,4 +120,4 @@ RUN mkdir -p ${INVOKEAI_ROOT} && chown -R ${CONTAINER_UID}:${CONTAINER_GID} ${IN
 
 COPY docker/docker-entrypoint.sh ./
 ENTRYPOINT ["/opt/invokeai/docker-entrypoint.sh"]
-CMD ["invokeai-web", "--host", "0.0.0.0"]
+CMD ["invokeai-web"]

docker/docker-compose.yml

@@ -8,35 +8,28 @@ x-invokeai: &invokeai
       context: ..
       dockerfile: docker/Dockerfile
 
-    # variables without a default will automatically inherit from the host environment
-    environment:
-      - INVOKEAI_ROOT
-      - HF_HOME
-
     # Create a .env file in the same directory as this docker-compose.yml file
     # and populate it with environment variables. See .env.sample
     env_file:
       - .env
 
+    # variables without a default will automatically inherit from the host environment
+    environment:
+      # if set, CONTAINER_INVOKEAI_ROOT will override the Invoke runtime directory location *inside* the container
+      - INVOKEAI_ROOT=${CONTAINER_INVOKEAI_ROOT:-/invokeai}
+      - HF_HOME
     ports:
-      - "${INVOKEAI_PORT:-9090}:9090"
+      - "${INVOKEAI_PORT:-9090}:${INVOKEAI_PORT:-9090}"
     volumes:
       - type: bind
         source: ${HOST_INVOKEAI_ROOT:-${INVOKEAI_ROOT:-~/invokeai}}
-        target: ${INVOKEAI_ROOT:-/invokeai}
+        target: ${CONTAINER_INVOKEAI_ROOT:-/invokeai}
+        bind:
+          create_host_path: true
       - ${HF_HOME:-~/.cache/huggingface}:${HF_HOME:-/invokeai/.cache/huggingface}
-      # - ${INVOKEAI_MODELS_DIR:-${INVOKEAI_ROOT:-/invokeai/models}}
-      # - ${INVOKEAI_MODELS_CONFIG_PATH:-${INVOKEAI_ROOT:-/invokeai/configs/models.yaml}}
     tty: true
     stdin_open: true
 
-    # # Example of running alternative commands/scripts in the container
-    # command:
-    #   - bash
-    #   - -c
-    #   - |
-    #     invokeai-model-install --yes --default-only --config_file ${INVOKEAI_ROOT}/config_custom.yaml
-    #     invokeai-nodes-web --host 0.0.0.0
 
 services:
   invokeai-nvidia:

docker/docker-entrypoint.sh

@@ -9,10 +9,6 @@ set -e -o pipefail
 ### Set INVOKEAI_ROOT pointing to a valid runtime directory
 # Otherwise configure the runtime dir first.
 
-### Configure the InvokeAI runtime directory (done by default)):
-# docker run --rm -it <this image> --configure
-# or skip with --no-configure
-
 ### Set the CONTAINER_UID envvar to match your user.
 # Ensures files created in the container are owned by you:
 #   docker run --rm -it -v /some/path:/invokeai -e CONTAINER_UID=$(id -u) <this image>
@@ -22,27 +18,6 @@ USER_ID=${CONTAINER_UID:-1000}
 USER=ubuntu
 usermod -u ${USER_ID} ${USER} 1>/dev/null
 
-configure() {
-    # Configure the runtime directory
-    if [[ -f ${INVOKEAI_ROOT}/invokeai.yaml ]]; then
-        echo "${INVOKEAI_ROOT}/invokeai.yaml exists. InvokeAI is already configured."
-        echo "To reconfigure InvokeAI, delete the above file."
-        echo "======================================================================"
-    else
-        mkdir -p "${INVOKEAI_ROOT}"
-        chown --recursive ${USER} "${INVOKEAI_ROOT}"
-        gosu ${USER} invokeai-configure --yes --default_only
-    fi
-}
-
-## Skip attempting to configure.
-## Must be passed first, before any other args.
-if [[ $1 != "--no-configure" ]]; then
-    configure
-else
-    shift
-fi
-
 ### Set the $PUBLIC_KEY env var to enable SSH access.
 # We do not install openssh-server in the image by default to avoid bloat.
 # but it is useful to have the full SSH server e.g. on Runpod.
@@ -58,7 +33,8 @@ if [[ -v "PUBLIC_KEY" ]] && [[ ! -d "${HOME}/.ssh" ]]; then
     service ssh start
 fi
 
-
+mkdir -p "${INVOKEAI_ROOT}"
+chown --recursive ${USER} "${INVOKEAI_ROOT}"
 cd "${INVOKEAI_ROOT}"
 
 # Run the CMD as the Container User (not root).

docs/RELEASE.md

@@ -0,0 +1,173 @@
+# Release Process
+
+The app is published in twice, in different build formats.
+
+- A [PyPI] distribution. This includes both a source distribution and built distribution (a wheel). Users install with `pip install invokeai`. The updater uses this build.
+- An installer on the [InvokeAI Releases Page]. This is a zip file with install scripts and a wheel. This is only used for new installs.
+
+## General Prep
+
+Make a developer call-out for PRs to merge. Merge and test things out.
+
+While the release workflow does not include end-to-end tests, it does pause before publishing so you can download and test the final build.
+
+## Release Workflow
+
+The `release.yml` workflow runs a number of jobs to handle code checks, tests, build and publish on PyPI.
+
+It is triggered on **tag push**, when the tag matches `v*`. It doesn't matter if you've prepped a release branch like `release/v3.5.0` or are releasing from `main` - it works the same.
+
+> Because commits are reference-counted, it is safe to create a release branch, tag it, let the workflow run, then delete the branch. So long as the tag exists, that commit will exist.
+
+### Triggering the Workflow
+
+Run `make tag-release` to tag the current commit and kick off the workflow.
+
+The release may also be dispatched [manually].
+
+### Workflow Jobs and Process
+
+The workflow consists of a number of concurrently-run jobs, and two final publish jobs.
+
+The publish jobs require manual approval and are only run if the other jobs succeed.
+
+#### `check-version` Job
+
+This job checks that the git ref matches the app version. It matches the ref against the `__version__` variable in `invokeai/version/invokeai_version.py`.
+
+When the workflow is triggered by tag push, the ref is the tag. If the workflow is run manually, the ref is the target selected from the **Use workflow from** dropdown.
+
+This job uses [samuelcolvin/check-python-version].
+
+> Any valid [version specifier] works, so long as the tag matches the version. The release workflow works exactly the same for `RC`, `post`, `dev`, etc.
+
+#### Check and Test Jobs
+
+- **`python-tests`**: runs `pytest` on matrix of platforms
+- **`python-checks`**: runs `ruff` (format and lint)
+- **`frontend-tests`**: runs `vitest`
+- **`frontend-checks`**: runs `prettier` (format), `eslint` (lint), `dpdm` (circular refs), `tsc` (static type check) and `knip` (unused imports)
+
+> **TODO** We should add `mypy` or `pyright` to the **`check-python`** job.
+
+> **TODO** We should add an end-to-end test job that generates an image.
+
+#### `build-installer` Job
+
+This sets up both python and frontend dependencies and builds the python package. Internally, this runs `installer/create_installer.sh` and uploads two artifacts:
+
+- **`dist`**: the python distribution, to be published on PyPI
+- **`InvokeAI-installer-${VERSION}.zip`**: the installer to be included in the GitHub release
+
+#### Sanity Check & Smoke Test
+
+At this point, the release workflow pauses as the remaining publish jobs require approval. Time to test the installer.
+
+Because the installer pulls from PyPI, and we haven't published to PyPI yet, you will need to install from the wheel:
+
+- Download and unzip `dist.zip` and the installer from the **Summary** tab of the workflow
+- Run the installer script using the `--wheel` CLI arg, pointing at the wheel:
+
+  ```sh
+  ./install.sh --wheel ../InvokeAI-4.0.0rc6-py3-none-any.whl
+  ```
+
+- Install to a temporary directory so you get the new user experience
+- Download a model and generate
+
+> The same wheel file is bundled in the installer and in the `dist` artifact, which is uploaded to PyPI. You should end up with the exactly the same installation as if the installer got the wheel from PyPI.
+
+##### Something isn't right
+
+If testing reveals any issues, no worries. Cancel the workflow, which will cancel the pending publish jobs (you didn't approve them prematurely, right?).
+
+Now you can start from the top:
+
+- Fix the issues and PR the fixes per usual
+- Get the PR approved and merged per usual
+- Switch to `main` and pull in the fixes
+- Run `make tag-release` to move the tag to `HEAD` (which has the fixes) and kick off the release workflow again
+- Re-do the sanity check
+
+#### PyPI Publish Jobs
+
+The publish jobs will run if any of the previous jobs fail.
+
+They use [GitHub environments], which are configured as [trusted publishers] on PyPI.
+
+Both jobs require a maintainer to approve them from the workflow's **Summary** tab.
+
+- Click the **Review deployments** button
+- Select the environment (either `testpypi` or `pypi`)
+- Click **Approve and deploy**
+
+> **If the version already exists on PyPI, the publish jobs will fail.** PyPI only allows a given version to be published once - you cannot change it. If version published on PyPI has a problem, you'll need to "fail forward" by bumping the app version and publishing a followup release.
+
+##### Failing PyPI Publish
+
+Check the [python infrastructure status page] for incidents.
+
+If there are no incidents, contact @hipsterusername or @lstein, who have owner access to GH and PyPI, to see if access has expired or something like that.
+
+#### `publish-testpypi` Job
+
+Publishes the distribution on the [Test PyPI] index, using the `testpypi` GitHub environment.
+
+This job is not required for the production PyPI publish, but included just in case you want to test the PyPI release.
+
+If approved and successful, you could try out the test release like this:
+
+```sh
+# Create a new virtual environment
+python -m venv ~/.test-invokeai-dist --prompt test-invokeai-dist
+# Install the distribution from Test PyPI
+pip install --index-url https://test.pypi.org/simple/ invokeai
+# Run and test the app
+invokeai-web
+# Cleanup
+deactivate
+rm -rf ~/.test-invokeai-dist
+```
+
+#### `publish-pypi` Job
+
+Publishes the distribution on the production PyPI index, using the `pypi` GitHub environment.
+
+## Publish the GitHub Release with installer
+
+Once the release is published to PyPI, it's time to publish the GitHub release.
+
+1. [Draft a new release] on GitHub, choosing the tag that triggered the release.
+1. Write the release notes, describing important changes. The **Generate release notes** button automatically inserts the changelog and new contributors, and you can copy/paste the intro from previous releases.
+1. Use `scripts/get_external_contributions.py` to get a list of external contributions to shout out in the release notes.
+1. Upload the zip file created in **`build`** job into the Assets section of the release notes.
+1. Check **Set as a pre-release** if it's a pre-release.
+1. Check **Create a discussion for this release**.
+1. Publish the release.
+1. Announce the release in Discord.
+
+> **TODO** Workflows can create a GitHub release from a template and upload release assets. One popular action to handle this is [ncipollo/release-action]. A future enhancement to the release process could set this up.
+
+## Manual Build
+
+The `build installer` workflow can be dispatched manually. This is useful to test the installer for a given branch or tag.
+
+No checks are run, it just builds.
+
+## Manual Release
+
+The `release` workflow can be dispatched manually. You must dispatch the workflow from the right tag, else it will fail the version check.
+
+This functionality is available as a fallback in case something goes wonky. Typically, releases should be triggered via tag push as described above.
+
+[InvokeAI Releases Page]: https://github.com/invoke-ai/InvokeAI/releases
+[PyPI]: https://pypi.org/
+[Draft a new release]: https://github.com/invoke-ai/InvokeAI/releases/new
+[Test PyPI]: https://test.pypi.org/
+[version specifier]: https://packaging.python.org/en/latest/specifications/version-specifiers/
+[ncipollo/release-action]: https://github.com/ncipollo/release-action
+[GitHub environments]: https://docs.github.com/en/actions/deployment/targeting-different-environments/using-environments-for-deployment
+[trusted publishers]: https://docs.pypi.org/trusted-publishers/
+[samuelcolvin/check-python-version]: https://github.com/samuelcolvin/check-python-version
+[manually]: #manual-release
+[python infrastructure status page]: https://status.python.org/

docs/contributing/INVOCATIONS.md

@@ -9,11 +9,15 @@ complex functionality.
 
 ## Invocations Directory
 
-InvokeAI Nodes can be found in the `invokeai/app/invocations` directory. These can be used as examples to create your own nodes.
+InvokeAI Nodes can be found in the `invokeai/app/invocations` directory. These
+can be used as examples to create your own nodes.
 
-New nodes should be added to a subfolder in `nodes` direction found at the root level of the InvokeAI installation location. Nodes added to this folder will be able to be used upon application startup. 
+New nodes should be added to a subfolder in `nodes` direction found at the root
+level of the InvokeAI installation location. Nodes added to this folder will be
+able to be used upon application startup.
+
+Example `nodes` subfolder structure:
 
-Example `nodes`  subfolder structure:
 ```py
 ├── __init__.py # Invoke-managed custom node loader
 │
@@ -30,14 +34,14 @@ Example `nodes`  subfolder structure:
         └── fancy_node.py
 ```
 
-Each node folder must have an `__init__.py` file that imports its nodes. Only nodes imported in the `__init__.py` file are loaded.
- See the README in the nodes folder for more examples: 
+Each node folder must have an `__init__.py` file that imports its nodes. Only
+nodes imported in the `__init__.py` file are loaded. See the README in the nodes
+folder for more examples:
 
 ```py
 from .cool_node import CoolInvocation
 ```
 
-
 ## Creating A New Invocation
 
 In order to understand the process of creating a new Invocation, let us actually
@@ -131,7 +135,6 @@ from invokeai.app.invocations.primitives import ImageField
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -167,7 +170,6 @@ from invokeai.app.invocations.primitives import ImageField
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -197,7 +199,6 @@ from invokeai.app.invocations.image import ImageOutput
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -229,30 +230,17 @@ class ResizeInvocation(BaseInvocation):
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Load the image using InvokeAI's predefined Image Service. Returns the PIL image.
-        image = context.services.images.get_pil_image(self.image.image_name)
+        # Load the input image as a PIL image
+        image = context.images.get_pil(self.image.image_name)
 
-        # Resizing the image
+        # Resize the image
         resized_image = image.resize((self.width, self.height))
 
-        # Save the image using InvokeAI's predefined Image Service. Returns the prepared PIL image.
-        output_image = context.services.images.create(
-            image=resized_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        # Save the image
+        image_dto = context.images.save(image=resized_image)
 
-        # Returning the Image
-        return ImageOutput(
-            image=ImageField(
-                image_name=output_image.image_name,
-            ),
-            width=output_image.width,
-            height=output_image.height,
-        )
+        # Return an ImageOutput
+        return ImageOutput.build(image_dto)
 ```
 
 **Note:** Do not be overwhelmed by the `ImageOutput` process. InvokeAI has a
@@ -343,27 +331,25 @@ class ImageColorStringOutput(BaseInvocationOutput):
 
 That's all there is to it.
 
-<!-- TODO: DANGER - we probably do not want people to create their own field types, because this requires a lot of work on the frontend to accomodate.
-
 ### Custom Input Fields
 
 Now that you know how to create your own Invocations, let us dive into slightly
 more advanced topics.
 
 While creating your own Invocations, you might run into a scenario where the
-existing input types in InvokeAI do not meet your requirements. In such cases,
-you can create your own input types.
+existing fields in InvokeAI do not meet your requirements. In such cases, you
+can create your own fields.
 
 Let us create one as an example. Let us say we want to create a color input
 field that represents a color code. But before we start on that here are some
 general good practices to keep in mind.
 
-**Good Practices**
+### Best Practices
 
 - There is no naming convention for input fields but we highly recommend that
   you name it something appropriate like `ColorField`.
 - It is not mandatory but it is heavily recommended to add a relevant
-  `docstring` to describe your input field.
+  `docstring` to describe your field.
 - Keep your field in the same file as the Invocation that it is made for or in
   another file where it is relevant.
 
@@ -378,10 +364,13 @@ class ColorField(BaseModel):
     pass
 ```
 
-Perfect. Now let us create our custom inputs for our field. This is exactly
-similar how you created input fields for your Invocation. All the same rules
-apply. Let us create four fields representing the _red(r)_, _blue(b)_,
-_green(g)_ and _alpha(a)_ channel of the color.
+Perfect. Now let us create the properties for our field. This is similar to how
+you created input fields for your Invocation. All the same rules apply. Let us
+create four fields representing the _red(r)_, _blue(b)_, _green(g)_ and
+_alpha(a)_ channel of the color.
+
+> Technically, the properties are _also_ called fields - but in this case, it
+> refers to a `pydantic` field.
 
 ```python
 class ColorField(BaseModel):
@@ -396,25 +385,11 @@ That's it. We now have a new input field type that we can use in our Invocations
 like this.
 
 ```python
-color: ColorField = Field(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
+color: ColorField = InputField(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
 ```
 
-### Custom Components For Frontend
+### Using the custom field
 
-Every backend input type should have a corresponding frontend component so the
-UI knows what to render when you use a particular field type.
+When you start the UI, your custom field will be automatically recognized.
 
-If you are using existing field types, we already have components for those. So
-you don't have to worry about creating anything new. But this might not always
-be the case. Sometimes you might want to create new field types and have the
-frontend UI deal with it in a different way.
-
-This is where we venture into the world of React and Javascript and create our
-own new components for our Invocations. Do not fear the world of JS. It's
-actually pretty straightforward.
-
-Let us create a new component for our custom color field we created above. When
-we use a color field, let us say we want the UI to display a color picker for
-the user to pick from rather than entering values. That is what we will build
-now.
--->
+Custom fields only support connection inputs in the Workflow Editor.

docs/contributing/frontend/OVERVIEW.md

@@ -0,0 +1,133 @@
+# Invoke UI
+
+Invoke's UI is made possible by many contributors and open-source libraries. Thank you!
+
+## Dev environment
+
+### Setup
+
+1. Install [node] and [pnpm].
+1. Run `pnpm i` to install all packages.
+
+#### Run in dev mode
+
+1. From `invokeai/frontend/web/`, run `pnpm dev`.
+1. From repo root, run `python scripts/invokeai-web.py`.
+1. Point your browser to the dev server address, e.g. <http://localhost:5173/>
+
+### Package scripts
+
+- `dev`: run the frontend in dev mode, enabling hot reloading
+- `build`: run all checks (madge, eslint, prettier, tsc) and then build the frontend
+- `typegen`: generate types from the OpenAPI schema (see [Type generation])
+- `lint:dpdm`: check circular dependencies
+- `lint:eslint`: check code quality
+- `lint:prettier`: check code formatting
+- `lint:tsc`: check type issues
+- `lint:knip`: check for unused exports or objects (failures here are just suggestions, not hard fails)
+- `lint`: run all checks concurrently
+- `fix`: run `eslint` and `prettier`, fixing fixable issues
+
+### Type generation
+
+We use [openapi-typescript] to generate types from the app's OpenAPI schema.
+
+The generated types are committed to the repo in [schema.ts].
+
+```sh
+# from the repo root, start the server
+python scripts/invokeai-web.py
+# from invokeai/frontend/web/, run the script
+pnpm typegen
+```
+
+### Localization
+
+We use [i18next] for localization, but translation to languages other than English happens on our [Weblate] project.
+
+Only the English source strings should be changed on this repo.
+
+### VSCode
+
+#### Example debugger config
+
+```jsonc
+{
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "type": "chrome",
+      "request": "launch",
+      "name": "Invoke UI",
+      "url": "http://localhost:5173",
+      "webRoot": "${workspaceFolder}/invokeai/frontend/web"
+    }
+  ]
+}
+```
+
+#### Remote dev
+
+We've noticed an intermittent timeout issue with the VSCode remote dev port forwarding.
+
+We suggest disabling the editor's port forwarding feature and doing it manually via SSH:
+
+```sh
+ssh -L 9090:localhost:9090 -L 5173:localhost:5173 user@host
+```
+
+## Contributing Guidelines
+
+Thanks for your interest in contributing to the Invoke Web UI!
+
+Please follow these guidelines when contributing.
+
+### Check in before investing your time
+
+Please check in before you invest your time on anything besides a trivial fix, in case it conflicts with ongoing work or isn't aligned with the vision for the app.
+
+If a feature request or issue doesn't already exist for the thing you want to work on, please create one.
+
+Ping `@psychedelicious` on [discord] in the `#frontend-dev` channel or in the feature request / issue you want to work on - we're happy to chat.
+
+### Code conventions
+
+- This is a fairly complex app with a deep component tree. Please use memoization (`useCallback`, `useMemo`, `memo`) with enthusiasm.
+- If you need to add some global, ephemeral state, please use [nanostores] if possible.
+- Be careful with your redux selectors. If they need to be parameterized, consider creating them inside a `useMemo`.
+- Feel free to use `lodash` (via `lodash-es`) to make the intent of your code clear.
+- Please add comments describing the "why", not the "how" (unless it is really arcane).
+
+### Commit format
+
+Please use the [conventional commits] spec for the web UI, with a scope of "ui":
+
+- `chore(ui): bump deps`
+- `chore(ui): lint`
+- `feat(ui): add some cool new feature`
+- `fix(ui): fix some bug`
+
+### Submitting a PR
+
+- Ensure your branch is tidy. Use an interactive rebase to clean up the commit history and reword the commit messages if they are not descriptive.
+- Run `pnpm lint`. Some issues are auto-fixable with `pnpm fix`.
+- Fill out the PR form when creating the PR.
+  - It doesn't need to be super detailed, but a screenshot or video is nice if you changed something visually.
+  - If a section isn't relevant, delete it. There are no UI tests at this time.
+
+## Other docs
+
+- [Workflows - Design and Implementation]
+- [State Management]
+
+[node]: https://nodejs.org/en/download/
+[pnpm]: https://github.com/pnpm/pnpm
+[discord]: https://discord.gg/ZmtBAhwWhy
+[i18next]: https://github.com/i18next/react-i18next
+[Weblate]: https://hosted.weblate.org/engage/invokeai/
+[openapi-typescript]: https://github.com/drwpow/openapi-typescript
+[Type generation]: #type-generation
+[schema.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/services/api/schema.ts
+[conventional commits]: https://www.conventionalcommits.org/en/v1.0.0/
+[Workflows - Design and Implementation]: ./WORKFLOWS.md
+[State Management]: ./STATE_MGMT.md

docs/contributing/frontend/WORKFLOWS.md

@@ -1,40 +1,5 @@
 # Workflows - Design and Implementation
 
-<!-- @import "[TOC]" {cmd="toc" depthFrom=1 depthTo=6 orderedList=false} -->
-
-<!-- code_chunk_output -->
-
-- [Workflows - Design and Implementation](#workflows---design-and-implementation)
-  - [Design](#design)
-    - [Linear UI](#linear-ui)
-    - [Workflow Editor](#workflow-editor)
-      - [Workflows](#workflows)
-        - [Workflow -> reactflow state -> InvokeAI graph](#workflow---reactflow-state---invokeai-graph)
-        - [Nodes vs Invocations](#nodes-vs-invocations)
-        - [Workflow Linear View](#workflow-linear-view)
-      - [OpenAPI Schema](#openapi-schema)
-        - [Field Instances and Templates](#field-instances-and-templates)
-        - [Stateful vs Stateless Fields](#stateful-vs-stateless-fields)
-        - [Collection and Polymorphic Fields](#collection-and-polymorphic-fields)
-  - [Implementation](#implementation)
-    - [zod Schemas and Types](#zod-schemas-and-types)
-    - [OpenAPI Schema Parsing](#openapi-schema-parsing)
-      - [Parsing Field Types](#parsing-field-types)
-        - [Primitive Types](#primitive-types)
-        - [Complex Types](#complex-types)
-        - [Collection Types](#collection-types)
-        - [Collection or Scalar Types](#collection-or-scalar-types)
-        - [Optional Fields](#optional-fields)
-      - [Building Field Input Templates](#building-field-input-templates)
-      - [Building Field Output Templates](#building-field-output-templates)
-    - [Managing reactflow State](#managing-reactflow-state)
-      - [Building Nodes and Edges](#building-nodes-and-edges)
-      - [Building a Workflow](#building-a-workflow)
-      - [Loading a Workflow](#loading-a-workflow)
-    - [Workflow Migrations](#workflow-migrations)
-
-<!-- /code_chunk_output -->
-
 > This document describes, at a high level, the design and implementation of workflows in the InvokeAI frontend. There are a substantial number of implementation details not included, but which are hopefully clear from the code.
 
 InvokeAI's backend uses graphs, composed of **nodes** and **edges**, to process data and generate images.
@@ -152,13 +117,13 @@ Stateless fields do not store their value in the node, so their field instances
 
 "Custom" fields will always be treated as stateless fields.
 
-##### Collection and Polymorphic Fields
+##### Collection and Scalar Fields
 
-Field types have a name and two flags which may identify it as a **collection** or **polymorphic** field.
+Field types have a name and two flags which may identify it as a **collection** or **collection or scalar** field.
 
-If a field is annotated in python as a list, its field type is parsed and flagged as a collection type (e.g. `list[int]`).
+If a field is annotated in python as a list, its field type is parsed and flagged as a **collection** type (e.g. `list[int]`).
 
-If it is annotated as a union of a type and list, the type will be flagged as a polymorphic type (e.g. `Union[int, list[int]]`). Fields may not be unions of different types (e.g. `Union[int, list[str]]` and `Union[int, str]` are not allowed).
+If it is annotated as a union of a type and list, the type will be flagged as a **collection or scalar** type (e.g. `Union[int, list[int]]`). Fields may not be unions of different types (e.g. `Union[int, list[str]]` and `Union[int, str]` are not allowed).
 
 ## Implementation
 
@@ -338,13 +303,13 @@ Migration logic is in [migrations.ts].
 [reactflow]: https://github.com/xyflow/xyflow 'reactflow'
 [reactflow-concepts]: https://reactflow.dev/learn/concepts/terms-and-definitions
 [reactflow-events]: https://reactflow.dev/api-reference/react-flow#event-handlers
-[buildWorkflow.ts]: ../src/features/nodes/util/workflow/buildWorkflow.ts
-[nodesSlice.ts]: ../src/features/nodes/store/nodesSlice.ts
-[buildLinearTextToImageGraph.ts]: ../src/features/nodes/util/graph/buildLinearTextToImageGraph.ts
-[buildNodesGraph.ts]: ../src/features/nodes/util/graph/buildNodesGraph.ts
-[buildInvocationNode.ts]: ../src/features/nodes/util/node/buildInvocationNode.ts
-[validateWorkflow.ts]: ../src/features/nodes/util/workflow/validateWorkflow.ts
-[migrations.ts]: ../src/features/nodes/util/workflow/migrations.ts
-[parseSchema.ts]: ../src/features/nodes/util/schema/parseSchema.ts
-[buildFieldInputTemplate.ts]: ../src/features/nodes/util/schema/buildFieldInputTemplate.ts
-[buildFieldOutputTemplate.ts]: ../src/features/nodes/util/schema/buildFieldOutputTemplate.ts
+[buildWorkflow.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/workflow/buildWorkflow.ts
+[nodesSlice.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/store/nodesSlice.ts
+[buildLinearTextToImageGraph.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/graph/buildLinearTextToImageGraph.ts
+[buildNodesGraph.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/graph/buildNodesGraph.ts
+[buildInvocationNode.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/node/buildInvocationNode.ts
+[validateWorkflow.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/workflow/validateWorkflow.ts
+[migrations.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/workflow/migrations.ts
+[parseSchema.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/schema/parseSchema.ts
+[buildFieldInputTemplate.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/schema/buildFieldInputTemplate.ts
+[buildFieldOutputTemplate.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/schema/buildFieldOutputTemplate.ts

docs/deprecated/2to3.md

@@ -1,53 +0,0 @@
-## :octicons-log-16: Important Changes Since Version 2.3
-
-### Nodes
-
-Behind the scenes, InvokeAI has been completely rewritten to support
-"nodes," small unitary operations that can be combined into graphs to
-form arbitrary workflows. For example, there is a prompt node that
-processes the prompt string and feeds it to a text2latent node that
-generates a latent image. The latents are then fed to a latent2image
-node that translates the latent image into a PNG.
-
-The WebGUI has a node editor that allows you to graphically design and
-execute custom node graphs. The ability to save and load graphs is
-still a work in progress, but coming soon.
-
-### Command-Line Interface Retired
-
-All "invokeai" command-line interfaces have been retired as of version
-3.4.
-
-To launch the Web GUI from the command-line, use the command
-`invokeai-web` rather than the traditional `invokeai --web`.
-
-### ControlNet
-
-This version of InvokeAI features ControlNet, a system that allows you
-to achieve exact poses for human and animal figures by providing a
-model to follow. Full details are found in [ControlNet](features/CONTROLNET.md)
-
-### New Schedulers
-
-The list of schedulers has been completely revamped and brought up to date:
-
-| **Short Name** | **Scheduler**                   | **Notes**                   |
-|----------------|---------------------------------|-----------------------------|
-| **ddim**       | DDIMScheduler                   |                             |
-| **ddpm**       | DDPMScheduler                   |                             |
-| **deis**       | DEISMultistepScheduler          |                             |
-| **lms**        | LMSDiscreteScheduler            |                             |
-| **pndm**       | PNDMScheduler                   |                             |
-| **heun**       | HeunDiscreteScheduler           | original noise schedule     |
-| **heun_k**     | HeunDiscreteScheduler           | using karras noise schedule |
-| **euler**      | EulerDiscreteScheduler          | original noise schedule     |
-| **euler_k**    | EulerDiscreteScheduler          | using karras noise schedule |
-| **kdpm_2**     | KDPM2DiscreteScheduler          |                             |
-| **kdpm_2_a**   | KDPM2AncestralDiscreteScheduler |                             |
-| **dpmpp_2s**   | DPMSolverSinglestepScheduler    |                             |
-| **dpmpp_2m**   | DPMSolverMultistepScheduler     | original noise scnedule     |
-| **dpmpp_2m_k** | DPMSolverMultistepScheduler     | using karras noise schedule |
-| **unipc**      | UniPCMultistepScheduler         | CPU only                    |
-| **lcm**        | LCMScheduler                    |                             |
-
-Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details.

docs/deprecated/CLI.md

@@ -1,589 +0,0 @@
----
-title: Command-Line Interface
----
-
-# :material-bash: CLI
-
-## **Interactive Command Line Interface**
-
-The InvokeAI command line interface (CLI) provides scriptable access
-to InvokeAI's features.Some advanced features are only available
-through the CLI, though they eventually find their way into the WebUI.
-
-The CLI is accessible from the `invoke.sh`/`invoke.bat` launcher by
-selecting option (1). Alternatively, it can be launched directly from
-the command line by activating the InvokeAI environment and giving the
-command:
-
-```bash
-invokeai
-```
-
-After some startup messages, you will be presented with the `invoke> `
-prompt. Here you can type prompts to generate images and issue other
-commands to load and manipulate generative models. The CLI has a large
-number of command-line options that control its behavior. To get a
-concise summary of the options, call `invokeai` with the `--help` argument:
-
-```bash
-invokeai --help
-```
-
-The script uses the readline library to allow for in-line editing, command
-history (++up++ and ++down++), autocompletion, and more. To help keep track of
-which prompts generated which images, the script writes a log file of image
-names and prompts to the selected output directory.
-
-Here is a typical session
-
-```bash
-PS1:C:\Users\fred> invokeai
-* Initializing, be patient...
-* Initializing, be patient...
->> Initialization file /home/lstein/invokeai/invokeai.init found. Loading...
->> Internet connectivity is True
->> InvokeAI, version 2.3.0-rc5
->> InvokeAI runtime directory is "/home/lstein/invokeai"
->> GFPGAN Initialized
->> CodeFormer Initialized
->> ESRGAN Initialized
->> Using device_type cuda
->> xformers memory-efficient attention is available and enabled
-     (...more initialization messages...)
-* Initialization done! Awaiting your command (-h for help, 'q' to quit)
-invoke> ashley judd riding a camel -n2 -s150
-Outputs:
-   outputs/img-samples/00009.png: "ashley judd riding a camel" -n2 -s150 -S 416354203
-   outputs/img-samples/00010.png: "ashley judd riding a camel" -n2 -s150 -S 1362479620
-
-invoke> "there's a fly in my soup" -n6 -g
-    outputs/img-samples/00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
-    seeds for individual rows: [2685670268, 1216708065, 2335773498, 822223658, 714542046, 3395302430]
-invoke> q
-```
-
-![invoke-py-demo](../assets/dream-py-demo.png)
-
-## Arguments
-
-The script recognizes a series of command-line switches that will
-change important global defaults, such as the directory for image
-outputs and the location of the model weight files.
-
-### List of arguments recognized at the command line
-
-These command-line arguments can be passed to `invoke.py` when you first run it
-from the Windows, Mac or Linux command line. Some set defaults that can be
-overridden on a per-prompt basis (see
-[List of prompt arguments](#list-of-prompt-arguments). Others
-
-| Argument <img width="240" align="right"/> | Shortcut <img width="100" align="right"/> | Default <img width="320" align="right"/>       | Description                                                                                          |
-| ----------------------------------------- | ----------------------------------------- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
-| `--help`                                  | `-h`                                      |                                                | Print a concise help message.                                                                        |
-| `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                          | Location for generated images.                                                                       |
-| `--prompt_as_dir`                         | `-p`                                      | `False`                                        | Name output directories using the prompt text.                                                       |
-| `--from_file <path>`                      |                                           | `None`                                         | Read list of prompts from a file. Use `-` to read from standard input                                |
-| `--model <modelname>`                     |                                           | `stable-diffusion-1.5`                         | Loads the initial model specified in configs/models.yaml. |
-| `--ckpt_convert `           |                                                         | `False`                                        | If provided both .ckpt and .safetensors files will be auto-converted into diffusers format in memory |
-| `--autoconvert <path>`                    |                          | `None`                                        | On startup, scan the indicated directory for new .ckpt/.safetensor files and automatically convert and import them |
-| `--precision`                             |                                           | `fp16`                                         | Provide `fp32` for full precision mode, `fp16` for half-precision. `fp32` needed for Macintoshes and some NVidia cards. |
-| `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                            | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
-| `--safety-checker`                        |                                           | `False`                                        | Activate safety checker for NSFW and other potentially disturbing imagery                            |
-| `--patchmatch`, `--no-patchmatch`                 |                                   | `--patchmatch`                                        | Load/Don't load the PatchMatch inpainting extension    |
-| `--xformers`, `--no-xformers`                 |                                   | `--xformers`                                        | Load/Don't load the Xformers memory-efficient attention module (CUDA only)    |
-| `--web`                                   |                                           | `False`                                        | Start in web server mode                                                                             |
-| `--host <ip addr>`                        |                                           | `localhost`                                    | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any.                |
-| `--port <port>`                           |                                           | `9090`                                         | Which port web server should listen for requests on.                                                 |
-| `--config <path>`                         |                                           | `configs/models.yaml`                          | Configuration file for models and their weights.                                                     |
-| `--iterations <int>`                      | `-n<int>`                                 | `1`                                            | How many images to generate per prompt.                                                              |
-| `--width <int>`                           | `-W<int>`                                 | `512`                                    | Width of generated image                                                                                                                                                                                                                         |
-| `--height <int>`                          | `-H<int>`                                 | `512`                                    | Height of generated image                                                                                                        | `--steps <int>`                           | `-s<int>`                                 | `50`                                     | How many steps of refinement to apply                                                                                                                                                                                                            |
-| `--strength <float>`                      | `-s<float>` | `0.75`  | For img2img: how hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
-| `--fit`                                   | `-F`        | `False` | For img2img: scale the init image to fit into the specified -H and -W dimensions                                                                             |
-| `--grid`                                  | `-g`                                      | `False`                                        | Save all image series as a grid rather than individually.                                            |
-| `--sampler <sampler>`                     | `-A<sampler>`                             | `k_lms`                                        | Sampler to use. Use `-h` to get list of available samplers.                                          |
-| `--seamless`                              |                                           | `False`                                        | Create interesting effects by tiling elements of the image.                                          |
-| `--embedding_path <path>`                 |                                           | `None`                                         | Path to pre-trained embedding manager checkpoints, for custom models                                 |
-| `--gfpgan_model_path`                     |                                           | `experiments/pretrained_models/GFPGANv1.4.pth` | Path to GFPGAN model file.                                              |
-| `--free_gpu_mem`                          |                                           | `False`                                        | Free GPU memory after sampling, to allow image decoding and saving in low VRAM conditions            |
-| `--precision`                             |                                           | `auto`                                         | Set model precision, default is selected by device. Options: auto, float32, float16, autocast        |
-
-!!! warning "These arguments are deprecated but still work"
-
-    <div align="center" markdown>
-
-    | Argument           |  Shortcut  |  Default            |  Description |
-    |--------------------|------------|---------------------|--------------|
-    | `--full_precision`  |             | `False`                | Same as `--precision=fp32`|
-    | `--weights <path>`   |            | `None`                | Path to weights file; use `--model stable-diffusion-1.4` instead |
-    | `--laion400m`        | `-l`         | `False`               | Use older LAION400m weights; use `--model=laion400m` instead |
-
-    </div>
-
-!!! tip
-
-      On Windows systems, you may run into
-      problems when passing the invoke script standard backslashed path
-      names because the Python interpreter treats "\" as an escape.
-      You can either double your slashes (ick): `C:\\path\\to\\my\\file`, or
-      use Linux/Mac style forward slashes (better): `C:/path/to/my/file`.
-
-## The .invokeai initialization file
-
-To start up invoke.py with your preferred settings, place your desired
-startup options in a file in your home directory named `.invokeai` The
-file should contain the startup options as you would type them on the
-command line (`--steps=10 --grid`), one argument per line, or a
-mixture of both using any of the accepted command switch formats:
-
-!!! example "my unmodified initialization file"
-
-    ```bash title="~/.invokeai" linenums="1"
-    # InvokeAI initialization file
-    # This is the InvokeAI initialization file, which contains command-line default values.
-    # Feel free to edit. If anything goes wrong, you can re-initialize this file by deleting
-    # or renaming it and then running invokeai-configure again.
-
-    # The --root option below points to the folder in which InvokeAI stores its models, configs and outputs.
-    --root="/Users/mauwii/invokeai"
-
-    # the --outdir option controls the default location of image files.
-    --outdir="/Users/mauwii/invokeai/outputs"
-
-    # You may place other  frequently-used startup commands here, one or more per line.
-    # Examples:
-    # --web --host=0.0.0.0
-    # --steps=20
-    # -Ak_euler_a -C10.0
-    ```
-
-!!! note
-
-    The  initialization file only accepts the command line arguments.
-    There are additional arguments that you can provide on the `invoke>` command
-    line (such as `-n` or `--iterations`) that cannot be entered into this file.
-    Also be alert for empty blank lines at the end of the file, which will cause
-    an arguments error at startup time.
-
-## List of prompt arguments
-
-After the invoke.py script initializes, it will present you with a `invoke>`
-prompt. Here you can enter information to generate images from text
-([txt2img](#txt2img)), to embellish an existing image or sketch
-([img2img](#img2img)), or to selectively alter chosen regions of the image
-([inpainting](#inpainting)).
-
-### txt2img
-
-!!! example ""
-
-    ```bash
-    invoke> waterfall and rainbow -W640 -H480
-    ```
-
-    This will create the requested image with the dimensions 640 (width)
-    and 480 (height).
-
-Here are the invoke> command that apply to txt2img:
-
-| Argument <img width="680" align="right"/> | Shortcut <img width="420" align="right"/> | Default <img width="480" align="right"/> | Description                                                                                                                                                                                                                                      |
-| ----------------------------------------- | ----------------------------------------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| "my prompt"                               |                                           |                                          | Text prompt to use. The quotation marks are optional.                                                                                                                                                                                            |
-| `--width <int>`                           | `-W<int>`                                 | `512`                                    | Width of generated image                                                                                                                                                                                                                         |
-| `--height <int>`                          | `-H<int>`                                 | `512`                                    | Height of generated image                                                                                                                                                                                                                        |
-| `--iterations <int>`                      | `-n<int>`                                 | `1`                                      | How many images to generate from this prompt                                                                                                                                                                                                     |
-| `--steps <int>`                           | `-s<int>`                                 | `50`                                     | How many steps of refinement to apply                                                                                                                                                                                                            |
-| `--cfg_scale <float>`                     | `-C<float>`                               | `7.5`                                    | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0                                                                                                       |
-| `--seed <int>`                            | `-S<int>`                                 | `None`                                   | Set the random seed for the next series of images. This can be used to recreate an image generated previously.                                                                                                                                   |
-| `--sampler <sampler>`                     | `-A<sampler>`                             | `k_lms`                                  | Sampler to use. Use -h to get list of available samplers.                                                                                                                                                                                        |
-| `--karras_max <int>`                      |                                           | `29`                                     | When using k\_\* samplers, set the maximum number of steps before shifting from using the Karras noise schedule (good for low step counts) to the LatentDiffusion noise schedule (good for high step counts) This value is sticky. [29]          |
-| `--hires_fix`                             |                                           |                                          | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution                                                                          |
-| `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                      | Select level of compression for output files, from 0 (no compression) to 9 (max compression)                                                                                                                                                     |
-| `--grid`                                  | `-g`                                      | `False`                                  | Turn on grid mode to return a single image combining all the images generated by this prompt                                                                                                                                                     |
-| `--individual`                            | `-i`                                      | `True`                                   | Turn off grid mode (deprecated; leave off --grid instead)                                                                                                                                                                                        |
-| `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                    | Temporarily change the location of these images                                                                                                                                                                                                  |
-| `--seamless`                              |                                           | `False`                                  | Activate seamless tiling for interesting effects                                                                                                                                                                                                 |
-| `--seamless_axes`                         |                                           | `x,y`                                    | Specify which axes to use circular convolution on.                                                                                                                                                                                               |
-| `--log_tokenization`                      | `-t`                                      | `False`                                  | Display a color-coded list of the parsed tokens derived from the prompt                                                                                                                                                                          |
-| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](../features/OTHER.md#weighted-prompts)                                                                                                                                                  |
-| `--upscale <int> <float>`                 | `-U <int> <float>`                        | `-U 1 0.75`                              | Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75.                                                                                                                |
-| `--facetool_strength <float>`             | `-G <float> `                             | `-G0`                                    | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0)                                                                                                                               |
-| `--facetool <name>`                       | `-ft <name>`                              | `-ft gfpgan`                             | Select face restoration algorithm to use: gfpgan, codeformer                                                                                                                                                                                     |
-| `--codeformer_fidelity`                   | `-cf <float>`                             | `0.75`                                   | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality                                                                                                     |
-| `--save_original`                         | `-save_orig`                              | `False`                                  | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced.                                                                                                                                             |
-| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](VARIATIONS.md). |
-| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](VARIATIONS.md) for now to use this.                                                                                                                                                           |
-| `--save_intermediates <n>`                |                                           | `None`                                   | Save the image from every nth step into an "intermediates" folder inside the output directory                                                                                                                                                    |
-| `--h_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
-| `--v_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
-
-!!! note
-
-    the width and height of the image must be multiples of 64. You can
-    provide different values, but they will be rounded down to the nearest multiple
-    of 64.
-
-!!! example "This is a example of img2img"
-
-    ```bash
-    invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
-    ```
-
-This will modify the indicated vacation photograph by making it more like the
-prompt. Results will vary greatly depending on what is in the image. We also ask
-to --fit the image into a box no bigger than 640x480. Otherwise the image size
-will be identical to the provided photo and you may run out of memory if it is
-large.
-
-In addition to the command-line options recognized by txt2img, img2img accepts
-additional options:
-
-| Argument <img width="160" align="right"/> | Shortcut    | Default | Description                                                                                                                                |
-| ----------------------------------------- | ----------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
-| `--init_img <path>`                       | `-I<path>`  | `None`  | Path to the initialization image                                                                                                           |
-| `--fit`                                   | `-F`        | `False` | Scale the image to fit into the specified -H and -W dimensions                                                                             |
-| `--strength <float>`                      | `-s<float>` | `0.75`  | How hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
-
-### inpainting
-
-!!! example ""
-
-    ```bash
-    invoke> waterfall and rainbow -I./vacation-photo.png -M./vacation-mask.png -W640 -H480 --fit
-    ```
-
-    This will do the same thing as img2img, but image alterations will
-    only occur within transparent areas defined by the mask file specified
-    by `-M`. You may also supply just a single initial image with the areas
-    to overpaint made transparent, but you must be careful not to destroy
-    the pixels underneath when you create the transparent areas. See
-    [Inpainting](INPAINTING.md) for details.
-
-inpainting accepts all the arguments used for txt2img and img2img, as well as
-the --mask (-M) and --text_mask (-tm) arguments:
-
-| Argument <img width="100" align="right"/> | Shortcut                 | Default | Description                                                                                      |
-| ----------------------------------------- | ------------------------ | ------- | ------------------------------------------------------------------------------------------------ |
-| `--init_mask <path>`                      | `-M<path>`               | `None`  | Path to an image the same size as the initial_image, with areas for inpainting made transparent. |
-| `--invert_mask `                          |                          | False   | If true, invert the mask so that transparent areas are opaque and vice versa.                    |
-| `--text_mask <prompt> [<float>]`          | `-tm <prompt> [<float>]` | <none>  | Create a mask from a text prompt describing part of the image                                    |
-
-The mask may either be an image with transparent areas, in which case the
-inpainting will occur in the transparent areas only, or a black and white image,
-in which case all black areas will be painted into.
-
-`--text_mask` (short form `-tm`) is a way to generate a mask using a text
-description of the part of the image to replace. For example, if you have an
-image of a breakfast plate with a bagel, toast and scrambled eggs, you can
-selectively mask the bagel and replace it with a piece of cake this way:
-
-```bash
-invoke> a piece of cake -I /path/to/breakfast.png -tm bagel
-```
-
-The algorithm uses <a
-href="https://github.com/timojl/clipseg">clipseg</a> to classify different
-regions of the image. The classifier puts out a confidence score for each region
-it identifies. Generally regions that score above 0.5 are reliable, but if you
-are getting too much or too little masking you can adjust the threshold down (to
-get more mask), or up (to get less). In this example, by passing `-tm` a higher
-value, we are insisting on a more stringent classification.
-
-```bash
-invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
-```
-
-### Custom Styles and Subjects
-
-You can load and use hundreds of community-contributed Textual
-Inversion models just by typing the appropriate trigger phrase. Please
-see [Concepts Library](../features/CONCEPTS.md) for more details.
-
-## Other Commands
-
-The CLI offers a number of commands that begin with "!".
-
-### Postprocessing images
-
-To postprocess a file using face restoration or upscaling, use the `!fix`
-command.
-
-#### `!fix`
-
-This command runs a post-processor on a previously-generated image. It takes a
-PNG filename or path and applies your choice of the `-U`, `-G`, or `--embiggen`
-switches in order to fix faces or upscale. If you provide a filename, the script
-will look for it in the current output directory. Otherwise you can provide a
-full or partial path to the desired file.
-
-Some examples:
-
-!!! example "Upscale to 4X its original size and fix faces using codeformer"
-
-    ```bash
-    invoke> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
-    ```
-
-!!! example "Use the GFPGAN algorithm to fix faces, then upscale to 3X using --embiggen"
-
-    ```bash
-    invoke> !fix 0000045.4829112.png -G0.8 -ft gfpgan
-    >> fixing outputs/img-samples/0000045.4829112.png
-    >> retrieved seed 4829112 and prompt "boy enjoying a banana split"
-    >> GFPGAN - Restoring Faces for image seed:4829112
-    Outputs:
-    [1] outputs/img-samples/000017.4829112.gfpgan-00.png: !fix "outputs/img-samples/0000045.4829112.png" -s 50 -S  -W 512 -H 512 -C 7.5 -A k_lms -G 0.8
-    ```
-
-#### `!mask`
-
-This command takes an image, a text prompt, and uses the `clipseg` algorithm to
-automatically generate a mask of the area that matches the text prompt. It is
-useful for debugging the text masking process prior to inpainting with the
-`--text_mask` argument. See [INPAINTING.md] for details.
-
-### Model selection and importation
-
-The CLI allows you to add new models on the fly, as well as to switch
-among them rapidly without leaving the script. There are several
-different model formats, each described in the [Model Installation
-Guide](../installation/050_INSTALLING_MODELS.md).
-
-#### `!models`
-
-This prints out a list of the models defined in `config/models.yaml'. The active
-model is bold-faced
-
-Example:
-
-<pre>
-inpainting-1.5            not loaded  Stable Diffusion inpainting model
-<b>stable-diffusion-1.5          active  Stable Diffusion v1.5</b>
-waifu-diffusion           not loaded  Waifu Diffusion v1.4
-</pre>
-
-#### `!switch <model>`
-
-This quickly switches from one model to another without leaving the CLI script.
-`invoke.py` uses a memory caching system; once a model has been loaded,
-switching back and forth is quick. The following example shows this in action.
-Note how the second column of the `!models` table changes to `cached` after a
-model is first loaded, and that the long initialization step is not needed when
-loading a cached model.
-
-#### `!import_model <hugging_face_repo_ID>`
-
-This imports and installs a `diffusers`-style model that is stored on
-the [HuggingFace Web Site](https://huggingface.co). You can look up
-any [Stable Diffusion diffusers
-model](https://huggingface.co/models?library=diffusers) and install it
-with a command like the following:
-
-```bash
-!import_model prompthero/openjourney
-```
-
-#### `!import_model <path/to/diffusers/directory>`
-
-If you have a copy of a `diffusers`-style model saved to disk, you can
-import it by passing the path to model's top-level directory.
-
-#### `!import_model <url>`
-
-For a `.ckpt` or `.safetensors` file, if you have a direct download
-URL for the file, you can provide it to `!import_model` and the file
-will be downloaded and installed for you.
-
-#### `!import_model <path/to/model/weights.ckpt>`
-
-This command imports a new model weights file into InvokeAI, makes it available
-for image generation within the script, and writes out the configuration for the
-model into `config/models.yaml` for use in subsequent sessions.
-
-Provide `!import_model` with the path to a weights file ending in `.ckpt`. If
-you type a partial path and press tab, the CLI will autocomplete. Although it
-will also autocomplete to `.vae` files, these are not currenty supported (but
-will be soon).
-
-When you hit return, the CLI will prompt you to fill in additional information
-about the model, including the short name you wish to use for it with the
-`!switch` command, a brief description of the model, the default image width and
-height to use with this model, and the model's configuration file. The latter
-three fields are automatically filled with reasonable defaults. In the example
-below, the bold-faced text shows what the user typed in with the exception of
-the width, height and configuration file paths, which were filled in
-automatically.
-
-#### `!import_model <path/to/directory_of_models>`
-
-If you provide the path of a directory that contains one or more
-`.ckpt` or `.safetensors` files, the CLI will scan the directory and
-interactively offer to import the models it finds there. Also see the
-`--autoconvert` command-line option.
-
-#### `!edit_model <name_of_model>`
-
-The `!edit_model` command can be used to modify a model that is already defined
-in `config/models.yaml`. Call it with the short name of the model you wish to
-modify, and it will allow you to modify the model's `description`, `weights` and
-other fields.
-
-Example:
-
-<pre>
-invoke> <b>!edit_model waifu-diffusion</b>
->> Editing model waifu-diffusion from configuration file ./configs/models.yaml
-description: <b>Waifu diffusion v1.4beta</b>
-weights: models/ldm/stable-diffusion-v1/<b>model-epoch10-float16.ckpt</b>
-config: configs/stable-diffusion/v1-inference.yaml
-width: 512
-height: 512
-
->> New configuration:
-waifu-diffusion:
-  config: configs/stable-diffusion/v1-inference.yaml
-  description: Waifu diffusion v1.4beta
-  weights: models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
-  height: 512
-  width: 512
-
-OK to import [n]? y
->> Caching model stable-diffusion-1.4 in system RAM
->> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
-...
-</pre>
-
-### History processing
-
-The CLI provides a series of convenient commands for reviewing previous actions,
-retrieving them, modifying them, and re-running them.
-
-#### `!history`
-
-The invoke script keeps track of all the commands you issue during a session,
-allowing you to re-run them. On Mac and Linux systems, it also writes the
-command-line history out to disk, giving you access to the most recent 1000
-commands issued.
-
-The `!history` command will return a numbered list of all the commands issued
-during the session (Windows), or the most recent 1000 commands (Mac|Linux). You
-can then repeat a command by using the command `!NNN`, where "NNN" is the
-history line number. For example:
-
-!!! example ""
-
-    ```bash
-    invoke> !history
-    ...
-    [14] happy woman sitting under tree wearing broad hat and flowing garment
-    [15] beautiful woman sitting under tree wearing broad hat and flowing garment
-    [18] beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6
-    [20] watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    [21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    ...
-    invoke> !20
-    invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    ```
-
-####`!fetch`
-
-This command retrieves the generation parameters from a previously generated
-image and either loads them into the command line (Linux|Mac), or prints them
-out in a comment for copy-and-paste (Windows). You may provide either the name
-of a file in the current output directory, or a full file path. Specify path to
-a folder with image png files, and wildcard \*.png to retrieve the dream command
-used to generate the images, and save them to a file commands.txt for further
-processing.
-
-!!! example "load the generation command for a single png file"
-
-    ```bash
-    invoke> !fetch 0000015.8929913.png
-    # the script returns the next line, ready for editing and running:
-    invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
-    ```
-
-!!! example "fetch the generation commands from a batch of files and store them into `selected.txt`"
-
-    ```bash
-    invoke> !fetch outputs\selected-imgs\*.png selected.txt
-    ```
-
-#### `!replay`
-
-This command replays a text file generated by !fetch or created manually
-
-!!! example
-
-    ```bash
-    invoke> !replay outputs\selected-imgs\selected.txt
-    ```
-
-!!! note
-
-    These commands may behave unexpectedly if given a PNG file that was
-    not generated by InvokeAI.
-
-#### `!search <search string>`
-
-This is similar to !history but it only returns lines that contain
-`search string`. For example:
-
-```bash
-invoke> !search surreal
-[21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-```
-
-#### `!clear`
-
-This clears the search history from memory and disk. Be advised that this
-operation is irreversible and does not issue any warnings!
-
-## Command-line editing and completion
-
-The command-line offers convenient history tracking, editing, and command
-completion.
-
-- To scroll through previous commands and potentially edit/reuse them, use the
-  ++up++ and ++down++ keys.
-- To edit the current command, use the ++left++ and ++right++ keys to position
-  the cursor, and then ++backspace++, ++delete++ or insert characters.
-- To move to the very beginning of the command, type ++ctrl+a++ (or
-  ++command+a++ on the Mac)
-- To move to the end of the command, type ++ctrl+e++.
-- To cut a section of the command, position the cursor where you want to start
-  cutting and type ++ctrl+k++
-- To paste a cut section back in, position the cursor where you want to paste,
-  and type ++ctrl+y++
-
-Windows users can get similar, but more limited, functionality if they launch
-`invoke.py` with the `winpty` program and have the `pyreadline3` library
-installed:
-
-```batch
-> winpty python scripts\invoke.py
-```
-
-On the Mac and Linux platforms, when you exit invoke.py, the last 1000 lines of
-your command-line history will be saved. When you restart `invoke.py`, you can
-access the saved history using the ++up++ key.
-
-In addition, limited command-line completion is installed. In various contexts,
-you can start typing your command and press ++tab++. A list of potential
-completions will be presented to you. You can then type a little more, hit
-++tab++ again, and eventually autocomplete what you want.
-
-When specifying file paths using the one-letter shortcuts, the CLI will attempt
-to complete pathnames for you. This is most handy for the `-I` (init image) and
-`-M` (init mask) paths. To initiate completion, start the path with a slash
-(`/`) or `./`. For example:
-
-```bash
-invoke> zebra with a mustache -I./test-pictures<TAB>
--I./test-pictures/Lincoln-and-Parrot.png  -I./test-pictures/zebra.jpg        -I./test-pictures/madonna.png
--I./test-pictures/bad-sketch.png          -I./test-pictures/man_with_eagle/
-```
-
-You can then type ++z++, hit ++tab++ again, and it will autofill to `zebra.jpg`.
-
-More text completion features (such as autocompleting seeds) are on their way.

docs/deprecated/EMBIGGEN.md

@@ -1,167 +0,0 @@
----
-title: Embiggen
----
-
-# :material-loupe: Embiggen
-
-**upscale your images on limited memory machines**
-
-GFPGAN and Real-ESRGAN are both memory intensive. In order to avoid
-crashes and memory overloads during the Stable Diffusion process,
-these effects are applied after Stable Diffusion has completed its
-work.
-
-In single image generations, you will see the output right away but
-when you are using multiple iterations, the images will first be
-generated and then upscaled and face restored after that process is
-complete. While the image generation is taking place, you will still
-be able to preview the base images.
-
-If you wish to stop during the image generation but want to upscale or
-face restore a particular generated image, pass it again with the same
-prompt and generated seed along with the `-U` and `-G` prompt
-arguments to perform those actions.
-
-## Embiggen
-
-If you wanted to be able to do more (pixels) without running out of VRAM,
-or you want to upscale with details that couldn't possibly appear
-without the context of a prompt, this is the feature to try out.
-
-Embiggen automates the process of taking an init image, upscaling it,
-cutting it into smaller tiles that slightly overlap, running all the
-tiles through img2img to refine details with respect to the prompt,
-and "stitching" the tiles back together into a cohesive image.
-
-It automatically computes how many tiles are needed, and so it can be fed
-*ANY* size init image and perform Img2Img on it (though it will be run only
-one tile at a time, which can cause problems, see the Note at the end).
-
-If you're familiar with "GoBig" (ala [progrock-stable](https://github.com/lowfuel/progrock-stable))
-it's similar to that, except it can work up to an arbitrarily large size
-(instead of just 2x), with tile overlaps configurable as a ratio, and
-has extra logic to re-run any number of the tile sub-sections of the image
-if for example a small part of a huge run got messed up.
-
-### Usage
-
-`-embiggen <scaling_factor> <esrgan_strength> <overlap_ratio OR overlap_pixels>`
-
-Takes a scaling factor relative to the size of the `--init_img` (`-I`), followed by
-ESRGAN upscaling strength (0 - 1.0), followed by minimum amount of overlap
-between tiles as a decimal ratio (0 - 1.0) *OR* a number of pixels.
-
-The scaling factor is how much larger than the `--init_img` the output
-should be, and will multiply both x and y axis, so an image that is a
-scaling factor of 3.0 has 3*3= 9 times as many pixels, and will take
-(at least) 9 times as long (see overlap for why it might be
-longer). If the `--init_img` is already the right size `-embiggen 1`,
-and it can also be less than one if the init_img is too big.
-
-Esrgan_strength defaults to 0.75, and the overlap_ratio defaults to
-0.25, both are optional.
-
-Unlike Img2Img, the `--width` (`-W`) and `--height` (`-H`) arguments
-do not control the size of the image as a whole, but the size of the
-tiles used to Embiggen the image.
-
-ESRGAN is used to upscale the `--init_img` prior to cutting it into
-tiles/pieces to run through img2img and then stitch back
-together. Embiggen can be run without ESRGAN; just set the strength to
-zero (e.g. `-embiggen 1.75 0`). The output of Embiggen can also be
-upscaled after it's finished (`-U`).
-
-The overlap is the minimum that tiles will overlap with adjacent
-tiles, specified as either a ratio or a number of pixels. How much the
-tiles overlap determines the likelihood the tiling will be noticable,
-really small overlaps (e.g. a couple of pixels) may produce noticeable
-grid-like fuzzy distortions in the final stitched image. Though, as
-the overlapping space doesn't contribute to making the image bigger,
-and the larger the overlap the more tiles (and the more time) it will
-take to finish.
-
-Because the overlapping parts of tiles don't "contribute" to
-increasing size, every tile after the first in a row or column
-effectively only covers an extra `1 - overlap_ratio` on each axis. If
-the input/`--init_img` is same size as a tile, the ideal (for time)
-scaling factors with the default overlap (0.25) are 1.75, 2.5, 3.25,
-4.0, etc.
-
-`-embiggen_tiles <spaced list of tiles>`
-
-An advanced usage useful if you only want to alter parts of the image
-while running Embiggen. It takes a list of tiles by number to run and
-replace onto the initial image e.g. `1 3 5`. It's useful for either
-fixing problem spots from a previous Embiggen run, or selectively
-altering the prompt for sections of an image - for creative or
-coherency reasons.
-
-Tiles are numbered starting with one, and left-to-right,
-top-to-bottom.  So, if you are generating a 3x3 tiled image, the
-middle row would be `4 5 6`.
-
-`-embiggen_strength <strength>`
-
-Another advanced option if you want to experiment with the strength parameter
-that embiggen uses when it calls Img2Img. Values range from 0.0 to 1.0
-and lower values preserve more of the character of the initial image.
-Values that are too high will result in a completely different end image,
-while values that are too low will result in an image not dissimilar to one
-you would get with ESRGAN upscaling alone. The default value is 0.4.
-
-### Examples
-
-!!! example ""
-
-    Running Embiggen with 512x512 tiles on an existing image, scaling up by a factor of 2.5x;
-    and doing the same again (default ESRGAN strength is 0.75, default overlap between tiles is 0.25):
-
-    ```bash
-    invoke > a photo of a forest at sunset -s 100 -W 512 -H 512 -I outputs/forest.png -f 0.4 -embiggen 2.5
-    invoke > a photo of a forest at sunset -s 100 -W 512 -H 512 -I outputs/forest.png -f 0.4 -embiggen 2.5 0.75 0.25
-    ```
-
-    If your starting image was also 512x512 this should have taken 9 tiles.
-
-!!! example ""
-
-    If there weren't enough clouds in the sky of that forest you just made
-    (and that image is about 1280 pixels (512*2.5) wide A.K.A. three
-    512x512 tiles with 0.25 overlaps wide) we can replace that top row of
-    tiles:
-
-    ```bash
-    invoke> a photo of puffy clouds over a forest at sunset -s 100 -W 512 -H 512 -I outputs/000002.seed.png -f 0.5 -embiggen_tiles 1 2 3
-    ```
-
-## Fixing Previously-Generated Images
-
-It is easy to apply embiggen to any previously-generated file without having to
-look up the original prompt and provide an initial image. Just use the
-syntax `!fix path/to/file.png <embiggen>`. For example, you can rewrite the
-previous command to look like this:
-
-```bash
-invoke> !fix ./outputs/000002.seed.png -embiggen_tiles 1 2 3
-```
-
-A new file named `000002.seed.fixed.png` will be created in the output directory. Note that
-the `!fix` command does not replace the original file, unlike the behavior at generate time.
-You do not need to provide the prompt, and `!fix` automatically selects a good strength for
-embiggen-ing.
-
-!!! note
-
-    Because the same prompt is used on all the tiled images, and the model
-    doesn't have the context of anything outside the tile being run - it
-    can end up creating repeated pattern (also called 'motifs') across all
-    the tiles based on that prompt. The best way to combat this is
-    lowering the `--strength` (`-f`) to stay more true to the init image,
-    and increasing the number of steps so there is more compute-time to
-    create the detail.  Anecdotally `--strength` 0.35-0.45 works pretty
-    well on most things. It may also work great in some examples even with
-    the `--strength` set high for patterns, landscapes, or subjects that
-    are more abstract. Because this is (relatively) fast, you can also
-    preserve the best parts from each.
-
-Author: [Travco](https://github.com/travco)

docs/deprecated/INPAINTING.md

@@ -1,310 +0,0 @@
----
-title: Inpainting
----
-
-# :octicons-paintbrush-16: Inpainting
-
-## **Creating Transparent Regions for Inpainting**
-
-Inpainting is really cool. To do it, you start with an initial image and use a
-photoeditor to make one or more regions transparent (i.e. they have a "hole" in
-them). You then provide the path to this image at the dream> command line using
-the `-I` switch. Stable Diffusion will only paint within the transparent region.
-
-There's a catch. In the current implementation, you have to prepare the initial
-image correctly so that the underlying colors are preserved under the
-transparent area. Many imaging editing applications will by default erase the
-color information under the transparent pixels and replace them with white or
-black, which will lead to suboptimal inpainting. It often helps to apply
-incomplete transparency, such as any value between 1 and 99%
-
-You also must take care to export the PNG file in such a way that the color
-information is preserved. There is often an option in the export dialog that
-lets you specify this.
-
-If your photoeditor is erasing the underlying color information, `dream.py` will
-give you a big fat warning. If you can't find a way to coax your photoeditor to
-retain color values under transparent areas, then you can combine the `-I` and
-`-M` switches to provide both the original unedited image and the masked
-(partially transparent) image:
-
-```bash
-invoke> "man with cat on shoulder" -I./images/man.png -M./images/man-transparent.png
-```
-
-## **Masking using Text**
-
-You can also create a mask using a text prompt to select the part of the image
-you want to alter, using the [clipseg](https://github.com/timojl/clipseg)
-algorithm. This works on any image, not just ones generated by InvokeAI.
-
-The `--text_mask` (short form `-tm`) option takes two arguments. The first
-argument is a text description of the part of the image you wish to mask (paint
-over). If the text description contains a space, you must surround it with
-quotation marks. The optional second argument is the minimum threshold for the
-mask classifier's confidence score, described in more detail below.
-
-To see how this works in practice, here's an image of a still life painting that
-I got off the web.
-
-<figure markdown>
-![still life scaled](../assets/still-life-scaled.jpg)
-</figure>
-
-You can selectively mask out the orange and replace it with a baseball in this
-way:
-
-```bash
-invoke> a baseball -I /path/to/still_life.png -tm orange
-```
-
-<figure markdown>
-![](../assets/still-life-inpainted.png)
-</figure>
-
-The clipseg classifier produces a confidence score for each region it
-identifies. Generally regions that score above 0.5 are reliable, but if you are
-getting too much or too little masking you can adjust the threshold down (to get
-more mask), or up (to get less). In this example, by passing `-tm` a higher
-value, we are insisting on a tigher mask. However, if you make it too high, the
-orange may not be picked up at all!
-
-```bash
-invoke> a baseball -I /path/to/breakfast.png -tm orange 0.6
-```
-
-The `!mask` command may be useful for debugging problems with the text2mask
-feature. The syntax is `!mask /path/to/image.png -tm <text> <threshold>`
-
-It will generate three files:
-
-- The image with the selected area highlighted.
-  - it will be named XXXXX.<imagename>.<prompt>.selected.png
-- The image with the un-selected area highlighted.
-  - it will be named XXXXX.<imagename>.<prompt>.deselected.png
-- The image with the selected area converted into a black and white image
-  according to the threshold level
-  - it will be named XXXXX.<imagename>.<prompt>.masked.png
-
-The `.masked.png` file can then be directly passed to the `invoke>` prompt in
-the CLI via the `-M` argument. Do not attempt this with the `selected.png` or
-`deselected.png` files, as they contain some transparency throughout the image
-and will not produce the desired results.
-
-Here is an example of how `!mask` works:
-
-```bash
-invoke> !mask ./test-pictures/curly.png -tm hair 0.5
->> generating masks from ./test-pictures/curly.png
->> Initializing clipseg model for text to mask inference
-Outputs:
-[941.1] outputs/img-samples/000019.curly.hair.deselected.png: !mask ./test-pictures/curly.png -tm hair 0.5
-[941.2] outputs/img-samples/000019.curly.hair.selected.png: !mask ./test-pictures/curly.png -tm hair 0.5
-[941.3] outputs/img-samples/000019.curly.hair.masked.png: !mask ./test-pictures/curly.png -tm hair 0.5
-```
-
-<figure markdown>
-![curly](../assets/outpainting/curly.png)
-<figcaption>Original image "curly.png"</figcaption>
-</figure>
-
-<figure markdown>
-![curly hair selected](../assets/inpainting/000019.curly.hair.selected.png)
-<figcaption>000019.curly.hair.selected.png</figcaption>
-</figure>
-
-<figure markdown>
-![curly hair deselected](../assets/inpainting/000019.curly.hair.deselected.png)
-<figcaption>000019.curly.hair.deselected.png</figcaption>
-</figure>
-
-<figure markdown>
-![curly hair masked](../assets/inpainting/000019.curly.hair.masked.png)
-<figcaption>000019.curly.hair.masked.png</figcaption>
-</figure>
-
-It looks like we selected the hair pretty well at the 0.5 threshold (which is
-the default, so we didn't actually have to specify it), so let's have some fun:
-
-```bash
-invoke> medusa with cobras -I ./test-pictures/curly.png -M 000019.curly.hair.masked.png -C20
->> loaded input image of size 512x512 from ./test-pictures/curly.png
-...
-Outputs:
-[946] outputs/img-samples/000024.801380492.png: "medusa with cobras" -s 50 -S 801380492 -W 512 -H 512 -C 20.0 -I ./test-pictures/curly.png -A k_lms -f 0.75
-```
-
-<figure markdown>
-![](../assets/inpainting/000024.801380492.png)
-</figure>
-
-You can also skip the `!mask` creation step and just select the masked
-
-region directly:
-
-```bash
-invoke> medusa with cobras -I ./test-pictures/curly.png -tm hair -C20
-```
-
-## Using the RunwayML inpainting model
-
-The
-[RunwayML Inpainting Model v1.5](https://huggingface.co/runwayml/stable-diffusion-inpainting)
-is a specialized version of
-[Stable Diffusion v1.5](https://huggingface.co/spaces/runwayml/stable-diffusion-v1-5)
-that contains extra channels specifically designed to enhance inpainting and
-outpainting. While it can do regular `txt2img` and `img2img`, it really shines
-when filling in missing regions. It has an almost uncanny ability to blend the
-new regions with existing ones in a semantically coherent way.
-
-To install the inpainting model, follow the
-[instructions](../installation/050_INSTALLING_MODELS.md) for installing a new model.
-You may use either the CLI (`invoke.py` script) or directly edit the
-`configs/models.yaml` configuration file to do this. The main thing to watch out
-for is that the the model `config` option must be set up to use
-`v1-inpainting-inference.yaml` rather than the `v1-inference.yaml` file that is
-used by Stable Diffusion 1.4 and 1.5.
-
-After installation, your `models.yaml` should contain an entry that looks like
-this one:
-
-```yml
-inpainting-1.5:
-  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
-  description: SD inpainting v1.5
-  config: configs/stable-diffusion/v1-inpainting-inference.yaml
-  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
-  width: 512
-  height: 512
-```
-
-As shown in the example, you may include a VAE fine-tuning weights file as well.
-This is strongly recommended.
-
-To use the custom inpainting model, launch `invoke.py` with the argument
-`--model inpainting-1.5` or alternatively from within the script use the
-`!switch inpainting-1.5` command to load and switch to the inpainting model.
-
-You can now do inpainting and outpainting exactly as described above, but there
-will (likely) be a noticeable improvement in coherence. Txt2img and Img2img will
-work as well.
-
-There are a few caveats to be aware of:
-
-1. The inpainting model is larger than the standard model, and will use nearly 4
-   GB of GPU VRAM. This makes it unlikely to run on a 4 GB graphics card.
-
-2. When operating in Img2img mode, the inpainting model is much less steerable
-   than the standard model. It is great for making small changes, such as
-   changing the pattern of a fabric, or slightly changing a subject's expression
-   or hair, but the model will resist making the dramatic alterations that the
-   standard model lets you do.
-
-3. While the `--hires` option works fine with the inpainting model, some special
-   features, such as `--embiggen` are disabled.
-
-4. Prompt weighting (`banana++ sushi`) and merging work well with the inpainting
-   model, but prompt swapping
-   (`a ("fluffy cat").swap("smiling dog") eating a hotdog`) will not have any
-   effect due to the way the model is set up. You may use text masking (with
-   `-tm thing-to-mask`) as an effective replacement.
-
-5. The model tends to oversharpen image if you use high step or CFG values. If
-   you need to do large steps, use the standard model.
-
-6. The `--strength` (`-f`) option has no effect on the inpainting model due to
-   its fundamental differences with the standard model. It will always take the
-   full number of steps you specify.
-
-## Troubleshooting
-
-Here are some troubleshooting tips for inpainting and outpainting.
-
-## Inpainting is not changing the masked region enough!
-
-One of the things to understand about how inpainting works is that it is
-equivalent to running img2img on just the masked (transparent) area. img2img
-builds on top of the existing image data, and therefore will attempt to preserve
-colors, shapes and textures to the best of its ability. Unfortunately this means
-that if you want to make a dramatic change in the inpainted region, for example
-replacing a red wall with a blue one, the algorithm will fight you.
-
-You have a couple of options. The first is to increase the values of the
-requested steps (`-sXXX`), strength (`-f0.XX`), and/or condition-free guidance
-(`-CXX.X`). If this is not working for you, a more extreme step is to provide
-the `--inpaint_replace 0.X` (`-r0.X`) option. This value ranges from 0.0 to 1.0.
-The higher it is the less attention the algorithm will pay to the data
-underneath the masked region. At high values this will enable you to replace
-colored regions entirely, but beware that the masked region mayl not blend in
-with the surrounding unmasked regions as well.
-
----
-
-## Recipe for GIMP
-
-[GIMP](https://www.gimp.org/) is a popular Linux photoediting tool.
-
-1. Open image in GIMP.
-2. Layer->Transparency->Add Alpha Channel
-3. Use lasso tool to select region to mask
-4. Choose Select -> Float to create a floating selection
-5. Open the Layers toolbar (^L) and select "Floating Selection"
-6. Set opacity to a value between 0% and 99%
-7. Export as PNG
-8. In the export dialogue, Make sure the "Save colour values from transparent
-   pixels" checkbox is selected.
-
----
-
-## Recipe for Adobe Photoshop
-
-1. Open image in Photoshop
-
-    <figure markdown>
-    ![step1](../assets/step1.png)
-    </figure>
-
-2. Use any of the selection tools (Marquee, Lasso, or Wand) to select the area
-   you desire to inpaint.
-
-    <figure markdown>
-    ![step2](../assets/step2.png)
-    </figure>
-
-3. Because we'll be applying a mask over the area we want to preserve, you
-   should now select the inverse by using the ++shift+ctrl+i++ shortcut, or
-   right clicking and using the "Select Inverse" option.
-
-4. You'll now create a mask by selecting the image layer, and Masking the
-   selection. Make sure that you don't delete any of the underlying image, or
-   your inpainting results will be dramatically impacted.
-
-    <figure markdown>
-    ![step4](../assets/step4.png)
-    </figure>
-
-5. Make sure to hide any background layers that are present. You should see the
-   mask applied to your image layer, and the image on your canvas should display
-   the checkered background.
-
-    <figure markdown>
-    ![step5](../assets/step5.png)
-    </figure>
-
-6. Save the image as a transparent PNG by using `File`-->`Save a Copy` from the
-   menu bar, or by using the keyboard shortcut ++alt+ctrl+s++
-
-    <figure markdown>
-    ![step6](../assets/step6.png)
-    </figure>
-
-7. After following the inpainting instructions above (either through the CLI or
-   the Web UI), marvel at your newfound ability to selectively invoke. Lookin'
-   good!
-
-    <figure markdown>
-   ![step7](../assets/step7.png)
-    </figure>
-
-8. In the export dialogue, Make sure the "Save colour values from transparent
-   pixels" checkbox is selected.

docs/deprecated/OUTPAINTING.md

@@ -1,171 +0,0 @@
----
-title: Outpainting
----
-
-# :octicons-paintbrush-16: Outpainting
-
-## Outpainting and outcropping
-
-Outpainting is a process by which the AI generates parts of the image that are
-outside its original frame. It can be used to fix up images in which the subject
-is off center, or when some detail (often the top of someone's head!) is cut
-off.
-
-InvokeAI supports two versions of outpainting, one called "outpaint" and the
-other "outcrop." They work slightly differently and each has its advantages and
-drawbacks.
-
-### Outpainting
-
-Outpainting is the same as inpainting, except that the painting occurs in the
-regions outside of the original image. To outpaint using the `invoke.py` command
-line script, prepare an image in which the borders to be extended are pure
-black. Add an alpha channel (if there isn't one already), and make the borders
-completely transparent and the interior completely opaque. If you wish to modify
-the interior as well, you may create transparent holes in the transparency
-layer, which `img2img` will paint into as usual.
-
-Pass the image as the argument to the `-I` switch as you would for regular
-inpainting:
-
-```bash
-invoke> a stream by a river -I /path/to/transparent_img.png
-```
-
-You'll likely be delighted by the results.
-
-### Tips
-
-1. Do not try to expand the image too much at once. Generally it is best to
-   expand the margins in 64-pixel increments. 128 pixels often works, but your
-   mileage may vary depending on the nature of the image you are trying to
-   outpaint into.
-
-2. There are a series of switches that can be used to adjust how the inpainting
-   algorithm operates. In particular, you can use these to minimize the seam
-   that sometimes appears between the original image and the extended part.
-   These switches are:
-
-| switch                     | default | description                                                            |
-| -------------------------- | ------- | ---------------------------------------------------------------------- |
-| `--seam_size SEAM_SIZE `   | `0`     | Size of the mask around the seam between original and outpainted image |
-| `--seam_blur SEAM_BLUR`    | `0`     | The amount to blur the seam inwards                                    |
-| `--seam_strength STRENGTH` | `0.7`   | The img2img strength to use when filling the seam                      |
-| `--seam_steps SEAM_STEPS`  | `10`    | The number of steps to use to fill the seam.                           |
-| `--tile_size TILE_SIZE`    | `32`    | The tile size to use for filling outpaint areas                        |
-
-### Outcrop
-
-The `outcrop` extension gives you a convenient `!fix` postprocessing command
-that allows you to extend a previously-generated image in 64 pixel increments in
-any direction. You can apply the module to any image previously-generated by
-InvokeAI. Note that it works with arbitrary PNG photographs, but not currently
-with JPG or other formats. Outcropping is particularly effective when combined
-with the
-[runwayML custom inpainting model](INPAINTING.md#using-the-runwayml-inpainting-model).
-
-Consider this image:
-
-<figure markdown>
-![curly_woman](../assets/outpainting/curly.png)
-</figure>
-
-Pretty nice, but it's annoying that the top of her head is cut off. She's also a
-bit off center. Let's fix that!
-
-```bash
-invoke> !fix images/curly.png --outcrop top 128 right 64 bottom 64
-```
-
-This is saying to apply the `outcrop` extension by extending the top of the
-image by 128 pixels, and the right and bottom of the image by 64 pixels. You can
-use any combination of top|left|right|bottom, and specify any number of pixels
-to extend. You can also abbreviate `--outcrop` to `-c`.
-
-The result looks like this:
-
-<figure markdown>
-![curly_woman_outcrop](../assets/outpainting/curly-outcrop-2.png)
-</figure>
-
-The new image is larger than the original (576x704) because 64 pixels were added
-to the top and right sides. You will need enough VRAM to process an image of
-this size.
-
-#### Outcropping non-InvokeAI images
-
-You can outcrop an arbitrary image that was not generated by InvokeAI,
-but your results will vary. The `inpainting-1.5` model is highly
-recommended, but if not feasible, then you may be able to improve the
-output by conditioning the outcropping with a text prompt that
-describes the scene using the `--new_prompt` argument:
-
-```bash
-invoke> !fix images/vacation.png --outcrop top 128 --new_prompt "family vacation"
-```
-
-You may also provide a different seed for outcropping to use by passing
-`-S<seed>`. A negative seed will generate a new random seed.
-
-A number of caveats:
-
-1. Although you can specify any pixel values, they will be rounded up to the
-   nearest multiple of 64. Smaller values are better. Larger extensions are more
-   likely to generate artefacts. However, if you wish you can run the !fix
-   command repeatedly to cautiously expand the image.
-
-2. The extension is stochastic, meaning that each time you run it you'll get a
-   slightly different result. You can run it repeatedly until you get an image
-   you like. Unfortunately `!fix` does not currently respect the `-n`
-   (`--iterations`) argument.
-
-3. Your results will be _much_ better if you use the `inpaint-1.5` model
-   released by runwayML and installed by default by `invokeai-configure`.
-   This model was trained specifically to harmoniously fill in image gaps. The
-   standard model will work as well, but you may notice color discontinuities at
-   the border.
-
-4. When using the `inpaint-1.5` model, you may notice subtle changes to the area
-   outside the masked region. This is because the model performs an
-   encoding/decoding on the image as a whole. This does not occur with the
-   standard model.
-
-## Outpaint
-
-The `outpaint` extension does the same thing, but with subtle differences.
-Starting with the same image, here is how we would add an additional 64 pixels
-to the top of the image:
-
-```bash
-invoke> !fix images/curly.png --out_direction top 64
-```
-
-(you can abbreviate `--out_direction` as `-D`.
-
-The result is shown here:
-
-<figure markdown>
-![curly_woman_outpaint](../assets/outpainting/curly-outpaint.png)
-</figure>
-
-Although the effect is similar, there are significant differences from
-outcropping:
-
-- You can only specify one direction to extend at a time.
-- The image is **not** resized. Instead, the image is shifted by the specified
-  number of pixels. If you look carefully, you'll see that less of the lady's
-  torso is visible in the image.
-- Because the image dimensions remain the same, there's no rounding to multiples
-  of 64.
-- Attempting to outpaint larger areas will frequently give rise to ugly ghosting
-  effects.
-- For best results, try increasing the step number.
-- If you don't specify a pixel value in `-D`, it will default to half of the
-  whole image, which is likely not what you want.
-
-!!! tip
-
-    Neither `outpaint` nor `outcrop` are perfect, but we continue to tune
-    and improve them. If one doesn't work, try the other. You may also
-    wish to experiment with other `img2img` arguments, such as `-C`, `-f`
-    and `-s`.

docs/deprecated/TRANSLATION.md

@@ -1,19 +0,0 @@
-# Translation
-
-InvokeAI uses [Weblate](https://weblate.org) for translation. Weblate is a FOSS project providing a scalable translation service. Weblate automates the tedious parts of managing translation of a growing project, and the service is generously provided at no cost to FOSS projects like InvokeAI.
-
-## Contributing
-
-If you'd like to contribute by adding or updating a translation, please visit our [Weblate project](https://hosted.weblate.org/engage/invokeai/). You'll need to sign in with your GitHub account (a number of other accounts are supported, including Google).
-
-Once signed in, select a language and then the Web UI component. From here you can Browse and Translate strings from English to your chosen language. Zen mode offers a simpler translation experience.
-
-Your changes will be attributed to you in the automated PR process; you don't need to do anything else.
-
-## Help & Questions
-
-Please check Weblate's [documentation](https://docs.weblate.org/en/latest/index.html) or ping @psychedelicious or @blessedcoolant on Discord if you have any questions.
-
-## Thanks
-
-Thanks to the InvokeAI community for their efforts to translate the project!

docs/deprecated/VARIATIONS.md

@@ -1,131 +0,0 @@
----
-title: Variations
----
-
-# :material-tune-variant: Variations
-
-## Intro
-
-InvokeAI's support for variations enables you to do the following:
-
-1. Generate a series of systematic variations of an image, given a prompt. The
-   amount of variation from one image to the next can be controlled.
-
-2. Given two or more variations that you like, you can combine them in a
-   weighted fashion.
-
-!!! Information ""
-
-    This cheat sheet provides a quick guide for how this works in practice, using
-    variations to create the desired image of Xena, Warrior Princess.
-
-## Step 1 -- Find a base image that you like
-
-The prompt we will use throughout is:
-
-`#!bash "lucy lawless as xena, warrior princess, character portrait, high resolution."`
-
-This will be indicated as `#!bash "prompt"` in the examples below.
-
-First we let SD create a series of images in the usual way, in this case
-requesting six iterations.
-
-<figure markdown>
-![var1](../assets/variation_walkthru/000001.3357757885.png)
-<figcaption> Seed 3357757885 looks nice </figcaption>
-</figure>
-
----
-
-## Step 2 - Generating Variations
-
-Let's try to generate some variations on this image. We select the "*"
-symbol in the line of icons above the image in order to fix the prompt
-and seed. Then we open up the "Variations" section of the generation
-panel and use the slider to set the variation amount to 0.2. The
-higher this value, the more each generated image will differ from the
-previous one.
-
-Now we run the prompt a second time, requesting six iterations. You
-will see six images that are thematically related to each other. Try
-increasing and decreasing the variation amount and see what happens.
-
-### **Variation Sub Seeding**
-
-Note that the output for each image has a `-V` option giving the "variant
-subseed" for that image, consisting of a seed followed by the variation amount
-used to generate it.
-
-This gives us a series of closely-related variations, including the two shown
-here.
-
-<figure markdown>
-![var2](../assets/variation_walkthru/000002.3647897225.png)
-<figcaption>subseed 3647897225</figcaption>
-</figure>
-
-<figure markdown>
-![var3](../assets/variation_walkthru/000002.1614299449.png)
-<figcaption>subseed 1614299449</figcaption>
-</figure>
-
-I like the expression on Xena's face in the first one (subseed 3647897225), and
-the armor on her shoulder in the second one (subseed 1614299449). Can we combine
-them to get the best of both worlds?
-
-We combine the two variations using `-V` (`--with_variations`). Again, we must
-provide the seed for the originally-chosen image in order for this to work.
-
-```bash
-invoke> "prompt"  -S3357757885 -V3647897225,0.1,1614299449,0.1
-Outputs:
-./outputs/Xena/000003.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1 -S3357757885
-```
-
-Here we are providing equal weights (0.1 and 0.1) for both the subseeds. The
-resulting image is close, but not exactly what I wanted:
-
-<figure markdown>
-![var4](../assets/variation_walkthru/000003.1614299449.png)
-<figcaption> subseed 1614299449 </figcaption>
-</figure>
-
-We could either try combining the images with different weights, or we can
-generate more variations around the almost-but-not-quite image. We do the
-latter, using both the `-V` (combining) and `-v` (variation strength) options.
-Note that we use `-n6` to generate 6 variations:
-
-```bash
-invoke> "prompt" -S3357757885 -V3647897225,0.1,1614299449,0.1 -v0.05 -n6
-Outputs:
-./outputs/Xena/000004.3279757577.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,3279757577:0.05 -S3357757885
-./outputs/Xena/000004.2853129515.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2853129515:0.05 -S3357757885
-./outputs/Xena/000004.3747154981.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,3747154981:0.05 -S3357757885
-./outputs/Xena/000004.2664260391.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2664260391:0.05 -S3357757885
-./outputs/Xena/000004.1642517170.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,1642517170:0.05 -S3357757885
-./outputs/Xena/000004.2183375608.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2183375608:0.05 -S3357757885
-```
-
-This produces six images, all slight variations on the combination of the chosen
-two images. Here's the one I like best:
-
-<figure markdown>
-![var5](../assets/variation_walkthru/000004.3747154981.png)
-<figcaption> subseed 3747154981 </figcaption>
-</figure>
-
-As you can see, this is a very powerful tool, which when combined with subprompt
-weighting, gives you great control over the content and quality of your
-generated images.
-
-## Variations and Samplers
-
-The sampler you choose has a strong effect on variation strength. Some
-samplers, such as `k_euler_a` are very "creative" and produce significant
-amounts of image-to-image variation even when the seed is fixed and the
-`-v` argument is very low. Others are more deterministic. Feel free to
-experiment until you find the combination that you like.
-
-Also be aware of the [Perlin Noise](../features/OTHER.md#thresholding-and-perlin-noise-initialization-options)
-feature, which provides another way of introducing variability into your
-image generation requests.

docs/features/CONFIGURATION.md

@@ -6,259 +6,153 @@ title: Configuration
 
 ## Intro
 
-InvokeAI has numerous runtime settings which can be used to adjust
-many aspects of its operations, including the location of files and
-directories, memory usage, and performance. These settings can be
-viewed and customized in several ways:
+Runtime settings, including the location of files and
+directories, memory usage, and performance, are managed via the
+`invokeai.yaml` config file or environment variables. A subset
+of settings may be set via commandline arguments.
 
-1. By editing settings in the `invokeai.yaml` file.
-2. By setting environment variables.
-3. On the command-line, when InvokeAI is launched.
+Settings sources are used in this order:
 
-In addition, the most commonly changed settings are accessible
-graphically via the `invokeai-configure` script.
+- CLI args
+- Environment variables
+- `invokeai.yaml` settings
+- Fallback: defaults
 
-### How the Configuration System Works
+### InvokeAI Root Directory
 
-When InvokeAI is launched, the very first thing it needs to do is to
-find its "root" directory, which contains its configuration files,
-installed models, its database of images, and the folder(s) of
-generated images themselves. In this document, the root directory will
-be referred to as ROOT.
+On startup, InvokeAI searches for its "root" directory. This is the directory
+that contains models, images, the database, and so on. It also contains
+a configuration file called `invokeai.yaml`.
 
-#### Finding the Root Directory
+InvokeAI searches for the root directory in this order:
 
-To find its root directory, InvokeAI uses the following recipe:
+1. The `--root <path>` CLI arg.
+2. The environment variable INVOKEAI_ROOT.
+3. The directory containing the currently active virtual environment.
+4. Fallback: a directory in the current user's home directory named `invokeai`.
 
-1. It first looks for the argument `--root <path>` on the command line
-it was launched from, and uses the indicated path if present.
+### InvokeAI Configuration File
 
-2. Next it looks for the environment variable INVOKEAI_ROOT, and uses
-the directory path found there if present.
+Inside the root directory, we read settings from the `invokeai.yaml` file.
 
-3. If neither of these are present, then InvokeAI looks for the
-folder containing the `.venv` Python virtual environment directory for
-the currently active environment. This directory is checked for files
-expected inside the InvokeAI root before it is used.
+It has two sections - one for internal use and one for user settings:
 
-4. Finally, InvokeAI looks for a directory in the current user's home
-directory named `invokeai`.
+```yaml
+# Internal metadata - do not edit:
+schema_version: 4
 
-#### Reading the InvokeAI Configuration File
-
-Once the root directory has been located, InvokeAI looks for a file
-named `ROOT/invokeai.yaml`, and if present reads configuration values
-from it. The top of this file looks like this:
-
-```
-InvokeAI:
-  Web Server:
-    host: localhost
-    port: 9090
-    allow_origins: []
-    allow_credentials: true
-    allow_methods:
-    - '*'
-    allow_headers:
-    - '*'
-  Features:
-    esrgan: true
-    internet_available: true
-    log_tokenization: false
-    patchmatch: true
-    restore: true
-...
+# Put user settings here - see https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/:
+host: 0.0.0.0 # serve the app on your local network
+models_dir: D:\invokeai\models # store models on an external drive
+precision: float16 # always use fp16 precision
 ```
 
-This lines in this file are used to establish default values for
-Invoke's settings. In the above fragment, the Web Server's listening
-port is set to 9090 by the `port` setting.
+The settings in this file will override the defaults. You only need
+to change this file if the default for a particular setting doesn't
+work for you.
 
-You can edit this file with a text editor such as "Notepad" (do not
-use Word or any other word processor). When editing, be careful to
-maintain the indentation, and do not add extraneous text, as syntax
-errors will prevent InvokeAI from launching. A basic guide to the
-format of YAML files can be found
-[here](https://circleci.com/blog/what-is-yaml-a-beginner-s-guide/).
+Some settings, like [Model Marketplace API Keys], require the YAML
+to be formatted correctly. Here is a [basic guide to YAML files].
 
 You can fix a broken `invokeai.yaml` by deleting it and running the
 configuration script again -- option [6] in the launcher, "Re-run the
 configure script".
 
-#### Reading Environment Variables
+#### Custom Config File Location
 
-Next InvokeAI looks for defined environment variables in the format
-`INVOKEAI_<setting_name>`, for example `INVOKEAI_port`. Environment
-variable values take precedence over configuration file variables. On
-a Macintosh system, for example, you could change the port that the
-web server listens on by setting the environment variable this way:
+You can use any config file with the `--config` CLI arg. Pass in the path to the `invokeai.yaml` file you want to use.
 
-```
-export INVOKEAI_port=8000
-invokeai-web
+Note that environment variables will trump any settings in the config file.
+
+### Environment Variables
+
+All settings may be set via environment variables by prefixing `INVOKEAI_`
+to the variable name. For example, `INVOKEAI_HOST` would set the `host`
+setting.
+
+For non-primitive values, pass a JSON-encoded string:
+
+```sh
+export INVOKEAI_REMOTE_API_TOKENS='[{"url_regex":"modelmarketplace", "token": "12345"}]'
 ```
 
-Please check out these
-[Macintosh](https://phoenixnap.com/kb/set-environment-variable-mac)
-and
-[Windows](https://phoenixnap.com/kb/windows-set-environment-variable)
-guides for setting temporary and permanent environment variables.
+We suggest using `invokeai.yaml`, as it is more user-friendly.
 
-#### Reading the Command Line
+### CLI Args
 
-Lastly, InvokeAI takes settings from the command line, which override
-everything else. The command-line settings have the same name as the
-corresponding configuration file settings, preceded by a `--`, for
-example `--port 8000`.
+A subset of settings may be specified using CLI args:
 
-If you are using the launcher (`invoke.sh` or `invoke.bat`) to launch
-InvokeAI, then just pass the command-line arguments to the launcher:
+- `--root`: specify the root directory
+- `--config`: override the default `invokeai.yaml` file location
 
-```
-invoke.bat --port 8000 --host 0.0.0.0
+### All Settings
+
+Following the table are additional explanations for certain settings.
+
+<!-- prettier-ignore-start -->
+::: invokeai.app.services.config.config_default.InvokeAIAppConfig
+    options:
+        heading_level: 4
+        members: false
+        show_docstring_description: false
+        group_by_category: true
+        show_category_heading: false
+<!-- prettier-ignore-end -->
+
+#### Model Marketplace API Keys
+
+Some model marketplaces require an API key to download models. You can provide a URL pattern and appropriate token in your `invokeai.yaml` file to provide that API key.
+
+The pattern can be any valid regex (you may need to surround the pattern with quotes):
+
+```yaml
+remote_api_tokens:
+  # Any URL containing `models.com` will automatically use `your_models_com_token`
+  - url_regex: models.com
+    token: your_models_com_token
+  # Any URL matching this contrived regex will use `some_other_token`
+  - url_regex: '^[a-z]{3}whatever.*\.com$'
+    token: some_other_token
 ```
 
-The arguments will be applied when you select the web server option
-(and the other options as well).
+The provided token will be added as a `Bearer` token to the network requests to download the model files. As far as we know, this works for all model marketplaces that require authorization.
 
-If, on the other hand, you prefer to launch InvokeAI directly from the
-command line, you would first activate the virtual environment (known
-as the "developer's console" in the launcher), and run `invokeai-web`:
+#### Model Hashing
 
-```
-> C:\Users\Fred\invokeai\.venv\scripts\activate
-(.venv) > invokeai-web --port 8000 --host 0.0.0.0
+Models are hashed during installation, providing a stable identifier for models across all platforms. Hashing is a one-time operation.
+
+```yaml
+hashing_algorithm: blake3_single # default value
 ```
 
-You can get a listing and brief instructions for each of the
-command-line options by giving the `--help` argument:
+You might want to change this setting, depending on your system:
 
-```
-(.venv) > invokeai-web --help
-usage: InvokeAI [-h] [--host HOST] [--port PORT] [--allow_origins [ALLOW_ORIGINS ...]] [--allow_credentials | --no-allow_credentials] [--allow_methods [ALLOW_METHODS ...]]
-                [--allow_headers [ALLOW_HEADERS ...]] [--esrgan | --no-esrgan] [--internet_available | --no-internet_available] [--log_tokenization | --no-log_tokenization]
-                [--patchmatch | --no-patchmatch] [--restore | --no-restore]
-                [--always_use_cpu | --no-always_use_cpu] [--free_gpu_mem | --no-free_gpu_mem] [--max_loaded_models MAX_LOADED_MODELS] [--max_cache_size MAX_CACHE_SIZE]
-                [--max_vram_cache_size MAX_VRAM_CACHE_SIZE] [--gpu_mem_reserved GPU_MEM_RESERVED] [--precision {auto,float16,float32,autocast}]
-                [--sequential_guidance | --no-sequential_guidance] [--xformers_enabled | --no-xformers_enabled] [--tiled_decode | --no-tiled_decode] [--root ROOT]
-                [--autoimport_dir AUTOIMPORT_DIR] [--lora_dir LORA_DIR] [--embedding_dir EMBEDDING_DIR] [--controlnet_dir CONTROLNET_DIR] [--conf_path CONF_PATH]
-                [--models_dir MODELS_DIR] [--legacy_conf_dir LEGACY_CONF_DIR] [--db_dir DB_DIR] [--outdir OUTDIR] [--from_file FROM_FILE]
-                [--use_memory_db | --no-use_memory_db] [--model MODEL] [--log_handlers [LOG_HANDLERS ...]] [--log_format {plain,color,syslog,legacy}]
-                [--log_level {debug,info,warning,error,critical}] [--version | --no-version]
-```
+- `blake3_single` (default): Single-threaded - best for spinning HDDs, still OK for SSDs
+- `blake3_multi`: Parallelized, memory-mapped implementation - best for SSDs, terrible for spinning disks
+- `random`: Skip hashing entirely - fastest but of course no hash
 
-## The Configuration Settings
+During the first startup after upgrading to v4, all of your models will be hashed. This can take a few minutes.
 
-The configuration settings are divided into several distinct
-groups in `invokeia.yaml`:
+Most common algorithms are supported, like `md5`, `sha256`, and `sha512`. These are typically much, much slower than either of the BLAKE3 variants.
 
-### Web Server
+#### Path Settings
 
-| Setting             | Default Value | Description                                                                                                                |
-|---------------------|---------------|----------------------------------------------------------------------------------------------------------------------------|
-| `host`              | `localhost`   | Name or IP address of the network interface that the web server will listen on                                             |
-| `port`              | `9090`        | Network port number that the web server will listen on                                                                     |
-| `allow_origins`     | `[]`          | A list of host names or IP addresses that are allowed to connect to the InvokeAI API in the format `['host1','host2',...]` |
-| `allow_credentials` | `true`        | Require credentials for a foreign host to access the InvokeAI API (don't change this)                                      |
-| `allow_methods`     | `*`           | List of HTTP methods ("GET", "POST") that the web server is allowed to use when accessing the API                          |
-| `allow_headers`     | `*`           | List of HTTP headers that the web server will accept when accessing the API                                                |
-| `ssl_certfile`      | null          | Path to an SSL certificate file, used to enable HTTPS.                                                                     |
-| `ssl_keyfile`       | null          | Path to an SSL keyfile, if the key is not included in the certificate file.                                                |
+These options set the paths of various directories and files used by InvokeAI. Any user-defined paths should be absolute paths.
 
-The documentation for InvokeAI's API can be accessed by browsing to the following URL: [http://localhost:9090/docs].
-
-### Features
-
-These configuration settings allow you to enable and disable various InvokeAI features:
-
-| Setting  | Default Value  |  Description |
-|----------|----------------|--------------|
-| `esrgan`     | `true`      | Activate the ESRGAN upscaling options|
-| `internet_available` | `true`     | When a resource is not available locally, try to fetch it via the internet |
-| `log_tokenization` | `false`      | Before each text2image generation, print a color-coded representation of the prompt to the console; this can help understand why a prompt is not working as expected |
-| `patchmatch` | `true`     | Activate the "patchmatch" algorithm for improved inpainting |
-
-### Generation
-
-These options tune InvokeAI's memory and performance characteristics.
-
-| Setting               | Default Value | Description                                                                                                                                                                                                                                                      |
-|-----------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `sequential_guidance` | `false`       | Calculate guidance in serial rather than in parallel, lowering memory requirements at the cost of some performance loss                                                                                                                                          |
-| `attention_type`      | `auto`        | Select the type of attention to use. One of `auto`,`normal`,`xformers`,`sliced`, or `torch-sdp`                                                                                                                                                                  |
-| `attention_slice_size` | `auto`       | When "sliced" attention is selected, set the slice size. One of `auto`, `balanced`, `max` or the integers 1-8|
-| `force_tiled_decode`  | `false`       | Force the VAE step to decode in tiles, reducing memory consumption at the cost of performance |
-
-### Device
-
-These options configure the generation execution device.
-
-| Setting               | Default Value | Description                                                                                                                                                                                                                                                      |
-|-----------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `device`           | `auto`        | Preferred execution device. One of `auto`, `cpu`, `cuda`, `cuda:1`, `mps`. `auto` will choose the device depending on the hardware platform and the installed torch capabilities. |
-| `precision`           | `auto`        | Floating point precision. One of `auto`, `float16` or `float32`. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system |
-
-
-### Paths
-
-These options set the paths of various directories and files used by
-InvokeAI. Relative paths are interpreted relative to INVOKEAI_ROOT, so
-if INVOKEAI_ROOT is `/home/fred/invokeai` and the path is
-`autoimport/main`, then the corresponding directory will be located at
-`/home/fred/invokeai/autoimport/main`.
-
-| Setting  | Default Value  |  Description |
-|----------|----------------|--------------|
-| `autoimport_dir` | `autoimport/main`     | At startup time, read and import any main model files found in this directory |
-| `lora_dir` | `autoimport/lora`     | At startup time, read and import any LoRA/LyCORIS models found in this directory |
-| `embedding_dir` | `autoimport/embedding`  | At startup time, read and import any textual inversion (embedding) models found in this directory |
-| `controlnet_dir` | `autoimport/controlnet`  | At startup time, read and import any ControlNet models found in this directory |
-| `conf_path` | `configs/models.yaml`  | Location of the `models.yaml` model configuration file |
-| `models_dir` | `models`  | Location of the directory containing models installed by InvokeAI's model manager |
-| `legacy_conf_dir` | `configs/stable-diffusion`  | Location of the directory containing the .yaml configuration files for legacy checkpoint models |
-| `db_dir` | `databases`  | Location of the directory containing InvokeAI's image, schema and session database |
-| `outdir` | `outputs`  | Location of the directory in which the gallery of generated and uploaded images will be stored |
-| `use_memory_db` | `false`  | Keep database information in memory rather than on disk; this will not preserve image gallery information across restarts |
-
-Note that the autoimport directories will be searched recursively,
-allowing you to organize the models into folders and subfolders in any
-way you wish. In addition, while we have split up autoimport
-directories by the type of model they contain, this isn't
-necessary. You can combine different model types in the same folder
-and InvokeAI will figure out what they are. So you can easily use just
-one autoimport directory by commenting out the unneeded paths:
-
-```
-Paths:
-  autoimport_dir: autoimport
-#  lora_dir: null
-#  embedding_dir: null
-#  controlnet_dir: null
-```
-
-### Logging
-
-These settings control the information, warning, and debugging
-messages printed to the console log while InvokeAI is running:
-
-| Setting  | Default Value  |  Description |
-|----------|----------------|--------------|
-| `log_handlers` | `console` | This controls where log messages are sent, and can be a list of one or more destinations. Values include `console`, `file`, `syslog` and `http`. These are described in more detail below |
-| `log_format` | `color` | This controls the formatting of the log messages. Values are `plain`, `color`, `legacy` and `syslog` |
-| `log_level`  | `debug` | This filters messages according to the level of severity and can be one of `debug`, `info`, `warning`, `error` and `critical`. For example, setting to `warning` will display all messages at the warning level or higher, but won't display "debug" or "info" messages |
+#### Logging
 
 Several different log handler destinations are available, and multiple destinations are supported by providing a list:
 
-```
-  log_handlers:
-     - console
-     - syslog=localhost
-     - file=/var/log/invokeai.log
+```yaml
+log_handlers:
+  - console
+  - syslog=localhost
+  - file=/var/log/invokeai.log
 ```
 
-* `console` is the default. It prints log messages to the command-line window from which InvokeAI was launched.
+- `console` is the default. It prints log messages to the command-line window from which InvokeAI was launched.
 
-* `syslog` is only available on Linux and Macintosh systems. It uses
+- `syslog` is only available on Linux and Macintosh systems. It uses
   the operating system's "syslog" facility to write log file entries
   locally or to a remote logging machine. `syslog` offers a variety
   of configuration options:
@@ -271,7 +165,7 @@ Several different log handler destinations are available, and multiple destinati
                         - Log to LAN-connected server "fredserver" using the facility LOG_USER and datagram packets.
 ```
 
-* `http` can be used to log to a remote web server. The server must be
+- `http` can be used to log to a remote web server. The server must be
   properly configured to receive and act on log messages. The option
   accepts the URL to the web server, and a `method` argument
   indicating whether the message should be submitted using the GET or
@@ -283,7 +177,10 @@ Several different log handler destinations are available, and multiple destinati
 
 The `log_format` option provides several alternative formats:
 
-* `color`    - default format providing time, date and a message, using text colors to distinguish different log severities
-* `plain`    - same as above, but monochrome text only
-* `syslog`   - the log level and error message only, allowing the syslog system to attach the time and date
-* `legacy`   - a format similar to the one used by the legacy 2.3 InvokeAI releases.
+- `color` - default format providing time, date and a message, using text colors to distinguish different log severities
+- `plain` - same as above, but monochrome text only
+- `syslog` - the log level and error message only, allowing the syslog system to attach the time and date
+- `legacy` - a format similar to the one used by the legacy 2.3 InvokeAI releases.
+
+[basic guide to yaml files]: https://circleci.com/blog/what-is-yaml-a-beginner-s-guide/
+[Model Marketplace API Keys]: #model-marketplace-api-keys

docs/features/DATABASE.md

@@ -0,0 +1,35 @@
+---
+title: Database
+---
+
+# Invoke's SQLite Database
+
+Invoke uses a SQLite database to store image, workflow, model, and execution data.
+
+We take great care to ensure your data is safe, by utilizing transactions and a database migration system.
+
+Even so, when testing an prerelease version of the app, we strongly suggest either backing up your database or using an in-memory database. This ensures any prelease hiccups or databases schema changes will not cause problems for your data.
+
+## Database Backup
+
+Backing up your database is very simple. Invoke's data is stored in an `$INVOKEAI_ROOT` directory - where your `invoke.sh`/`invoke.bat` and `invokeai.yaml` files live.
+
+To back up your database, copy the `invokeai.db` file from `$INVOKEAI_ROOT/databases/invokeai.db` to somewhere safe.
+
+If anything comes up during prelease testing, you can simply copy your backup back into `$INVOKEAI_ROOT/databases/`.
+
+## In-Memory Database
+
+SQLite can run on an in-memory database. Your existing database is untouched when this mode is enabled, but your existing data won't be accessible.
+
+This is very useful for testing, as there is no chance of a database change modifying your "physical" database.
+
+To run Invoke with a memory database, edit your `invokeai.yaml` file, and add `use_memory_db: true` to the `Paths:` stanza:
+
+```yaml
+InvokeAI:
+  Development:
+    use_memory_db: true
+```
+
+Delete this line (or set it to `false`) to use your main database.

docs/features/LORAS.md

@@ -20,10 +20,7 @@ are applied to generate imagery. LoRAs may be supplied with a
 simply apply their effect without being triggered.
 
 LoRAs are typically stored in .safetensors files, which are the most
-secure way to store and transmit these types of weights. You may
-install any number of `.safetensors` LoRA files simply by copying them
-into the `autoimport/lora` directory of the corresponding InvokeAI models
-directory (usually `invokeai` in your home directory).
+secure way to store and transmit these types of weights.
 
 To use these when generating, open the LoRA menu item in the options
 panel, select the LoRAs you want to apply and ensure that they have

docs/help/FAQ.md

@@ -1,43 +1,213 @@
-# FAQs
+# FAQ
 
-**Where do I get started? How can I install Invoke?**
+!!! info "How to Reinstall"
 
-- You can download the latest installers [here](https://github.com/invoke-ai/InvokeAI/releases) - Note that any releases marked as *pre-release* are in a beta state. You may experience some issues, but we appreciate your help testing those! For stable/reliable installations, please install the **[Latest Release](https://github.com/invoke-ai/InvokeAI/releases/latest)**
+    Many issues can be resolved by re-installing the application. You won't lose any data by re-installing. We suggest downloading the [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest) and using it to re-install the application. Consult the [installer guide](../installation/010_INSTALL_AUTOMATED.md) for more information.
 
-**How can I download models? Can I use models I already have downloaded?**
+    When you run the installer, you'll have an option to select the version to install. If you aren't ready to upgrade, you choose the current version to fix a broken install.
 
-- Models can be downloaded through the model manager, or through option [4] in the invoke.bat/invoke.sh launcher script. To download a model through the Model Manager, use the HuggingFace Repo ID by pressing the “Copy” button next to the repository name. Alternatively, to download a model from CivitAi, use the download link in the Model Manager.
-- Models that are already downloaded can be used by creating a symlink to the model location in the `autoimport` folder or by using the Model Manger’s “Scan for Models” function.
+If the troubleshooting steps on this page don't get you up and running, please either [create an issue] or hop on [discord] for help.
 
-**My images are taking a long time to generate. How can I speed up generation?** 
+## How to Install
 
-- A common solution is to reduce the size of your RAM & VRAM cache to 0.25. This ensures your system has enough memory to generate images.
-- Additionally, check the [hardware requirements](https://invoke-ai.github.io/InvokeAI/#hardware-requirements) to ensure that your system is capable of generating images.
-- Lastly, double check your generations are happening on your GPU (if you have one). InvokeAI will log what is being used for generation upon startup. 
+You can download the latest installers [here](https://github.com/invoke-ai/InvokeAI/releases).
 
-**I’ve installed Python on Windows but the installer says it can’t find it?**
+Note that any releases marked as _pre-release_ are in a beta state. You may experience some issues, but we appreciate your help testing those! For stable/reliable installations, please install the [latest release].
 
-- Then ensure that you checked  **'Add python.exe to PATH'** when installing Python. This can be found at the bottom of the Python Installer window. If you already have Python installed, this can be done with the modify / repair feature of the installer.
+## Downloading models and using existing models
 
-**I’ve installed everything successfully but I still get an error about Triton when starting Invoke?**
+The Model Manager tab in the UI provides a few ways to install models, including using your already-downloaded models. You'll see a popup directing you there on first startup. For more information, see the [model install docs].
 
-- This can be safely ignored. InvokeAI doesn't use Triton, but if you are on Linux and wish to dismiss the error, you can install Triton.
+## Missing models after updating to v4
 
-**I updated to 3.4.0 and now xFormers can’t load C++/CUDA?**
+If you find some models are missing after updating to v4, it's likely they weren't correctly registered before the update and didn't get picked up in the migration.
 
-- An issue occurred with your PyTorch update. Follow these steps to fix :
-    1. Launch your invoke.bat / invoke.sh and select the option to open the developer console
-    2. Run:`pip install ".[xformers]" --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121`
-    - If you run into an error with `typing_extensions`, re-open the developer console and run:  `pip install -U typing-extensions`
+You can use the `Scan Folder` tab in the Model Manager UI to fix this. The models will either be in the old, now-unused `autoimport` folder, or your `models` folder.
 
-**It says my pip is out of date - is that why my install isn't working?**
-- An out of date won't cause an installation to fail. The cause of the error can likely be found above the message that says pip is out of date.
-- If you saw that warning but the install went well, don't worry about it (but you can update pip afterwards if you'd like).   
+- Find and copy your install's old `autoimport` folder path, install the main install folder.
+- Go to the Model Manager and click `Scan Folder`.
+- Paste the path and scan.
+- IMPORTANT: Uncheck `Inplace install`.
+- Click `Install All` to install all found models, or just install the models you want.
+
+Next, find and copy your install's `models` folder path (this could be your custom models folder path, or the `models` folder inside the main install folder).
+
+Follow the same steps to scan and import the missing models.
+
+## Slow generation
+
+- Check the [system requirements] to ensure that your system is capable of generating images.
+- Check the `ram` setting in `invokeai.yaml`. This setting tells Invoke how much of your system RAM can be used to cache models. Having this too high or too low can slow things down. That said, it's generally safest to not set this at all and instead let Invoke manage it.
+- Check the `vram` setting in `invokeai.yaml`. This setting tells Invoke how much of your GPU VRAM can be used to cache models. Counter-intuitively, if this setting is too high, Invoke will need to do a lot of shuffling of models as it juggles the VRAM cache and the currently-loaded model. The default value of 0.25 is generally works well for GPUs without 16GB or more VRAM. Even on a 24GB card, the default works well.
+- Check that your generations are happening on your GPU (if you have one). InvokeAI will log what is being used for generation upon startup. If your GPU isn't used, re-install to ensure the correct versions of torch get installed.
+
+## Installer cannot find python (Windows)
+
+Ensure that you checked **Add python.exe to PATH** when installing Python. This can be found at the bottom of the Python Installer window. If you already have Python installed, you can re-run the python installer, choose the Modify option and check the box.
+
+## Triton error on startup
+
+This can be safely ignored. InvokeAI doesn't use Triton, but if you are on Linux and wish to dismiss the error, you can install Triton.
+
+## Updated to 3.4.0 and xformers can’t load C++/CUDA
+
+An issue occurred with your PyTorch update. Follow these steps to fix :
+
+1. Launch your invoke.bat / invoke.sh and select the option to open the developer console
+2. Run:`pip install ".[xformers]" --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121`
+   - If you run into an error with `typing_extensions`, re-open the developer console and run: `pip install -U typing-extensions`
+
+Note that v3.4.0 is an old, unsupported version. Please upgrade to the [latest release].
+
+## Install failed and says `pip` is out of date
+
+An out of date `pip` typically won't cause an installation to fail. The cause of the error can likely be found above the message that says `pip` is out of date.
+
+If you saw that warning but the install went well, don't worry about it (but you can update `pip` afterwards if you'd like).
+
+## Replicate image found online
 
-**How can I generate the exact same that I found on the internet?**
 Most example images with prompts that you'll find on the internet have been generated using different software, so you can't expect to get identical results. In order to reproduce an image, you need to replicate the exact settings and processing steps, including (but not limited to) the model, the positive and negative prompts, the seed, the sampler, the exact image size, any upscaling steps, etc.
 
+## OSErrors on Windows while installing dependencies
 
-**Where can I get more help?** 
+During a zip file installation or an update, installation stops with an error like this:
 
-- Create an issue on [GitHub](https://github.com/invoke-ai/InvokeAI/issues) or post in the [#help channel](https://discord.com/channels/1020123559063990373/1149510134058471514) of the InvokeAI Discord
+![broken-dependency-screenshot](../assets/troubleshooting/broken-dependency.png){:width="800px"}
+
+To resolve this, re-install the application as described above.
+
+## HuggingFace install failed due to invalid access token
+
+Some HuggingFace models require you to authenticate using an [access token].
+
+Invoke doesn't manage this token for you, but it's easy to set it up:
+
+- Follow the instructions in the link above to create an access token. Copy it.
+- Run the launcher script.
+- Select option 2 (developer console).
+- Paste the following command:
+
+  ```sh
+  python -c "import huggingface_hub; huggingface_hub.login()"
+  ```
+
+- Paste your access token when prompted and press Enter. You won't see anything when you paste it.
+- Type `n` if prompted about git credentials.
+
+If you get an error, try the command again - maybe the token didn't paste correctly.
+
+Once your token is set, start Invoke and try downloading the model again. The installer will automatically use the access token.
+
+If the install still fails, you may not have access to the model.
+
+## Stable Diffusion XL generation fails after trying to load UNet
+
+InvokeAI is working in other respects, but when trying to generate
+images with Stable Diffusion XL you get a "Server Error". The text log
+in the launch window contains this log line above several more lines of
+error messages:
+
+`INFO --> Loading model:D:\LONG\PATH\TO\MODEL, type sdxl:main:unet`
+
+This failure mode occurs when there is a network glitch during
+downloading the very large SDXL model.
+
+To address this, first go to the Model Manager and delete the
+Stable-Diffusion-XL-base-1.X model. Then, click the HuggingFace tab,
+paste the Repo ID stabilityai/stable-diffusion-xl-base-1.0 and install
+the model.
+
+## Package dependency conflicts during installation or update
+
+If you have previously installed InvokeAI or another Stable Diffusion
+package, the installer may occasionally pick up outdated libraries and
+either the installer or `invoke` will fail with complaints about
+library conflicts.
+
+To resolve this, re-install the application as described above.
+
+## Invalid configuration file
+
+Everything seems to install ok, you get a `ValidationError` when starting up the app.
+
+This is caused by an invalid setting in the `invokeai.yaml` configuration file. The error message should tell you what is wrong.
+
+Check the [configuration docs] for more detail about the settings and how to specify them.
+
+## Out of Memory Issues
+
+The models are large, VRAM is expensive, and you may find yourself
+faced with Out of Memory errors when generating images. Here are some
+tips to reduce the problem:
+
+!!! info "Optimizing for GPU VRAM"
+
+    === "4GB VRAM GPU"
+
+        This should be adequate for 512x512 pixel images using Stable Diffusion 1.5
+        and derived models, provided that you do not use the NSFW checker. It won't be loaded unless you go into the UI settings and turn it on.
+
+        If you are on a CUDA-enabled GPU, we will automatically use xformers or torch-sdp to reduce VRAM requirements, though you can explicitly configure this. See the [configuration docs].
+
+    === "6GB VRAM GPU"
+
+        This is a border case. Using the SD 1.5 series you should be able to
+        generate images up to 640x640 with the NSFW checker enabled, and up to
+        1024x1024 with it disabled.
+
+        If you run into persistent memory issues there are a series of
+        environment variables that you can set before launching InvokeAI that
+        alter how the PyTorch machine learning library manages memory. See
+        <https://pytorch.org/docs/stable/notes/cuda.html#memory-management> for
+        a list of these tweaks.
+
+    === "12GB VRAM GPU"
+
+        This should be sufficient to generate larger images up to about 1280x1280.
+
+## Memory Leak (Linux)
+
+If you notice a memory leak, it could be caused to memory fragmentation as models are loaded and/or moved from CPU to GPU.
+
+A workaround is to tune memory allocation with an environment variable:
+
+```bash
+# Force blocks >1MB to be allocated with `mmap` so that they are released to the system immediately when they are freed.
+MALLOC_MMAP_THRESHOLD_=1048576
+```
+
+!!! warning "Speed vs Memory Tradeoff"
+
+    Your generations may be slower overall when setting this environment variable.
+
+!!! info "Possibly dependent on `libc` implementation"
+
+    It's not known if this issue occurs with other `libc` implementations such as `musl`.
+
+    If you encounter this issue and your system uses a different implementation, please try this environment variable and let us know if it fixes the issue.
+
+<h3>Detailed Discussion</h3>
+
+Python (and PyTorch) relies on the memory allocator from the C Standard Library (`libc`). On linux, with the GNU C Standard Library implementation (`glibc`), our memory access patterns have been observed to cause severe memory fragmentation.
+
+This fragmentation results in large amounts of memory that has been freed but can't be released back to the OS. Loading models from disk and moving them between CPU/CUDA seem to be the operations that contribute most to the fragmentation.
+
+This memory fragmentation issue can result in OOM crashes during frequent model switching, even if `ram` (the max RAM cache size) is set to a reasonable value (e.g. a OOM crash with `ram=16` on a system with 32GB of RAM).
+
+This problem may also exist on other OSes, and other `libc` implementations. But, at the time of writing, it has only been investigated on linux with `glibc`.
+
+To better understand how the `glibc` memory allocator works, see these references:
+
+- Basics: <https://www.gnu.org/software/libc/manual/html_node/The-GNU-Allocator.html>
+- Details: <https://sourceware.org/glibc/wiki/MallocInternals>
+
+Note the differences between memory allocated as chunks in an arena vs. memory allocated with `mmap`. Under `glibc`'s default configuration, most model tensors get allocated as chunks in an arena making them vulnerable to the problem of fragmentation.
+
+[model install docs]: ../installation/050_INSTALLING_MODELS.md
+[system requirements]: ../installation/INSTALL_REQUIREMENTS.md
+[latest release]: https://github.com/invoke-ai/InvokeAI/releases/latest
+[create an issue]: https://github.com/invoke-ai/InvokeAI/issues
+[discord]: https://discord.gg/ZmtBAhwWhy
+[configuration docs]: ../features/CONFIGURATION.md
+[access token]: https://huggingface.co/docs/hub/security-tokens#how-to-manage-user-access-tokens

docs/help/deprecated/TROUBLESHOOT.md

@@ -1,128 +0,0 @@
----
-title: F.A.Q.
----
-
-# :material-frequently-asked-questions: F.A.Q.
-
-## **Frequently-Asked-Questions**
-
-Here are a few common installation problems and their solutions. Often these are
-caused by incomplete installations or crashes during the install process.
-
----
-
-### During `conda env create`, conda hangs indefinitely
-
-If it is because of the last PIP step (usually stuck in the Git Clone step, you
-can check the detailed log by this method):
-
-```bash
-export PIP_LOG="/tmp/pip_log.txt"
-touch ${PIP_LOG}
-tail -f ${PIP_LOG} &
-conda env create -f environment-mac.yaml --debug --verbose
-killall tail
-rm ${PIP_LOG}
-```
-
-**SOLUTION**
-
-Conda sometimes gets stuck at the last PIP step, in which several git
-repositories are cloned and built.
-
-Enter the stable-diffusion directory and completely remove the `src` directory
-and all its contents. The safest way to do this is to enter the stable-diffusion
-directory and give the command `git clean -f`. If this still doesn't fix the
-problem, try "conda clean -all" and then restart at the `conda env create` step.
-
-To further understand the problem to checking the install lot using this method:
-
-```bash
-export PIP_LOG="/tmp/pip_log.txt"
-touch ${PIP_LOG}
-tail -f ${PIP_LOG} &
-conda env create -f environment-mac.yaml --debug --verbose
-killall tail
-rm ${PIP_LOG}
-```
-
----
-
-### `invoke.py` crashes with the complaint that it can't find `ldm.simplet2i.py`
-
-Or it complains that function is being passed incorrect parameters.
-
-**SOLUTION**
-
-Reinstall the stable diffusion modules. Enter the `stable-diffusion` directory
-and give the command `pip install -e .`
-
----
-
-### Missing modules
-
-`invoke.py` dies, complaining of various missing modules, none of which starts
-with `ldm`.
-
-**SOLUTION**
-
-From within the `InvokeAI` directory, run `conda env update` This is also
-frequently the solution to complaints about an unknown function in a module.
-
----
-
-### How can I try new features
-
-There's a feature or bugfix in the Stable Diffusion GitHub that you want to try
-out.
-
-**SOLUTIONS**
-
-#### **Main Branch**
-
-If the fix/feature is on the `main` branch, enter the stable-diffusion directory
-and do a `git pull`.
-
-Usually this will be sufficient, but if you start to see errors about missing or
-incorrect modules, use the command `pip install -e .` and/or `conda env update`
-(These commands won't break anything.)
-
-`pip install -e .` and/or `conda env update -f environment.yaml`
-
-(These commands won't break anything.)
-
-#### **Sub Branch**
-
-If the feature/fix is on a branch (e.g. "_foo-bugfix_"), the recipe is similar,
-but do a `git pull <name of branch>`.
-
-#### **Not Committed**
-
-If the feature/fix is in a pull request that has not yet been made part of the
-main branch or a feature/bugfix branch, then from the page for the desired pull
-request, look for the line at the top that reads "_xxxx wants to merge xx
-commits into lstein:main from YYYYYY_". Copy the URL in YYYY. It should have the
-format
-
-`https://github.com/<name of contributor>/stable-diffusion/tree/<name of branch>`
-
-Then **go to the directory above stable-diffusion** and rename the directory to
-"_stable-diffusion.lstein_", "_stable-diffusion.old_", or anything else. You can
-then git clone the branch that contains the pull request:
-
-`git clone https://github.com/<name of contributor>/stable-diffusion/tree/<name of branch>`
-
-You will need to go through the install procedure again, but it should be fast
-because all the dependencies are already loaded.
-
----
-
-### CUDA out of memory
-
-Image generation crashed with CUDA out of memory error after successful
-sampling.
-
-**SOLUTION**
-
-Try to run script with option `--free_gpu_mem` This will free memory before
-image decoding step.

docs/index.md

@@ -153,8 +153,7 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 ## :material-target: Troubleshooting
 
 Please check out our **[:material-frequently-asked-questions:
-Troubleshooting
-Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)** to
+FAQ](help/FAQ/)** to
 get solutions for common installation problems and other issues.
 
 ## :octicons-repo-push-24: Contributing

docs/installation/010_INSTALL_AUTOMATED.md

@@ -1,580 +1,105 @@
----
-title: Installing with the Automated Installer
----
+# Automatic Install
 
-# InvokeAI Automated Installation
+The installer is used for both new installs and updates.
 
-## Introduction
+Both release and pre-release versions can be installed using it. It also supports install a wheel if needed.
 
-The automated installer is a Python script that automates the steps
-needed to install and run InvokeAI on a stock computer running recent
-versions of Linux, MacOS or Windows. It will leave you with a version
-that runs a stable version of InvokeAI with the option to upgrade to
-experimental versions later.
+Be sure to review the [installation requirements] and ensure your system has everything it needs to install Invoke.
 
-## Walk through
+## Getting the Latest Installer
 
-1.  <a name="hardware_requirements">**Hardware Requirements**: </a>Make sure that your system meets the [hardware
-    requirements](../index.md#hardware-requirements) and has the
-    appropriate GPU drivers installed. For a system with an NVIDIA
-    card installed, you will need to install the CUDA driver, while
-    AMD-based cards require the ROCm driver. In most cases, if you've
-    already used the system for gaming or other graphics-intensive
-    tasks, the appropriate drivers will already be installed. If
-    unsure, check the [GPU Driver Guide](030_INSTALL_CUDA_AND_ROCM.md)
+Download the `InvokeAI-installer-vX.Y.Z.zip` file from the [latest release] page. It is at the bottom of the page, under **Assets**.
 
-    !!! info "Required Space"
+After unzipping the installer, you should have a `InvokeAI-Installer` folder with some files inside, including `install.bat` and `install.sh`.
 
-        Installation requires roughly 18G of free disk space to load
-        the libraries and recommended model weights files.
+## Running the Installer
 
-        Regardless of your destination disk, your *system drive*
-        (`C:\` on Windows, `/` on macOS/Linux) requires at least 6GB
-        of free disk space to download and cache python
-        dependencies.
+!!! tip
 
-	NOTE for Linux users: if your temporary directory is mounted
-        as a `tmpfs`, ensure it has sufficient space.
+    Windows users should first double-click the `WinLongPathsEnabled.reg` file to prevent a failed installation due to long file paths.
 
-2.  <a name="software_requirements">**Software Requirements**: </a>Check that your system has an up-to-date Python installed. To do
-    this, open up a command-line window ("Terminal" on Linux and
-    Macintosh, "Command" or "Powershell" on Windows) and type `python
-    --version`. If Python is installed, it will print out the version
-    number. If it is version `3.10.*` or `3.11.*` you meet
-    requirements.
+Double-click the install script:
 
-    !!! warning "What to do if you have an unsupported version"
+=== "Windows"
 
-        Go to [Python Downloads](https://www.python.org/downloads/)
-        and download the appropriate installer package for your
-        platform. We recommend [Version
-        3.10.12](https://www.python.org/downloads/release/python-3109/),
-        which has been extensively tested with InvokeAI.
-
-    _Please select your platform in the section below for platform-specific
-    setup requirements._
-
-    === "Windows"
-        During the Python configuration process, look out for a
-        checkbox to add Python to your PATH and select it. If the
-        install script complains that it can't find python, then open
-        the Python installer again and choose "Modify" existing
-        installation.
-
-        Installation requires an up to date version of the Microsoft
-        Visual C libraries. Please install the 2015-2022 libraries
-        available here:
-        https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170
-
-        Please double-click on the file `WinLongPathsEnabled.reg` and
-        accept the dialog box that asks you if you wish to modify your registry.
-        This activates long filename support on your system and will prevent
-        mysterious errors during installation.
-
-    === "Linux"
-         To install an appropriate version of Python on Ubuntu 22.04
-         and higher, run the following:
-
-         ```
-         sudo apt update
-         sudo apt install -y python3 python3-pip python3-venv
-         sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
-         ```
-
-         On Ubuntu 20.04, the process is slightly different:
-
-         ```
-         sudo apt update
-         sudo apt install -y software-properties-common
-         sudo add-apt-repository -y ppa:deadsnakes/ppa
-         sudo apt install -y python3.10 python3-pip python3.10-venv
-         sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
-         ```
-
-         Both `python` and `python3` commands are now pointing at
-         Python3.10. You can still access older versions of Python by
-         calling `python2`, `python3.8`, etc.
-
-         Linux systems require a couple of additional graphics
-         libraries to be installed for proper functioning of
-         `python3-opencv`. Please run the following:
-
-         `sudo apt update && sudo apt install -y libglib2.0-0 libgl1-mesa-glx`
-
-    === "Mac"
-
-        After installing Python, you may need to run the
-        following command from the Terminal in order to install the Web
-        certificates needed to download model data from https sites. If
-        you see lots of CERTIFICATE ERRORS during the last part of the
-        install, this is the problem, and you can fix it with this command:
-
-            `/Applications/Python\ 3.10/Install\ Certificates.command`
-
-        You may need to install the Xcode command line tools. These
-        are a set of tools that are needed to run certain applications in a
-        Terminal, including InvokeAI. This package is provided
-        directly by Apple. To install, open a terminal window and run `xcode-select --install`. You will get a macOS system popup guiding you through the
-        install. If you already have them installed, you will instead see some
-        output in the Terminal advising you that the tools are already installed. More information can be found at [FreeCode Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
-
-3.  **Download the Installer**: The InvokeAI installer is distributed as a ZIP files. Go to the
-    [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest),
-    and look for a file named:
-
-    - InvokeAI-installer-v3.X.X.zip
-
-    where "3.X.X" is the latest released version. The file is located
-    at the very bottom of the release page, under **Assets**.
-
-4.  **Unpack the installer**: Unpack the zip file into a convenient directory. This will create a new
-    directory named "InvokeAI-Installer". When unpacked, the directory
-    will look like this:
-
-    <figure markdown>
-    ![zipfile-screenshot](../assets/installer-walkthrough/unpacked-zipfile.png)
-    </figure>
-
-5.  **Launch the installer script from the desktop**: If you are using a desktop GUI, double-click the installer file
-    appropriate for your platform. It will be named `install.bat` on
-    Windows systems and `install.sh` on Linux and Macintosh
-    systems. Be aware that your system's file browser may suppress the
-    display of the file extension.
-
-    On Windows systems if you get an "Untrusted Publisher" warning.
-    Click on "More Info" and then select "Run Anyway." You trust us, right?
-
-6.  **[Alternative] Launch the installer script from the command line**: Alternatively, from the command line, run the shell script or .bat file:
-
-    ```cmd
-    C:\Documents\Linco> cd InvokeAI-Installer
-    C:\Documents\Linco\invokeAI> .\install.bat
+    ```sh
+    install.bat
     ```
 
-7.  **Select the location to install InvokeAI**: The script will ask you to choose where to install InvokeAI. Select a
-    directory with at least 18G of free space for a full install. InvokeAI and
-    all its support files will be installed into a new directory named
-    `invokeai` located at the location you specify.
+=== "Linux/macOS"
 
-    <figure markdown>
-    ![confirm-install-directory-screenshot](../assets/installer-walkthrough/confirm-directory.png)
-    </figure>
-
-    - The default is to install the `invokeai` directory in your home directory,
-      usually `C:\Users\YourName\invokeai` on Windows systems,
-      `/home/YourName/invokeai` on Linux systems, and `/Users/YourName/invokeai`
-      on Macintoshes, where "YourName" is your login name.
-
-    -If you have previously installed InvokeAI, you will be asked to
-     confirm whether you want to reinstall into this directory.  You
-     may choose to reinstall, in which case your version will be upgraded,
-     or choose a different directory.
-
-    - The script uses tab autocompletion to suggest directory path completions.
-      Type part of the path (e.g. "C:\Users") and press ++tab++ repeatedly
-      to suggest completions.
-
-8.  **Select your GPU**: The installer will autodetect your platform and will request you to
-    confirm the type of GPU your graphics card has. On Linux systems,
-    you will have the choice of CUDA (NVidia cards), ROCm (AMD cards),
-    or CPU (no graphics acceleration). On Windows, you'll have the
-    choice of CUDA vs CPU, and on Macs you'll be offered CPU only. When
-    you select CPU on M1/M2/M3 Macintoshes, you will get MPS-based
-    graphics acceleration without installing additional drivers. If you
-    are unsure what GPU you are using, you can ask the installer to
-    guess.
-
-9.  **Watch it go!**: Sit back and let the install script work. It will install the third-party
-    libraries needed by InvokeAI and the application itself.
-
-    Be aware that some of the library download and install steps take a long
-    time. In particular, the `pytorch` package is quite large and often appears
-    to get "stuck" at 99.9%. Have patience and the installation step will
-    eventually resume. However, there are occasions when the library install
-    does legitimately get stuck. If you have been waiting for more than ten
-    minutes and nothing is happening, you can interrupt the script with ^C. You
-    may restart it and it will pick up where it left off.
-
-    <figure markdown>
-    ![initial-settings-screenshot](../assets/installer-walkthrough/settings-form.png)
-    </figure>
-
-10. **Post-install Configuration**: After installation completes, the
-    installer will launch the configuration form, which will guide you
-    through the first-time process of adjusting some of InvokeAI's
-    startup settings. To move around this form use ctrl-N for
-    &lt;N&gt;ext and ctrl-P for &lt;P&gt;revious, or use &lt;tab&gt;
-    and shift-&lt;tab&gt; to move forward and back. Once you are in a
-    multi-checkbox field use the up and down cursor keys to select the
-    item you want, and &lt;space&gt; to toggle it on and off.  Within
-    a directory field, pressing &lt;tab&gt; will provide autocomplete
-    options.
-
-    Generally the defaults are fine, and you can come back to this screen at
-    any time to tweak your system. Here are the options you can adjust:
-
-    - ***HuggingFace Access Token***
-      InvokeAI has the ability to download embedded styles and subjects
-      from the HuggingFace Concept Library on-demand. However, some of
-      the concept library files are password protected. To make download
-      smoother, you can set up an account at huggingface.co, obtain an
-      access token, and paste it into this field. Note that you paste
-      to this screen using ctrl-shift-V
-
-    - ***Free GPU memory after each generation***
-        This is useful for low-memory machines and helps minimize the
-	amount of GPU VRAM used by InvokeAI.
-
-    - ***Enable xformers support if available***
-        If the xformers library was successfully installed, this will activate
-	it to reduce memory consumption and increase rendering speed noticeably.
-	Note that xformers has the side effect of generating slightly different
-	images even when presented with the same seed and other settings.
-
-    - ***Force CPU to be used on GPU systems***
-        This will use the (slow) CPU rather than the accelerated GPU. This
-	can be used to generate images on systems that don't have a compatible
-	GPU.
-
-    - ***Precision***
-        This controls whether to use float32 or float16 arithmetic.
-	float16 uses less memory but is also slightly less accurate.
-	Ordinarily the right arithmetic is picked automatically ("auto"),
-	but you may have to use float32 to get images on certain systems
-	and graphics cards. The "autocast" option is deprecated and
-	shouldn't be used unless you are asked to by a member of the team.
-
-    - **Size of the RAM cache used for fast model switching***
-        This allows you to keep models in memory and switch rapidly among
-	them rather than having them load from disk each time. This slider
-	controls how many models to keep loaded at once. A typical SD-1 or SD-2 model
-	uses 2-3 GB of memory. A typical SDXL model uses 6-7 GB. Providing more
-	RAM will allow more models to be co-resident.
-
-    - ***Output directory for images***
-      This is the path to a directory in which InvokeAI will store all its
-      generated images.
-
-    - ***Autoimport Folder***
-      This is the directory in which you can place models you have
-	  downloaded and wish to load into InvokeAI. You can place a variety
-	  of models in this directory, including diffusers folders, .ckpt files,
-	  .safetensors files, as well as LoRAs, ControlNet and Textual Inversion
-	  files (both folder and file versions). To help organize this folder,
-	  you can create several levels of subfolders and drop your models into
-      whichever ones you want.
-	
-    - ***LICENSE***     
-
-    At the bottom of the screen you will see a checkbox for accepting
-    the CreativeML Responsible AI Licenses. You need to accept the license
-    in order to download Stable Diffusion models from the next screen.
-
-    _You can come back to the startup options form_ as many times as you like.
-    From the `invoke.sh` or `invoke.bat` launcher, select option (6) to relaunch
-    this script. On the command line, it is named `invokeai-configure`.
-
-11. **Downloading Models**: After you press `[NEXT]` on the screen, you will be taken
-    to another screen that prompts you to download a series of starter models. The ones
-    we recommend are preselected for you, but you are encouraged to use the checkboxes to
-    pick and choose.
-    You will probably wish to download `autoencoder-840000` for use with models that
-    were trained with an older version of the Stability VAE.
-
-    <figure markdown>
-    ![select-models-screenshot](../assets/installer-walkthrough/installing-models.png)
-    </figure>
-    
-    Below the preselected list of starter models is a large text field which you can use
-    to specify a series of models to import. You can specify models in a variety of formats,
-    each separated by a space or newline. The formats accepted are:
-
-    - The path to a .ckpt or .safetensors file. On most systems, you can drag a file from
-      the file browser to the textfield to automatically paste the path. Be sure to remove
-      extraneous quotation marks and other things that come along for the ride.
-
-    - The path to a directory containing a combination of `.ckpt` and `.safetensors` files.
-      The directory will be scanned from top to bottom (including subfolders) and any
-      file that can be imported will be.
-
-    - A URL pointing to a `.ckpt` or `.safetensors` file. You can cut
-      and paste directly from a web page, or simply drag the link from the web page
-      or navigation bar. (You can also use ctrl-shift-V to paste into this field)
-      The file will be downloaded and installed.
-      
-    - The HuggingFace repository ID (repo_id) for a `diffusers` model. These IDs have
-       the format _author_name/model_name_, as in `andite/anything-v4.0`
-      
-    - The path to a local directory containing a `diffusers`
-      model. These directories always have the file `model_index.json`
-      at their top level.
-
-    _Select a directory for models to import_ You may select a local
-    directory for autoimporting at startup time. If you select this
-    option, the directory you choose will be scanned for new
-    .ckpt/.safetensors files each time InvokeAI starts up, and any new
-    files will be automatically imported and made available for your
-    use.
-
-    _Convert imported models into diffusers_ When legacy checkpoint
-    files are imported, you may select to use them unmodified (the
-    default) or to convert them into `diffusers` models. The latter
-    load much faster and have slightly better rendering performance,
-    but not all checkpoint files can be converted. Note that Stable Diffusion
-    Version 2.X files are **only** supported in `diffusers` format and will
-    be converted regardless.
-     
-     _You can come back to the model install form_ as many times as you like.
-     From the `invoke.sh` or `invoke.bat` launcher, select option (5) to relaunch
-     this script. On the command line, it is named `invokeai-model-install`.
-
-12. **Running InvokeAI for the first time**: The script will now exit and you'll be ready to generate some images. Look
-    for the directory `invokeai` installed in the location you chose at the
-    beginning of the install session. Look for a shell script named `invoke.sh`
-    (Linux/Mac) or `invoke.bat` (Windows). Launch the script by double-clicking
-    it or typing its name at the command-line:
-
-    ```cmd
-    C:\Documents\Linco> cd invokeai
-    C:\Documents\Linco\invokeAI> invoke.bat
+    ```sh
+    install.sh
     ```
 
-    - The `invoke.bat` (`invoke.sh`) script will give you the choice
-      of starting (1) the command-line interface, (2) the web GUI, (3)
-      textual inversion training, and (4) model merging.
+!!! info "Running the Installer from the commandline"
 
-    - By default, the script will launch the web interface. When you
-      do this, you'll see a series of startup messages ending with
-      instructions to point your browser at
-      http://localhost:9090. Click on this link to open up a browser
-      and start exploring InvokeAI's features.
+    You can also run the install script from cmd/powershell (Windows) or terminal (Linux/macOS).
 
-12. **InvokeAI Options**: You can launch InvokeAI with several different command-line arguments that
-    customize its behavior. For example, you can change the location of the
-    image output directory or balance memory usage vs performance. See
-    [Configuration](../features/CONFIGURATION.md) for a full list of the options.
+!!! warning "Untrusted Publisher (Windows)"
 
-    - To set defaults that will take effect every time you launch InvokeAI,
-      use a text editor (e.g. Notepad) to exit the file
-      `invokeai\invokeai.init`. It contains a variety of examples that you can
-      follow to add and modify launch options.
+    You may get a popup saying the file comes from an `Untrusted Publisher`. Click `More Info` and `Run Anyway` to get past this.
 
-    - The launcher script also offers you an option labeled "open the developer
-      console". If you choose this option, you will be dropped into a
-      command-line interface in which you can run python commands directly,
-      access developer tools, and launch InvokeAI with customized options.
+The installation process is simple, with a few prompts:
 
+- Select the version to install. Unless you have a specific reason to install a specific version, select the default (the latest version).
+- Select location for the install. Be sure you have enough space in this folder for the base application, as described in the [installation requirements].
+- Select a GPU device.
 
-    !!! warning "Do not move or remove the `invokeai` directory"
-      
-        The `invokeai` directory contains the `invokeai` application, its
-        configuration files, the model weight files, and outputs of image generation.
-        Once InvokeAI is installed, do not move or remove this directory."
+!!! info "Slow Installation"
 
+    The installer needs to download several GB of data and install it all. It may appear to get stuck at 99.9% when installing `pytorch` or during a step labeled "Installing collected packages".
 
-<a name="troubleshooting"></a>
-## Troubleshooting
+    If it is stuck for over 10 minutes, something has probably gone wrong and you should close the window and restart.
 
-### _OSErrors on Windows while installing dependencies_
+## Running the Application
 
-During a zip file installation or an online update, installation stops
-with an error like this:
+Find the install location you selected earlier. Double-click the launcher script to run the app:
 
-![broken-dependency-screenshot](../assets/troubleshooting/broken-dependency.png){:width="800px"}
+=== "Windows"
 
-This seems to happen particularly often with the `pydantic` and
-`numpy` packages. The most reliable solution requires several manual
-steps to complete installation.
+    ```sh
+    invoke.bat
+    ```
 
-Open up a Powershell window and navigate to the `invokeai` directory
-created by the installer. Then give the following series of commands:
+=== "Linux/macOS"
 
-```cmd
-rm .\.venv -r -force
-python -mvenv .venv
-.\.venv\Scripts\activate
-pip install invokeai
-invokeai-configure --yes --root .
+    ```sh
+    invoke.sh
+    ```
+
+Choose the first option to run the UI. After a series of startup messages, you'll see something like this:
+
+```
+Uvicorn running on http://127.0.0.1:9090 (Press CTRL+C to quit)
 ```
 
-If you see anything marked as an error during this process please stop
-and seek help on the Discord [installation support
-channel](https://discord.com/channels/1020123559063990373/1041391462190956654). A
-few warning messages are OK.
+Copy the URL into your browser and you should see the UI.
 
-If you are updating from a previous version, this should restore your
-system to a working state. If you are installing from scratch, there
-is one additional command to give:
+## First-time Setup
 
-```cmd
-wget -O invoke.bat https://raw.githubusercontent.com/invoke-ai/InvokeAI/main/installer/templates/invoke.bat.in
-```
+You will need to [install some models] before you can generate.
 
-This will create the `invoke.bat` script needed to launch InvokeAI and
-its related programs.
+Check the [configuration docs] for details on configuring the application.
 
+## Updating
 
-### _Stable Diffusion XL Generation Fails after Trying to Load unet_
+Updating is exactly the same as installing - download the latest installer, choose the latest version and off you go.
 
-InvokeAI is working in other respects, but when trying to generate
-images with Stable Diffusion XL you get a "Server Error". The text log
-in the launch window contains this log line above several more lines of
-error messages:
+!!! info "Dependency Resolution Issues"
 
-```INFO --> Loading model:D:\LONG\PATH\TO\MODEL, type sdxl:main:unet```
+    We've found that pip's dependency resolution can cause issues when upgrading packages. One very common problem was pip "downgrading" torch from CUDA to CPU, but things broke in other novel ways.
 
-This failure mode occurs when there is a network glitch during
-downloading the very large SDXL model.
+    The installer doesn't have this kind of problem, so we use it for updating as well.
 
-To address this, first go to the Web Model Manager and delete the
-Stable-Diffusion-XL-base-1.X model. Then navigate to HuggingFace and
-manually download the .safetensors version of the model. The 1.0
-version is located at
-https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main
-and the file is named `sd_xl_base_1.0.safetensors`.
+## Installation Issues
 
-Save this file to disk and then reenter the Model Manager. Navigate to
-Import Models->Add Model, then type (or drag-and-drop) the path to the
-.safetensors file. Press "Add Model".
+If you have installation issues, please review the [FAQ]. You can also [create an issue] or ask for help on [discord].
 
-### _Package dependency conflicts_
-
-If you have previously installed InvokeAI or another Stable Diffusion
-package, the installer may occasionally pick up outdated libraries and
-either the installer or `invoke` will fail with complaints about
-library conflicts. In this case, run the `invoke.sh`/`invoke.bat`
-command and enter the Developer's Console by picking option (5). This
-will take you to a command-line prompt.
-
-Then give this command:
-
-`pip install InvokeAI --force-reinstall`
-
-This should fix the issues.
-
-### InvokeAI runs extremely slowly on Linux or Windows systems
-
-The most frequent cause of this problem is when the installation
-process installed the CPU-only version of the torch machine-learning
-library, rather than a version that takes advantage of GPU
-acceleration. To confirm this issue, look at the InvokeAI startup
-messages. If you see a message saying ">> Using device CPU", then
-this is what happened.
-
-To fix this problem, first determine whether you have an NVidia or an
-AMD GPU. The former uses the CUDA driver, and the latter uses ROCm
-(only available on Linux). Then run the `invoke.sh`/`invoke.bat`
-command and enter the Developer's Console by picking option (5). This
-will take you to a command-line prompt.
-
-Then type the following commands:
-
-=== "NVIDIA System"
-    ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121
-    pip install xformers
-    ```
-
-=== "AMD System"
-    ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.6
-    ```
-
-### Corrupted configuration file
-
-Everything seems to install ok, but `invokeai` complains of a corrupted
-configuration file and goes back into the configuration process (asking you to
-download models, etc), but this doesn't fix the problem.
-
-This issue is often caused by a misconfigured configuration directive in the
-`invokeai\invokeai.init` initialization file that contains startup settings. The
-easiest way to fix the problem is to move the file out of the way and re-run
-`invokeai-configure`. Enter the developer's console (option 3 of the launcher
-script) and run this command:
-
-```cmd
-invokeai-configure --root=.
-```
-
-Note the dot (.) after `--root`. It is part of the command.
-
-_If none of these maneuvers fixes the problem_ then please report the problem to
-the [InvokeAI Issues](https://github.com/invoke-ai/InvokeAI/issues) section, or
-visit our [Discord Server](https://discord.gg/ZmtBAhwWhy) for interactive
-assistance.
-
-### Out of Memory Issues
-
-The models are large, VRAM is expensive, and you may find yourself
-faced with Out of Memory errors when generating images. Here are some
-tips to reduce the problem:
-
-* **4 GB of VRAM**
-
-This should be adequate for 512x512 pixel images using Stable Diffusion 1.5
-and derived models, provided that you **disable** the NSFW checker. To
-disable the filter, do one of the following:
-
-   * Select option (6) "_change InvokeAI startup options_" from the
-     launcher. This will bring up the console-based startup settings
-     dialogue and allow you to unselect the "NSFW Checker" option.
-   * Start the startup settings dialogue directly by running
-     `invokeai-configure --skip-sd-weights --skip-support-models`
-     from the command line.
-   * Find the `invokeai.init` initialization file in the InvokeAI root
-     directory, open it in a text editor, and change `--nsfw_checker`
-     to `--no-nsfw_checker`
-
-If you are on a CUDA system, you can realize significant memory
-savings by activating the `xformers` library as described above. The
-downside is `xformers` introduces non-deterministic behavior, such
-that images generated with exactly the same prompt and settings will
-be slightly different from each other. See above for more information.
-
-* **6 GB of VRAM**
-
-This is a border case. Using the SD 1.5 series you should be able to
-generate images up to 640x640 with the NSFW checker enabled, and up to
-1024x1024 with it disabled and `xformers` activated. 
-
-If you run into persistent memory issues there are a series of
-environment variables that you can set before launching InvokeAI that
-alter how the PyTorch machine learning library manages memory.  See
-https://pytorch.org/docs/stable/notes/cuda.html#memory-management for
-a list of these tweaks.
-
-* **12 GB of VRAM**
-
-This should be sufficient to generate larger images up to about
-1280x1280. If you wish to push further, consider activating
-`xformers`.
-
-### Other Problems
-
-If you run into problems during or after installation, the InvokeAI team is
-available to help you. Either create an
-[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub site, or
-make a request for help on the "bugs-and-support" channel of our
-[Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100% volunteer
-organization, but typically somebody will be available to help you within 24
-hours, and often much sooner.
-
-## Updating to newer versions
-
-This distribution is changing rapidly, and we add new features
-regularly. Releases are announced at
-http://github.com/invoke-ai/InvokeAI/releases, and at
-https://pypi.org/project/InvokeAI/ To update to the latest released
-version (recommended), follow these steps:
-
-1. Start the `invoke.sh`/`invoke.bat` launch script from within the
-   `invokeai` root directory.
-
-2. Choose menu item (10) "Update InvokeAI".
-
-3. This will launch a menu that gives you the option of:
-
-   1. Updating to the latest official release;
-   2. Updating to the bleeding-edge development version; or
-   3. Manually entering the tag or branch name of a version of
-      InvokeAI you wish to try out.
+[installation requirements]: INSTALLATION.md#installation-requirements
+[FAQ]: ../help/FAQ.md
+[install some models]: 050_INSTALLING_MODELS.md
+[configuration docs]: ../features/CONFIGURATION.md
+[latest release]: https://github.com/invoke-ai/InvokeAI/releases/latest
+[create an issue]: https://github.com/invoke-ai/InvokeAI/issues
+[discord]: https://discord.gg/ZmtBAhwWhy

docs/installation/020_INSTALL_MANUAL.md

@@ -1,122 +1,55 @@
----
-title: Installing Manually
----
-
-<figure markdown>
-
-# :fontawesome-brands-linux: Linux | :fontawesome-brands-apple: macOS | :fontawesome-brands-windows: Windows
-
-</figure>
+# Manual Install
 
 !!! warning "This is for Advanced Users"
 
-    **Python experience is mandatory**
+    **Python experience is mandatory.**
 
 ## Introduction
 
-!!! tip "Conda"
-    As of InvokeAI v2.3.0 installation using the `conda` package manager is no longer being supported. It will likely still work, but we are not testing this installation method.
+InvokeAI is distributed as a python package on PyPI, installable with `pip`. There are a few things that are handled by the installer and launcher that you'll need to manage manually, described in this guide.
 
-On Windows systems, you are encouraged to install and use the
-[PowerShell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.3),
-which provides compatibility with Linux and Mac shells and nice
-features such as command-line completion.
+### Requirements
 
-### Prerequisites
-
-Before you start, make sure you have the following preqrequisites
-installed.  These are described in more detail in [Automated
-Installation](010_INSTALL_AUTOMATED.md), and in many cases will
-already be installed (if, for example, you have used your system for
-gaming):
-
-* **Python**
-
-    version 3.10 through 3.11
-
-* **CUDA Tools**
-
-    For those with _NVidia GPUs_, you will need to
-    install the [CUDA toolkit and optionally the XFormers library](070_INSTALL_XFORMERS.md).
-
-* **ROCm Tools**
-
-    For _Linux users with AMD GPUs_, you will need
-    to install the [ROCm toolkit](./030_INSTALL_CUDA_AND_ROCM.md). Note that
-    InvokeAI does not support AMD GPUs on Windows systems due to
-    lack of a Windows ROCm library.
-
-* **Visual C++ Libraries**
-
-    _Windows users_ must install the free
-    [Visual C++ libraries from Microsoft](https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170)
-
-* **The Xcode command line tools**
-
-    for _Macintosh users_. Instructions are available at
-    [Free Code Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
-
-    * _Macintosh users_ may also need to run the `Install Certificates` command
-      if model downloads give lots of certificate errors. Run:
-      `/Applications/Python\ 3.10/Install\ Certificates.command`
+Before you start, go through the [installation requirements].
 
 ### Installation Walkthrough
 
-To install InvokeAI with virtual environments and the PIP package
-manager, please follow these steps:
-
-1.  Please make sure you are using Python 3.10 through 3.11. The rest of the install
-    procedure depends on this and will not work with other versions:
-
-    ```bash
-    python -V
-    ```
-
-2.  Create a directory to contain your InvokeAI library, configuration
+1. Create a directory to contain your InvokeAI library, configuration
     files, and models. This is known as the "runtime" or "root"
     directory, and often lives in your home directory under the name `invokeai`.
 
-    Please keep in mind the disk space requirements - you will need at
-    least 20GB for the models and the virtual environment.  From now
-    on we will refer to this directory as `INVOKEAI_ROOT`. For convenience,
-    the steps below create a shell variable of that name which contains the
-    path to `HOME/invokeai`.
+    We will refer to this directory as `INVOKEAI_ROOT`. For convenience, create an environment variable pointing to the directory.
 
-    === "Linux/Mac"
+    === "Linux/macOS"
 
         ```bash
         export INVOKEAI_ROOT=~/invokeai
         mkdir $INVOKEAI_ROOT
         ```
 
-    === "Windows (Powershell)"
+    === "Windows (PowerShell)"
 
         ```bash
         Set-Variable -Name INVOKEAI_ROOT -Value $Home/invokeai
         mkdir $INVOKEAI_ROOT
         ```
 
-3. Enter the root (invokeai) directory and create a virtual Python
-   environment within it named `.venv`. If the command `python`
-   doesn't work, try `python3`. Note that while you may create the
-   virtual environment anywhere in the file system, we recommend that
-   you create it within the root directory as shown here. This makes
-   it possible for the InvokeAI applications to find the model data
-   and configuration. If you do not choose to install the virtual
-   environment inside the root directory, then you **must** set the
-   `INVOKEAI_ROOT` environment variable in your shell environment, for
-   example, by editing `~/.bashrc` or `~/.zshrc` files, or setting the
-   Windows environment variable using the Advanced System Settings dialogue.
-   Refer to your operating system documentation for details.
+1. Enter the root (invokeai) directory and create a virtual Python environment within it named `.venv`.
+
+    !!! warning "Virtual Environment Location"
+
+        While you may create the virtual environment anywhere in the file system, we recommend that you create it within the root directory as shown here. This allows the application to automatically detect its data directories.
+
+        If you choose a different location for the venv, then you _must_ set the `INVOKEAI_ROOT` environment variable or specify the root directory using the `--root` CLI arg.
 
     ```terminal
     cd $INVOKEAI_ROOT
-    python -m venv .venv --prompt InvokeAI
+    python3 -m venv .venv --prompt InvokeAI
     ```
 
-4.  Activate the new environment:
+1. Activate the new environment:
 
-    === "Linux/Mac"
+    === "Linux/macOS"
 
         ```bash
         source .venv/bin/activate
@@ -128,51 +61,43 @@ manager, please follow these steps:
         .venv\Scripts\activate
         ```
 
+    !!! info "Permissions Error (Windows)"
+
         If you get a permissions error at this point, run this command and try again
 
         `Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser`
 
-    The command-line prompt should change to to show `(InvokeAI)` at the
-    beginning of the prompt. Note that all the following steps should be
-    run while inside the INVOKEAI_ROOT directory
+    The command-line prompt should change to to show `(InvokeAI)` at the beginning of the prompt.
 
-5.  Make sure that pip is installed in your virtual environment and up to date:
+    The following steps should be run while inside the `INVOKEAI_ROOT` directory.
+
+1. Make sure that pip is installed in your virtual environment and up to date:
 
     ```bash
-    python -m pip install --upgrade pip
+    python3 -m pip install --upgrade pip
     ```
 
-6. Install the InvokeAI Package. The `--extra-index-url` option is used to select among
-   CUDA, ROCm and CPU/MPS drivers as shown below:
+1. Install the InvokeAI Package. The base command is `pip install InvokeAI --use-pep517`, but you may need to change this depending on your system and the desired features.
 
-    === "CUDA (NVidia)"
+    - You may need to provide an [extra index URL]. Select your platform configuration using [this tool on the PyTorch website]. Copy the `--extra-index-url` string from this and append it to your install command.
 
-        ```bash
-        pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-        ```
+        !!! example "Install with an extra index URL"
 
-    === "ROCm (AMD)"
+            ```bash
+            pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
+            ```
 
-        ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
-        ```
+    - If you have a CUDA GPU and want to install with `xformers`, you need to add an option to the package name. Note that `xformers` is not necessary. PyTorch includes an implementation of the SDP attention algorithm with the same performance.
 
-    === "CPU (Intel Macs & non-GPU systems)"
+        !!! example "Install with `xformers`"
 
-        ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
-        ```
+            ```bash
+            pip install "InvokeAI[xformers]" --use-pep517
+            ```
 
-    === "MPS (M1 and M2 Macs)"
+1. Deactivate and reactivate your runtime directory so that the invokeai-specific commands become available in the environment:
 
-        ```bash
-        pip install InvokeAI --use-pep517
-        ```
-
-7.  Deactivate and reactivate your runtime directory so that the invokeai-specific commands
-    become available in the environment
-
-    === "Linux/Macintosh"
+    === "Linux/macOS"
 
         ```bash
         deactivate && source .venv/bin/activate
@@ -185,221 +110,10 @@ manager, please follow these steps:
         .venv\Scripts\activate
         ```
 
-8.  Set up the runtime directory
+1. Run the application:
 
-    In this step you will initialize your runtime directory with the downloaded
-    models, model config files, directory for textual inversion embeddings, and
-    your outputs.
-
-    ```terminal
-    invokeai-configure --root .
-    ```
-	
-	Don't miss the dot at the end of the command!
-
-    The script `invokeai-configure` will interactively guide you through the
-    process of downloading and installing the weights files needed for InvokeAI.
-    Note that the main Stable Diffusion weights file is protected by a license
-    agreement that you have to agree to. The script will list the steps you need
-    to take to create an account on the site that hosts the weights files,
-    accept the agreement, and provide an access token that allows InvokeAI to
-    legally download and install the weights files.
-
-    If you get an error message about a module not being installed, check that
-    the `invokeai` environment is active and if not, repeat step 5.
-
-    !!! tip
-
-        If you have already downloaded the weights file(s) for another Stable
-        Diffusion distribution, you may skip this step (by selecting "skip" when
-        prompted) and configure InvokeAI to use the previously-downloaded files. The
-        process for this is described in [Installing Models](050_INSTALLING_MODELS.md).
-
-9.  Run the command-line- or the web- interface:
-
-    From within INVOKEAI_ROOT, activate the environment
-    (with `source .venv/bin/activate` or `.venv\scripts\activate`), and then run
-    the script `invokeai`. If the virtual environment you selected is NOT inside
-    INVOKEAI_ROOT, then you must specify the path to the root directory by adding
-    `--root_dir \path\to\invokeai` to the commands below:
-
-    !!! example ""
-
-        !!! warning "Make sure that the virtual environment is activated, which should create `(.venv)` in front of your prompt!"
-
-        === "local Webserver"
-
-            ```bash
-            invokeai-web
-            ```
-
-        === "Public Webserver"
-
-            ```bash
-            invokeai-web --host 0.0.0.0
-            ```
-
-        === "CLI"
-
-            ```bash
-            invokeai
-            ```
-
-        If you choose the run the web interface, point your browser at
-        http://localhost:9090 in order to load the GUI.
-
-    !!! tip
-
-        You can permanently set the location of the runtime directory
-        by setting the environment variable `INVOKEAI_ROOT` to the
-        path of the directory. As mentioned previously, this is
-        *highly recommended** if your virtual environment is located outside of
-        your runtime directory.
-
-    !!! tip
-
-        On linux, it is recommended to run invokeai with the following env var: `MALLOC_MMAP_THRESHOLD_=1048576`. For example: `MALLOC_MMAP_THRESHOLD_=1048576 invokeai --web`. This helps to prevent memory fragmentation that can lead to memory accumulation over time. This env var is set automatically when running via `invoke.sh`.
-
-10.  Render away!
-
-    Browse the [features](../features/index.md) section to learn about all the
-    things you can do with InvokeAI.
-
-
-11.  Subsequently, to relaunch the script, activate the virtual environment, and
-    then launch `invokeai` command. If you forget to activate the virtual
-    environment you will most likeley receive a `command not found` error.
+    Run `invokeai-web` to start the UI. You must activate the virtual environment before running the app.
 
     !!! warning
 
-        Do not move the runtime directory after installation. The virtual environment will get confused if the directory is moved.
-
-12. Other scripts
-
-    The [Textual Inversion](../features/TRAINING.md) script can be launched with the command:
-
-    ```bash
-    invokeai-ti --gui
-    ```
-
-    Similarly, the [Model Merging](../features/MODEL_MERGING.md) script can be launched with the command:
-
-    ```bash
-    invokeai-merge --gui
-    ```
-
-    Leave off the `--gui` option to run the script using command-line arguments. Pass the `--help` argument
-    to get usage instructions.
-
-## Developer Install
-
-!!! warning
-
-    InvokeAI uses a SQLite database. By running on `main`, you accept responsibility for your database. This
-    means making regular backups (especially before pulling) and/or fixing it yourself in the event that a
-    PR introduces a schema change.
-    
-    If you don't need persistent backend storage, you can use an ephemeral in-memory database by setting
-    `use_memory_db: true` under `Path:` in your `invokeai.yaml` file.
-
-    If this is untenable, you should run the application via the official installer or a manual install of the
-    python package from pypi. These releases will not break your database.
-
-
-If you have an interest in how InvokeAI works, or you would like to
-add features or bugfixes, you are encouraged to install the source
-code for InvokeAI. For this to work, you will need to install the
-`git` source code management program. If it is not already installed
-on your system, please see the [Git Installation
-Guide](https://github.com/git-guides/install-git)
-
-You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md).
-
-If you have a "normal" installation, you should create a totally separate virtual environment for the git-based installation, else the two may interfere.
-
-> **Why do I need the frontend toolchain**?
->
-> The InvokeAI project uses trunk-based development. That means our `main` branch is the development branch, and releases are tags on that branch. Because development is very active, we don't keep an updated build of the UI in `main` - we only build it for production releases.
->
-> That means that between releases, to have a functioning application when running directly from the repo, you will need to run the UI in dev mode or build it regularly (any time the UI code changes).
-
-1. Create a fork of the InvokeAI repository through the GitHub UI or [this link](https://github.com/invoke-ai/InvokeAI/fork) 
-2. From the command line, run this command:
-   ```bash
-   git clone https://github.com/<your_github_username>/InvokeAI.git
-   ```
-
-    This will create a directory named `InvokeAI` and populate it with the
-    full source code from your fork of the InvokeAI repository.
-
-3. Activate the InvokeAI virtual environment as per step (4) of the manual
-installation protocol (important!)
-
-4. Enter the InvokeAI repository directory and run one of these
-   commands, based on your GPU:
-
-    === "CUDA (NVidia)"
-        ```bash
-        pip install -e .[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-        ```
-
-    === "ROCm (AMD)"
-        ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
-        ```
-
-    === "CPU (Intel Macs & non-GPU systems)"
-        ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
-        ```
-
-    === "MPS (M1 and M2 Macs)"
-        ```bash
-        pip install -e . --use-pep517
-        ```
-
-    Be sure to pass `-e` (for an editable install) and don't forget the
-    dot ("."). It is part of the command.
-
-5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md) and do a production build of the UI as described.
-
-6.  You can now run `invokeai` and its related commands. The code will be
-    read from the repository, so that you can edit the .py source files
-    and watch the code's behavior change.
-
-    When you pull in new changes to the repo, be sure to re-build the UI.
-
-7.  If you wish to contribute to the InvokeAI project, you are
-    encouraged to establish a GitHub account and "fork"
-    https://github.com/invoke-ai/InvokeAI into your own copy of the
-    repository. You can then use GitHub functions to create and submit
-    pull requests to contribute improvements to the project.
-
-    Please see [Contributing](../index.md#contributing) for hints
-    on getting started.
-
-### Unsupported Conda Install
-
-Congratulations, you found the "secret" Conda installation
-instructions. If you really **really** want to use Conda with InvokeAI
-you can do so using this unsupported recipe:
-
-```
-mkdir ~/invokeai
-conda create -n invokeai python=3.10
-conda activate invokeai
-pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-invokeai-configure --root ~/invokeai
-invokeai --root ~/invokeai --web
-```
-
-The `pip install` command shown in this recipe is for Linux/Windows
-systems with an NVIDIA GPU. See step (6) above for the command to use
-with other platforms/GPU combinations. If you don't wish to pass the
-`--root` argument to `invokeai` with each launch, you may set the
-environment variable INVOKEAI_ROOT to point to the installation directory.
-
-Note that if you run into problems with the Conda installation, the InvokeAI
-staff will **not** be able to help you out. Caveat Emptor!
-
-[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939
+        If the virtual environment is _not_ inside the root directory, then you _must_ specify the path to the root directory with `--root_dir \path\to\invokeai` or the `INVOKEAI_ROOT` environment variable.

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -1,149 +0,0 @@
----
-title: NVIDIA Cuda / AMD ROCm
----
-
-<figure markdown>
-
-# :simple-nvidia: CUDA | :simple-amd: ROCm
-
-</figure>
-
-In order for InvokeAI to run at full speed, you will need a graphics
-card with a supported GPU. InvokeAI supports NVidia cards via the CUDA
-driver on Windows and Linux, and AMD cards via the ROCm driver on Linux.
-
-## :simple-nvidia: CUDA
-
-### Linux and Windows Install
-
-If you have used your system for other graphics-intensive tasks, such
-as gaming, you may very well already have the CUDA drivers
-installed. To confirm, open up a command-line window and type:
-
-```
-nvidia-smi
-```
-
-If this command produces a status report on the GPU(s) installed on
-your system, CUDA is installed and you have no more work to do. If
-instead you get "command not found", or similar, then the driver will
-need to be installed.
-
-We strongly recommend that you install the CUDA Toolkit package
-directly from NVIDIA. **Do not try to install Ubuntu's
-nvidia-cuda-toolkit package. It is out of date and will cause
-conflicts among the NVIDIA driver and binaries.**
-
-Go to [CUDA Toolkit
-Downloads](https://developer.nvidia.com/cuda-downloads), and use the
-target selection wizard to choose your operating system, hardware
-platform, and preferred installation method (e.g. "local" versus
-"network").
-
-This will provide you with a downloadable install file or, depending
-on your choices, a recipe for downloading and running a install shell
-script. Be sure to read and follow the full installation instructions.
-
-After an install that seems successful, you can confirm by again
-running `nvidia-smi` from the command line.
-
-### Linux Install with a Runtime Container
-
-On Linux systems, an alternative to installing CUDA Toolkit directly on
-your system is to run an NVIDIA software container that has the CUDA
-libraries already in place. This is recommended if you are already 
-familiar with containerization technologies such as Docker.
-
-For downloads and instructions, visit the [NVIDIA CUDA Container
-Runtime Site](https://developer.nvidia.com/nvidia-container-runtime)
-
-### cuDNN Installation for 40/30 Series Optimization* (Optional)
-
-1. Find the InvokeAI folder
-2. Click on .venv folder - e.g., YourInvokeFolderHere\\.venv
-3. Click on Lib folder - e.g., YourInvokeFolderHere\\.venv\Lib
-4. Click on site-packages folder - e.g., YourInvokeFolderHere\\.venv\Lib\site-packages
-5. Click on Torch directory - e.g., YourInvokeFolderHere\InvokeAI\\.venv\Lib\site-packages\torch
-6. Click on the lib folder - e.g., YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib
-7. Copy everything inside the folder and save it elsewhere as a backup.
-8. Go to __https://developer.nvidia.com/cudnn__
-9. Login or create an Account. 
-10. Choose the newer version of cuDNN. **Note:** 
-There are two versions, 11.x or 12.x for the differents architectures(Turing,Maxwell Etc...) of GPUs.
-You can find which version you should download from [this link](https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html).
-13. Download the latest version and extract it from the download location
-14. Find the bin folder E\cudnn-windows-x86_64-__Whatever Version__\bin
-15. Copy and paste the .dll files into YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib **Make sure to copy, and not move the files**
-16. If prompted, replace any existing files 
-
-**Notes:** 
-* If no change is seen or any issues are encountered, follow the same steps as above and paste the torch/lib backup folder you made earlier and replace it. If you didn't make a backup, you can also uninstall and reinstall torch through the command line to repair this folder. 
-* This optimization is  intended for the newer version of graphics card (40/30 series) but results have been seen with older graphics card.
-
-
-### Torch Installation
-
-When installing torch and torchvision manually with `pip`, remember to provide
-the argument `--extra-index-url
-https://download.pytorch.org/whl/cu121` as described in the [Manual
-Installation Guide](020_INSTALL_MANUAL.md).
-
-## :simple-amd: ROCm
-
-### Linux Install
-
-AMD GPUs are only supported on Linux platforms due to the lack of a
-Windows ROCm driver at the current time. Also be aware that support
-for newer AMD GPUs is spotty. Your mileage may vary.
-
-It is possible that the ROCm driver is already installed on your
-machine. To test, open up a terminal window and issue the following
-command:
-
-```
-rocm-smi
-```
-
-If you get a table labeled "ROCm System Management Interface" the
-driver is installed and you are done. If you get "command not found,"
-then the driver needs to be installed.
-
-Go to AMD's [ROCm Downloads
-Guide](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation_new.html#installation-methods)
-and scroll to the _Installation Methods_ section. Find the subsection
-for the install method for your preferred Linux distribution, and
-issue the commands given in the recipe.
-
-Annoyingly, the official AMD site does not have a recipe for the most
-recent version of Ubuntu, 22.04. However, this [community-contributed
-recipe](https://novaspirit.github.io/amdgpu-rocm-ubu22/) is reported
-to work well.
-
-After installation, please run `rocm-smi` a second time to confirm
-that the driver is present and the GPU is recognized. You may need to
-do a reboot in order to load the driver.
-
-### Linux Install with a ROCm-docker Container
-
-If you are comfortable with the Docker containerization system, then
-you can build a ROCm docker file. The source code and installation
-recipes are available
-[Here](https://github.com/RadeonOpenCompute/ROCm-docker/blob/master/quick-start.md)
-
-### Torch Installation
-
-When installing torch and torchvision manually with `pip`, remember to provide
-the argument `--extra-index-url
-https://download.pytorch.org/whl/rocm5.6` as described in the [Manual
-Installation Guide](020_INSTALL_MANUAL.md).
-
-This will be done automatically for you if you use the installer
-script.
-
-Be aware that the torch machine learning library does not seamlessly
-interoperate with all AMD GPUs and you may experience garbled images,
-black images, or long startup delays before rendering commences. Most
-of these issues can be solved by Googling for workarounds. If you have
-a problem and find a solution, please post an
-[Issue](https://github.com/invoke-ai/InvokeAI/issues) so that other
-users benefit and we can update this document.

docs/installation/050_INSTALLING_MODELS.md

@@ -1,186 +1,52 @@
----
-title: Installing Models
----
-
-# :octicons-paintbrush-16: Installing Models
+# Installing Models
 
 ## Checkpoint and Diffusers Models
 
-The model checkpoint files ('\*.ckpt') are the Stable Diffusion
-"secret sauce". They are the product of training the AI on millions of
-captioned images gathered from multiple sources.
+The model checkpoint files (`*.ckpt`) are the Stable Diffusion "secret sauce". They are the product of training the AI on millions of captioned images gathered from multiple sources.
 
-Originally there was only a single Stable Diffusion weights file,
-which many people named `model.ckpt`. Now there are dozens or more
-that have been fine tuned to provide particulary styles, genres, or
-other features. In addition, there are several new formats that
-improve on the original checkpoint format: a `.safetensors` format
-which prevents malware from masquerading as a model, and `diffusers`
-models, the most recent innovation.
+Originally there was only a single Stable Diffusion weights file, which many people named `model.ckpt`.
 
-InvokeAI supports all three formats but strongly prefers the
-`diffusers` format. These are distributed as directories containing
-multiple subfolders, each of which contains a different aspect of the
-model. The advantage of this is that the models load from disk really
-fast. Another advantage is that `diffusers` models are supported by a
-large and active set of open source developers working at and with
-HuggingFace organization, and improvements in both rendering quality
-and performance are being made at a rapid pace. Among other features
-is the ability to download and install a `diffusers` model just by
-providing its HuggingFace repository ID.
+Today, there are thousands of models, fine tuned to excel at specific styles, genres, or themes.
 
-While InvokeAI will continue to support `.ckpt` and `.safetensors`
-models for the near future, these are deprecated and support will
-likely be withdrawn at some point in the not-too-distant future.
+!!! tip "Model Formats"
 
-This manual will guide you through installing and configuring model
-weight files and converting legacy `.ckpt` and `.safetensors` files
-into performant `diffusers` models.
+    We also have two more popular model formats, both created [HuggingFace](https://huggingface.co/):
 
-## Base Models
+    - `safetensors`: Single file, like `.ckpt` files. Prevents malware from lurking in a model.
+    - `diffusers`: Splits the model components into separate files, allowing very fast loading.
 
-InvokeAI comes with support for a good set of starter models. You'll
-find them listed in the master models file
-`configs/INITIAL_MODELS.yaml` in the InvokeAI root directory. The
-subset that are currently installed are found in
-`configs/models.yaml`.
+    InvokeAI supports all three formats. Our backend will convert models to `diffusers` format before running them. This is a transparent process.
 
-Note that these files are covered by an "Ethical AI" license which
-forbids certain uses. When you initially download them, you are asked
-to accept the license terms. In addition, some of these models carry
-additional license terms that limit their use in commercial
-applications or on public servers. Be sure to familiarize yourself
-with the model terms by visiting the URLs in the table above.
+## Starter Models
 
-## Community-Contributed Models
+When you first start InvokeAI, you'll see a popup prompting you to install some starter models from the Model Manager. Click the `Starter Models` tab to see the list.
 
-[HuggingFace](https://huggingface.co/models?library=diffusers)
-is a great resource for diffusers models, and is also the home of a
-[fast-growing repository](https://huggingface.co/sd-concepts-library)
-of embedding (".bin") models that add subjects and/or styles to your
-images. The latter are automatically installed on the fly when you
-include the text `<concept-name>` in your prompt. See [Concepts
-Library](../features/CONCEPTS.md) for more information.
+You'll find a collection of popular and high-quality models available for easy download.
 
-Another popular site for community-contributed models is
-[CIVITAI](https://civitai.com). This extensive site currently supports
-only `.safetensors` and `.ckpt` models, but they can be easily loaded
-into InvokeAI and/or converted into optimized `diffusers` models. Be
-aware that CIVITAI hosts many models that generate NSFW content.
+Some models carry license terms that limit their use in commercial applications or on public servers. It's your responsibility to adhere to the license terms.
 
-## Installation
+## Other Models
 
-There are two ways to install and manage models:
+You can install other models using the Model Manager. You'll find tabs for the following install methods:
 
-1. The `invokeai-model-install` script which will download and install
-them for you.  In addition to supporting main models, you can install
-ControlNet, LoRA and Textual Inversion models.
+- **URL or Local Path**: Provide the path to a model on your computer, or a direct link to the model. Some sites require you to use an API token to download models, which you can [set up in the config file].
+- **HuggingFace**: Paste a HF Repo ID to install it. If there are multiple models in the repo, you'll get a list to choose from. Repo IDs look like this: `XpucT/Deliberate`. There is a copy button on each repo to copy the ID.
+- **Scan Folder**: Scan a local folder for models. You can install all of the detected models in one click.
 
-2. The web interface (WebUI) has a GUI for importing and managing
-   models.
+!!! tip "Autoimport"
 
-3. By placing models (or symbolic links to models) inside one of the
-InvokeAI root directory's `autoimport` folder.
+    The dedicated autoimport folder is removed as of v4.0.0. You can do the same thing on the **Scan Folder** tab - paste the folder you'd like to import from and then click `Install All`.
 
-### Installation via `invokeai-model-install`
+### Diffusers models in HF repo subfolders
 
-From the `invoke` launcher, choose option [4] "Download and install
-models." This will launch the same script that prompted you to select
-models at install time. You can use this to add models that you
-skipped the first time around. It is all right to specify a model that
-was previously downloaded; the script will just confirm that the files
-are complete.
+HuggingFace repos can be structured in any way. Some model authors include multiple models within the same folder.
 
-The installer has different panels for installing main models from
-HuggingFace, models from Civitai and other arbitrary web sites,
-ControlNet models, LoRA/LyCORIS models, and Textual Inversion
-embeddings. Each section has a text box in which you can enter a new
-model to install. You can refer to a model using its:
+In this situation, you may need to provide some additional information to identify the model you want, by adding `:subfolder_name` to the repo ID.
 
-1. Local path to the .ckpt, .safetensors or diffusers folder on your local machine
-2. A directory on your machine that contains multiple models
-3. A URL that points to a downloadable model
-4. A HuggingFace repo id
+!!! example
 
-Previously-installed models are shown with checkboxes. Uncheck a box
-to unregister the model from InvokeAI. Models that are physically
-installed inside the InvokeAI root directory will be deleted and
-purged (after a confirmation warning). Models that are located outside
-the InvokeAI root directory will be unregistered but not deleted.
+    Say you have a repo ID `monster-labs/control_v1p_sd15_qrcode_monster`, and the model you want is inside the `v2` subfolder.
 
-Note: The installer script uses a console-based text interface that requires
-significant amounts of horizontal and vertical space. If the display
-looks messed up, just enlarge the terminal window and/or relaunch the
-script.
+    Add `:v2` to the repo ID and use that when installing the model: `monster-labs/control_v1p_sd15_qrcode_monster:v2`
 
-If you wish you can script model addition and deletion, as well as
-listing installed models. Start the "developer's console" and give the
-command `invokeai-model-install --help`. This will give you a series
-of command-line parameters that will let you control model
-installation. Examples:
-
-```
-# (list all controlnet models)
-invokeai-model-install --list controlnet
-
-# (install the model at the indicated URL)
-invokeai-model-install --add https://civitai.com/api/download/models/128713
-
-# (delete the named model)
-invokeai-model-install --delete sd-1/main/analog-diffusion
-```
-
-### Installation via the Web GUI
-
-To install a new model using the Web GUI, do the following:
-
-1. Open the InvokeAI Model Manager (cube at the bottom of the
-left-hand panel) and navigate to *Import Models*
-
-2. In the field labeled *Location* type in the path to the model you
-wish to install. You may use a URL, HuggingFace repo id, or a path on
-your local disk.
-
-3. Alternatively, the *Scan for Models* button allows you to paste in
-the path to a folder somewhere on your machine. It will be scanned for
-importable models and prompt you to add the ones of your choice.
-
-4. Press *Add Model* and wait for confirmation that the model
-was added.
-
-To delete a model, Select *Model Manager* to list all the currently
-installed models. Press the trash can icons to delete any models you
-wish to get rid of. Models whose weights are located inside the
-InvokeAI `models` directory will be purged from disk, while those
-located outside will be unregistered from InvokeAI, but not deleted.
-
-You can see where model weights are located by clicking on the model name.
-This will bring up an editable info panel showing the model's characteristics,
-including the `Model Location` of its files.
-
-### Installation via the `autoimport` function
-
-In the InvokeAI root directory you will find a series of folders under
-`autoimport`, one each for main models, controlnets, embeddings and
-Loras.  Any models that you add to these directories will be scanned
-at startup time and registered automatically.
-
-You may create symbolic links from these folders to models located
-elsewhere on disk and they will be autoimported. You can also create
-subfolders and organize them as you wish.
-
-The location of the autoimport directories are controlled by settings
-in `invokeai.yaml`. See [Configuration](../features/CONFIGURATION.md).
-
-### Installing models that live in HuggingFace subfolders
-
-On rare occasions you may need to install a diffusers-style model that
-lives in a subfolder of a HuggingFace repo id. In this event, simply
-add ":_subfolder-name_" to the end of the repo id. For example, if the
-repo id is "monster-labs/control_v1p_sd15_qrcode_monster" and the model
-you wish to fetch lives in a subfolder named "v2", then the repo id to
-pass to the various model installers should be 
-
-```
-monster-labs/control_v1p_sd15_qrcode_monster:v2
-```
+[set up in the config file]: ../../features/CONFIGURATION#model-marketplace-api-keys

docs/installation/070_INSTALL_XFORMERS.md

@@ -1,204 +0,0 @@
----
-title: Installing xFormers
----
-
-# :material-image-size-select-large: Installing xformers
-
-xFormers is toolbox that integrates with the pyTorch and CUDA
-libraries to provide accelerated performance and reduced memory
-consumption for applications using the transformers machine learning
-architecture. After installing xFormers, InvokeAI users who have
-CUDA GPUs will see a noticeable decrease in GPU memory consumption and
-an increase in speed.
-
-xFormers can be installed into a working InvokeAI installation without
-any code changes or other updates. This document explains how to
-install xFormers.
-
-## Pip Install
-
-For both Windows and Linux, you can install `xformers` in just a
-couple of steps from the command line.
-
-If you are used to launching `invoke.sh` or `invoke.bat` to start
-InvokeAI, then run the launcher and select the "developer's console"
-to get to the command line. If you run invoke.py directly from the
-command line, then just be sure to activate it's virtual environment.
-
-Then run the following three commands:
-
-```sh
-pip install xformers~=0.0.22
-pip install triton    # WON'T WORK ON WINDOWS
-python -m xformers.info output
-```
-
-The first command installs `xformers`, the second installs the
-`triton` training accelerator, and the third prints out the `xformers`
-installation status. On Windows, please omit the `triton` package,
-which is not available on that platform.
-
-If all goes well, you'll see a report like the
-following:
-
-```sh
-xFormers 0.0.22
-memory_efficient_attention.cutlassF:               available
-memory_efficient_attention.cutlassB:               available
-memory_efficient_attention.flshattF:               available
-memory_efficient_attention.flshattB:               available
-memory_efficient_attention.smallkF:                available
-memory_efficient_attention.smallkB:                available
-memory_efficient_attention.tritonflashattF:        available
-memory_efficient_attention.tritonflashattB:        available
-indexing.scaled_index_addF:                        available
-indexing.scaled_index_addB:                        available
-indexing.index_select:                             available
-swiglu.dual_gemm_silu:                             available
-swiglu.gemm_fused_operand_sum:                     available
-swiglu.fused.p.cpp:                                available
-is_triton_available:                               True
-is_functorch_available:                            False
-pytorch.version:                                   2.1.0+cu121
-pytorch.cuda:                                      available
-gpu.compute_capability:                            8.9
-gpu.name:                                          NVIDIA GeForce RTX 4070
-build.info:                                        available
-build.cuda_version:                                1108
-build.python_version:                              3.10.11
-build.torch_version:                               2.1.0+cu121
-build.env.TORCH_CUDA_ARCH_LIST:                    5.0+PTX 6.0 6.1 7.0 7.5 8.0 8.6
-build.env.XFORMERS_BUILD_TYPE:                     Release
-build.env.XFORMERS_ENABLE_DEBUG_ASSERTIONS:        None
-build.env.NVCC_FLAGS:                              None
-build.env.XFORMERS_PACKAGE_FROM:                   wheel-v0.0.20
-build.nvcc_version:                                11.8.89
-source.privacy:                                    open source
-```
-
-## Source Builds
-
-`xformers` is currently under active development and at some point you
-may wish to build it from sourcce to get the latest features and
-bugfixes.
-
-### Source Build on Linux
-
-Note that xFormers only works with true NVIDIA GPUs and will not work
-properly with the ROCm driver for AMD acceleration.
-
-xFormers is not currently available as a pip binary wheel and must be
-installed from source. These instructions were written for a system
-running Ubuntu 22.04, but other Linux distributions should be able to
-adapt this recipe.
-
-#### 1. Install CUDA Toolkit 12.1
-
-You will need the CUDA developer's toolkit in order to compile and
-install xFormers. **Do not try to install Ubuntu's nvidia-cuda-toolkit
-package.** It is out of date and will cause conflicts among the NVIDIA
-driver and binaries. Instead install the CUDA Toolkit package provided
-by NVIDIA itself. Go to [CUDA Toolkit 12.1
-Downloads](https://developer.nvidia.com/cuda-12-1-0-download-archive)
-and use the target selection wizard to choose your platform and Linux
-distribution. Select an installer type of "runfile (local)" at the
-last step.
-
-This will provide you with a recipe for downloading and running a
-install shell script that will install the toolkit and drivers.
-
-#### 2. Confirm/Install pyTorch 2.1.0 with CUDA 12.1 support
-
-If you are using InvokeAI 3.0.2 or higher, these will already be
-installed. If not, you can check whether you have the needed libraries
-using a quick command. Activate the invokeai virtual environment,
-either by entering the "developer's console", or manually with a
-command similar to `source ~/invokeai/.venv/bin/activate` (depending
-on where your `invokeai` directory is.
-
-Then run the command:
-
-```sh
-python -c 'exec("import torch\nprint(torch.__version__)")'
-```
-
-If it prints __2.1.0+cu121__ you're good. If not, you can install the
-most up to date libraries with this command:
-
-```sh
-pip install --upgrade --force-reinstall torch torchvision
-```
-
-#### 3. Install the triton module
-
-This module isn't necessary for xFormers image inference optimization,
-but avoids a startup warning.
-
-```sh
-pip install triton
-```
-
-#### 4. Install source code build prerequisites
-
-To build xFormers from source, you will need the `build-essentials`
-package. If you don't have it installed already, run:
-
-```sh
-sudo apt install build-essential
-```
-
-#### 5. Build xFormers
-
-There is no pip wheel package for xFormers at this time (January
-2023). Although there is a conda package, InvokeAI no longer
-officially supports conda installations and you're on your own if you
-wish to try this route.
-
-Following the recipe provided at the [xFormers GitHub
-page](https://github.com/facebookresearch/xformers), and with the
-InvokeAI virtual environment active (see step 1) run the following
-commands:
-
-```sh
-pip install ninja
-export TORCH_CUDA_ARCH_LIST="6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6"
-pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers
-```
-
-The TORCH_CUDA_ARCH_LIST is a list of GPU architectures to compile
-xFormer support for. You can speed up compilation by selecting
-the architecture specific for your system. You'll find the list of
-GPUs and their architectures at NVIDIA's [GPU Compute
-Capability](https://developer.nvidia.com/cuda-gpus) table.
-
-If the compile and install completes successfully, you can check that
-xFormers is installed with this command:
-
-```sh
-python -m xformers.info
-```
-
-If suiccessful, the top of the listing should indicate "available" for
-each of the `memory_efficient_attention` modules, as shown here:
-
-```sh
-memory_efficient_attention.cutlassF:               available
-memory_efficient_attention.cutlassB:               available
-memory_efficient_attention.flshattF:               available
-memory_efficient_attention.flshattB:               available
-memory_efficient_attention.smallkF:                available
-memory_efficient_attention.smallkB:                available
-memory_efficient_attention.tritonflashattF:        available
-memory_efficient_attention.tritonflashattB:        available
-[...]
-```
-
-You can now launch InvokeAI and enjoy the benefits of xFormers.
-
-### Windows
-
-To come
-
-
----
-(c) Copyright 2023 Lincoln Stein and the InvokeAI Development Team

docs/installation/Developers_documentation/BUILDING_BINARY_INSTALLERS.md

@@ -1,89 +0,0 @@
----
-title: build binary installers
----
-
-# :simple-buildkite: How to build "binary" installers (InvokeAI-mac/windows/linux_on_*.zip)
-
-## 1. Ensure `installers/requirements.in` is correct
-
-and up to date on the branch to be installed.
-
-## <a name="step-2"></a> 2. Run `pip-compile` on each platform.
-
-On each target platform, in the branch that is to be installed, and
-inside the InvokeAI git root folder, run the following commands:
-
-```commandline
-conda activate invokeai # or however you activate python
-pip install pip-tools
-pip-compile --allow-unsafe --generate-hashes --output-file=binary_installer/<reqsfile>.txt binary_installer/requirements.in
-```
-where `<reqsfile>.txt` is whichever of
-```commandline
-py3.10-darwin-arm64-mps-reqs.txt
-py3.10-darwin-x86_64-reqs.txt
-py3.10-linux-x86_64-cuda-reqs.txt
-py3.10-windows-x86_64-cuda-reqs.txt
-```
-matches the current OS and architecture.
-> There is no way to cross-compile these. They must be done on a system matching the target OS and arch.
-
-## <a name="step-3"></a> 3. Set github repository and branch
-
-Once all reqs files have been collected and committed **to the branch
-to be installed**, edit `binary_installer/install.sh.in` and `binary_installer/install.bat.in` so that `RELEASE_URL`
-and `RELEASE_SOURCEBALL` point to the github repo and branch that is
-to be installed.
-
-For example, to install `main` branch of `InvokeAI`, they should be
-set as follows:
-
-`install.sh.in`:
-```commandline
-RELEASE_URL=https://github.com/invoke-ai/InvokeAI
-RELEASE_SOURCEBALL=/archive/refs/heads/main.tar.gz
-```
-
-`install.bat.in`:
-```commandline
-set RELEASE_URL=https://github.com/invoke-ai/InvokeAI
-set RELEASE_SOURCEBALL=/archive/refs/heads/main.tar.gz
-```
-
-Or, to install `damians-cool-feature` branch of `damian0815`, set them
-as follows:
-
-`install.sh.in`:
-```commandline
-RELEASE_URL=https://github.com/damian0815/InvokeAI
-RELEASE_SOURCEBALL=/archive/refs/heads/damians-cool-feature.tar.gz
-```
-
-`install.bat.in`:
-```commandline
-set RELEASE_URL=https://github.com/damian0815/InvokeAI
-set RELEASE_SOURCEBALL=/archive/refs/heads/damians-cool-feature.tar.gz
-```
-
-The branch and repo specified here **must** contain the correct reqs
-files. The installer zip files **do not** contain requirements files,
-they are pulled from the specified branch during the installation
-process.
-
-## 4. Create zip files.
-
-cd into the `installers/` folder and run
-`./create_installers.sh`. This will create
-`InvokeAI-mac_on_<branch>.zip`,
-`InvokeAI-windows_on_<branch>.zip` and
-`InvokeAI-linux_on_<branch>.zip`. These files can be distributed to end users.
-
-These zips will continue to function as installers for all future
-pushes to those branches, as long as necessary changes to
-`requirements.in` are propagated in a timely manner to the
-`py3.10-*-reqs.txt` files using pip-compile as outlined in [step
-2](#step-2).
-
-To actually install, users should unzip the appropriate zip file into an empty
-folder and run `install.sh` on macOS/Linux or `install.bat` on
-Windows.

docs/installation/INSTALLATION.md

@@ -1,88 +1,41 @@
-# Overview
+# Installation Overview
 
-We offer several ways to install InvokeAI, each one suited to your
-experience and preferences. We suggest that everyone start by
-reviewing the
-[hardware](010_INSTALL_AUTOMATED.md#hardware_requirements) and
-[software](010_INSTALL_AUTOMATED.md#software_requirements)
-requirements, as they are the same across each install method. Then
-pick the install method most suitable to your level of experience and
-needs.
+Before installing, review the [installation requirements] to ensure your system is set up properly.
 
-See the [troubleshooting
-section](010_INSTALL_AUTOMATED.md#troubleshooting) of the automated
-install guide for frequently-encountered installation issues.
+See the [FAQ] for frequently-encountered installation issues.
 
-This fork is supported across Linux, Windows and Macintosh. Linux users can use
-either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
-driver).
+If you need more help, join our [discord] or [create an issue].
 
+<h2>Automatic Install</h2>
 
-## **[Automated Installer (Recommended)](010_INSTALL_AUTOMATED.md)**
- ✅ This is the recommended installation method for first-time users. 
+✅ The automatic install is the best way to run InvokeAI. Check out the [installation guide] to get started.
 
-  This is a script that will install all of InvokeAI's essential
-  third party libraries and InvokeAI itself.
+<h2>Manual Install</h2>
 
-🖥️ **Download the latest installer .zip file here** : https://github.com/invoke-ai/InvokeAI/releases/latest
-  
-- *Look for the file labelled "InvokeAI-installer-v3.X.X.zip" at the bottom of the page*
-- If you experience issues, read through the full [installation instructions](010_INSTALL_AUTOMATED.md) to make sure you have met all of the installation requirements. If you need more help, join the [Discord](discord.gg/invoke-ai) or create an issue on [Github](https://github.com/invoke-ai/InvokeAI).
+If you are familiar with python and want more control over the packages that are installed, you can [install InvokeAI manually via PyPI].
 
+<h2>Developer Install</h2>
 
+If you want to contribute to InvokeAI, consult the [developer install guide].
 
-## **[Manual Installation](020_INSTALL_MANUAL.md)**
-This method is recommended for experienced users and developers.
+<h2>Docker Install</h2>
 
-  In this method you will manually run the commands needed to install
-  InvokeAI and its dependencies. We offer two recipes: one suited to
-  those who prefer the `conda` tool, and one suited to those who prefer
-  `pip` and Python virtual environments. In our hands the pip install
-  is faster and more reliable, but your mileage may vary.
-  Note that the conda installation method is currently deprecated and
-  will not be supported at some point in the future.
-
-## **[Docker Installation](040_INSTALL_DOCKER.md)**
 This method is recommended for those familiar with running Docker containers.
 
 We offer a method for creating Docker containers containing InvokeAI and its dependencies. This method is recommended for individuals with experience with Docker containers and understand the pluses and minuses of a container-based install.
 
-## Other Installation Guides
-  - [PyPatchMatch](060_INSTALL_PATCHMATCH.md)
-  - [XFormers](070_INSTALL_XFORMERS.md)
-  - [CUDA and ROCm Drivers](030_INSTALL_CUDA_AND_ROCM.md)
-  - [Installing New Models](050_INSTALLING_MODELS.md)
+See the [docker installation guide].
 
-## :fontawesome-solid-computer: Hardware Requirements
+<h2>Other Installation Guides</h2>
 
-### :octicons-cpu-24: System
-
-You wil need one of the following:
-
-- :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
-- :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
-  only)
-- :fontawesome-brands-apple: An Apple computer with an M1 chip.
-
-** SDXL 1.0 Requirements*
-To use SDXL, user must have one of the following: 
-- :simple-nvidia: An NVIDIA-based graphics card with 8 GB or more VRAM memory.
-- :simple-amd: An AMD-based graphics card with 16 GB or more VRAM memory (Linux
-  only)
-- :fontawesome-brands-apple: An Apple computer with an M1 chip.
-
-
-### :fontawesome-solid-memory: Memory and Disk
-
-- At least 12 GB Main Memory RAM.
-- At least 18 GB of free disk space for the machine learning model, Python, and
-  all its dependencies.
-
-We do **not recommend** the following video cards due to issues with their
-running in half-precision mode and having insufficient VRAM to render 512x512
-images in full-precision mode:
-
-- NVIDIA 10xx series cards such as the 1080ti
-- GTX 1650 series cards
-- GTX 1660 series cards
+- [PyPatchMatch](060_INSTALL_PATCHMATCH.md)
+- [Installing Models](050_INSTALLING_MODELS.md)
 
+[install InvokeAI manually via PyPI]: 020_INSTALL_MANUAL.md
+[developer install guide]: INSTALL_DEVELOPMENT.md
+[docker installation guide]: 040_INSTALL_DOCKER.md
+[installation guide]: 010_INSTALL_AUTOMATED.md
+[FAQ]: ../help/FAQ.md
+[discord]: discord.gg/invoke-ai
+[create an issue]: https://github.com/invoke-ai/InvokeAI/issues
+[installation requirements]: INSTALL_REQUIREMENTS.md

docs/installation/INSTALL_DEVELOPMENT.md

@@ -0,0 +1,36 @@
+# Developer Install
+
+!!! warning
+
+    InvokeAI uses a SQLite database. By running on `main`, you accept responsibility for your database. This
+    means making regular backups (especially before pulling) and/or fixing it yourself in the event that a
+    PR introduces a schema change.
+
+    If you don't need persistent backend storage, you can use an ephemeral in-memory database by setting
+    `use_memory_db: true` in your `invokeai.yaml` file. You'll also want to set `scan_models_on_startup: true`
+    so that your models are registered on startup.
+
+    If this is untenable, you should run the application via the official installer or a manual install of the
+    python package from PyPI. These releases will not break your database.
+
+If you have an interest in how InvokeAI works, or you would like to add features or bugfixes, you are encouraged to install the source code for InvokeAI.
+
+!!! info "Why do I need the frontend toolchain?"
+
+    The repo doesn't contain a build of the frontend. You'll be responsible for rebuilding it (or running it in dev mode) to use the app, as described in the [frontend dev toolchain] docs.
+
+<h2> Installation </h2>
+
+1. [Fork and clone] the [InvokeAI repo].
+1. Follow the [manual installation] docs to create a new virtual environment for the development install.
+   - When installing the InvokeAI package, add `-e` to the command so you get an [editable install].
+1. Install the [frontend dev toolchain] and do a production build of the UI as described.
+1. You can now run the app as described in the [manual installation] docs.
+
+As described in the [frontend dev toolchain] docs, you can run the UI using a dev server. If you do this, you won't need to continually rebuild the frontend. Instead, you run the dev server and use the app with the server URL it provides.
+
+[Fork and clone]: https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/fork-a-repo
+[InvokeAI repo]: https://github.com/invoke-ai/InvokeAI
+[frontend dev toolchain]: ../contributing/frontend/OVERVIEW.md
+[manual installation]: ./020_INSTALL_MANUAL.md
+[editable install]: https://pip.pypa.io/en/latest/cli/pip_install/#cmdoption-e

docs/installation/INSTALL_REQUIREMENTS.md

@@ -0,0 +1,181 @@
+# Requirements
+
+## GPU
+
+!!! warning "Problematic Nvidia GPUs"
+
+    We do not recommend these GPUs. They cannot operate with half precision, but have insufficient VRAM to generate 512x512 images at full precision.
+
+    - NVIDIA 10xx series cards such as the 1080 TI
+    - GTX 1650 series cards
+    - GTX 1660 series cards
+
+Invoke runs best with a dedicated GPU, but will fall back to running on CPU, albeit much slower. You'll need a beefier GPU for SDXL.
+
+!!! example "Stable Diffusion 1.5"
+
+    === "Nvidia"
+
+        ```
+        Any GPU with at least 4GB VRAM.
+        ```
+
+    === "AMD"
+
+        ```
+        Any GPU with at least 4GB VRAM. Linux only.
+        ```
+
+    === "Mac"
+
+        ```
+        Any Apple Silicon Mac with at least 8GB memory.
+        ```
+
+!!! example "Stable Diffusion XL"
+
+    === "Nvidia"
+
+        ```
+        Any GPU with at least 8GB VRAM. Linux only.
+        ```
+
+    === "AMD"
+
+        ```
+        Any GPU with at least 16GB VRAM.
+        ```
+
+    === "Mac"
+
+        ```
+        Any Apple Silicon Mac with at least 16GB memory.
+        ```
+
+## RAM
+
+At least 12GB of RAM.
+
+## Disk
+
+SSDs will, of course, offer the best performance.
+
+The base application disk usage depends on the torch backend.
+
+!!! example "Disk"
+
+    === "Nvidia (CUDA)"
+
+        ```
+        ~6.5GB
+        ```
+
+    === "AMD (ROCm)"
+
+        ```
+        ~12GB
+        ```
+
+    === "Mac (MPS)"
+
+        ```
+        ~3.5GB
+        ```
+
+You'll need to set aside some space for images, depending on how much you generate. A couple GB is enough to get started.
+
+You'll need a good chunk of space for models. Even if you only install the most popular models and the usual support models (ControlNet, IP Adapter ,etc), you will quickly hit 50GB of models.
+
+!!! info "`tmpfs` on Linux"
+
+    If your temporary directory is mounted as a `tmpfs`, ensure it has sufficient space.
+
+## Python
+
+Invoke requires python 3.10 or 3.11. If you don't already have one of these versions installed, we suggest installing 3.11, as it will be supported for longer.
+
+Check that your system has an up-to-date Python installed by running `python --version` in the terminal (Linux, macOS) or cmd/powershell (Windows).
+
+<h3>Installing Python (Windows)</h3>
+
+- Install python 3.11 with [an official installer].
+- The installer includes an option to add python to your PATH. Be sure to enable this. If you missed it, re-run the installer, choose to modify an existing installation, and tick that checkbox.
+- You may need to install [Microsoft Visual C++ Redistributable].
+
+<h3>Installing Python (macOS)</h3>
+
+- Install python 3.11 with [an official installer].
+- If model installs fail with a certificate error, you may need to run this command (changing the python version to match what you have installed): `/Applications/Python\ 3.10/Install\ Certificates.command`
+- If you haven't already, you will need to install the XCode CLI Tools by running `xcode-select --install` in a terminal.
+
+<h3>Installing Python (Linux)</h3>
+
+- Follow the [linux install instructions], being sure to install python 3.11.
+- You'll need to install `libglib2.0-0` and `libgl1-mesa-glx` for OpenCV to work. For example, on a Debian system: `sudo apt update && sudo apt install -y libglib2.0-0 libgl1-mesa-glx`
+
+## Drivers
+
+If you have an Nvidia or AMD GPU, you may need to manually install drivers or other support packages for things to work well or at all.
+
+### Nvidia
+
+Run `nvidia-smi` on your system's command line to verify that drivers and CUDA are installed. If this command fails, or doesn't report versions, you will need to install drivers.
+
+Go to the [CUDA Toolkit Downloads] and carefully follow the instructions for your system to get everything installed.
+
+Confirm that `nvidia-smi` displays driver and CUDA versions after installation.
+
+#### Linux - via Nvidia Container Runtime
+
+An alternative to installing CUDA locally is to use the [Nvidia Container Runtime] to run the application in a container.
+
+#### Windows - Nvidia cuDNN DLLs
+
+An out-of-date cuDNN library can greatly hamper performance on 30-series and 40-series cards. Check with the community on discord to compare your `it/s` if you think you may need this fix.
+
+First, locate the destination for the DLL files and make a quick back up:
+
+1. Find your InvokeAI installation folder, e.g. `C:\Users\Username\InvokeAI\`.
+1. Open the `.venv` folder, e.g. `C:\Users\Username\InvokeAI\.venv` (you may need to show hidden files to see it).
+1. Navigate deeper to the `torch` package, e.g. `C:\Users\Username\InvokeAI\.venv\Lib\site-packages\torch`.
+1. Copy the `lib` folder inside `torch` and back it up somewhere.
+
+Next, download and copy the updated cuDNN DLLs:
+
+1. Go to <https://developer.nvidia.com/cudnn>.
+1. Create an account if needed and log in.
+1. Choose the newest version of cuDNN that works with your GPU architecture. Consult the [cuDNN support matrix] to determine the correct version for your GPU.
+1. Download the latest version and extract it.
+1. Find the `bin` folder, e.g. `cudnn-windows-x86_64-SOME_VERSION\bin`.
+1. Copy and paste the `.dll` files into the `lib` folder you located earlier. Replace files when prompted.
+
+If, after restarting the app, this doesn't improve your performance, either restore your back up or re-run the installer to reset `torch` back to its original state.
+
+### AMD
+
+!!! info "Linux Only"
+
+    AMD GPUs are supported on Linux only, due to ROCm (the AMD equivalent of CUDA) support being Linux only.
+
+!!! warning "Bumps Ahead"
+
+    While the application does run on AMD GPUs, there are occasional bumps related to spotty torch support.
+
+Run `rocm-smi` on your system's command line verify that drivers and ROCm are installed. If this command fails, or doesn't report versions, you will need to install them.
+
+Go to the [ROCm Documentation] and carefully follow the instructions for your system to get everything installed.
+
+Confirm that `rocm-smi` displays driver and CUDA versions after installation.
+
+#### Linux - via Docker Container
+
+An alternative to installing ROCm locally is to use a [ROCm docker container] to run the application in a container.
+
+[ROCm docker container]: https://github.com/ROCm/ROCm-docker
+[ROCm Documentation]: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html
+[cuDNN support matrix]: https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html
+[Nvidia Container Runtime]: https://developer.nvidia.com/container-runtime
+[linux install instructions]: https://docs.python-guide.org/starting/install3/linux/
+[Microsoft Visual C++ Redistributable]: https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170
+[an official installer]: https://www.python.org/downloads/release/python-3118/
+[CUDA Toolkit Downloads]: https://developer.nvidia.com/cuda-downloads

docs/installation/deprecated_documentation/INSTALL_BINARY.md

@@ -1,64 +0,0 @@
----
-title: InvokeAI Binary Installer
----
-
-The InvokeAI binary installer is a shell script that will install InvokeAI onto a stock
-computer running recent versions of Linux, MacOSX or Windows. It will leave you
-with a version that runs a stable version of InvokeAI. When a new version of
-InvokeAI is released, you will download and reinstall the new version.
-
-If you wish to tinker with unreleased versions of InvokeAI that introduce
-potentially unstable new features, you should consider using the
-[source installer](INSTALL_SOURCE.md) or one of the
-[manual install](../020_INSTALL_MANUAL.md) methods.
-
-**Important Caveats**
-  - This script does not support AMD GPUs. For Linux AMD support,
-    please use the manual or source code installer methods.
-
-  - This script has difficulty on some Macintosh machines
-    that have previously been used for Python development due to
-    conflicting development tools versions. Mac developers may wish
-    to try the source code installer or one of the manual methods instead.
-
-!!! todo
-
-    Before you begin, make sure that you meet
-    the[hardware requirements](/#hardware-requirements) and has the
-    appropriate GPU drivers installed. In particular, if you are a Linux user with
-    an AMD GPU installed, you may need to install the
-    [ROCm-driver](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).
-
-Installation requires roughly 18G of free disk space to load the libraries and
-recommended model weights files.
-
-## Steps to Install
-
-1. Download the
-   [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest) of
-   InvokeAI's installer for your platform. Look for a file named `InvokeAI-binary-<your platform>.zip`
-
-2. Place the downloaded package someplace where you have plenty of HDD space,
-   and have full permissions (i.e. `~/` on Lin/Mac; your home folder on Windows)
-
-3. Extract the 'InvokeAI' folder from the downloaded package
-
-4. Open the extracted 'InvokeAI' folder
-
-5. Double-click 'install.bat' (Windows), or 'install.sh' (Lin/Mac) (or run from
-   a terminal)
-
-6. Follow the prompts
-
-7. After installation, please run the 'invoke.bat' file (on Windows) or
-   'invoke.sh' file (on Linux/Mac) to start InvokeAI.
-
-## Troubleshooting
-
-If you run into problems during or after installation, the InvokeAI team is
-available to help you. Either create an
-[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub site, or
-make a request for help on the "bugs-and-support" channel of our
-[Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100% volunteer
-organization, but typically somebody will be available to help you within 24
-hours, and often much sooner.

docs/installation/deprecated_documentation/INSTALL_JUPYTER.md

@@ -1,32 +0,0 @@
----
-title: Running InvokeAI on Google Colab using a Jupyter Notebook
----
-
-## Introduction
-
-We have a [Jupyter
-notebook](https://github.com/invoke-ai/InvokeAI/blob/main/notebooks/Stable_Diffusion_AI_Notebook.ipynb)
-with cell-by-cell installation steps. It will download the code in
-this repo as one of the steps, so instead of cloning this repo, simply
-download the notebook from the link above and load it up in VSCode
-(with the appropriate extensions installed)/Jupyter/JupyterLab and
-start running the cells one-by-one.
-
-!!! Note "you will need NVIDIA drivers, Python 3.10, and Git installed beforehand"
-
-## Running Online On Google Colabotary
-[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/invoke-ai/InvokeAI/blob/main/notebooks/Stable_Diffusion_AI_Notebook.ipynb)
-
-## Running Locally (Cloning)
-
-1. Install the Jupyter Notebook python library (one-time):
-pip install jupyter
-
-2. Clone the InvokeAI repository:
-git clone https://github.com/invoke-ai/InvokeAI.git
-cd invoke-ai
-3. Create a virtual environment using conda:
-conda create -n invoke jupyter
-4. Activate the environment and start the Jupyter notebook:
-conda activate invoke
-jupyter notebook

docs/installation/deprecated_documentation/INSTALL_LINUX.md

@@ -1,135 +0,0 @@
----
-title: Manual Installation, Linux
----
-
-# :fontawesome-brands-linux: Linux
-
-## Installation
-
-1.  You will need to install the following prerequisites if they are not already
-    available. Use your operating system's preferred installer.
-
-    - Python (version 3.8.5 recommended; higher may work)
-    - git
-
-2.  Install the Python Anaconda environment manager.
-
-    ```bash
-    ~$  wget https://repo.anaconda.com/archive/Anaconda3-2022.05-Linux-x86_64.sh
-    ~$  chmod +x Anaconda3-2022.05-Linux-x86_64.sh
-    ~$  ./Anaconda3-2022.05-Linux-x86_64.sh
-    ```
-
-    After installing anaconda, you should log out of your system and log back
-    in. If the installation worked, your command prompt will be prefixed by the
-    name of the current anaconda environment - `(base)`.
-
-3.  Copy the InvokeAI source code from GitHub:
-
-    ```bash
-    (base) ~$ git clone https://github.com/invoke-ai/InvokeAI.git
-    ```
-
-    This will create InvokeAI folder where you will follow the rest of the
-    steps.
-
-4.  Enter the newly-created InvokeAI folder. From this step forward make sure
-    that you are working in the InvokeAI directory!
-
-    ```bash
-    (base) ~$ cd InvokeAI
-    (base) ~/InvokeAI$
-    ```
-
-5.  Use anaconda to copy necessary python packages, create a new python
-    environment named `invokeai` and then activate the environment.
-
-    !!! todo "For systems with a CUDA (Nvidia) card:"
-
-       ```bash
-       (base) rm -rf src      # (this is a precaution in case there is already a src directory)
-       (base) ~/InvokeAI$ conda env create -f environment-cuda.yml
-       (base) ~/InvokeAI$ conda activate invokeai
-       (invokeai) ~/InvokeAI$
-       ```
-
-    !!! todo "For systems with an AMD card (using ROCm driver):"
-
-       ```bash
-       (base) rm -rf src      # (this is a precaution in case there is already a src directory)
-       (base) ~/InvokeAI$ conda env create -f environment-AMD.yml
-       (base) ~/InvokeAI$ conda activate invokeai
-       (invokeai) ~/InvokeAI$
-       ```
-
-    After these steps, your command prompt will be prefixed by `(invokeai)` as
-    shown above.
-
-6.  Load the big stable diffusion weights files and a couple of smaller
-    machine-learning models:
-
-    ```bash
-    (invokeai) ~/InvokeAI$ python3 scripts/configure_invokeai.py
-    ```
-
-    !!! note
-
-        This script will lead you through the process of creating an account on Hugging Face,
-        accepting the terms and conditions of the Stable Diffusion model license,
-        and obtaining an access token for downloading. It will then download and
-        install the weights files for you.
-
-        Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing
-        the same thing.
-
-7.  Start generating images!
-
-    !!! todo "Run InvokeAI!"
-
-        !!! warning "IMPORTANT"
-
-            Make sure that the conda environment is activated, which should create
-            `(invokeai)` in front of your prompt!
-
-        === "CLI"
-
-            ```bash
-            python scripts/invoke.py
-            ```
-
-        === "local Webserver"
-
-            ```bash
-            python scripts/invoke.py --web
-            ```
-
-        === "Public Webserver"
-
-            ```bash
-            python scripts/invoke.py --web --host 0.0.0.0
-            ```
-
-        To use an alternative model you may invoke the `!switch` command in
-        the CLI, or pass `--model <model_name>` during `invoke.py` launch for
-        either the CLI or the Web UI. See [Command Line
-        Client](../../deprecated/CLI.md#model-selection-and-importation). The
-        model names are defined in `configs/models.yaml`.
-
-8. Subsequently, to relaunch the script, be sure to run "conda activate
-   invokeai" (step 5, second command), enter the `InvokeAI` directory, and then
-   launch the invoke script (step 8). If you forget to activate the 'invokeai'
-   environment, the script will fail with multiple `ModuleNotFound` errors.
-
-## Updating to newer versions of the script
-
-This distribution is changing rapidly. If you used the `git clone` method
-(step 5) to download the InvokeAI directory, then to update to the latest and
-greatest version, launch the Anaconda window, enter `InvokeAI` and type:
-
-```bash
-(invokeai) ~/InvokeAI$ git pull
-(invokeai) ~/InvokeAI$ rm -rf src   # prevents conda freezing errors
-(invokeai) ~/InvokeAI$ conda env update -f environment.yml
-```
-
-This will bring your local copy into sync with the remote one.

docs/installation/deprecated_documentation/INSTALL_MAC.md

@@ -1,525 +0,0 @@
----
-title: Manual Installation, macOS
----
-
-# :fontawesome-brands-apple: macOS
-
-Invoke AI runs quite well on M1 Macs and we have a number of M1 users in the
-community.
-
-While the repo does run on Intel Macs, we only have a couple reports. If you
-have an Intel Mac and run into issues, please create an issue on Github and we
-will do our best to help.
-
-## Requirements
-
-- macOS 12.3 Monterey or later
-- About 10GB of storage (and 10GB of data if your internet connection has data
-  caps)
-- Any M1 Macs or an Intel Macs with 4GB+ of VRAM (ideally more)
-
-## Installation
-
-!!! todo "Homebrew"
-
-    First you will install the "brew" package manager. Skip this if brew is already installed.
-
-    ```bash title="install brew (and Xcode command line tools)"
-    /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
-    ```
-
-!!! todo "Conda Installation"
-
-    Now there are two different ways to set up the Python (miniconda) environment:
-
-       1. Standalone
-       2. with pyenv
-
-    If you don't know what we are talking about, choose Standalone. If you are familiar with python environments, choose "with pyenv"
-
-    === "Standalone"
-
-        ```bash title="Install cmake, protobuf, and rust"
-        brew install cmake protobuf rust
-        ```
-
-        ```bash title="Clone the InvokeAI repository"
-        # Clone the Invoke AI repo
-        git clone https://github.com/invoke-ai/InvokeAI.git
-        cd InvokeAI
-        ```
-
-        Choose the appropriate architecture for your system and install miniconda:
-
-        === "M1 arm64"
-
-            ```bash title="Install miniconda for M1 arm64"
-            curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh \
-              -o Miniconda3-latest-MacOSX-arm64.sh
-            /bin/bash Miniconda3-latest-MacOSX-arm64.sh
-            ```
-
-        === "Intel x86_64"
-
-            ```bash title="Install miniconda for Intel"
-            curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh \
-              -o Miniconda3-latest-MacOSX-x86_64.sh
-            /bin/bash Miniconda3-latest-MacOSX-x86_64.sh
-            ```
-
-    === "with pyenv"
-
-        ```bash
-        brew install pyenv-virtualenv
-        pyenv install anaconda3-2022.05
-        pyenv virtualenv anaconda3-2022.05
-        eval "$(pyenv init -)"
-        pyenv activate anaconda3-2022.05
-        ```
-
-!!! todo "Clone the Invoke AI repo"
-
-    ```bash
-    git clone https://github.com/invoke-ai/InvokeAI.git
-    cd InvokeAI
-    ```
-
-!!! todo "Create the environment & install packages"
-
-    === "M1 Mac"
-
-        ```bash
-        PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-arm64 conda env create -f environment-mac.yml
-        ```
-
-    === "Intel x86_64 Mac"
-
-        ```bash
-        PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-64 conda env create -f environment-mac.yml
-        ```
-
-    ```bash
-    # Activate the environment (you need to do this every time you want to run SD)
-    conda activate invokeai
-    ```
-
-    !!! info
-
-        `export PIP_EXISTS_ACTION=w` is a precaution to fix `conda env
-        create -f environment-mac.yml` never finishing in some situations. So
-        it isn't required but won't hurt.
-
-!!! todo "Download the model weight files"
-
-    The `configure_invokeai.py` script downloads and installs the model weight
-    files for you. It will lead you through the process of getting a Hugging Face
-    account, accepting the Stable Diffusion model weight license agreement, and
-    creating a download token:
-
-    ```bash
-    # This will take some time, depending on the speed of your internet connection
-    # and will consume about 10GB of space
-    python scripts/configure_invokeai.py
-    ```
-
-!!! todo "Run InvokeAI!"
-
-    !!! warning "IMPORTANT"
-
-        Make sure that the conda environment is activated, which should create
-        `(invokeai)` in front of your prompt!
-
-    === "CLI"
-
-        ```bash
-        python scripts/invoke.py
-        ```
-
-    === "local Webserver"
-
-        ```bash
-        python scripts/invoke.py --web
-        ```
-
-    === "Public Webserver"
-
-        ```bash
-        python scripts/invoke.py --web --host 0.0.0.0
-        ```
-
-    To use an alternative model you may invoke the `!switch` command in
-    the CLI, or pass `--model <model_name>` during `invoke.py` launch for
-    either the CLI or the Web UI. See [Command Line
-    Client](../../deprecated/CLI.md#model-selection-and-importation). The
-    model names are defined in `configs/models.yaml`.
-
----
-
-## Common problems
-
-After you followed all the instructions and try to run invoke.py, you might get
-several errors. Here's the errors I've seen and found solutions for.
-
-### Is it slow?
-
-```bash title="Be sure to specify 1 sample and 1 iteration."
-python ./scripts/orig_scripts/txt2img.py \
-  --prompt "ocean" \
-  --ddim_steps 5 \
-  --n_samples 1 \
-  --n_iter 1
-```
-
----
-
-### Doesn't work anymore?
-
-PyTorch nightly includes support for MPS. Because of this, this setup is
-inherently unstable. One morning I woke up and it no longer worked no matter
-what I did until I switched to miniforge. However, I have another Mac that works
-just fine with Anaconda. If you can't get it to work, please search a little
-first because many of the errors will get posted and solved. If you can't find a
-solution please [create an issue](https://github.com/invoke-ai/InvokeAI/issues).
-
-One debugging step is to update to the latest version of PyTorch nightly.
-
-```bash
-conda install \
-  pytorch \
-  torchvision \
-  -c pytorch-nightly \
-  -n invokeai
-```
-
-If it takes forever to run `conda env create -f environment-mac.yml`, try this:
-
-```bash
-git clean -f
-conda clean \
-  --yes \
-  --all
-```
-
-Or you could try to completley reset Anaconda:
-
-```bash
-conda update \
-  --force-reinstall \
-  -y \
-  -n base \
-  -c defaults conda
-```
-
----
-
-### "No module named cv2", torch, 'invokeai', 'transformers', 'taming', etc
-
-There are several causes of these errors:
-
-1. Did you remember to `conda activate invokeai`? If your terminal prompt begins
-   with "(invokeai)" then you activated it. If it begins with "(base)" or
-   something else you haven't.
-
-2. You might've run `./scripts/configure_invokeai.py` or `./scripts/invoke.py`
-   instead of `python ./scripts/configure_invokeai.py` or
-   `python ./scripts/invoke.py`. The cause of this error is long so it's below.
-
-    <!-- I could not find out where the error is, otherwise would have marked it as a footnote -->
-
-3. if it says you're missing taming you need to rebuild your virtual
-   environment.
-
-   ```bash
-   conda deactivate
-   conda env remove -n invokeai
-   conda env create -f environment-mac.yml
-   ```
-
-4. If you have activated the invokeai virtual environment and tried rebuilding
-   it, maybe the problem could be that I have something installed that you don't
-   and you'll just need to manually install it. Make sure you activate the
-   virtual environment so it installs there instead of globally.
-
-   ```bash
-   conda activate invokeai
-   pip install <package name>
-   ```
-
-You might also need to install Rust (I mention this again below).
-
----
-
-### How many snakes are living in your computer?
-
-You might have multiple Python installations on your system, in which case it's
-important to be explicit and consistent about which one to use for a given
-project. This is because virtual environments are coupled to the Python that
-created it (and all the associated 'system-level' modules).
-
-When you run `python` or `python3`, your shell searches the colon-delimited
-locations in the `PATH` environment variable (`echo $PATH` to see that list) in
-that order - first match wins. You can ask for the location of the first
-`python3` found in your `PATH` with the `which` command like this:
-
-```bash
-% which python3
-/usr/bin/python3
-```
-
-Anything in `/usr/bin` is
-[part of the OS](https://developer.apple.com/library/archive/documentation/FileManagement/Conceptual/FileSystemProgrammingGuide/FileSystemOverview/FileSystemOverview.html#//apple_ref/doc/uid/TP40010672-CH2-SW6).
-However, `/usr/bin/python3` is not actually python3, but rather a stub that
-offers to install Xcode (which includes python 3). If you have Xcode installed
-already, `/usr/bin/python3` will execute
-`/Library/Developer/CommandLineTools/usr/bin/python3` or
-`/Applications/Xcode.app/Contents/Developer/usr/bin/python3` (depending on which
-Xcode you've selected with `xcode-select`).
-
-Note that `/usr/bin/python` is an entirely different python - specifically,
-python 2. Note: starting in macOS 12.3, `/usr/bin/python` no longer exists.
-
-```bash
-% which python3
-/opt/homebrew/bin/python3
-```
-
-If you installed python3 with Homebrew and you've modified your path to search
-for Homebrew binaries before system ones, you'll see the above path.
-
-```bash
-% which python
-/opt/anaconda3/bin/python
-```
-
-If you have Anaconda installed, you will see the above path. There is a
-`/opt/anaconda3/bin/python3` also.
-
-We expect that `/opt/anaconda3/bin/python` and `/opt/anaconda3/bin/python3`
-should actually be the _same python_, which you can verify by comparing the
-output of `python3 -V` and `python -V`.
-
-```bash
-(invokeai) % which python
-/Users/name/miniforge3/envs/invokeai/bin/python
-```
-
-The above is what you'll see if you have miniforge and correctly activated the
-invokeai environment, while usingd the standalone setup instructions above.
-
-If you otherwise installed via pyenv, you will get this result:
-
-```bash
-(anaconda3-2022.05) % which python
-/Users/name/.pyenv/shims/python
-```
-
-It's all a mess and you should know
-[how to modify the path environment variable](https://support.apple.com/guide/terminal/use-environment-variables-apd382cc5fa-4f58-4449-b20a-41c53c006f8f/mac)
-if you want to fix it. Here's a brief hint of the most common ways you can
-modify it (don't really have the time to explain it all here).
-
-- ~/.zshrc
-- ~/.bash_profile
-- ~/.bashrc
-- /etc/paths.d
-- /etc/path
-
-Which one you use will depend on what you have installed, except putting a file
-in /etc/paths.d - which also is the way I prefer to do.
-
-Finally, to answer the question posed by this section's title, it may help to
-list all of the `python` / `python3` things found in `$PATH` instead of just the
-first hit. To do so, add the `-a` switch to `which`:
-
-```bash
-% which -a python3
-...
-```
-
-This will show a list of all binaries which are actually available in your PATH.
-
----
-
-### Debugging?
-
-Tired of waiting for your renders to finish before you can see if it works?
-Reduce the steps! The image quality will be horrible but at least you'll get
-quick feedback.
-
-```bash
-python ./scripts/txt2img.py \
-  --prompt "ocean" \
-  --ddim_steps 5 \
-  --n_samples 1 \
-  --n_iter 1
-```
-
----
-
-### OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'
-
-```bash
-python scripts/configure_invokeai.py
-```
-
----
-
-### "The operator [name] is not current implemented for the MPS device." (sic)
-
-!!! example "example error"
-
-    ```bash
-    ... NotImplementedError: The operator 'aten::_index_put_impl_' is not current
-    implemented for the MPS device. If you want this op to be added in priority
-    during the prototype phase of this feature, please comment on
-    https://github.com/pytorch/pytorch/issues/77764.
-    As a temporary fix, you can set the environment variable
-    `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op.
-    WARNING: this will be slower than running natively on MPS.
-    ```
-
-The InvokeAI version includes this fix in
-[environment-mac.yml](https://github.com/invoke-ai/InvokeAI/blob/main/environment-mac.yml).
-
-### "Could not build wheels for tokenizers"
-
-I have not seen this error because I had Rust installed on my computer before I
-started playing with Stable Diffusion. The fix is to install Rust.
-
-```bash
-curl \
-  --proto '=https' \
-  --tlsv1.2 \
-  -sSf https://sh.rustup.rs | sh
-```
-
----
-
-### How come `--seed` doesn't work?
-
-!!! Information
-
-    Completely reproducible results are not guaranteed across PyTorch releases,
-    individual commits, or different platforms. Furthermore, results may not be
-    reproducible between CPU and GPU executions, even when using identical seeds.
-
-[PyTorch docs](https://pytorch.org/docs/stable/notes/randomness.html)
-
-Second, we might have a fix that at least gets a consistent seed sort of. We're
-still working on it.
-
-### libiomp5.dylib error?
-
-```bash
-OMP: Error #15: Initializing libiomp5.dylib, but found libomp.dylib already initialized.
-```
-
-You are likely using an Intel package by mistake. Be sure to run conda with the
-environment variable `CONDA_SUBDIR=osx-arm64`, like so:
-
-`CONDA_SUBDIR=osx-arm64 conda install ...`
-
-This error happens with Anaconda on Macs when the Intel-only `mkl` is pulled in
-by a dependency.
-[nomkl](https://stackoverflow.com/questions/66224879/what-is-the-nomkl-python-package-used-for)
-is a metapackage designed to prevent this, by making it impossible to install
-`mkl`, but if your environment is already broken it may not work.
-
-Do _not_ use `os.environ['KMP_DUPLICATE_LIB_OK']='True'` or equivalents as this
-masks the underlying issue of using Intel packages.
-
----
-
-### Not enough memory
-
-This seems to be a common problem and is probably the underlying problem for a
-lot of symptoms (listed below). The fix is to lower your image size or to add
-`model.half()` right after the model is loaded. I should probably test it out.
-I've read that the reason this fixes problems is because it converts the model
-from 32-bit to 16-bit and that leaves more RAM for other things. I have no idea
-how that would affect the quality of the images though.
-
-See [this issue](https://github.com/CompVis/stable-diffusion/issues/71).
-
----
-
-### "Error: product of dimension sizes > 2\*\*31'"
-
-This error happens with img2img, which I haven't played with too much yet. But I
-know it's because your image is too big or the resolution isn't a multiple of
-32x32. Because the stable-diffusion model was trained on images that were 512 x
-512, it's always best to use that output size (which is the default). However,
-if you're using that size and you get the above error, try 256 x 256 or 512 x
-256 or something as the source image.
-
-BTW, 2\*\*31-1 =
-[2,147,483,647](https://en.wikipedia.org/wiki/2,147,483,647#In_computing), which
-is also 32-bit signed [LONG_MAX](https://en.wikipedia.org/wiki/C_data_types) in
-C.
-
----
-
-### I just got Rickrolled! Do I have a virus?
-
-You don't have a virus. It's part of the project. Here's
-[Rick](https://github.com/invoke-ai/InvokeAI/blob/main/assets/rick.jpeg) and
-here's
-[the code](https://github.com/invoke-ai/InvokeAI/blob/69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc/scripts/txt2img.py#L79)
-that swaps him in. It's a NSFW filter, which IMO, doesn't work very good (and we
-call this "computer vision", sheesh).
-
----
-
-### My images come out black
-
-We might have this fixed, we are still testing.
-
-There's a [similar issue](https://github.com/CompVis/stable-diffusion/issues/69)
-on CUDA GPU's where the images come out green. Maybe it's the same issue?
-Someone in that issue says to use "--precision full", but this fork actually
-disables that flag. I don't know why, someone else provided that code and I
-don't know what it does. Maybe the `model.half()` suggestion above would fix
-this issue too. I should probably test it.
-
-### "view size is not compatible with input tensor's size and stride"
-
-```bash
-File "/opt/anaconda3/envs/invokeai/lib/python3.10/site-packages/torch/nn/functional.py", line 2511, in layer_norm
-return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
-RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
-```
-
-Update to the latest version of invoke-ai/InvokeAI. We were patching pytorch but
-we found a file in stable-diffusion that we could change instead. This is a
-32-bit vs 16-bit problem.
-
-### The processor must support the Intel bla bla bla
-
-What? Intel? On an Apple Silicon?
-
-```bash
-Intel MKL FATAL ERROR: This system does not meet the minimum requirements for use of the Intel(R) Math Kernel Library. The processor must support the Intel(R) Supplemental Streaming SIMD Extensions 3 (Intel(R) SSSE3) instructions. The processor must support the Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) instructions. The processor must support the Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
-```
-
-This is due to the Intel `mkl` package getting picked up when you try to install
-something that depends on it-- Rosetta can translate some Intel instructions but
-not the specialized ones here. To avoid this, make sure to use the environment
-variable `CONDA_SUBDIR=osx-arm64`, which restricts the Conda environment to only
-use ARM packages, and use `nomkl` as described above.
-
----
-
-### input types 'tensor<2x1280xf32>' and 'tensor<\*xf16>' are not broadcast compatible
-
-May appear when just starting to generate, e.g.:
-
-```bash
-invoke> clouds
-Generating:   0%|                                                              | 0/1 [00:00<?, ?it/s]/Users/[...]/dev/stable-diffusion/ldm/modules/embedding_manager.py:152: UserWarning: The operator 'aten::nonzero' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/_temp/anaconda/conda-bld/pytorch_1662016319283/work/aten/src/ATen/mps/MPSFallback.mm:11.)
-  placeholder_idx = torch.where(
-                                                                                                    loc("mps_add"("(mpsFileLoc): /AppleInternal/Library/BuildRoots/20d6c351-ee94-11ec-bcaf-7247572f23b4/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShadersGraph/mpsgraph/MetalPerformanceShadersGraph/Core/Files/MPSGraphUtilities.mm":219:0)): error: input types 'tensor<2x1280xf32>' and 'tensor<*xf16>' are not broadcast compatible
-LLVM ERROR: Failed to infer result type(s).
-Abort trap: 6
-/Users/[...]/opt/anaconda3/envs/invokeai/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
-  warnings.warn('resource_tracker: There appear to be %d '
-```

docs/installation/deprecated_documentation/INSTALL_PCP.md

@@ -1,17 +0,0 @@
----
-title: Installing InvokeAI with the Pre-Compiled PIP Installer
----
-
-# THIS NEEDS TO BE FLESHED OUT
-
-## Introduction
-
-## Walkthrough
-
-## Updating to newer versions
-
-### Updating the stable version
-
-### Updating to the development version
-
-## Troubleshooting

docs/installation/deprecated_documentation/INSTALL_SOURCE.md

@@ -1,225 +0,0 @@
----
-title: Source Installer
----
-
-# The InvokeAI Source Installer
-
-## Introduction
-
-The source installer is a shell script that attempts to automate every step
-needed to install and run InvokeAI on a stock computer running recent versions
-of Linux, MacOS or Windows. It will leave you with a version that runs a stable
-version of InvokeAI with the option to upgrade to experimental versions later.
-
-Before you begin, make sure that you meet the
-[hardware requirements](../../index.md#hardware-requirements) and has the appropriate
-GPU drivers installed. In particular, if you are a Linux user with an AMD GPU
-installed, you may need to install the
-[ROCm driver](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).
-
-Installation requires roughly 18G of free disk space to load the libraries and
-recommended model weights files.
-
-## Walk through
-
-Though there are multiple steps, there really is only one click involved to kick
-off the process.
-
-1.  The source installer is distributed in ZIP files. Go to the
-    [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest), and
-    look for a series of files named:
-
-    - [invokeAI-src-installer-2.2.3-mac.zip](https://github.com/invoke-ai/InvokeAI/releases/latest/download/invokeAI-src-installer-2.2.3-mac.zip)
-    - [invokeAI-src-installer-2.2.3-windows.zip](https://github.com/invoke-ai/InvokeAI/releases/latest/download/invokeAI-src-installer-2.2.3-windows.zip)
-    - [invokeAI-src-installer-2.2.3-linux.zip](https://github.com/invoke-ai/InvokeAI/releases/latest/download/invokeAI-src-installer-2.2.3-linux.zip)
-
-    Download the one that is appropriate for your operating system.
-
-2.  Unpack the zip file into a directory that has at least 18G of free space. Do
-    _not_ unpack into a directory that has an earlier version of InvokeAI.
-
-    This will create a new directory named "InvokeAI". This example shows how
-    this would look using the `unzip` command-line tool, but you may use any
-    graphical or command-line Zip extractor:
-
-    ```cmd
-    C:\Documents\Linco> unzip invokeAI-windows.zip
-    Archive:  C: \Linco\Downloads\invokeAI-linux.zip
-    creating: invokeAI\
-    inflating: invokeAI\install.bat
-    inflating: invokeAI\readme.txt
-    ```
-
-3. If you are a macOS user, you may need to install the Xcode command line tools.
-   These are a set of tools that are needed to run certain applications in a Terminal,
-   including InvokeAI. This package is provided directly by Apple.
-
-   To install, open a terminal window and run `xcode-select --install`. You will get
-   a macOS system popup guiding you through the install. If you already have them
-   installed, you will instead see some output in the Terminal advising you that the
-   tools are already installed.
-
-   More information can be found here:
-   https://www.freecodecamp.org/news/install-xcode-command-line-tools/
-
-4.  If you are using a desktop GUI, double-click the installer file. It will be
-    named `install.bat` on Windows systems and `install.sh` on Linux and
-    Macintosh systems.
-
-5.  Alternatively, from the command line, run the shell script or .bat file:
-
-    ```cmd
-    C:\Documents\Linco> cd invokeAI
-    C:\Documents\Linco\invokeAI> install.bat
-    ```
-
-6.  Sit back and let the install script work. It will install various binary
-    requirements including Conda, Git and Python, then download the current
-    InvokeAI code and install it along with its dependencies.
-
-    Be aware that some of the library download and install steps take a long time.
-    In particular, the `pytorch` package is quite large and often appears to get
-    "stuck" at 99.9%. Similarly, the `pip installing requirements` step may
-    appear to hang. Have patience and the installation step will eventually
-    resume. However, there are occasions when the library install does
-    legitimately get stuck. If you have been waiting for more than ten minutes
-    and nothing is happening, you can interrupt the script with ^C. You may restart
-    it and it will pick up where it left off.
-
-7.  After installation completes, the installer will launch a script called
-    `configure_invokeai.py`, which will guide you through the first-time process of
-    selecting one or more Stable Diffusion model weights files, downloading and
-    configuring them.
-
-    Note that the main Stable Diffusion weights file is protected by a license
-    agreement that you must agree to in order to use. The script will list the
-    steps you need to take to create an account on the official site that hosts
-    the weights files, accept the agreement, and provide an access token that
-    allows InvokeAI to legally download and install the weights files.
-
-    If you have already downloaded the weights file(s) for another Stable
-    Diffusion distribution, you may skip this step (by selecting "skip" when
-    prompted) and configure InvokeAI to use the previously-downloaded files. The
-    process for this is described in [Installing Models](../050_INSTALLING_MODELS.md).
-
-8.  The script will now exit and you'll be ready to generate some images. The
-    invokeAI directory will contain numerous files. Look for a shell script
-    named `invoke.sh` (Linux/Mac) or `invoke.bat` (Windows). Launch the script
-    by double-clicking it or typing its name at the command-line:
-
-    ```cmd
-    C:\Documents\Linco> cd invokeAI
-    C:\Documents\Linco\invokeAI> invoke.bat
-    ```
-
-The `invoke.bat` (`invoke.sh`) script will give you the choice of starting (1)
-the command-line interface, or (2) the web GUI. If you start the latter, you can
-load the user interface by pointing your browser at http://localhost:9090.
-
-The `invoke` script also offers you a third option labeled "open the developer
-console". If you choose this option, you will be dropped into a command-line
-interface in which you can run python commands directly, access developer tools,
-and launch InvokeAI with customized options. To do the latter, you would launch
-the script `scripts/invoke.py` as shown in this example:
-
-```cmd
-python scripts/invoke.py --web --max_load_models=3 \
-    --model=waifu-1.3 --steps=30 --outdir=C:/Documents/AIPhotos
-```
-
-These options are described in detail in the
-[Command-Line Interface](../../deprecated/CLI.md) documentation.
-
-## Troubleshooting
-
-_Package dependency conflicts_ If you have previously installed
-InvokeAI or another Stable Diffusion package, the installer may
-occasionally pick up outdated libraries and either the installer or
-`invoke` will fail with complaints out library conflicts. There are
-two steps you can take to clear this problem. Both of these are done
-from within the "developer's console", which you can get to by
-launching `invoke.sh` (or `invoke.bat`) and selecting launch option
-#3:
-
-1. Remove the previous `invokeai` environment completely. From within
-   the developer's console, give the command `conda env remove -n
-   invokeai`. This will delete previous files installed by `invoke`.
-
-   Then exit from the developer's console and launch the script
-   `update.sh` (or `update.bat`). This will download the most recent
-   InvokeAI (including bug fixes) and reinstall the environment.
-   You should then be able to run `invoke.sh`/`invoke.bat`.
-
-2. If this doesn't work, you can try cleaning your system's conda
-   cache. This is slightly more extreme, but won't interfere with
-   any other python-based programs installed on your computer.
-   From the developer's console, run the command `conda clean -a`
-   and answer "yes" to all prompts.
-
-   After this is done, run `update.sh` and try again as before.
-
-_"Corrupted configuration file."__ Everything seems to install ok, but
-`invoke` complains of a corrupted configuration file and goes calls
-`configure_invokeai.py` to fix, but this doesn't fix the problem.
-
-This issue is often caused by a misconfigured configuration directive
-in the `.invokeai` initialization file that contains startup settings.
-This can be corrected by fixing the offending line.
-
-First find `.invokeai`. It is a small text file located in your home
-directory, `~/.invokeai` on Mac and Linux systems, and `C:\Users\*your
-name*\.invokeai` on Windows systems. Open it with a text editor
-(e.g. Notepad on Windows, TextEdit on Macs, or `nano` on Linux)
-and look for the lines starting with `--root` and `--outdir`.
-
-An example is here:
-
-```cmd
---root="/home/lstein/invokeai"
---outdir="/home/lstein/invokeai/outputs"
-```
-
-There should not be whitespace before or after the directory paths,
-and the paths should not end with slashes:
-
-```cmd
---root="/home/lstein/invokeai "     # wrong! no whitespace here
---root="/home\lstein\invokeai\"     # wrong! shouldn't end in a slash
-```
-
-Fix the problem with your text editor and save as a **plain text**
-file. This should clear the issue.
-
-_If none of these maneuvers fixes the problem_ then please report the
-problem to the [InvokeAI
-Issues](https://github.com/invoke-ai/InvokeAI/issues) section, or
-visit our [Discord Server](https://discord.gg/ZmtBAhwWhy) for interactive assistance.
-
-## Updating to newer versions
-
-This section describes how to update InvokeAI to new versions of the software.
-
-### Updating the stable version
-
-This distribution is changing rapidly, and we add new features on a daily basis.
-To update to the latest released version (recommended), run the `update.sh`
-(Linux/Mac) or `update.bat` (Windows) scripts. This will fetch the latest
-release and re-run the `configure_invokeai` script to download any updated models
-files that may be needed. You can also use this to add additional models that
-you did not select at installation time.
-
-You can now close the developer console and run `invoke` as before. If you get
-complaints about missing models, then you may need to do the additional step of
-running `configure_invokeai.py`. This happens relatively infrequently. To do this,
-simply open up the developer's console again and type
-`python scripts/configure_invokeai.py`.
-
-## Troubleshooting
-
-If you run into problems during or after installation, the InvokeAI team is
-available to help you. Either create an
-[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub site, or
-make a request for help on the "bugs-and-support" channel of our
-[Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100% volunteer
-organization, but typically somebody will be available to help you within 24
-hours, and often much sooner.

docs/installation/deprecated_documentation/INSTALL_WINDOWS.md

@@ -1,137 +0,0 @@
----
-title: Manual Installation, Windows
----
-
-# :fontawesome-brands-windows: Windows
-
-## **Notebook install (semi-automated)**
-
-We have a
-[Jupyter notebook](https://github.com/invoke-ai/InvokeAI/blob/main/notebooks/Stable_Diffusion_AI_Notebook.ipynb)
-with cell-by-cell installation steps. It will download the code in this repo as
-one of the steps, so instead of cloning this repo, simply download the notebook
-from the link above and load it up in VSCode (with the appropriate extensions
-installed)/Jupyter/JupyterLab and start running the cells one-by-one.
-
-Note that you will need NVIDIA drivers, Python 3.10, and Git installed beforehand.
-
-## **Manual Install with Conda**
-
-1. Install Anaconda3 (miniconda3 version) from [here](https://docs.anaconda.com/anaconda/install/windows/)
-
-2. Install Git from [here](https://git-scm.com/download/win)
-
-3. Launch Anaconda from the Windows Start menu. This will bring up a command
-   window. Type all the remaining commands in this window.
-
-4. Run the command:
-
-    ```batch
-    git clone https://github.com/invoke-ai/InvokeAI.git
-    ```
-
-    This will create stable-diffusion folder where you will follow the rest of
-    the steps.
-
-5. Enter the newly-created InvokeAI folder. From this step forward make sure that you are working in the InvokeAI directory!
-
-    ```batch
-    cd InvokeAI
-    ```
-
-6. Run the following commands:
-
-    !!! todo "For systems with a CUDA (Nvidia) card:"
-
-       ```bash
-       rmdir src      # (this is a precaution in case there is already a src directory)
-       conda env create -f environment-cuda.yml
-       conda activate invokeai
-       (invokeai)>
-       ```
-
-    !!! todo "For systems with an AMD card (using ROCm driver):"
-
-       ```bash
-       rmdir src      # (this is a precaution in case there is already a src directory)
-       conda env create -f environment-AMD.yml
-       conda activate invokeai
-       (invokeai)>
-       ```
-
-    This will install all python requirements and activate the "invokeai" environment
-    which sets PATH and other environment variables properly.
-
-7. Load the big stable diffusion weights files and a couple of smaller machine-learning models:
-
-    ```bash
-    python scripts/configure_invokeai.py
-    ```
-
-    !!! note
-
-          This script will lead you through the process of creating an account on Hugging Face,
-          accepting the terms and conditions of the Stable Diffusion model license, and
-          obtaining an access token for downloading. It will then download and install the
-          weights files for you.
-
-          Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing the
-          same thing.
-
-8. Start generating images!
-
-    !!! example ""
-
-        !!! warning "IMPORTANT"
-
-            Make sure that the conda environment is activated, which should create
-            `(invokeai)` in front of your prompt!
-
-        === "CLI"
-
-            ```bash
-            python scripts/invoke.py
-            ```
-
-        === "local Webserver"
-
-            ```bash
-            python scripts/invoke.py --web
-            ```
-
-        === "Public Webserver"
-
-            ```bash
-            python scripts/invoke.py --web --host 0.0.0.0
-            ```
-
-        To use an alternative model you may invoke the `!switch` command in
-        the CLI, or pass `--model <model_name>` during `invoke.py` launch for
-        either the CLI or the Web UI. See [Command Line
-        Client](../../deprecated/CLI.md#model-selection-and-importation). The
-        model names are defined in `configs/models.yaml`.
-
-9. Subsequently, to relaunch the script, first activate the Anaconda
-command window (step 3),enter the InvokeAI directory (step 5, `cd
-\path\to\InvokeAI`), run `conda activate invokeai` (step 6b), and then
-launch the invoke script (step 9).
-
-!!! tip "Tildebyte has written an alternative"
-
-    ["Easy peasy Windows install"](https://github.com/invoke-ai/InvokeAI/wiki/Easy-peasy-Windows-install)
-    which uses the Windows Powershell and pew. If you are having trouble with
-    Anaconda on Windows, give this a try (or try it first!)
-
----
-
-This distribution is changing rapidly. If you used the `git clone` method
-(step 5) to download the stable-diffusion directory, then to update to the
-latest and greatest version, launch the Anaconda window, enter
-`stable-diffusion`, and type:
-
-```bash
-git pull
-conda env update
-```
-
-This will bring your local copy into sync with the remote one.

docs/nodes/INVOCATION_API.md

@@ -0,0 +1,63 @@
+# Invocation API
+
+Each invocation's `invoke` method is provided a single arg - the Invocation
+Context.
+
+This object provides access to various methods, used to interact with the
+application. Loading and saving images, logging messages, etc.
+
+!!! warning ""
+
+    This API may shift slightly until the release of v4.0.0 as we work through a few final updates to the Model Manager.
+
+```py
+class MyInvocation(BaseInvocation):
+  ...
+  def invoke(self, context: InvocationContext) -> ImageOutput:
+      image_pil = context.images.get_pil(image_name)
+      # Do something to the image
+      image_dto = context.images.save(image_pil)
+      # Log a message
+      context.logger.info(f"Did something cool, image saved!")
+      ...
+```
+
+The full API is documented below.
+
+## Invocation Mixins
+
+Two important mixins are provided to facilitate working with metadata and gallery boards.
+
+### `WithMetadata`
+
+Inherit from this class (in addition to `BaseInvocation`) to add a `metadata` input to your node. When you do this, you can access the metadata dict from `self.metadata` in the `invoke()` function.
+
+The dict will be populated via the node's input, and you can add any metadata you'd like to it. When you call `context.images.save()`, if the metadata dict has any data, it be automatically embedded in the image.
+
+### `WithBoard`
+
+Inherit from this class (in addition to `BaseInvocation`) to add a `board` input to your node. This renders as a drop-down to select a board. The user's selection will be accessible from `self.board` in the `invoke()` function.
+
+When you call `context.images.save()`, if a board was selected, the image will added to that board as it is saved.
+
+<!-- prettier-ignore-start -->
+::: invokeai.app.services.shared.invocation_context.InvocationContext
+    options:
+        members: false
+
+::: invokeai.app.services.shared.invocation_context.ImagesInterface
+
+::: invokeai.app.services.shared.invocation_context.TensorsInterface
+
+::: invokeai.app.services.shared.invocation_context.ConditioningInterface
+
+::: invokeai.app.services.shared.invocation_context.ModelsInterface
+
+::: invokeai.app.services.shared.invocation_context.LoggerInterface
+
+::: invokeai.app.services.shared.invocation_context.ConfigInterface
+
+::: invokeai.app.services.shared.invocation_context.UtilInterface
+
+::: invokeai.app.services.shared.invocation_context.BoardsInterface
+<!-- prettier-ignore-end -->

docs/nodes/NODES_MIGRATION_V3_V4.md

@@ -0,0 +1,148 @@
+# Invoke v4.0.0 Nodes API Migration guide
+
+Invoke v4.0.0 is versioned as such due to breaking changes to the API utilized
+by nodes, both core and custom.
+
+## Motivation
+
+Prior to v4.0.0, the `invokeai` python package has not be set up to be utilized
+as a library. That is to say, it didn't have any explicitly public API, and node
+authors had to work with the unstable internal application API.
+
+v4.0.0 introduces a stable public API for nodes.
+
+## Changes
+
+There are two node-author-facing changes:
+
+1. Import Paths
+1. Invocation Context API
+
+### Import Paths
+
+All public objects are now exported from `invokeai.invocation_api`:
+
+```py
+# Old
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    InputField,
+    InvocationContext,
+    invocation,
+)
+from invokeai.app.invocations.primitives import ImageField
+
+# New
+from invokeai.invocation_api import (
+    BaseInvocation,
+    ImageField,
+    InputField,
+    InvocationContext,
+    invocation,
+)
+```
+
+It's possible that we've missed some classes you need in your node. Please let
+us know if that's the case.
+
+### Invocation Context API
+
+Most nodes utilize the Invocation Context, an object that is passed to the
+`invoke` that provides access to data and services a node may need.
+
+Until now, that object and the services it exposed were internal. Exposing them
+to nodes means that changes to our internal implementation could break nodes.
+The methods on the services are also often fairly complicated and allowed nodes
+to footgun.
+
+In v4.0.0, this object has been refactored to be much simpler.
+
+See [INVOCATION_API](./INVOCATION_API.md) for full details of the API.
+
+!!! warning ""
+
+    This API may shift slightly until the release of v4.0.0 as we work through a few final updates to the Model Manager.
+
+#### Improved Service Methods
+
+The biggest offender was the image save method:
+
+```py
+# Old
+image_dto = context.services.images.create(
+    image=image,
+    image_origin=ResourceOrigin.INTERNAL,
+    image_category=ImageCategory.GENERAL,
+    node_id=self.id,
+    session_id=context.graph_execution_state_id,
+    is_intermediate=self.is_intermediate,
+    metadata=self.metadata,
+    workflow=context.workflow,
+)
+
+# New
+image_dto = context.images.save(image=image)
+```
+
+Other methods are simplified, or enhanced with additional functionality:
+
+```py
+# Old
+image = context.services.images.get_pil_image(image_name)
+
+# New
+image = context.images.get_pil(image_name)
+image_cmyk = context.images.get_pil(image_name, "CMYK")
+```
+
+We also had some typing issues around tensors:
+
+```py
+# Old
+# `latents` typed as `torch.Tensor`, but could be `ConditioningFieldData`
+latents = context.services.latents.get(self.latents.latents_name)
+# `data` typed as `torch.Tenssor,` but could be `ConditioningFieldData`
+context.services.latents.save(latents_name, data)
+
+# New - separate methods for tensors and conditioning data w/ correct typing
+# Also, the service generates the names
+tensor_name = context.tensors.save(tensor)
+tensor = context.tensors.load(tensor_name)
+# For conditioning
+cond_name = context.conditioning.save(cond_data)
+cond_data = context.conditioning.load(cond_name)
+```
+
+#### Output Construction
+
+Core Outputs have builder functions right on them - no need to manually
+construct these objects, or use an extra utility:
+
+```py
+# Old
+image_output = ImageOutput(
+    image=ImageField(image_name=image_dto.image_name),
+    width=image_dto.width,
+    height=image_dto.height,
+)
+latents_output = build_latents_output(latents_name=name, latents=latents, seed=None)
+noise_output = NoiseOutput(
+    noise=LatentsField(latents_name=latents_name, seed=seed),
+    width=latents.size()[3] * 8,
+    height=latents.size()[2] * 8,
+)
+cond_output = ConditioningOutput(
+    conditioning=ConditioningField(
+        conditioning_name=conditioning_name,
+    ),
+)
+
+# New
+image_output = ImageOutput.build(image_dto)
+latents_output = LatentsOutput.build(latents_name=name, latents=noise, seed=self.seed)
+noise_output = NoiseOutput.build(latents_name=name, latents=noise, seed=self.seed)
+cond_output = ConditioningOutput.build(conditioning_name)
+```
+
+You can still create the objects using constructors if you want, but we suggest
+using the builder methods.

docs/nodes/communityNodes.md

@@ -354,12 +354,21 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 **Description:** A set of nodes for Metadata. Collect Metadata from within an `iterate` node & extract metadata from an image.
 
-- `Metadata Item Linked` - Allows collecting of metadata while within an iterate node with no need for a collect node or conversion to metadata node.
-- `Metadata From Image` - Provides Metadata from an image.
-- `Metadata To String` - Extracts a String value of a label from metadata.
-- `Metadata To Integer` - Extracts an Integer value of a label from metadata.
-- `Metadata To Float` - Extracts a Float value of a label from metadata.
-- `Metadata To Scheduler` - Extracts a Scheduler value of a label from metadata.
+- `Metadata Item Linked` - Allows collecting of metadata while within an iterate node with no need for a collect node or conversion to metadata node
+- `Metadata From Image` - Provides Metadata from an image
+- `Metadata To String` - Extracts a String value of a label from metadata
+- `Metadata To Integer` - Extracts an Integer value of a label from metadata
+- `Metadata To Float` - Extracts a Float value of a label from metadata
+- `Metadata To Scheduler` - Extracts a Scheduler value of a label from metadata
+- `Metadata To Bool` - Extracts Bool types from metadata
+- `Metadata To Model` - Extracts model types from metadata
+- `Metadata To SDXL Model` - Extracts SDXL model types from metadata
+- `Metadata To LoRAs` - Extracts Loras from metadata. 
+- `Metadata To SDXL LoRAs` - Extracts SDXL Loras from metadata
+- `Metadata To ControlNets` - Extracts ControNets from metadata
+- `Metadata To IP-Adapters` - Extracts IP-Adapters from metadata
+- `Metadata To T2I-Adapters` - Extracts T2I-Adapters from metadata
+- `Denoise Latents + Metadata` - This is an inherited version of the existing `Denoise Latents` node but with a metadata input and output. 
 
 **Node Link:** https://github.com/skunkworxdark/metadata-linked-nodes
 

docs/nodes/defaultNodes.md

@@ -19,6 +19,8 @@ their descriptions.
 | Conditioning Primitive                                        | A conditioning tensor primitive value                                                                                                                |
 | Content Shuffle Processor                                     | Applies content shuffle processing to image                                                                                                          |
 | ControlNet                                                    | Collects ControlNet info to pass to other nodes                                                                                                      |
+| Create Denoise Mask                                           | Converts a greyscale or transparency image into a mask for denoising.                                                                                |
+| Create Gradient Mask                                          | Creates a mask for Gradient ("soft", "differential") inpainting that gradually expands during denoising. Improves edge coherence.                    |
 | Denoise Latents                                               | Denoises noisy latents to decodable images                                                                                                           |
 | Divide Integers                                               | Divides two numbers                                                                                                                                  |
 | Dynamic Prompt                                                | Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator                                                                      |

docs/requirements-mkdocs.txt

@@ -1,5 +0,0 @@
-mkdocs
-mkdocs-material>=8, <9
-mkdocs-git-revision-date-localized-plugin
-mkdocs-redirects==1.2.0
-

docs/stylesheets/extra.css

@@ -1,5 +0,0 @@
-:root {
-    --md-primary-fg-color:        #35A4DB;
-    --md-primary-fg-color--light: #35A4DB;
-    --md-primary-fg-color--dark:  #35A4DB;
-  }

installer/create_installer.sh

@@ -2,22 +2,18 @@
 
 set -e
 
-BCYAN="\e[1;36m"
-BYELLOW="\e[1;33m"
-BGREEN="\e[1;32m"
-BRED="\e[1;31m"
-RED="\e[31m"
-RESET="\e[0m"
-
-function is_bin_in_path {
-    builtin type -P "$1" &>/dev/null
-}
+BCYAN="\033[1;36m"
+BYELLOW="\033[1;33m"
+BGREEN="\033[1;32m"
+BRED="\033[1;31m"
+RED="\033[31m"
+RESET="\033[0m"
 
 function git_show {
     git show -s --format=oneline --abbrev-commit "$1" | cat
 }
 
-if [[ -v "VIRTUAL_ENV" ]]; then
+if [[ ! -z "${VIRTUAL_ENV}" ]]; then
     # we can't just call 'deactivate' because this function is not exported
     # to the environment of this script from the bash process that runs the script
     echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
@@ -26,31 +22,63 @@ fi
 
 cd "$(dirname "$0")"
 
-echo
-echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
-echo "The current working directory is $(pwd)"
-read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
-echo
-
-# Some machines only have `python3` in PATH, others have `python` - make an alias.
-# We can use a function to approximate an alias within a non-interactive shell.
-if ! is_bin_in_path python && is_bin_in_path python3; then
-    function python {
-        python3 "$@"
-    }
-fi
-
 VERSION=$(
     cd ..
-    python -c "from invokeai.version import __version__ as version; print(version)"
+    python3 -c "from invokeai.version import __version__ as version; print(version)"
 )
-PATCH=""
-VERSION="v${VERSION}${PATCH}"
+VERSION="v${VERSION}"
+
+if [[ ! -z ${CI} ]]; then
+    echo
+    echo -e "${BCYAN}CI environment detected${RESET}"
+    echo
+else
+    echo
+    echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
+    echo "The current working directory is $(pwd)"
+    read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
+    echo
+fi
 
 echo -e "${BGREEN}HEAD${RESET}:"
 git_show HEAD
 echo
 
+# ---------------------- FRONTEND ----------------------
+
+pushd ../invokeai/frontend/web >/dev/null
+echo "Installing frontend dependencies..."
+echo
+pnpm i --frozen-lockfile
+echo
+if [[ ! -z ${CI} ]]; then
+    echo "Building frontend without checks..."
+    # In CI, we have already done the frontend checks and can just build
+    pnpm vite build
+else
+    echo "Running checks and building frontend..."
+    # This runs all the frontend checks and builds
+    pnpm build
+fi
+echo
+popd
+
+# ---------------------- BACKEND ----------------------
+
+echo
+echo "Building wheel..."
+echo
+
+# install the 'build' package in the user site packages, if needed
+# could be improved by using a temporary venv, but it's tiny and harmless
+if [[ $(python3 -c 'from importlib.util import find_spec; print(find_spec("build") is None)') == "True" ]]; then
+    pip install --user build
+fi
+
+rm -rf ../build
+
+python3 -m build --outdir dist/ ../.
+
 # ----------------------
 
 echo
@@ -78,10 +106,28 @@ chmod a+x InvokeAI-Installer/install.sh
 cp install.bat.in InvokeAI-Installer/install.bat
 cp WinLongPathsEnabled.reg InvokeAI-Installer/
 
-# Zip everything up
-zip -r InvokeAI-installer-$VERSION.zip InvokeAI-Installer
+FILENAME=InvokeAI-installer-$VERSION.zip
 
-# clean up
-rm -rf InvokeAI-Installer tmp dist ../invokeai/frontend/web/dist/
+# Zip everything up
+zip -r ${FILENAME} InvokeAI-Installer
+
+echo
+echo -e "${BGREEN}Built installer: ./${FILENAME}${RESET}"
+echo -e "${BGREEN}Built PyPi distribution: ./dist${RESET}"
+
+# clean up, but only if we are not in a github action
+if [[ -z ${CI} ]]; then
+    echo
+    echo "Cleaning up intermediate build files..."
+    rm -rf InvokeAI-Installer tmp ../invokeai/frontend/web/dist/
+fi
+
+if [[ ! -z ${CI} ]]; then
+    echo
+    echo "Setting GitHub action outputs..."
+    echo "INSTALLER_FILENAME=${FILENAME}" >>$GITHUB_OUTPUT
+    echo "INSTALLER_PATH=installer/${FILENAME}" >>$GITHUB_OUTPUT
+    echo "DIST_PATH=installer/dist/" >>$GITHUB_OUTPUT
+fi
 
 exit 0

installer/install.bat.in

@@ -16,7 +16,7 @@ if "%1" == "use-cache" (
 @rem The version in the next line is replaced by an up to date release number
 @rem when create_installer.sh is run. Change the release number there.
 set INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
-set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
+set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/help/FAQ/
 set PYTHON_URL=https://www.python.org/downloads/windows/
 set MINIMUM_PYTHON_VERSION=3.10.0
 set PYTHON_URL=https://www.python.org/downloads/release/python-3109/

installer/lib/installer.py

@@ -3,8 +3,10 @@
 InvokeAI installer script
 """
 
+import locale
 import os
 import platform
+import re
 import shutil
 import subprocess
 import sys
@@ -16,12 +18,23 @@ from typing import Optional, Tuple
 SUPPORTED_PYTHON = ">=3.10.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
 BOOTSTRAP_VENV_PREFIX = "invokeai-installer-tmp"
+DOCS_URL = "https://invoke-ai.github.io/InvokeAI/"
+DISCORD_URL = "https://discord.gg/ZmtBAhwWhy"
 
 OS = platform.uname().system
 ARCH = platform.uname().machine
 VERSION = "latest"
 
 
+def get_version_from_wheel_filename(wheel_filename: str) -> str:
+    match = re.search(r"-(\d+\.\d+\.\d+)", wheel_filename)
+    if match:
+        version = match.group(1)
+        return version
+    else:
+        raise ValueError(f"Could not extract version from wheel filename: {wheel_filename}")
+
+
 class Installer:
     """
     Deploys an InvokeAI installation into a given path
@@ -36,7 +49,7 @@ class Installer:
         self.bootstrap()
         self.available_releases = get_github_releases()
 
-    def mktemp_venv(self) -> TemporaryDirectory:
+    def mktemp_venv(self) -> TemporaryDirectory[str]:
         """
         Creates a temporary virtual environment for the installer itself
 
@@ -58,7 +71,7 @@ class Installer:
 
         return venv_dir
 
-    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory | None:
+    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory[str] | None:
         """
         Bootstrap the installer venv with packages required at install time
         """
@@ -87,7 +100,7 @@ class Installer:
         except subprocess.CalledProcessError as e:
             print(e)
 
-    def app_venv(self, venv_parent) -> Path:
+    def app_venv(self, venv_parent: Path) -> Path:
         """
         Create a virtualenv for the InvokeAI installation
         """
@@ -106,26 +119,29 @@ class Installer:
         return venv_dir
 
     def install(
-        self, version=None, root: str = "~/invokeai", yes_to_all=False, find_links: Optional[Path] = None
+        self,
+        root: str = "~/invokeai",
+        yes_to_all: bool = False,
+        find_links: Optional[str] = None,
+        wheel: Optional[Path] = None,
     ) -> None:
-        """
-        Install the InvokeAI application into the given runtime path
+        """Install the InvokeAI application into the given runtime path
 
-        :param root: Destination path for the installation
-        :type root: str
-        :param version: InvokeAI version to install
-        :type version: str
-        :param yes: Accept defaults to all questions
-        :type yes: bool
-        :param find_links: A local directory to search for requirement wheels before going to remote indexes
-        :type find_links: Path
+        Args:
+            root: Destination path for the installation
+            yes_to_all: Accept defaults to all questions
+            find_links: A local directory to search for requirement wheels before going to remote indexes
+            wheel: A wheel file to install
         """
 
         import messages
 
-        messages.welcome(self.available_releases)
-
-        version = messages.choose_version(self.available_releases)
+        if wheel:
+            messages.installing_from_wheel(wheel.name)
+            version = get_version_from_wheel_filename(wheel.name)
+        else:
+            messages.welcome(self.available_releases)
+            version = messages.choose_version(self.available_releases)
 
         auto_dest = Path(os.environ.get("INVOKEAI_ROOT", root)).expanduser().resolve()
         destination = auto_dest if yes_to_all else messages.dest_path(root)
@@ -140,17 +156,24 @@ class Installer:
 
         # install dependencies and the InvokeAI application
         (extra_index_url, optional_modules) = get_torch_source() if not yes_to_all else (None, None)
-        self.instance.install(
-            extra_index_url,
-            optional_modules,
-            find_links,
-        )
+        self.instance.install(extra_index_url, optional_modules, find_links, wheel)
 
         # install the launch/update scripts into the runtime directory
         self.instance.install_user_scripts()
 
-        # run through the configuration flow
-        self.instance.configure()
+        message = f"""
+*** Installation Successful ***
+
+To start the application, run:
+    {destination}/invoke.{"bat" if sys.platform == "win32" else "sh"}
+
+For more information, troubleshooting and support, visit our docs at:
+    {DOCS_URL}
+
+Join the community on Discord:
+    {DISCORD_URL}
+"""
+        print(message)
 
 
 class InvokeAiInstance:
@@ -181,18 +204,20 @@ class InvokeAiInstance:
 
         return (self.runtime, self.venv)
 
-    def install(self, extra_index_url=None, optional_modules=None, find_links=None):
-        """
-        Install the package from PyPi.
+    def install(
+        self,
+        extra_index_url: Optional[str] = None,
+        optional_modules: Optional[str] = None,
+        find_links: Optional[str] = None,
+        wheel: Optional[Path] = None,
+    ):
+        """Install the package from PyPi or a wheel, if provided.
 
-        :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
-        :type extra_index_url: str
-
-        :param optional_modules: optional modules to install using "[module1,module2]" format.
-        :type optional_modules: str
-
-        :param find_links: path to a directory containing wheels to be searched prior to going to the internet
-        :type find_links: Path
+        Args:
+            extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
+            optional_modules: optional modules to install using "[module1,module2]" format.
+            find_links: path to a directory containing wheels to be searched prior to going to the internet
+            wheel: a wheel file to install
         """
 
         import messages
@@ -216,7 +241,7 @@ class InvokeAiInstance:
 
         messages.simple_banner("Installing the InvokeAI Application :art:")
 
-        from plumbum import FG, ProcessExecutionError, local  # type: ignore
+        from plumbum import FG, ProcessExecutionError, local
 
         pip = local[self.pip]
 
@@ -225,12 +250,12 @@ class InvokeAiInstance:
             "--require-virtualenv",
             "--force-reinstall",
             "--use-pep517",
-            str(src),
+            str(src) if not wheel else str(wheel),
             "--find-links" if find_links is not None else None,
             find_links,
             "--extra-index-url" if extra_index_url is not None else None,
             extra_index_url,
-            pre_flag,
+            pre_flag if not wheel else None,  # Ignore the flag if we are installing a wheel
         ]
 
         try:
@@ -242,53 +267,6 @@ class InvokeAiInstance:
             )
             sys.exit(1)
 
-    def configure(self):
-        """
-        Configure the InvokeAI runtime directory
-        """
-
-        auto_install = False
-        # set sys.argv to a consistent state
-        new_argv = [sys.argv[0]]
-        for i in range(1, len(sys.argv)):
-            el = sys.argv[i]
-            if el in ["-r", "--root"]:
-                new_argv.append(el)
-                new_argv.append(sys.argv[i + 1])
-            elif el in ["-y", "--yes", "--yes-to-all"]:
-                auto_install = True
-        sys.argv = new_argv
-
-        import messages
-        import requests  # to catch download exceptions
-
-        auto_install = auto_install or messages.user_wants_auto_configuration()
-        if auto_install:
-            sys.argv.append("--yes")
-        else:
-            messages.introduction()
-
-        from invokeai.frontend.install.invokeai_configure import invokeai_configure
-
-        # NOTE: currently the config script does its own arg parsing! this means the command-line switches
-        # from the installer will also automatically propagate down to the config script.
-        # this may change in the future with config refactoring!
-        succeeded = False
-        try:
-            invokeai_configure()
-            succeeded = True
-        except requests.exceptions.ConnectionError as e:
-            print(f"\nA network error was encountered during configuration and download: {str(e)}")
-        except OSError as e:
-            print(f"\nAn OS error was encountered during configuration and download: {str(e)}")
-        except Exception as e:
-            print(f"\nA problem was encountered during the configuration and download steps: {str(e)}")
-        finally:
-            if not succeeded:
-                print('To try again, find the "invokeai" directory, run the script "invoke.sh" or "invoke.bat"')
-                print("and choose option 7 to fix a broken install, optionally followed by option 5 to install models.")
-                print("Alternatively you can relaunch the installer.")
-
     def install_user_scripts(self):
         """
         Copy the launch and update scripts to the runtime dir
@@ -339,7 +317,9 @@ def upgrade_pip(venv_path: Path) -> str | None:
     python = str(venv_path.expanduser().resolve() / python)
 
     try:
-        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode()
+        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode(
+            encoding=locale.getpreferredencoding()
+        )
     except subprocess.CalledProcessError as e:
         print(e)
         result = None
@@ -370,7 +350,7 @@ def set_sys_path(venv_path: Path) -> None:
     sys.path.append(str(Path(venv_path, lib, "site-packages").expanduser().resolve()))
 
 
-def get_github_releases() -> tuple[list, list] | None:
+def get_github_releases() -> tuple[list[str], list[str]] | None:
     """
     Query Github for published (pre-)release versions.
     Return a tuple where the first element is a list of stable releases and the second element is a list of pre-releases.
@@ -381,7 +361,8 @@ def get_github_releases() -> tuple[list, list] | None:
 
     ## get latest releases using github api
     url = "https://api.github.com/repos/invoke-ai/InvokeAI/releases"
-    releases, pre_releases = [], []
+    releases: list[str] = []
+    pre_releases: list[str] = []
     try:
         res = requests.get(url)
         res.raise_for_status()
@@ -426,22 +407,29 @@ def get_torch_source() -> Tuple[str | None, str | None]:
     # device can be one of: "cuda", "rocm", "cpu", "cuda_and_dml, autodetect"
     device = select_gpu()
 
+    # The correct extra index URLs for torch are inconsistent, see https://pytorch.org/get-started/locally/#start-locally
+
     url = None
-    optional_modules = "[onnx]"
+    optional_modules: str | None = None
     if OS == "Linux":
         if device.value == "rocm":
             url = "https://download.pytorch.org/whl/rocm5.6"
         elif device.value == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
-
+        elif device.value == "cuda":
+            # CUDA uses the default PyPi index
+            optional_modules = "[xformers,onnx-cuda]"
     elif OS == "Windows":
         if device.value == "cuda":
             url = "https://download.pytorch.org/whl/cu121"
             optional_modules = "[xformers,onnx-cuda]"
-        if device.value == "cuda_and_dml":
-            url = "https://download.pytorch.org/whl/cu121"
-            optional_modules = "[xformers,onnx-directml]"
+        elif device.value == "cpu":
+            # CPU  uses the default PyPi index, no optional modules
+            pass
+    elif OS == "Darwin":
+        # macOS uses the default PyPi index, no optional modules
+        pass
 
-    # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
+    # Fall back to defaults
 
     return (url, optional_modules)

installer/lib/main.py

@@ -30,16 +30,17 @@ if __name__ == "__main__":
     )
 
     parser.add_argument(
-        "--version",
-        dest="version",
-        help="Version of InvokeAI to install. Default to the latest stable release. A special 'pre' value will install the latest published pre-release version.",
+        "--find-links",
+        dest="find_links",
+        help="Specifies a directory of local wheel files to be searched prior to searching the online repositories.",
+        type=Path,
         default=None,
     )
 
     parser.add_argument(
-        "--find-links",
-        dest="find_links",
-        help="Specifies a directory of local wheel files to be searched prior to searching the online repositories.",
+        "--wheel",
+        dest="wheel",
+        help="Specifies a wheel for the InvokeAI package. Used for troubleshooting or testing prereleases.",
         type=Path,
         default=None,
     )

installer/lib/messages.py

@@ -7,8 +7,9 @@ import os
 import platform
 from enum import Enum
 from pathlib import Path
+from typing import Optional
 
-from prompt_toolkit import HTML, prompt
+from prompt_toolkit import prompt
 from prompt_toolkit.completion import FuzzyWordCompleter, PathCompleter
 from prompt_toolkit.validation import Validator
 from rich import box, print
@@ -19,13 +20,6 @@ from rich.style import Style
 from rich.syntax import Syntax
 from rich.text import Text
 
-"""
-INVOKE_AI_SRC=https://github.com/invoke-ai/InvokeAI/archive/refs/tags/${INVOKEAI_VERSION}.zip
-INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
-TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
-"""
-
-
 OS = platform.uname().system
 ARCH = platform.uname().machine
 
@@ -36,7 +30,7 @@ else:
     console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
 
-def welcome(available_releases: tuple | None = None) -> None:
+def welcome(available_releases: tuple[list[str], list[str]] | None = None) -> None:
     @group()
     def text():
         if (platform_specific := _platform_specific_help()) is not None:
@@ -72,7 +66,34 @@ def welcome(available_releases: tuple | None = None) -> None:
     console.line()
 
 
-def choose_version(available_releases: tuple | None = None) -> str:
+def installing_from_wheel(wheel_filename: str) -> None:
+    """Display a message about installing from a wheel"""
+
+    @group()
+    def text():
+        yield Text.from_markup(f"You are installing from a wheel file: [bold]{wheel_filename}\n")
+        yield Text.from_markup(
+            "[bold orange3]If you are not sure why you are doing this, you should cancel and install InvokeAI normally."
+        )
+
+    console.print(
+        Panel(
+            title="Installing from Wheel",
+            renderable=text(),
+            box=box.DOUBLE,
+            expand=True,
+            padding=(1, 2),
+        )
+    )
+
+    should_proceed = Confirm.ask("Do you want to proceed?")
+
+    if not should_proceed:
+        console.print("Installation cancelled.")
+        exit()
+
+
+def choose_version(available_releases: tuple[list[str], list[str]] | None = None) -> str:
     """
     Prompt the user to choose an Invoke version to install
     """
@@ -98,39 +119,6 @@ def choose_version(available_releases: tuple | None = None) -> str:
     return "stable" if response == "" else response
 
 
-def user_wants_auto_configuration() -> bool:
-    """Prompt the user to choose between manual and auto configuration."""
-    console.rule("InvokeAI Configuration Section")
-    console.print(
-        Panel(
-            Group(
-                "\n".join(
-                    [
-                        "Libraries are installed and InvokeAI will now set up its root directory and configuration. Choose between:",
-                        "",
-                        "  * AUTOMATIC configuration:  install reasonable defaults and a minimal set of starter models.",
-                        "  * MANUAL configuration: manually inspect and adjust configuration options and pick from a larger set of starter models.",
-                        "",
-                        "Later you can fine tune your configuration by selecting option [6] 'Change InvokeAI startup options' from the invoke.bat/invoke.sh launcher script.",
-                    ]
-                ),
-            ),
-            box=box.MINIMAL,
-            padding=(1, 1),
-        )
-    )
-    choice = (
-        prompt(
-            HTML("Choose <b>&lt;a&gt;</b>utomatic or <b>&lt;m&gt;</b>anual configuration [a/m] (a): "),
-            validator=Validator.from_callable(
-                lambda n: n == "" or n.startswith(("a", "A", "m", "M")), error_message="Please select 'a' or 'm'"
-            ),
-        )
-        or "a"
-    )
-    return choice.lower().startswith("a")
-
-
 def confirm_install(dest: Path) -> bool:
     if dest.exists():
         print(f":stop_sign: Directory {dest} already exists!")
@@ -147,7 +135,7 @@ def confirm_install(dest: Path) -> bool:
     return dest_confirmed
 
 
-def dest_path(dest=None) -> Path | None:
+def dest_path(dest: Optional[str | Path] = None) -> Path | None:
     """
     Prompt the user for the destination path and create the path
 
@@ -219,10 +207,8 @@ def dest_path(dest=None) -> Path | None:
 
 class GpuType(Enum):
     CUDA = "cuda"
-    CUDA_AND_DML = "cuda_and_dml"
     ROCM = "rocm"
     CPU = "cpu"
-    AUTODETECT = "autodetect"
 
 
 def select_gpu() -> GpuType:
@@ -238,10 +224,6 @@ def select_gpu() -> GpuType:
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
         GpuType.CUDA,
     )
-    nvidia_with_dml = (
-        "an [gold1 b]NVIDIA[/] GPU (using CUDA™, and DirectML™ for ONNX) -- ALPHA",
-        GpuType.CUDA_AND_DML,
-    )
     amd = (
         "an [gold1 b]AMD[/] GPU (using ROCm™)",
         GpuType.ROCM,
@@ -250,27 +232,19 @@ def select_gpu() -> GpuType:
         "Do not install any GPU support, use CPU for generation (slow)",
         GpuType.CPU,
     )
-    autodetect = (
-        "I'm not sure what to choose",
-        GpuType.AUTODETECT,
-    )
 
     options = []
     if OS == "Windows":
-        options = [nvidia, nvidia_with_dml, cpu]
+        options = [nvidia, cpu]
     if OS == "Linux":
         options = [nvidia, amd, cpu]
     elif OS == "Darwin":
         options = [cpu]
-        # future CoreML?
 
     if len(options) == 1:
         print(f'Your platform [gold1]{OS}-{ARCH}[/] only supports the "{options[0][1]}" driver. Proceeding with that.')
         return options[0][1]
 
-    # "I don't know" is always added the last option
-    options.append(autodetect)  # type: ignore
-
     options = {str(i): opt for i, opt in enumerate(options, 1)}
 
     console.rule(":space_invader: GPU (Graphics Card) selection :space_invader:")
@@ -304,11 +278,6 @@ def select_gpu() -> GpuType:
         ),
     )
 
-    if options[choice][1] is GpuType.AUTODETECT:
-        console.print(
-            "No problem. We will install CUDA support first :crossed_fingers: If Invoke does not detect a GPU, please re-run the installer and select one of the other GPU types."
-        )
-
     return options[choice][1]
 
 
@@ -351,34 +320,6 @@ def windows_long_paths_registry() -> None:
     )
 
 
-def introduction() -> None:
-    """
-    Display a banner when starting configuration of the InvokeAI application
-    """
-
-    console.rule()
-
-    console.print(
-        Panel(
-            title=":art: Configuring InvokeAI :art:",
-            renderable=Group(
-                "",
-                "[b]This script will:",
-                "",
-                "1. Configure the InvokeAI application directory",
-                "2. Help download the Stable Diffusion weight files",
-                "   and other large models that are needed for text to image generation",
-                "3. Create initial configuration files.",
-                "",
-                "[i]At any point you may interrupt this program and resume later.",
-                "",
-                "[b]For the best user experience, please enlarge or maximize this window",
-            ),
-        )
-    )
-    console.line(2)
-
-
 def _platform_specific_help() -> Text | None:
     if OS == "Darwin":
         text = Text.from_markup(

installer/tag_release.sh

@@ -2,12 +2,12 @@
 
 set -e
 
-BCYAN="\e[1;36m"
-BYELLOW="\e[1;33m"
-BGREEN="\e[1;32m"
-BRED="\e[1;31m"
-RED="\e[31m"
-RESET="\e[0m"
+BCYAN="\033[1;36m"
+BYELLOW="\033[1;33m"
+BGREEN="\033[1;32m"
+BRED="\033[1;31m"
+RED="\033[31m"
+RESET="\033[0m"
 
 function does_tag_exist {
     git rev-parse --quiet --verify "refs/tags/$1" >/dev/null
@@ -23,49 +23,40 @@ function git_show {
 
 VERSION=$(
     cd ..
-    python -c "from invokeai.version import __version__ as version; print(version)"
+    python3 -c "from invokeai.version import __version__ as version; print(version)"
 )
 PATCH=""
-MAJOR_VERSION=$(echo $VERSION | sed 's/\..*$//')
 VERSION="v${VERSION}${PATCH}"
-LATEST_TAG="v${MAJOR_VERSION}-latest"
 
 if does_tag_exist $VERSION; then
     echo -e "${BCYAN}${VERSION}${RESET} already exists:"
     git_show_ref tags/$VERSION
     echo
 fi
-if does_tag_exist $LATEST_TAG; then
-    echo -e "${BCYAN}${LATEST_TAG}${RESET} already exists:"
-    git_show_ref tags/$LATEST_TAG
-    echo
-fi
 
 echo -e "${BGREEN}HEAD${RESET}:"
 git_show
 echo
 
-echo -e -n "Create tags ${BCYAN}${VERSION}${RESET} and ${BCYAN}${LATEST_TAG}${RESET} @ ${BGREEN}HEAD${RESET}, ${RED}deleting existing tags on remote${RESET}? "
+echo -e "${BGREEN}git remote -v${RESET}:"
+git remote -v
+echo
+
+echo -e -n "Create tags ${BCYAN}${VERSION}${RESET} @ ${BGREEN}HEAD${RESET}, ${RED}deleting existing tags on origin remote${RESET}? "
 read -e -p 'y/n [n]: ' input
 RESPONSE=${input:='n'}
 if [ "$RESPONSE" == 'y' ]; then
     echo
-    echo -e "Deleting ${BCYAN}${VERSION}${RESET} tag on remote..."
-    git push --delete origin $VERSION
+    echo -e "Deleting ${BCYAN}${VERSION}${RESET} tag on origin remote..."
+    git push origin :refs/tags/$VERSION
 
-    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${VERSION}${RESET} locally..."
+    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${VERSION}${RESET} on locally..."
     if ! git tag -fa $VERSION; then
         echo "Existing/invalid tag"
         exit -1
     fi
 
-    echo -e "Deleting ${BCYAN}${LATEST_TAG}${RESET} tag on remote..."
-    git push --delete origin $LATEST_TAG
-
-    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${LATEST_TAG}${RESET} locally..."
-    git tag -fa $LATEST_TAG
-
-    echo -e "Pushing updated tags to remote..."
+    echo -e "Pushing updated tags to origin remote..."
     git push origin --tags
 fi
 exit 0

installer/templates/invoke.bat.in

@@ -9,37 +9,19 @@ set INVOKEAI_ROOT=.
 :start
 echo Desired action:
 echo 1. Generate images with the browser-based interface
-echo 2. Run textual inversion training
-echo 3. Merge models (diffusers type only)
-echo 4. Download and install models
-echo 5. Change InvokeAI startup options
-echo 6. Re-run the configure script to fix a broken install or to complete a major upgrade
-echo 7. Open the developer console
-echo 8. Update InvokeAI (DEPRECATED - please use the installer)
-echo 9. Run the InvokeAI image database maintenance script
-echo 10. Command-line help
+echo 2. Open the developer console
+echo 3. Run the InvokeAI image database maintenance script
+echo 4. Command-line help
 echo Q - Quit
-set /P choice="Please enter 1-10, Q: [1] "
+echo.
+echo To update, download and run the installer from https://github.com/invoke-ai/InvokeAI/releases/latest.
+echo.
+set /P choice="Please enter 1-4, Q: [1] "
 if not defined choice set choice=1
 IF /I "%choice%" == "1" (
     echo Starting the InvokeAI browser-based UI..
     python .venv\Scripts\invokeai-web.exe %*
 ) ELSE IF /I "%choice%" == "2" (
-    echo Starting textual inversion training..
-    python .venv\Scripts\invokeai-ti.exe --gui
-) ELSE IF /I "%choice%" == "3" (
-    echo Starting model merging script..
-    python .venv\Scripts\invokeai-merge.exe --gui
-) ELSE IF /I "%choice%" == "4" (
-    echo Running invokeai-model-install...
-    python .venv\Scripts\invokeai-model-install.exe
-) ELSE IF /I "%choice%" == "5" (
-    echo Running invokeai-configure...
-    python .venv\Scripts\invokeai-configure.exe --skip-sd-weight --skip-support-models
-) ELSE IF /I "%choice%" == "6" (
-    echo Running invokeai-configure...
-    python .venv\Scripts\invokeai-configure.exe --yes --skip-sd-weight
-) ELSE IF /I "%choice%" == "7" (
     echo Developer Console
     echo Python command is:
     where python
@@ -51,15 +33,10 @@ IF /I "%choice%" == "1" (
     echo *************************
     echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
     call cmd /k
-) ELSE IF /I "%choice%" == "8" (
-    echo UPDATING FROM WITHIN THE APP IS BEING DEPRECATED.
-    echo Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.
-    timeout 4
-    python -m invokeai.frontend.install.invokeai_update
-) ELSE IF /I "%choice%" == "9" (
+) ELSE IF /I "%choice%" == "3" (
    echo Running the db maintenance script...
    python .venv\Scripts\invokeai-db-maintenance.exe
-) ELSE IF /I "%choice%" == "10" (
+) ELSE IF /I "%choice%" == "4" (
     echo Displaying command line help...
     python .venv\Scripts\invokeai-web.exe --help %*
     pause

installer/templates/invoke.sh.in

@@ -23,32 +23,15 @@ cd "$scriptdir"
 . .venv/bin/activate
 
 export INVOKEAI_ROOT="$scriptdir"
+
+# Stash the CLI args - when we prompt for user input, `$@` is overwritten
 PARAMS=$@
 
-# Check to see if dialog is installed (it seems to be fairly standard, but good to check regardless) and if the user has passed the --no-tui argument to disable the dialog TUI
-tui=true
-if command -v dialog &>/dev/null; then
-    # This must use $@ to properly loop through the arguments passed by the user
-    for arg in "$@"; do
-        if [ "$arg" == "--no-tui" ]; then
-            tui=false
-            # Remove the --no-tui argument to avoid errors later on when passing arguments to InvokeAI
-            PARAMS=$(echo "$PARAMS" | sed 's/--no-tui//')
-            break
-        fi
-    done
-else
-    tui=false
-fi
-
-# Set required env var for torch on mac MPS
+# This setting allows torch to fall back to CPU for operations that are not supported by MPS on macOS.
 if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
-# Avoid glibc memory fragmentation. See invokeai/backend/model_management/README.md for details.
-export MALLOC_MMAP_THRESHOLD_=1048576
-
 # Primary function for the case statement to determine user input
 do_choice() {
     case $1 in
@@ -58,49 +41,17 @@ do_choice() {
         invokeai-web $PARAMS
         ;;
     2)
-        clear
-        printf "Textual inversion training\n"
-        invokeai-ti --gui $PARAMS
-        ;;
-    3)
-        clear
-        printf "Merge models (diffusers type only)\n"
-        invokeai-merge --gui $PARAMS
-        ;;
-    4)
-        clear
-        printf "Download and install models\n"
-        invokeai-model-install --root ${INVOKEAI_ROOT}
-        ;;
-    5)
-        clear
-        printf "Change InvokeAI startup options\n"
-        invokeai-configure --root ${INVOKEAI_ROOT} --skip-sd-weights --skip-support-models
-        ;;
-    6)
-        clear
-        printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
-        invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only --skip-sd-weights
-        ;;
-    7)
         clear
         printf "Open the developer console\n"
         file_name=$(basename "${BASH_SOURCE[0]}")
         bash --init-file "$file_name"
         ;;
-    8)
-        clear
-        printf "UPDATING FROM WITHIN THE APP IS BEING DEPRECATED\n"
-        printf "Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.\n"
-        sleep 4
-        python -m invokeai.frontend.install.invokeai_update
-        ;;
-    9)
+    3)
         clear
         printf "Running the db maintenance script\n"
         invokeai-db-maintenance --root ${INVOKEAI_ROOT}
         ;;
-    10)
+    4)
         clear
         printf "Command-line help\n"
         invokeai-web --help
@@ -114,69 +65,26 @@ do_choice() {
     clear
 }
 
-# Dialog-based TUI for launcing Invoke functions
-do_dialog() {
-    options=(
-        1 "Generate images with a browser-based interface"
-        2 "Textual inversion training"
-        3 "Merge models (diffusers type only)"
-        4 "Download and install models"
-        5 "Change InvokeAI startup options"
-        6 "Re-run the configure script to fix a broken install or to complete a major upgrade"
-        7 "Open the developer console"
-        8 "Update InvokeAI (DEPRECATED - please use the installer)"
-	9 "Run the InvokeAI image database maintenance script"
-	10 "Command-line help"
-    )
-
-    choice=$(dialog --clear \
-        --backtitle "\Zb\Zu\Z3InvokeAI" \
-        --colors \
-        --title "What would you like to do?" \
-        --ok-label "Run" \
-        --cancel-label "Exit" \
-        --help-button \
-        --help-label "CLI Help" \
-        --menu "Select an option:" \
-        0 0 0 \
-        "${options[@]}" \
-        2>&1 >/dev/tty) || clear
-    do_choice "$choice"
-    clear
-}
-
 # Command-line interface for launching Invoke functions
 do_line_input() {
     clear
-    printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
     printf "What would you like to do?\n"
     printf "1: Generate images using the browser-based interface\n"
-    printf "2: Run textual inversion training\n"
-    printf "3: Merge models (diffusers type only)\n"
-    printf "4: Download and install models\n"
-    printf "5: Change InvokeAI startup options\n"
-    printf "6: Re-run the configure script to fix a broken install\n"
-    printf "7: Open the developer console\n"
-    printf "8: Update InvokeAI\n"
-    printf "9: Run the InvokeAI image database maintenance script\n"
-    printf "10: Command-line help\n"
+    printf "2: Open the developer console\n"
+    printf "3: Run the InvokeAI image database maintenance script\n"
+    printf "4: Command-line help\n"
     printf "Q: Quit\n\n"
-    read -p "Please enter 1-10, Q: [1] " yn
+    printf "To update, download and run the installer from https://github.com/invoke-ai/InvokeAI/releases/latest.\n\n"
+    read -p "Please enter 1-4, Q: [1] " yn
     choice=${yn:='1'}
     do_choice $choice
     clear
 }
 
-# Main IF statement for launching Invoke with either the TUI or CLI, and for checking if the user is in the developer console
+# Main IF statement for launching Invoke, and for checking if the user is in the developer console
 if [ "$0" != "bash" ]; then
     while true; do
-        if $tui; then
-            # .dialogrc must be located in the same directory as the invoke.sh script
-            export DIALOGRC="./.dialogrc"
-            do_dialog
-        else
-            do_line_input
-        fi
+        do_line_input
     done
 else # in developer console
     python --version

invokeai/README

@@ -1,11 +0,0 @@
-Organization of the source tree:
-
-app -- Home of nodes invocations and services
-assets -- Images and other data files used by InvokeAI
-backend -- Non-user facing libraries, including the rendering
-	core.
-configs -- Configuration files used at install and run times
-frontend -- User-facing scripts, including the CLI and the WebUI
-version -- Current InvokeAI version string, stored
-	in version/invokeai_version.py
-	

invokeai/app/api/dependencies.py

@@ -2,9 +2,12 @@
 
 from logging import Logger
 
-from invokeai.app.services.item_storage.item_storage_memory import ItemStorageMemory
+import torch
+
+from invokeai.app.services.object_serializer.object_serializer_disk import ObjectSerializerDisk
+from invokeai.app.services.object_serializer.object_serializer_forward_cache import ObjectSerializerForwardCache
 from invokeai.app.services.shared.sqlite.sqlite_util import init_db
-from invokeai.backend.model_manager.metadata import ModelMetadataStore
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
 
@@ -12,26 +15,22 @@ from ..services.board_image_records.board_image_records_sqlite import SqliteBoar
 from ..services.board_images.board_images_default import BoardImagesService
 from ..services.board_records.board_records_sqlite import SqliteBoardRecordStorage
 from ..services.boards.boards_default import BoardService
+from ..services.bulk_download.bulk_download_default import BulkDownloadService
 from ..services.config import InvokeAIAppConfig
 from ..services.download import DownloadQueueService
 from ..services.image_files.image_files_disk import DiskImageFileStorage
 from ..services.image_records.image_records_sqlite import SqliteImageRecordStorage
 from ..services.images.images_default import ImageService
 from ..services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
-from ..services.invocation_processor.invocation_processor_default import DefaultInvocationProcessor
-from ..services.invocation_queue.invocation_queue_memory import MemoryInvocationQueue
 from ..services.invocation_services import InvocationServices
 from ..services.invocation_stats.invocation_stats_default import InvocationStatsService
 from ..services.invoker import Invoker
-from ..services.latents_storage.latents_storage_disk import DiskLatentsStorage
-from ..services.latents_storage.latents_storage_forward_cache import ForwardCacheLatentsStorage
-from ..services.model_install import ModelInstallService
+from ..services.model_images.model_images_default import ModelImageFileStorageDisk
 from ..services.model_manager.model_manager_default import ModelManagerService
 from ..services.model_records import ModelRecordServiceSQL
 from ..services.names.names_default import SimpleNameService
 from ..services.session_processor.session_processor_default import DefaultSessionProcessor
 from ..services.session_queue.session_queue_sqlite import SqliteSessionQueue
-from ..services.shared.graph import GraphExecutionState
 from ..services.urls.urls_default import LocalUrlService
 from ..services.workflow_records.workflow_records_sqlite import SqliteWorkflowRecordsStorage
 from .events import FastAPIEventService
@@ -65,11 +64,15 @@ class ApiDependencies:
     def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger) -> None:
         logger.info(f"InvokeAI version {__version__}")
         logger.info(f"Root directory = {str(config.root_path)}")
-        logger.debug(f"Internet connectivity is {config.internet_available}")
 
-        output_folder = config.output_path
+        output_folder = config.outputs_path
+        if output_folder is None:
+            raise ValueError("Output folder is not set")
+
         image_files = DiskImageFileStorage(f"{output_folder}/images")
 
+        model_images_folder = config.models_path
+
         db = init_db(config=config, logger=logger, image_files=image_files)
 
         configuration = config
@@ -80,26 +83,26 @@ class ApiDependencies:
         board_records = SqliteBoardRecordStorage(db=db)
         boards = BoardService()
         events = FastAPIEventService(event_handler_id)
-        graph_execution_manager = ItemStorageMemory[GraphExecutionState]()
+        bulk_download = BulkDownloadService()
         image_records = SqliteImageRecordStorage(db=db)
         images = ImageService()
         invocation_cache = MemoryInvocationCache(max_cache_size=config.node_cache_size)
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
-        model_manager = ModelManagerService(config, logger)
-        model_record_service = ModelRecordServiceSQL(db=db)
+        tensors = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[torch.Tensor](output_folder / "tensors", ephemeral=True)
+        )
+        conditioning = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[ConditioningFieldData](output_folder / "conditioning", ephemeral=True)
+        )
         download_queue_service = DownloadQueueService(event_bus=events)
-        metadata_store = ModelMetadataStore(db=db)
-        model_install_service = ModelInstallService(
-            app_config=config,
-            record_store=model_record_service,
+        model_images_service = ModelImageFileStorageDisk(model_images_folder / "model_images")
+        model_manager = ModelManagerService.build_model_manager(
+            app_config=configuration,
+            model_record_service=ModelRecordServiceSQL(db=db),
             download_queue=download_queue_service,
-            metadata_store=metadata_store,
-            event_bus=events,
+            events=events,
         )
         names = SimpleNameService()
         performance_statistics = InvocationStatsService()
-        processor = DefaultInvocationProcessor()
-        queue = MemoryInvocationQueue()
         session_processor = DefaultSessionProcessor()
         session_queue = SqliteSessionQueue(db=db)
         urls = LocalUrlService()
@@ -110,27 +113,25 @@ class ApiDependencies:
             board_images=board_images,
             board_records=board_records,
             boards=boards,
+            bulk_download=bulk_download,
             configuration=configuration,
             events=events,
-            graph_execution_manager=graph_execution_manager,
             image_files=image_files,
             image_records=image_records,
             images=images,
             invocation_cache=invocation_cache,
-            latents=latents,
             logger=logger,
+            model_images=model_images_service,
             model_manager=model_manager,
-            model_records=model_record_service,
             download_queue=download_queue_service,
-            model_install=model_install_service,
             names=names,
             performance_statistics=performance_statistics,
-            processor=processor,
-            queue=queue,
             session_processor=session_processor,
             session_queue=session_queue,
             urls=urls,
             workflow_records=workflow_records,
+            tensors=tensors,
+            conditioning=conditioning,
         )
 
         ApiDependencies.invoker = Invoker(services)

invokeai/app/api/routers/app_info.py

@@ -12,8 +12,7 @@ from pydantic import BaseModel, Field
 
 from invokeai.app.invocations.upscale import ESRGAN_MODELS
 from invokeai.app.services.invocation_cache.invocation_cache_common import InvocationCacheStatus
-from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
-from invokeai.backend.image_util.patchmatch import PatchMatch
+from invokeai.backend.image_util.infill_methods.patchmatch import PatchMatch
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 from invokeai.backend.util.logging import logging
 from invokeai.version import __version__
@@ -101,7 +100,7 @@ async def get_app_deps() -> AppDependencyVersions:
 
 @app_router.get("/config", operation_id="get_config", status_code=200, response_model=AppConfig)
 async def get_config() -> AppConfig:
-    infill_methods = ["tile", "lama", "cv2"]
+    infill_methods = ["tile", "lama", "cv2", "color"]  # TODO: add mosaic back
     if PatchMatch.patchmatch_available():
         infill_methods.append("patchmatch")
 
@@ -114,9 +113,7 @@ async def get_config() -> AppConfig:
     if SafetyChecker.safety_checker_available():
         nsfw_methods.append("nsfw_checker")
 
-    watermarking_methods = []
-    if InvisibleWatermark.invisible_watermark_available():
-        watermarking_methods.append("invisible_watermark")
+    watermarking_methods = ["invisible_watermark"]
 
     return AppConfig(
         infill_methods=infill_methods,

invokeai/app/api/routers/download_queue.py

@@ -36,7 +36,7 @@ async def list_downloads() -> List[DownloadJob]:
         400: {"description": "Bad request"},
     },
 )
-async def prune_downloads():
+async def prune_downloads() -> Response:
     """Prune completed and errored jobs."""
     queue = ApiDependencies.invoker.services.download_queue
     queue.prune_jobs()
@@ -55,7 +55,7 @@ async def download(
 ) -> DownloadJob:
     """Download the source URL to the file or directory indicted in dest."""
     queue = ApiDependencies.invoker.services.download_queue
-    return queue.download(source, dest, priority, access_token)
+    return queue.download(source, Path(dest), priority, access_token)
 
 
 @download_queue_router.get(
@@ -87,7 +87,7 @@ async def get_download_job(
 )
 async def cancel_download_job(
     id: int = Path(description="ID of the download job to cancel."),
-):
+) -> Response:
     """Cancel a download job using its ID."""
     try:
         queue = ApiDependencies.invoker.services.download_queue
@@ -105,7 +105,7 @@ async def cancel_download_job(
         204: {"description": "Download jobs have been cancelled"},
     },
 )
-async def cancel_all_download_jobs():
+async def cancel_all_download_jobs() -> Response:
     """Cancel all download jobs."""
     ApiDependencies.invoker.services.download_queue.cancel_all_jobs()
     return Response(status_code=204)

invokeai/app/api/routers/images.py

@@ -2,13 +2,13 @@ import io
 import traceback
 from typing import Optional
 
-from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
+from fastapi import BackgroundTasks, Body, HTTPException, Path, Query, Request, Response, UploadFile
 from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
 from PIL import Image
 from pydantic import BaseModel, Field, ValidationError
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator
+from invokeai.app.invocations.fields import MetadataField, MetadataFieldValidator
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ImageRecordChanges, ResourceOrigin
 from invokeai.app.services.images.images_common import ImageDTO, ImageUrlsDTO
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
@@ -375,16 +375,67 @@ async def unstar_images_in_list(
 
 class ImagesDownloaded(BaseModel):
     response: Optional[str] = Field(
-        description="If defined, the message to display to the user when images begin downloading"
+        default=None, description="The message to display to the user when images begin downloading"
+    )
+    bulk_download_item_name: Optional[str] = Field(
+        default=None, description="The name of the bulk download item for which events will be emitted"
     )
 
 
-@images_router.post("/download", operation_id="download_images_from_list", response_model=ImagesDownloaded)
+@images_router.post(
+    "/download", operation_id="download_images_from_list", response_model=ImagesDownloaded, status_code=202
+)
 async def download_images_from_list(
-    image_names: list[str] = Body(description="The list of names of images to download", embed=True),
+    background_tasks: BackgroundTasks,
+    image_names: Optional[list[str]] = Body(
+        default=None, description="The list of names of images to download", embed=True
+    ),
     board_id: Optional[str] = Body(
-        default=None, description="The board from which image should be downloaded from", embed=True
+        default=None, description="The board from which image should be downloaded", embed=True
     ),
 ) -> ImagesDownloaded:
-    # return ImagesDownloaded(response="Your images are downloading")
-    raise HTTPException(status_code=501, detail="Endpoint is not yet implemented")
+    if (image_names is None or len(image_names) == 0) and board_id is None:
+        raise HTTPException(status_code=400, detail="No images or board id specified.")
+    bulk_download_item_id: str = ApiDependencies.invoker.services.bulk_download.generate_item_id(board_id)
+
+    background_tasks.add_task(
+        ApiDependencies.invoker.services.bulk_download.handler,
+        image_names,
+        board_id,
+        bulk_download_item_id,
+    )
+    return ImagesDownloaded(bulk_download_item_name=bulk_download_item_id + ".zip")
+
+
+@images_router.api_route(
+    "/download/{bulk_download_item_name}",
+    methods=["GET"],
+    operation_id="get_bulk_download_item",
+    response_class=Response,
+    responses={
+        200: {
+            "description": "Return the complete bulk download item",
+            "content": {"application/zip": {}},
+        },
+        404: {"description": "Image not found"},
+    },
+)
+async def get_bulk_download_item(
+    background_tasks: BackgroundTasks,
+    bulk_download_item_name: str = Path(description="The bulk_download_item_name of the bulk download item to get"),
+) -> FileResponse:
+    """Gets a bulk download zip file"""
+    try:
+        path = ApiDependencies.invoker.services.bulk_download.get_path(bulk_download_item_name)
+
+        response = FileResponse(
+            path,
+            media_type="application/zip",
+            filename=bulk_download_item_name,
+            content_disposition_type="inline",
+        )
+        response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
+        background_tasks.add_task(ApiDependencies.invoker.services.bulk_download.delete, bulk_download_item_name)
+        return response
+    except Exception:
+        raise HTTPException(status_code=404)

invokeai/app/api/routers/model_manager.py

@@ -0,0 +1,677 @@
+# Copyright (c) 2023 Lincoln D. Stein
+"""FastAPI route for model configuration records."""
+
+import io
+import pathlib
+import shutil
+import traceback
+from copy import deepcopy
+from typing import Any, Dict, List, Optional
+
+from fastapi import Body, Path, Query, Response, UploadFile
+from fastapi.responses import FileResponse
+from fastapi.routing import APIRouter
+from PIL import Image
+from pydantic import AnyHttpUrl, BaseModel, ConfigDict, Field
+from starlette.exceptions import HTTPException
+from typing_extensions import Annotated
+
+from invokeai.app.services.model_install import ModelInstallJob
+from invokeai.app.services.model_records import (
+    DuplicateModelException,
+    InvalidModelException,
+    ModelRecordChanges,
+    UnknownModelException,
+)
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    MainCheckpointConfig,
+    ModelFormat,
+    ModelType,
+    SubModelType,
+)
+from invokeai.backend.model_manager.metadata.fetch.huggingface import HuggingFaceMetadataFetch
+from invokeai.backend.model_manager.metadata.metadata_base import ModelMetadataWithFiles, UnknownMetadataException
+from invokeai.backend.model_manager.search import ModelSearch
+from invokeai.backend.model_manager.starter_models import STARTER_MODELS, StarterModel, StarterModelWithoutDependencies
+
+from ..dependencies import ApiDependencies
+
+model_manager_router = APIRouter(prefix="/v2/models", tags=["model_manager"])
+
+# images are immutable; set a high max-age
+IMAGE_MAX_AGE = 31536000
+
+
+class ModelsList(BaseModel):
+    """Return list of configs."""
+
+    models: List[AnyModelConfig]
+
+    model_config = ConfigDict(use_enum_values=True)
+
+
+##############################################################################
+# These are example inputs and outputs that are used in places where Swagger
+# is unable to generate a correct example.
+##############################################################################
+example_model_config = {
+    "path": "string",
+    "name": "string",
+    "base": "sd-1",
+    "type": "main",
+    "format": "checkpoint",
+    "config_path": "string",
+    "key": "string",
+    "hash": "string",
+    "description": "string",
+    "source": "string",
+    "converted_at": 0,
+    "variant": "normal",
+    "prediction_type": "epsilon",
+    "repo_variant": "fp16",
+    "upcast_attention": False,
+}
+
+example_model_input = {
+    "path": "/path/to/model",
+    "name": "model_name",
+    "base": "sd-1",
+    "type": "main",
+    "format": "checkpoint",
+    "config_path": "configs/stable-diffusion/v1-inference.yaml",
+    "description": "Model description",
+    "vae": None,
+    "variant": "normal",
+}
+
+##############################################################################
+# ROUTES
+##############################################################################
+
+
+@model_manager_router.get(
+    "/",
+    operation_id="list_model_records",
+)
+async def list_model_records(
+    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
+    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
+    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
+    model_format: Optional[ModelFormat] = Query(
+        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
+    ),
+) -> ModelsList:
+    """Get a list of models."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    found_models: list[AnyModelConfig] = []
+    if base_models:
+        for base_model in base_models:
+            found_models.extend(
+                record_store.search_by_attr(
+                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
+                )
+            )
+    else:
+        found_models.extend(
+            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
+        )
+    for model in found_models:
+        cover_image = ApiDependencies.invoker.services.model_images.get_url(model.key)
+        model.cover_image = cover_image
+    return ModelsList(models=found_models)
+
+
+@model_manager_router.get(
+    "/get_by_attrs",
+    operation_id="get_model_records_by_attrs",
+    response_model=AnyModelConfig,
+)
+async def get_model_records_by_attrs(
+    name: str = Query(description="The name of the model"),
+    type: ModelType = Query(description="The type of the model"),
+    base: BaseModelType = Query(description="The base model of the model"),
+) -> AnyModelConfig:
+    """Gets a model by its attributes. The main use of this route is to provide backwards compatibility with the old
+    model manager, which identified models by a combination of name, base and type."""
+    configs = ApiDependencies.invoker.services.model_manager.store.search_by_attr(
+        base_model=base, model_type=type, model_name=name
+    )
+    if not configs:
+        raise HTTPException(status_code=404, detail="No model found with these attributes")
+
+    return configs[0]
+
+
+@model_manager_router.get(
+    "/i/{key}",
+    operation_id="get_model_record",
+    responses={
+        200: {
+            "description": "The model configuration was retrieved successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+    },
+)
+async def get_model_record(
+    key: str = Path(description="Key of the model record to fetch."),
+) -> AnyModelConfig:
+    """Get a model record"""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    try:
+        config: AnyModelConfig = record_store.get_model(key)
+        cover_image = ApiDependencies.invoker.services.model_images.get_url(key)
+        config.cover_image = cover_image
+        return config
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+# @model_manager_router.get("/summary", operation_id="list_model_summary")
+# async def list_model_summary(
+#     page: int = Query(default=0, description="The page to get"),
+#     per_page: int = Query(default=10, description="The number of models per page"),
+#     order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
+# ) -> PaginatedResults[ModelSummary]:
+#     """Gets a page of model summary data."""
+#     record_store = ApiDependencies.invoker.services.model_manager.store
+#     results: PaginatedResults[ModelSummary] = record_store.list_models(page=page, per_page=per_page, order_by=order_by)
+#     return results
+
+
+class FoundModel(BaseModel):
+    path: str = Field(description="Path to the model")
+    is_installed: bool = Field(description="Whether or not the model is already installed")
+
+
+@model_manager_router.get(
+    "/scan_folder",
+    operation_id="scan_for_models",
+    responses={
+        200: {"description": "Directory scanned successfully"},
+        400: {"description": "Invalid directory path"},
+    },
+    status_code=200,
+    response_model=List[FoundModel],
+)
+async def scan_for_models(
+    scan_path: str = Query(description="Directory path to search for models", default=None),
+) -> List[FoundModel]:
+    path = pathlib.Path(scan_path)
+    if not scan_path or not path.is_dir():
+        raise HTTPException(
+            status_code=400,
+            detail=f"The search path '{scan_path}' does not exist or is not directory",
+        )
+
+    search = ModelSearch()
+    try:
+        found_model_paths = search.search(path)
+        models_path = ApiDependencies.invoker.services.configuration.models_path
+
+        # If the search path includes the main models directory, we need to exclude core models from the list.
+        # TODO(MM2): Core models should be handled by the model manager so we can determine if they are installed
+        # without needing to crawl the filesystem.
+        core_models_path = pathlib.Path(models_path, "core").resolve()
+        non_core_model_paths = [p for p in found_model_paths if not p.is_relative_to(core_models_path)]
+
+        installed_models = ApiDependencies.invoker.services.model_manager.store.search_by_attr()
+
+        scan_results: list[FoundModel] = []
+
+        # Check if the model is installed by comparing paths, appending to the scan result.
+        for p in non_core_model_paths:
+            path = str(p)
+            is_installed = any(str(models_path / m.path) == path for m in installed_models)
+            found_model = FoundModel(path=path, is_installed=is_installed)
+            scan_results.append(found_model)
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"An error occurred while searching the directory: {e}",
+        )
+    return scan_results
+
+
+class HuggingFaceModels(BaseModel):
+    urls: List[AnyHttpUrl] | None = Field(description="URLs for all checkpoint format models in the metadata")
+    is_diffusers: bool = Field(description="Whether the metadata is for a Diffusers format model")
+
+
+@model_manager_router.get(
+    "/hugging_face",
+    operation_id="get_hugging_face_models",
+    responses={
+        200: {"description": "Hugging Face repo scanned successfully"},
+        400: {"description": "Invalid hugging face repo"},
+    },
+    status_code=200,
+    response_model=HuggingFaceModels,
+)
+async def get_hugging_face_models(
+    hugging_face_repo: str = Query(description="Hugging face repo to search for models", default=None),
+) -> HuggingFaceModels:
+    try:
+        metadata = HuggingFaceMetadataFetch().from_id(hugging_face_repo)
+    except UnknownMetadataException:
+        raise HTTPException(
+            status_code=400,
+            detail="No HuggingFace repository found",
+        )
+
+    assert isinstance(metadata, ModelMetadataWithFiles)
+
+    return HuggingFaceModels(
+        urls=metadata.ckpt_urls,
+        is_diffusers=metadata.is_diffusers,
+    )
+
+
+@model_manager_router.patch(
+    "/i/{key}",
+    operation_id="update_model_record",
+    responses={
+        200: {
+            "description": "The model was updated successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+        409: {"description": "There is already a model corresponding to the new name"},
+    },
+    status_code=200,
+)
+async def update_model_record(
+    key: Annotated[str, Path(description="Unique key of model")],
+    changes: Annotated[ModelRecordChanges, Body(description="Model config", example=example_model_input)],
+) -> AnyModelConfig:
+    """Update a model's config."""
+    logger = ApiDependencies.invoker.services.logger
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    installer = ApiDependencies.invoker.services.model_manager.install
+    try:
+        record_store.update_model(key, changes=changes)
+        model_response: AnyModelConfig = installer.sync_model_path(key)
+        logger.info(f"Updated model: {key}")
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return model_response
+
+
+@model_manager_router.get(
+    "/i/{key}/image",
+    operation_id="get_model_image",
+    responses={
+        200: {
+            "description": "The model image was fetched successfully",
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model image could not be found"},
+    },
+    status_code=200,
+)
+async def get_model_image(
+    key: str = Path(description="The name of model image file to get"),
+) -> FileResponse:
+    """Gets an image file that previews the model"""
+
+    try:
+        path = ApiDependencies.invoker.services.model_images.get_path(key)
+
+        response = FileResponse(
+            path,
+            media_type="image/png",
+            filename=key + ".png",
+            content_disposition_type="inline",
+        )
+        response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
+        return response
+    except Exception:
+        raise HTTPException(status_code=404)
+
+
+@model_manager_router.patch(
+    "/i/{key}/image",
+    operation_id="update_model_image",
+    responses={
+        200: {
+            "description": "The model image was updated successfully",
+        },
+        400: {"description": "Bad request"},
+    },
+    status_code=200,
+)
+async def update_model_image(
+    key: Annotated[str, Path(description="Unique key of model")],
+    image: UploadFile,
+) -> None:
+    if not image.content_type or not image.content_type.startswith("image"):
+        raise HTTPException(status_code=415, detail="Not an image")
+
+    contents = await image.read()
+    try:
+        pil_image = Image.open(io.BytesIO(contents))
+
+    except Exception:
+        ApiDependencies.invoker.services.logger.error(traceback.format_exc())
+        raise HTTPException(status_code=415, detail="Failed to read image")
+
+    logger = ApiDependencies.invoker.services.logger
+    model_images = ApiDependencies.invoker.services.model_images
+    try:
+        model_images.save(pil_image, key)
+        logger.info(f"Updated image for model: {key}")
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return
+
+
+@model_manager_router.delete(
+    "/i/{key}",
+    operation_id="delete_model",
+    responses={
+        204: {"description": "Model deleted successfully"},
+        404: {"description": "Model not found"},
+    },
+    status_code=204,
+)
+async def delete_model(
+    key: str = Path(description="Unique key of model to remove from model registry."),
+) -> Response:
+    """
+    Delete model record from database.
+
+    The configuration record will be removed. The corresponding weights files will be
+    deleted as well if they reside within the InvokeAI "models" directory.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        installer.delete(key)
+        logger.info(f"Deleted model: {key}")
+        return Response(status_code=204)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.delete(
+    "/i/{key}/image",
+    operation_id="delete_model_image",
+    responses={
+        204: {"description": "Model image deleted successfully"},
+        404: {"description": "Model image not found"},
+    },
+    status_code=204,
+)
+async def delete_model_image(
+    key: str = Path(description="Unique key of model image to remove from model_images directory."),
+) -> None:
+    logger = ApiDependencies.invoker.services.logger
+    model_images = ApiDependencies.invoker.services.model_images
+    try:
+        model_images.delete(key)
+        logger.info(f"Deleted model image: {key}")
+        return
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.post(
+    "/install",
+    operation_id="install_model",
+    responses={
+        201: {"description": "The model imported successfully"},
+        415: {"description": "Unrecognized file/folder format"},
+        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+    },
+    status_code=201,
+)
+async def install_model(
+    source: str = Query(description="Model source to install, can be a local path, repo_id, or remote URL"),
+    inplace: Optional[bool] = Query(description="Whether or not to install a local model in place", default=False),
+    # TODO(MM2): Can we type this?
+    config: Optional[Dict[str, Any]] = Body(
+        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
+        default=None,
+        example={"name": "string", "description": "string"},
+    ),
+    access_token: Optional[str] = None,
+) -> ModelInstallJob:
+    """Install a model using a string identifier.
+
+    `source` can be any of the following.
+
+    1. A path on the local filesystem ('C:\\users\\fred\\model.safetensors')
+    2. A Url pointing to a single downloadable model file
+    3. A HuggingFace repo_id with any of the following formats:
+       - model/name
+       - model/name:fp16:vae
+       - model/name::vae          -- use default precision
+       - model/name:fp16:path/to/model.safetensors
+       - model/name::path/to/model.safetensors
+
+    `config` is an optional dict containing model configuration values that will override
+    the ones that are probed automatically.
+
+    `access_token` is an optional access token for use with Urls that require
+    authentication.
+
+    Models will be downloaded, probed, configured and installed in a
+    series of background threads. The return object has `status` attribute
+    that can be used to monitor progress.
+
+    See the documentation for `import_model_record` for more information on
+    interpreting the job information returned by this route.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        result: ModelInstallJob = installer.heuristic_import(
+            source=source,
+            config=config,
+            access_token=access_token,
+            inplace=bool(inplace),
+        )
+        logger.info(f"Started installation of {source}")
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return result
+
+
+@model_manager_router.get(
+    "/install",
+    operation_id="list_model_installs",
+)
+async def list_model_installs() -> List[ModelInstallJob]:
+    """Return the list of model install jobs.
+
+    Install jobs have a numeric `id`, a `status`, and other fields that provide information on
+    the nature of the job and its progress. The `status` is one of:
+
+    * "waiting" -- Job is waiting in the queue to run
+    * "downloading" -- Model file(s) are downloading
+    * "running" -- Model has downloaded and the model probing and registration process is running
+    * "completed" -- Installation completed successfully
+    * "error" -- An error occurred. Details will be in the "error_type" and "error" fields.
+    * "cancelled" -- Job was cancelled before completion.
+
+    Once completed, information about the model such as its size, base
+    model and type can be retrieved from the `config_out` field. For multi-file models such as diffusers,
+    information on individual files can be retrieved from `download_parts`.
+
+    See the example and schema below for more information.
+    """
+    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_manager.install.list_jobs()
+    return jobs
+
+
+@model_manager_router.get(
+    "/install/{id}",
+    operation_id="get_model_install_job",
+    responses={
+        200: {"description": "Success"},
+        404: {"description": "No such job"},
+    },
+)
+async def get_model_install_job(id: int = Path(description="Model install id")) -> ModelInstallJob:
+    """
+    Return model install job corresponding to the given source. See the documentation for 'List Model Install Jobs'
+    for information on the format of the return value.
+    """
+    try:
+        result: ModelInstallJob = ApiDependencies.invoker.services.model_manager.install.get_job_by_id(id)
+        return result
+    except ValueError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.delete(
+    "/install/{id}",
+    operation_id="cancel_model_install_job",
+    responses={
+        201: {"description": "The job was cancelled successfully"},
+        415: {"description": "No such job"},
+    },
+    status_code=201,
+)
+async def cancel_model_install_job(id: int = Path(description="Model install job ID")) -> None:
+    """Cancel the model install job(s) corresponding to the given job ID."""
+    installer = ApiDependencies.invoker.services.model_manager.install
+    try:
+        job = installer.get_job_by_id(id)
+    except ValueError as e:
+        raise HTTPException(status_code=415, detail=str(e))
+    installer.cancel_job(job)
+
+
+@model_manager_router.delete(
+    "/install",
+    operation_id="prune_model_install_jobs",
+    responses={
+        204: {"description": "All completed and errored jobs have been pruned"},
+        400: {"description": "Bad request"},
+    },
+)
+async def prune_model_install_jobs() -> Response:
+    """Prune all completed and errored jobs from the install job list."""
+    ApiDependencies.invoker.services.model_manager.install.prune_jobs()
+    return Response(status_code=204)
+
+
+@model_manager_router.put(
+    "/convert/{key}",
+    operation_id="convert_model",
+    responses={
+        200: {
+            "description": "Model converted successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "Model not found"},
+        409: {"description": "There is already a model registered at this location"},
+    },
+)
+async def convert_model(
+    key: str = Path(description="Unique key of the safetensors main model to convert to diffusers format."),
+) -> AnyModelConfig:
+    """
+    Permanently convert a model into diffusers format, replacing the safetensors version.
+    Note that during the conversion process the key and model hash will change.
+    The return value is the model configuration for the converted model.
+    """
+    model_manager = ApiDependencies.invoker.services.model_manager
+    loader = model_manager.load
+    logger = ApiDependencies.invoker.services.logger
+    store = ApiDependencies.invoker.services.model_manager.store
+    installer = ApiDependencies.invoker.services.model_manager.install
+
+    try:
+        model_config = store.get_model(key)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+
+    if not isinstance(model_config, MainCheckpointConfig):
+        logger.error(f"The model with key {key} is not a main checkpoint model.")
+        raise HTTPException(400, f"The model with key {key} is not a main checkpoint model.")
+
+    # loading the model will convert it into a cached diffusers file
+    try:
+        cc_size = loader.convert_cache.max_size
+        if cc_size == 0:  # temporary set the convert cache to a positive number so that cached model is written
+            loader._convert_cache.max_size = 1.0
+        loader.load_model(model_config, submodel_type=SubModelType.Scheduler)
+    finally:
+        loader._convert_cache.max_size = cc_size
+
+    # Get the path of the converted model from the loader
+    cache_path = loader.convert_cache.cache_path(key)
+    assert cache_path.exists()
+
+    # temporarily rename the original safetensors file so that there is no naming conflict
+    original_name = model_config.name
+    model_config.name = f"{original_name}.DELETE"
+    changes = ModelRecordChanges(name=model_config.name)
+    store.update_model(key, changes=changes)
+
+    # install the diffusers
+    try:
+        new_key = installer.install_path(
+            cache_path,
+            config={
+                "name": original_name,
+                "description": model_config.description,
+                "hash": model_config.hash,
+                "source": model_config.source,
+            },
+        )
+    except DuplicateModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+
+    # delete the original safetensors file
+    installer.delete(key)
+
+    # delete the cached version
+    shutil.rmtree(cache_path)
+
+    # return the config record for the new diffusers directory
+    new_config: AnyModelConfig = store.get_model(new_key)
+    return new_config
+
+
+@model_manager_router.get("/starter_models", operation_id="get_starter_models", response_model=list[StarterModel])
+async def get_starter_models() -> list[StarterModel]:
+    installed_models = ApiDependencies.invoker.services.model_manager.store.search_by_attr()
+    installed_model_sources = {m.source for m in installed_models}
+    starter_models = deepcopy(STARTER_MODELS)
+    for model in starter_models:
+        if model.source in installed_model_sources:
+            model.is_installed = True
+        # Remove already-installed dependencies
+        missing_deps: list[StarterModelWithoutDependencies] = []
+        for dep in model.dependencies or []:
+            if dep.source not in installed_model_sources:
+                missing_deps.append(dep)
+        model.dependencies = missing_deps
+
+    return starter_models

invokeai/app/api/routers/model_records.py

@@ -1,472 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein
-"""FastAPI route for model configuration records."""
-
-import pathlib
-from hashlib import sha1
-from random import randbytes
-from typing import Any, Dict, List, Optional, Set
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, ConfigDict
-from starlette.exceptions import HTTPException
-from typing_extensions import Annotated
-
-from invokeai.app.services.model_install import ModelInstallJob, ModelSource
-from invokeai.app.services.model_records import (
-    DuplicateModelException,
-    InvalidModelException,
-    ModelRecordOrderBy,
-    ModelSummary,
-    UnknownModelException,
-)
-from invokeai.app.services.shared.pagination import PaginatedResults
-from invokeai.backend.model_manager.config import (
-    AnyModelConfig,
-    BaseModelType,
-    ModelFormat,
-    ModelType,
-)
-from invokeai.backend.model_manager.merge import MergeInterpolationMethod, ModelMerger
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-from ..dependencies import ApiDependencies
-
-model_records_router = APIRouter(prefix="/v1/model/record", tags=["model_manager_v2_unstable"])
-
-
-class ModelsList(BaseModel):
-    """Return list of configs."""
-
-    models: List[AnyModelConfig]
-
-    model_config = ConfigDict(use_enum_values=True)
-
-
-class ModelTagSet(BaseModel):
-    """Return tags for a set of models."""
-
-    key: str
-    name: str
-    author: str
-    tags: Set[str]
-
-
-@model_records_router.get(
-    "/",
-    operation_id="list_model_records",
-)
-async def list_model_records(
-    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
-    model_format: Optional[ModelFormat] = Query(
-        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
-    ),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_records
-    found_models: list[AnyModelConfig] = []
-    if base_models:
-        for base_model in base_models:
-            found_models.extend(
-                record_store.search_by_attr(
-                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
-                )
-            )
-    else:
-        found_models.extend(
-            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
-        )
-    return ModelsList(models=found_models)
-
-
-@model_records_router.get(
-    "/i/{key}",
-    operation_id="get_model_record",
-    responses={
-        200: {"description": "Success"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-    },
-)
-async def get_model_record(
-    key: str = Path(description="Key of the model record to fetch."),
-) -> AnyModelConfig:
-    """Get a model record"""
-    record_store = ApiDependencies.invoker.services.model_records
-    try:
-        return record_store.get_model(key)
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.get("/meta", operation_id="list_model_summary")
-async def list_model_summary(
-    page: int = Query(default=0, description="The page to get"),
-    per_page: int = Query(default=10, description="The number of models per page"),
-    order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
-) -> PaginatedResults[ModelSummary]:
-    """Gets a page of model summary data."""
-    return ApiDependencies.invoker.services.model_records.list_models(page=page, per_page=per_page, order_by=order_by)
-
-
-@model_records_router.get(
-    "/meta/i/{key}",
-    operation_id="get_model_metadata",
-    responses={
-        200: {"description": "Success"},
-        400: {"description": "Bad request"},
-        404: {"description": "No metadata available"},
-    },
-)
-async def get_model_metadata(
-    key: str = Path(description="Key of the model repo metadata to fetch."),
-) -> Optional[AnyModelRepoMetadata]:
-    """Get a model metadata object."""
-    record_store = ApiDependencies.invoker.services.model_records
-    result = record_store.get_metadata(key)
-    if not result:
-        raise HTTPException(status_code=404, detail="No metadata for a model with this key")
-    return result
-
-
-@model_records_router.get(
-    "/tags",
-    operation_id="list_tags",
-)
-async def list_tags() -> Set[str]:
-    """Get a unique set of all the model tags."""
-    record_store = ApiDependencies.invoker.services.model_records
-    return record_store.list_tags()
-
-
-@model_records_router.get(
-    "/tags/search",
-    operation_id="search_by_metadata_tags",
-)
-async def search_by_metadata_tags(
-    tags: Set[str] = Query(default=None, description="Tags to search for"),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_records
-    results = record_store.search_by_metadata_tag(tags)
-    return ModelsList(models=results)
-
-
-@model_records_router.patch(
-    "/i/{key}",
-    operation_id="update_model_record",
-    responses={
-        200: {"description": "The model was updated successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-        409: {"description": "There is already a model corresponding to the new name"},
-    },
-    status_code=200,
-    response_model=AnyModelConfig,
-)
-async def update_model_record(
-    key: Annotated[str, Path(description="Unique key of model")],
-    info: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
-) -> AnyModelConfig:
-    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_records
-    try:
-        model_response = record_store.update_model(key, config=info)
-        logger.info(f"Updated model: {key}")
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return model_response
-
-
-@model_records_router.delete(
-    "/i/{key}",
-    operation_id="del_model_record",
-    responses={
-        204: {"description": "Model deleted successfully"},
-        404: {"description": "Model not found"},
-    },
-    status_code=204,
-)
-async def del_model_record(
-    key: str = Path(description="Unique key of model to remove from model registry."),
-) -> Response:
-    """
-    Delete model record from database.
-
-    The configuration record will be removed. The corresponding weights files will be
-    deleted as well if they reside within the InvokeAI "models" directory.
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_install
-        installer.delete(key)
-        logger.info(f"Deleted model: {key}")
-        return Response(status_code=204)
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.post(
-    "/i/",
-    operation_id="add_model_record",
-    responses={
-        201: {"description": "The model added successfully"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-        415: {"description": "Unrecognized file/folder format"},
-    },
-    status_code=201,
-)
-async def add_model_record(
-    config: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
-) -> AnyModelConfig:
-    """Add a model using the configuration information appropriate for its type."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_records
-    if config.key == "<NOKEY>":
-        config.key = sha1(randbytes(100)).hexdigest()
-        logger.info(f"Created model {config.key} for {config.name}")
-    try:
-        record_store.add_model(config.key, config)
-    except DuplicateModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-
-    # now fetch it out
-    return record_store.get_model(config.key)
-
-
-@model_records_router.post(
-    "/import",
-    operation_id="import_model_record",
-    responses={
-        201: {"description": "The model imported successfully"},
-        415: {"description": "Unrecognized file/folder format"},
-        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-)
-async def import_model(
-    source: ModelSource,
-    config: Optional[Dict[str, Any]] = Body(
-        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
-        default=None,
-    ),
-) -> ModelInstallJob:
-    """Add a model using its local path, repo_id, or remote URL.
-
-    Models will be downloaded, probed, configured and installed in a
-    series of background threads. The return object has `status` attribute
-    that can be used to monitor progress.
-
-    The source object is a discriminated Union of LocalModelSource,
-    HFModelSource and URLModelSource. Set the "type" field to the
-    appropriate value:
-
-    * To install a local path using LocalModelSource, pass a source of form:
-      `{
-        "type": "local",
-        "path": "/path/to/model",
-        "inplace": false
-      }`
-       The "inplace" flag, if true, will register the model in place in its
-       current filesystem location. Otherwise, the model will be copied
-       into the InvokeAI models directory.
-
-    * To install a HuggingFace repo_id using HFModelSource, pass a source of form:
-      `{
-        "type": "hf",
-        "repo_id": "stabilityai/stable-diffusion-2.0",
-        "variant": "fp16",
-        "subfolder": "vae",
-        "access_token": "f5820a918aaf01"
-      }`
-     The `variant`, `subfolder` and `access_token` fields are optional.
-
-    * To install a remote model using an arbitrary URL, pass:
-      `{
-        "type": "url",
-        "url": "http://www.civitai.com/models/123456",
-        "access_token": "f5820a918aaf01"
-      }`
-    The `access_token` field is optonal
-
-    The model's configuration record will be probed and filled in
-    automatically.  To override the default guesses, pass "metadata"
-    with a Dict containing the attributes you wish to override.
-
-    Installation occurs in the background. Either use list_model_install_jobs()
-    to poll for completion, or listen on the event bus for the following events:
-
-      "model_install_running"
-      "model_install_completed"
-      "model_install_error"
-
-    On successful completion, the event's payload will contain the field "key"
-    containing the installed ID of the model. On an error, the event's payload
-    will contain the fields "error_type" and "error" describing the nature of the
-    error and its traceback, respectively.
-
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_install
-        result: ModelInstallJob = installer.import_model(
-            source=source,
-            config=config,
-        )
-        logger.info(f"Started installation of {source}")
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=424, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return result
-
-
-@model_records_router.get(
-    "/import",
-    operation_id="list_model_install_jobs",
-)
-async def list_model_install_jobs() -> List[ModelInstallJob]:
-    """Return list of model install jobs."""
-    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_install.list_jobs()
-    return jobs
-
-
-@model_records_router.get(
-    "/import/{id}",
-    operation_id="get_model_install_job",
-    responses={
-        200: {"description": "Success"},
-        404: {"description": "No such job"},
-    },
-)
-async def get_model_install_job(id: int = Path(description="Model install id")) -> ModelInstallJob:
-    """Return model install job corresponding to the given source."""
-    try:
-        return ApiDependencies.invoker.services.model_install.get_job_by_id(id)
-    except ValueError as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.delete(
-    "/import/{id}",
-    operation_id="cancel_model_install_job",
-    responses={
-        201: {"description": "The job was cancelled successfully"},
-        415: {"description": "No such job"},
-    },
-    status_code=201,
-)
-async def cancel_model_install_job(id: int = Path(description="Model install job ID")) -> None:
-    """Cancel the model install job(s) corresponding to the given job ID."""
-    installer = ApiDependencies.invoker.services.model_install
-    try:
-        job = installer.get_job_by_id(id)
-    except ValueError as e:
-        raise HTTPException(status_code=415, detail=str(e))
-    installer.cancel_job(job)
-
-
-@model_records_router.patch(
-    "/import",
-    operation_id="prune_model_install_jobs",
-    responses={
-        204: {"description": "All completed and errored jobs have been pruned"},
-        400: {"description": "Bad request"},
-    },
-)
-async def prune_model_install_jobs() -> Response:
-    """Prune all completed and errored jobs from the install job list."""
-    ApiDependencies.invoker.services.model_install.prune_jobs()
-    return Response(status_code=204)
-
-
-@model_records_router.patch(
-    "/sync",
-    operation_id="sync_models_to_config",
-    responses={
-        204: {"description": "Model config record database resynced with files on disk"},
-        400: {"description": "Bad request"},
-    },
-)
-async def sync_models_to_config() -> Response:
-    """
-    Traverse the models and autoimport directories.
-
-    Model files without a corresponding
-    record in the database are added. Orphan records without a models file are deleted.
-    """
-    ApiDependencies.invoker.services.model_install.sync_to_config()
-    return Response(status_code=204)
-
-
-@model_records_router.put(
-    "/merge",
-    operation_id="merge",
-)
-async def merge(
-    keys: List[str] = Body(description="Keys for two to three models to merge", min_length=2, max_length=3),
-    merged_model_name: Optional[str] = Body(description="Name of destination model", default=None),
-    alpha: float = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
-    force: bool = Body(
-        description="Force merging of models created with different versions of diffusers",
-        default=False,
-    ),
-    interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method", default=None),
-    merge_dest_directory: Optional[str] = Body(
-        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
-        default=None,
-    ),
-) -> AnyModelConfig:
-    """
-    Merge diffusers models.
-
-        keys: List of 2-3 model keys to merge together. All models must use the same base type.
-        merged_model_name: Name for the merged model [Concat model names]
-        alpha: Alpha value (0.0-1.0). Higher values give more weight to the second model [0.5]
-        force: If true, force the merge even if the models were generated by different versions of the diffusers library [False]
-        interp: Interpolation method. One of "weighted_sum", "sigmoid", "inv_sigmoid" or "add_difference" [weighted_sum]
-        merge_dest_directory: Specify a directory to store the merged model in [models directory]
-    """
-    print(f"here i am, keys={keys}")
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(f"Merging models: {keys} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
-        dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
-        installer = ApiDependencies.invoker.services.model_install
-        merger = ModelMerger(installer)
-        model_names = [installer.record_store.get_model(x).name for x in keys]
-        response = merger.merge_diffusion_models_and_save(
-            model_keys=keys,
-            merged_model_name=merged_model_name or "+".join(model_names),
-            alpha=alpha,
-            interp=interp,
-            force=force,
-            merge_dest_directory=dest,
-        )
-    except UnknownModelException:
-        raise HTTPException(
-            status_code=404,
-            detail=f"One or more of the models '{keys}' not found",
-        )
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response

invokeai/app/api/routers/models.py

@@ -1,427 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654), 2023 Kent Keirsey (https://github.com/hipsterusername), 2023 Lincoln D. Stein
-
-import pathlib
-from typing import Annotated, List, Literal, Optional, Union
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, ConfigDict, Field, TypeAdapter
-from starlette.exceptions import HTTPException
-
-from invokeai.backend import BaseModelType, ModelType
-from invokeai.backend.model_management import MergeInterpolationMethod
-from invokeai.backend.model_management.models import (
-    OPENAPI_MODEL_CONFIGS,
-    InvalidModelException,
-    ModelNotFoundException,
-    SchedulerPredictionType,
-)
-
-from ..dependencies import ApiDependencies
-
-models_router = APIRouter(prefix="/v1/models", tags=["models"])
-
-UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-UpdateModelResponseValidator = TypeAdapter(UpdateModelResponse)
-
-ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelResponseValidator = TypeAdapter(ImportModelResponse)
-
-ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ConvertModelResponseValidator = TypeAdapter(ConvertModelResponse)
-
-MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-
-
-class ModelsList(BaseModel):
-    models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
-
-    model_config = ConfigDict(use_enum_values=True)
-
-
-ModelsListValidator = TypeAdapter(ModelsList)
-
-
-@models_router.get(
-    "/",
-    operation_id="list_models",
-    responses={200: {"model": ModelsList}},
-)
-async def list_models(
-    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-) -> ModelsList:
-    """Gets a list of models"""
-    if base_models and len(base_models) > 0:
-        models_raw = []
-        for base_model in base_models:
-            models_raw.extend(ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type))
-    else:
-        models_raw = ApiDependencies.invoker.services.model_manager.list_models(None, model_type)
-    models = ModelsListValidator.validate_python({"models": models_raw})
-    return models
-
-
-@models_router.patch(
-    "/{base_model}/{model_type}/{model_name}",
-    operation_id="update_model",
-    responses={
-        200: {"description": "The model was updated successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-        409: {"description": "There is already a model corresponding to the new name"},
-    },
-    status_code=200,
-    response_model=UpdateModelResponse,
-)
-async def update_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
-) -> UpdateModelResponse:
-    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        previous_info = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        )
-
-        # rename operation requested
-        if info.model_name != model_name or info.base_model != base_model:
-            ApiDependencies.invoker.services.model_manager.rename_model(
-                base_model=base_model,
-                model_type=model_type,
-                model_name=model_name,
-                new_name=info.model_name,
-                new_base=info.base_model,
-            )
-            logger.info(f"Successfully renamed {base_model.value}/{model_name}=>{info.base_model}/{info.model_name}")
-            # update information to support an update of attributes
-            model_name = info.model_name
-            base_model = info.base_model
-            new_info = ApiDependencies.invoker.services.model_manager.list_model(
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-            )
-            if new_info.get("path") != previous_info.get(
-                "path"
-            ):  # model manager moved model path during rename - don't overwrite it
-                info.path = new_info.get("path")
-
-        # replace empty string values with None/null to avoid phenomenon of vae: ''
-        info_dict = info.model_dump()
-        info_dict = {x: info_dict[x] if info_dict[x] else None for x in info_dict.keys()}
-
-        ApiDependencies.invoker.services.model_manager.update_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-            model_attributes=info_dict,
-        )
-
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        )
-        model_response = UpdateModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    except Exception as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=400, detail=str(e))
-
-    return model_response
-
-
-@models_router.post(
-    "/import",
-    operation_id="import_model",
-    responses={
-        201: {"description": "The model imported successfully"},
-        404: {"description": "The model could not be found"},
-        415: {"description": "Unrecognized file/folder format"},
-        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-    response_model=ImportModelResponse,
-)
-async def import_model(
-    location: str = Body(description="A model path, repo_id or URL to import"),
-    prediction_type: Optional[Literal["v_prediction", "epsilon", "sample"]] = Body(
-        description="Prediction type for SDv2 checkpoints and rare SDv1 checkpoints",
-        default=None,
-    ),
-) -> ImportModelResponse:
-    """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
-
-    location = location.strip("\"' ")
-    items_to_import = {location}
-    prediction_types = {x.value: x for x in SchedulerPredictionType}
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
-            items_to_import=items_to_import,
-            prediction_type_helper=lambda x: prediction_types.get(prediction_type),
-        )
-        info = installed_models.get(location)
-
-        if not info:
-            logger.error("Import failed")
-            raise HTTPException(status_code=415)
-
-        logger.info(f"Successfully imported {location}, got {info}")
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=info.name, base_model=info.base_model, model_type=info.model_type
-        )
-        return ImportModelResponseValidator.validate_python(model_raw)
-
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-
-
-@models_router.post(
-    "/add",
-    operation_id="add_model",
-    responses={
-        201: {"description": "The model added successfully"},
-        404: {"description": "The model could not be found"},
-        424: {"description": "The model appeared to add successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-    response_model=ImportModelResponse,
-)
-async def add_model(
-    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
-) -> ImportModelResponse:
-    """Add a model using the configuration information appropriate for its type. Only local models can be added by path"""
-
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        ApiDependencies.invoker.services.model_manager.add_model(
-            info.model_name,
-            info.base_model,
-            info.model_type,
-            model_attributes=info.model_dump(),
-        )
-        logger.info(f"Successfully added {info.model_name}")
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=info.model_name,
-            base_model=info.base_model,
-            model_type=info.model_type,
-        )
-        return ImportModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-
-
-@models_router.delete(
-    "/{base_model}/{model_type}/{model_name}",
-    operation_id="del_model",
-    responses={
-        204: {"description": "Model deleted successfully"},
-        404: {"description": "Model not found"},
-    },
-    status_code=204,
-    response_model=None,
-)
-async def delete_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-) -> Response:
-    """Delete Model"""
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        ApiDependencies.invoker.services.model_manager.del_model(
-            model_name, base_model=base_model, model_type=model_type
-        )
-        logger.info(f"Deleted model: {model_name}")
-        return Response(status_code=204)
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@models_router.put(
-    "/convert/{base_model}/{model_type}/{model_name}",
-    operation_id="convert_model",
-    responses={
-        200: {"description": "Model converted successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "Model not found"},
-    },
-    status_code=200,
-    response_model=ConvertModelResponse,
-)
-async def convert_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-    convert_dest_directory: Optional[str] = Query(
-        default=None, description="Save the converted model to the designated directory"
-    ),
-) -> ConvertModelResponse:
-    """Convert a checkpoint model into a diffusers model, optionally saving to the indicated destination directory, or `models` if none."""
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(f"Converting model: {model_name}")
-        dest = pathlib.Path(convert_dest_directory) if convert_dest_directory else None
-        ApiDependencies.invoker.services.model_manager.convert_model(
-            model_name,
-            base_model=base_model,
-            model_type=model_type,
-            convert_dest_directory=dest,
-        )
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name, base_model=base_model, model_type=model_type
-        )
-        response = ConvertModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException as e:
-        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found: {str(e)}")
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response
-
-
-@models_router.get(
-    "/search",
-    operation_id="search_for_models",
-    responses={
-        200: {"description": "Directory searched successfully"},
-        404: {"description": "Invalid directory path"},
-    },
-    status_code=200,
-    response_model=List[pathlib.Path],
-)
-async def search_for_models(
-    search_path: pathlib.Path = Query(description="Directory path to search for models"),
-) -> List[pathlib.Path]:
-    if not search_path.is_dir():
-        raise HTTPException(
-            status_code=404,
-            detail=f"The search path '{search_path}' does not exist or is not directory",
-        )
-    return ApiDependencies.invoker.services.model_manager.search_for_models(search_path)
-
-
-@models_router.get(
-    "/ckpt_confs",
-    operation_id="list_ckpt_configs",
-    responses={
-        200: {"description": "paths retrieved successfully"},
-    },
-    status_code=200,
-    response_model=List[pathlib.Path],
-)
-async def list_ckpt_configs() -> List[pathlib.Path]:
-    """Return a list of the legacy checkpoint configuration files stored in `ROOT/configs/stable-diffusion`, relative to ROOT."""
-    return ApiDependencies.invoker.services.model_manager.list_checkpoint_configs()
-
-
-@models_router.post(
-    "/sync",
-    operation_id="sync_to_config",
-    responses={
-        201: {"description": "synchronization successful"},
-    },
-    status_code=201,
-    response_model=bool,
-)
-async def sync_to_config() -> bool:
-    """Call after making changes to models.yaml, autoimport directories or models directory to synchronize
-    in-memory data structures with disk data structures."""
-    ApiDependencies.invoker.services.model_manager.sync_to_config()
-    return True
-
-
-# There's some weird pydantic-fastapi behaviour that requires this to be a separate class
-# TODO: After a few updates, see if it works inside the route operation handler?
-class MergeModelsBody(BaseModel):
-    model_names: List[str] = Field(description="model name", min_length=2, max_length=3)
-    merged_model_name: Optional[str] = Field(description="Name of destination model")
-    alpha: Optional[float] = Field(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5)
-    interp: Optional[MergeInterpolationMethod] = Field(description="Interpolation method")
-    force: Optional[bool] = Field(
-        description="Force merging of models created with different versions of diffusers",
-        default=False,
-    )
-
-    merge_dest_directory: Optional[str] = Field(
-        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
-        default=None,
-    )
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@models_router.put(
-    "/merge/{base_model}",
-    operation_id="merge_models",
-    responses={
-        200: {"description": "Model converted successfully"},
-        400: {"description": "Incompatible models"},
-        404: {"description": "One or more models not found"},
-    },
-    status_code=200,
-    response_model=MergeModelResponse,
-)
-async def merge_models(
-    body: Annotated[MergeModelsBody, Body(description="Model configuration", embed=True)],
-    base_model: BaseModelType = Path(description="Base model"),
-) -> MergeModelResponse:
-    """Convert a checkpoint model into a diffusers model"""
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(
-            f"Merging models: {body.model_names} into {body.merge_dest_directory or '<MODELS>'}/{body.merged_model_name}"
-        )
-        dest = pathlib.Path(body.merge_dest_directory) if body.merge_dest_directory else None
-        result = ApiDependencies.invoker.services.model_manager.merge_models(
-            model_names=body.model_names,
-            base_model=base_model,
-            merged_model_name=body.merged_model_name or "+".join(body.model_names),
-            alpha=body.alpha,
-            interp=body.interp,
-            force=body.force,
-            merge_dest_directory=dest,
-        )
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            result.name,
-            base_model=base_model,
-            model_type=ModelType.Main,
-        )
-        response = ConvertModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException:
-        raise HTTPException(
-            status_code=404,
-            detail=f"One or more of the models '{body.model_names}' not found",
-        )
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response

invokeai/app/api/routers/sessions.py

@@ -1,276 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
-
-from fastapi import HTTPException, Path
-from fastapi.routing import APIRouter
-
-from ...services.shared.graph import GraphExecutionState
-from ..dependencies import ApiDependencies
-
-session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
-
-
-# @session_router.post(
-#     "/",
-#     operation_id="create_session",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid json"},
-#     },
-#     deprecated=True,
-# )
-# async def create_session(
-#     queue_id: str = Query(default="", description="The id of the queue to associate the session with"),
-#     graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
-# ) -> GraphExecutionState:
-#     """Creates a new session, optionally initializing it with an invocation graph"""
-#     session = ApiDependencies.invoker.create_execution_state(queue_id=queue_id, graph=graph)
-#     return session
-
-
-# @session_router.get(
-#     "/",
-#     operation_id="list_sessions",
-#     responses={200: {"model": PaginatedResults[GraphExecutionState]}},
-#     deprecated=True,
-# )
-# async def list_sessions(
-#     page: int = Query(default=0, description="The page of results to get"),
-#     per_page: int = Query(default=10, description="The number of results per page"),
-#     query: str = Query(default="", description="The query string to search for"),
-# ) -> PaginatedResults[GraphExecutionState]:
-#     """Gets a list of sessions, optionally searching"""
-#     if query == "":
-#         result = ApiDependencies.invoker.services.graph_execution_manager.list(page, per_page)
-#     else:
-#         result = ApiDependencies.invoker.services.graph_execution_manager.search(query, page, per_page)
-#     return result
-
-
-@session_router.get(
-    "/{session_id}",
-    operation_id="get_session",
-    responses={
-        200: {"model": GraphExecutionState},
-        404: {"description": "Session not found"},
-    },
-)
-async def get_session(
-    session_id: str = Path(description="The id of the session to get"),
-) -> GraphExecutionState:
-    """Gets a session"""
-    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-    if session is None:
-        raise HTTPException(status_code=404)
-    else:
-        return session
-
-
-# @session_router.post(
-#     "/{session_id}/nodes",
-#     operation_id="add_node",
-#     responses={
-#         200: {"model": str},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def add_node(
-#     session_id: str = Path(description="The id of the session"),
-#     node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
-#         description="The node to add"
-#     ),
-# ) -> str:
-#     """Adds a node to the graph"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         session.add_node(node)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session.id
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# @session_router.put(
-#     "/{session_id}/nodes/{node_path}",
-#     operation_id="update_node",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def update_node(
-#     session_id: str = Path(description="The id of the session"),
-#     node_path: str = Path(description="The path to the node in the graph"),
-#     node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
-#         description="The new node"
-#     ),
-# ) -> GraphExecutionState:
-#     """Updates a node in the graph and removes all linked edges"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         session.update_node(node_path, node)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# @session_router.delete(
-#     "/{session_id}/nodes/{node_path}",
-#     operation_id="delete_node",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def delete_node(
-#     session_id: str = Path(description="The id of the session"),
-#     node_path: str = Path(description="The path to the node to delete"),
-# ) -> GraphExecutionState:
-#     """Deletes a node in the graph and removes all linked edges"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         session.delete_node(node_path)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# @session_router.post(
-#     "/{session_id}/edges",
-#     operation_id="add_edge",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def add_edge(
-#     session_id: str = Path(description="The id of the session"),
-#     edge: Edge = Body(description="The edge to add"),
-# ) -> GraphExecutionState:
-#     """Adds an edge to the graph"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         session.add_edge(edge)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# # TODO: the edge being in the path here is really ugly, find a better solution
-# @session_router.delete(
-#     "/{session_id}/edges/{from_node_id}/{from_field}/{to_node_id}/{to_field}",
-#     operation_id="delete_edge",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def delete_edge(
-#     session_id: str = Path(description="The id of the session"),
-#     from_node_id: str = Path(description="The id of the node the edge is coming from"),
-#     from_field: str = Path(description="The field of the node the edge is coming from"),
-#     to_node_id: str = Path(description="The id of the node the edge is going to"),
-#     to_field: str = Path(description="The field of the node the edge is going to"),
-# ) -> GraphExecutionState:
-#     """Deletes an edge from the graph"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         edge = Edge(
-#             source=EdgeConnection(node_id=from_node_id, field=from_field),
-#             destination=EdgeConnection(node_id=to_node_id, field=to_field),
-#         )
-#         session.delete_edge(edge)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# @session_router.put(
-#     "/{session_id}/invoke",
-#     operation_id="invoke_session",
-#     responses={
-#         200: {"model": None},
-#         202: {"description": "The invocation is queued"},
-#         400: {"description": "The session has no invocations ready to invoke"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def invoke_session(
-#     queue_id: str = Query(description="The id of the queue to associate the session with"),
-#     session_id: str = Path(description="The id of the session to invoke"),
-#     all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
-# ) -> Response:
-#     """Invokes a session"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     if session.is_complete():
-#         raise HTTPException(status_code=400)
-
-#     ApiDependencies.invoker.invoke(queue_id, session, invoke_all=all)
-#     return Response(status_code=202)
-
-
-# @session_router.delete(
-#     "/{session_id}/invoke",
-#     operation_id="cancel_session_invoke",
-#     responses={202: {"description": "The invocation is canceled"}},
-#     deprecated=True,
-# )
-# async def cancel_session_invoke(
-#     session_id: str = Path(description="The id of the session to cancel"),
-# ) -> Response:
-#     """Invokes a session"""
-#     ApiDependencies.invoker.cancel(session_id)
-#     return Response(status_code=202)

invokeai/app/api/sockets.py

@@ -12,16 +12,26 @@ class SocketIO:
     __sio: AsyncServer
     __app: ASGIApp
 
+    __sub_queue: str = "subscribe_queue"
+    __unsub_queue: str = "unsubscribe_queue"
+
+    __sub_bulk_download: str = "subscribe_bulk_download"
+    __unsub_bulk_download: str = "unsubscribe_bulk_download"
+
     def __init__(self, app: FastAPI):
         self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
         self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="/ws/socket.io")
         app.mount("/ws", self.__app)
 
-        self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)
-        self.__sio.on("unsubscribe_queue", handler=self._handle_unsub_queue)
+        self.__sio.on(self.__sub_queue, handler=self._handle_sub_queue)
+        self.__sio.on(self.__unsub_queue, handler=self._handle_unsub_queue)
         local_handler.register(event_name=EventServiceBase.queue_event, _func=self._handle_queue_event)
         local_handler.register(event_name=EventServiceBase.model_event, _func=self._handle_model_event)
 
+        self.__sio.on(self.__sub_bulk_download, handler=self._handle_sub_bulk_download)
+        self.__sio.on(self.__unsub_bulk_download, handler=self._handle_unsub_bulk_download)
+        local_handler.register(event_name=EventServiceBase.bulk_download_event, _func=self._handle_bulk_download_event)
+
     async def _handle_queue_event(self, event: Event):
         await self.__sio.emit(
             event=event[1]["event"],
@@ -39,3 +49,18 @@ class SocketIO:
 
     async def _handle_model_event(self, event: Event) -> None:
         await self.__sio.emit(event=event[1]["event"], data=event[1]["data"])
+
+    async def _handle_bulk_download_event(self, event: Event):
+        await self.__sio.emit(
+            event=event[1]["event"],
+            data=event[1]["data"],
+            room=event[1]["data"]["bulk_download_id"],
+        )
+
+    async def _handle_sub_bulk_download(self, sid, data, *args, **kwargs):
+        if "bulk_download_id" in data:
+            await self.__sio.enter_room(sid, data["bulk_download_id"])
+
+    async def _handle_unsub_bulk_download(self, sid, data, *args, **kwargs):
+        if "bulk_download_id" in data:
+            await self.__sio.leave_room(sid, data["bulk_download_id"])

invokeai/app/api_app.py

@@ -1,82 +1,90 @@
-# parse_args() must be called before any other imports. if it is not called first, consumers of the config
-# which are imported/used before parse_args() is called will get the default config values instead of the
-# values from the command line or config file.
-import sys
+import asyncio
+import logging
+import mimetypes
+import socket
+from contextlib import asynccontextmanager
+from inspect import signature
+from pathlib import Path
+from typing import Any
 
+import torch
+import uvicorn
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.middleware.gzip import GZipMiddleware
+from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
+from fastapi.openapi.utils import get_openapi
+from fastapi.responses import HTMLResponse
+from fastapi_events.handlers.local import local_handler
+from fastapi_events.middleware import EventHandlerASGIMiddleware
+from pydantic.json_schema import models_json_schema
+from torch.backends.mps import is_available as is_mps_available
+
+# for PyCharm:
+# noinspection PyUnresolvedReferences
+import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
+import invokeai.frontend.web as web_dir
 from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
-from invokeai.version.invokeai_version import __version__
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.services.config.config_default import get_config
+from invokeai.app.services.session_processor.session_processor_common import ProgressImage
+from invokeai.backend.util.devices import get_torch_device_name
 
-from .services.config import InvokeAIAppConfig
+from ..backend.util.logging import InvokeAILogger
+from .api.dependencies import ApiDependencies
+from .api.routers import (
+    app_info,
+    board_images,
+    boards,
+    download_queue,
+    images,
+    model_manager,
+    session_queue,
+    utilities,
+    workflows,
+)
+from .api.sockets import SocketIO
+from .invocations.baseinvocation import (
+    BaseInvocation,
+    UIConfigBase,
+)
+from .invocations.fields import InputFieldJSONSchemaExtra, OutputFieldJSONSchemaExtra
 
-app_config = InvokeAIAppConfig.get_config()
-app_config.parse_args()
-if app_config.version:
-    print(f"InvokeAI version {__version__}")
-    sys.exit(0)
-
-if True:  # hack to make flake8 happy with imports coming after setting up the config
-    import asyncio
-    import mimetypes
-    import socket
-    from inspect import signature
-    from pathlib import Path
-    from typing import Any
-
-    import uvicorn
-    from fastapi import FastAPI
-    from fastapi.middleware.cors import CORSMiddleware
-    from fastapi.middleware.gzip import GZipMiddleware
-    from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
-    from fastapi.openapi.utils import get_openapi
-    from fastapi.responses import HTMLResponse
-    from fastapi_events.handlers.local import local_handler
-    from fastapi_events.middleware import EventHandlerASGIMiddleware
-    from pydantic.json_schema import models_json_schema
-    from torch.backends.mps import is_available as is_mps_available
-
-    # for PyCharm:
-    # noinspection PyUnresolvedReferences
-    import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
-    import invokeai.frontend.web as web_dir
-
-    from ..backend.util.logging import InvokeAILogger
-    from .api.dependencies import ApiDependencies
-    from .api.routers import (
-        app_info,
-        board_images,
-        boards,
-        download_queue,
-        images,
-        model_records,
-        models,
-        session_queue,
-        sessions,
-        utilities,
-        workflows,
-    )
-    from .api.sockets import SocketIO
-    from .invocations.baseinvocation import (
-        BaseInvocation,
-        InputFieldJSONSchemaExtra,
-        OutputFieldJSONSchemaExtra,
-        UIConfigBase,
-    )
-
-    if is_mps_available():
-        import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
+app_config = get_config()
+
+
+if is_mps_available():
+    import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
 
 
-app_config = InvokeAIAppConfig.get_config()
-app_config.parse_args()
 logger = InvokeAILogger.get_logger(config=app_config)
 # fix for windows mimetypes registry entries being borked
 # see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
 mimetypes.add_type("application/javascript", ".js")
 mimetypes.add_type("text/css", ".css")
 
+torch_device_name = get_torch_device_name()
+logger.info(f"Using torch device: {torch_device_name}")
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # Add startup event to load dependencies
+    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
+    yield
+    # Shut down threads
+    ApiDependencies.shutdown()
+
+
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
-app = FastAPI(title="Invoke - Community Edition", docs_url=None, redoc_url=None, separate_input_output_schemas=False)
+app = FastAPI(
+    title="Invoke - Community Edition",
+    docs_url=None,
+    redoc_url=None,
+    separate_input_output_schemas=False,
+    lifespan=lifespan,
+)
 
 # Add event handler
 event_handler_id: int = id(app)
@@ -99,24 +107,9 @@ app.add_middleware(
 app.add_middleware(GZipMiddleware, minimum_size=1000)
 
 
-# Add startup event to load dependencies
-@app.on_event("startup")
-async def startup_event() -> None:
-    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
-
-
-# Shut down threads
-@app.on_event("shutdown")
-async def shutdown_event() -> None:
-    ApiDependencies.shutdown()
-
-
 # Include all routers
-app.include_router(sessions.session_router, prefix="/api")
-
 app.include_router(utilities.utilities_router, prefix="/api")
-app.include_router(models.models_router, prefix="/api")
-app.include_router(model_records.model_records_router, prefix="/api")
+app.include_router(model_manager.model_manager_router, prefix="/api")
 app.include_router(download_queue.download_queue_router, prefix="/api")
 app.include_router(images.images_router, prefix="/api")
 app.include_router(boards.boards_router, prefix="/api")
@@ -154,18 +147,22 @@ def custom_openapi() -> dict[str, Any]:
         # TODO: note that we assume the schema_key here is the TYPE.__name__
         # This could break in some cases, figure out a better way to do it
         output_type_titles[schema_key] = output_schema["title"]
+        openapi_schema["components"]["schemas"][schema_key] = output_schema
+        openapi_schema["components"]["schemas"][schema_key]["class"] = "output"
 
-    # Add Node Editor UI helper schemas
-    ui_config_schemas = models_json_schema(
+    # Some models don't end up in the schemas as standalone definitions
+    additional_schemas = models_json_schema(
         [
             (UIConfigBase, "serialization"),
             (InputFieldJSONSchemaExtra, "serialization"),
             (OutputFieldJSONSchemaExtra, "serialization"),
+            (ModelIdentifierField, "serialization"),
+            (ProgressImage, "serialization"),
         ],
         ref_template="#/components/schemas/{model}",
     )
-    for schema_key, ui_config_schema in ui_config_schemas[1]["$defs"].items():
-        openapi_schema["components"]["schemas"][schema_key] = ui_config_schema
+    for schema_key, schema_json in additional_schemas[1]["$defs"].items():
+        openapi_schema["components"]["schemas"][schema_key] = schema_json
 
     # Add a reference to the output type to additionalProperties of the invoker schema
     for invoker in all_invocations:
@@ -176,23 +173,24 @@ def custom_openapi() -> dict[str, Any]:
         outputs_ref = {"$ref": f"#/components/schemas/{output_type_title}"}
         invoker_schema["output"] = outputs_ref
         invoker_schema["class"] = "invocation"
-        openapi_schema["components"]["schemas"][f"{output_type_title}"]["class"] = "output"
 
-    from invokeai.backend.model_management.models import get_model_config_enums
+    # This code no longer seems to be necessary?
+    # Leave it here just in case
+    #
+    # from invokeai.backend.model_manager import get_model_config_formats
+    # formats = get_model_config_formats()
+    # for model_config_name, enum_set in formats.items():
 
-    for model_config_format_enum in set(get_model_config_enums()):
-        name = model_config_format_enum.__qualname__
+    #     if model_config_name in openapi_schema["components"]["schemas"]:
+    #         # print(f"Config with name {name} already defined")
+    #         continue
 
-        if name in openapi_schema["components"]["schemas"]:
-            # print(f"Config with name {name} already defined")
-            continue
-
-        openapi_schema["components"]["schemas"][name] = {
-            "title": name,
-            "description": "An enumeration.",
-            "type": "string",
-            "enum": [v.value for v in model_config_format_enum],
-        }
+    #     openapi_schema["components"]["schemas"][model_config_name] = {
+    #         "title": model_config_name,
+    #         "description": "An enumeration.",
+    #         "type": "string",
+    #         "enum": [v.value for v in enum_set],
+    #     }
 
     app.openapi_schema = openapi_schema
     return app.openapi_schema
@@ -230,6 +228,22 @@ app.mount(
 )  # docs favicon is in here
 
 
+def check_cudnn(logger: logging.Logger) -> None:
+    """Check for cuDNN issues that could be causing degraded performance."""
+    if torch.backends.cudnn.is_available():
+        try:
+            # Note: At the time of writing (torch 2.2.1), torch.backends.cudnn.version() only raises an error the first
+            # time it is called. Subsequent calls will return the version number without complaining about a mismatch.
+            cudnn_version = torch.backends.cudnn.version()
+            logger.info(f"cuDNN version: {cudnn_version}")
+        except RuntimeError as e:
+            logger.warning(
+                "Encountered a cuDNN version issue. This may result in degraded performance. This issue is usually "
+                "caused by an incompatible cuDNN version installed in your python environment, or on the host "
+                f"system. Full error message:\n{e}"
+            )
+
+
 def invoke_api() -> None:
     def find_port(port: int) -> int:
         """Find a port not in use starting at given port"""
@@ -241,10 +255,6 @@ def invoke_api() -> None:
             else:
                 return port
 
-    from invokeai.backend.install.check_root import check_invokeai_root
-
-    check_invokeai_root(app_config)  # note, may exit with an exception if root not set up
-
     if app_config.dev_reload:
         try:
             import jurigged
@@ -260,6 +270,8 @@ def invoke_api() -> None:
     if port != app_config.port:
         logger.warn(f"Port {app_config.port} in use, using port {port}")
 
+    check_cudnn(logger)
+
     # Start our own event loop for eventing usage
     loop = asyncio.new_event_loop()
     config = uvicorn.Config(

invokeai/app/invocations/__init__.py

@@ -3,9 +3,9 @@ import sys
 from importlib.util import module_from_spec, spec_from_file_location
 from pathlib import Path
 
-from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.config.config_default import get_config
 
-custom_nodes_path = Path(InvokeAIAppConfig.get_config().custom_nodes_path.resolve())
+custom_nodes_path = Path(get_config().custom_nodes_path)
 custom_nodes_path.mkdir(parents=True, exist_ok=True)
 
 custom_nodes_init_path = str(custom_nodes_path / "__init__.py")

invokeai/app/invocations/baseinvocation.py

@@ -8,17 +8,33 @@ import warnings
 from abc import ABC, abstractmethod
 from enum import Enum
 from inspect import signature
-from types import UnionType
-from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union, cast
+from typing import (
+    TYPE_CHECKING,
+    Annotated,
+    Any,
+    Callable,
+    ClassVar,
+    Iterable,
+    Literal,
+    Optional,
+    Type,
+    TypeVar,
+    Union,
+    cast,
+)
 
 import semver
-from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter, create_model
-from pydantic.fields import FieldInfo, _Unset
+from pydantic import BaseModel, ConfigDict, Field, TypeAdapter, create_model
+from pydantic.fields import FieldInfo
 from pydantic_core import PydanticUndefined
+from typing_extensions import TypeAliasType
 
-from invokeai.app.services.config.config_default import InvokeAIAppConfig
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import (
+    FieldKind,
+    Input,
+)
+from invokeai.app.services.config.config_default import get_config
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.metaenum import MetaEnum
 from invokeai.app.util.misc import uuid_string
 from invokeai.backend.util.logging import InvokeAILogger
@@ -52,393 +68,6 @@ class Classification(str, Enum, metaclass=MetaEnum):
     Prototype = "prototype"
 
 
-class Input(str, Enum, metaclass=MetaEnum):
-    """
-    The type of input a field accepts.
-    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
-      are instantiated.
-    - `Input.Connection`: The field must have its value provided by a connection.
-    - `Input.Any`: The field may have its value provided either directly or by a connection.
-    """
-
-    Connection = "connection"
-    Direct = "direct"
-    Any = "any"
-
-
-class FieldKind(str, Enum, metaclass=MetaEnum):
-    """
-    The kind of field.
-    - `Input`: An input field on a node.
-    - `Output`: An output field on a node.
-    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
-    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
-    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
-    allowing "metadata" for that field.
-    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
-    but which are used to store information about the node. For example, the `id` and `type` fields are node
-    attributes.
-
-    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
-    startup, and when generating the OpenAPI schema for the workflow editor.
-    """
-
-    Input = "input"
-    Output = "output"
-    Internal = "internal"
-    NodeAttribute = "node_attribute"
-
-
-class UIType(str, Enum, metaclass=MetaEnum):
-    """
-    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
-
-    - Model Fields
-    The most common node-author-facing use will be for model fields. Internally, there is no difference
-    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
-    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
-    the field is an SDXL main model field.
-
-    - Any Field
-    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
-    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
-
-    - Scheduler Field
-    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
-
-    - Internal Fields
-    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
-    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
-    should not be used by node authors.
-
-    - DEPRECATED Fields
-    These types are deprecated and should not be used by node authors. A warning will be logged if one is
-    used, and the type will be ignored. They are included here for backwards compatibility.
-    """
-
-    # region Model Field Types
-    SDXLMainModel = "SDXLMainModelField"
-    SDXLRefinerModel = "SDXLRefinerModelField"
-    ONNXModel = "ONNXModelField"
-    VaeModel = "VAEModelField"
-    LoRAModel = "LoRAModelField"
-    ControlNetModel = "ControlNetModelField"
-    IPAdapterModel = "IPAdapterModelField"
-    # endregion
-
-    # region Misc Field Types
-    Scheduler = "SchedulerField"
-    Any = "AnyField"
-    # endregion
-
-    # region Internal Field Types
-    _Collection = "CollectionField"
-    _CollectionItem = "CollectionItemField"
-    # endregion
-
-    # region DEPRECATED
-    Boolean = "DEPRECATED_Boolean"
-    Color = "DEPRECATED_Color"
-    Conditioning = "DEPRECATED_Conditioning"
-    Control = "DEPRECATED_Control"
-    Float = "DEPRECATED_Float"
-    Image = "DEPRECATED_Image"
-    Integer = "DEPRECATED_Integer"
-    Latents = "DEPRECATED_Latents"
-    String = "DEPRECATED_String"
-    BooleanCollection = "DEPRECATED_BooleanCollection"
-    ColorCollection = "DEPRECATED_ColorCollection"
-    ConditioningCollection = "DEPRECATED_ConditioningCollection"
-    ControlCollection = "DEPRECATED_ControlCollection"
-    FloatCollection = "DEPRECATED_FloatCollection"
-    ImageCollection = "DEPRECATED_ImageCollection"
-    IntegerCollection = "DEPRECATED_IntegerCollection"
-    LatentsCollection = "DEPRECATED_LatentsCollection"
-    StringCollection = "DEPRECATED_StringCollection"
-    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
-    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
-    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
-    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
-    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
-    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
-    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
-    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
-    StringPolymorphic = "DEPRECATED_StringPolymorphic"
-    MainModel = "DEPRECATED_MainModel"
-    UNet = "DEPRECATED_UNet"
-    Vae = "DEPRECATED_Vae"
-    CLIP = "DEPRECATED_CLIP"
-    Collection = "DEPRECATED_Collection"
-    CollectionItem = "DEPRECATED_CollectionItem"
-    Enum = "DEPRECATED_Enum"
-    WorkflowField = "DEPRECATED_WorkflowField"
-    IsIntermediate = "DEPRECATED_IsIntermediate"
-    BoardField = "DEPRECATED_BoardField"
-    MetadataItem = "DEPRECATED_MetadataItem"
-    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
-    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
-    MetadataDict = "DEPRECATED_MetadataDict"
-    # endregion
-
-
-class UIComponent(str, Enum, metaclass=MetaEnum):
-    """
-    The type of UI component to use for a field, used to override the default components, which are
-    inferred from the field type.
-    """
-
-    None_ = "none"
-    Textarea = "textarea"
-    Slider = "slider"
-
-
-class InputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
-    and by the workflow editor during schema parsing and UI rendering.
-    """
-
-    input: Input
-    orig_required: bool
-    field_kind: FieldKind
-    default: Optional[Any] = None
-    orig_default: Optional[Any] = None
-    ui_hidden: bool = False
-    ui_type: Optional[UIType] = None
-    ui_component: Optional[UIComponent] = None
-    ui_order: Optional[int] = None
-    ui_choice_labels: Optional[dict[str, str]] = None
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-class OutputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
-    during schema parsing and UI rendering.
-    """
-
-    field_kind: FieldKind
-    ui_hidden: bool
-    ui_type: Optional[UIType]
-    ui_order: Optional[int]
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-def InputField(
-    # copied from pydantic's Field
-    # TODO: Can we support default_factory?
-    default: Any = _Unset,
-    default_factory: Callable[[], Any] | None = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    input: Input = Input.Any,
-    ui_type: Optional[UIType] = None,
-    ui_component: Optional[UIComponent] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-    ui_choice_labels: Optional[dict[str, str]] = None,
-) -> Any:
-    """
-    Creates an input field for an invocation.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param Input input: [Input.Any] The kind of input this field requires. \
-      `Input.Direct` means a value must be provided on instantiation. \
-      `Input.Connection` means the value must be provided by a connection. \
-      `Input.Any` means either will do.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
-      The UI will always render a suitable component, but sometimes you want something different than the default. \
-      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
-      For this case, you could provide `UIComponent.Textarea`.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
-
-    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
-    """
-
-    json_schema_extra_ = InputFieldJSONSchemaExtra(
-        input=input,
-        ui_type=ui_type,
-        ui_component=ui_component,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        ui_choice_labels=ui_choice_labels,
-        field_kind=FieldKind.Input,
-        orig_required=True,
-    )
-
-    """
-    There is a conflict between the typing of invocation definitions and the typing of an invocation's
-    `invoke()` function.
-
-    On instantiation of a node, the invocation definition is used to create the python class. At this time,
-    any number of fields may be optional, because they may be provided by connections.
-
-    On calling of `invoke()`, however, those fields may be required.
-
-    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
-
-    `image` is required during the call to `invoke()`, but when the python class is instantiated,
-    the field may not be present. This is fine, because that image field will be provided by a
-    connection from an ancestor node, which outputs an image.
-
-    This means we want to type the `image` field as optional for the node class definition, but required
-    for the `invoke()` function.
-
-    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
-    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
-    any static type analysis tools will complain.
-
-    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
-    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
-    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
-    """
-
-    if default_factory is not _Unset and default_factory is not None:
-        default = default_factory()
-        logger.warn('"default_factory" is not supported, calling it now to set "default"')
-
-    # These are the args we may wish pass to the pydantic `Field()` function
-    field_args = {
-        "default": default,
-        "title": title,
-        "description": description,
-        "pattern": pattern,
-        "strict": strict,
-        "gt": gt,
-        "ge": ge,
-        "lt": lt,
-        "le": le,
-        "multiple_of": multiple_of,
-        "allow_inf_nan": allow_inf_nan,
-        "max_digits": max_digits,
-        "decimal_places": decimal_places,
-        "min_length": min_length,
-        "max_length": max_length,
-    }
-
-    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
-    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
-
-    # Because we are manually making fields optional, we need to store the original required bool for reference later
-    json_schema_extra_.orig_required = default is PydanticUndefined
-
-    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
-    if input is Input.Any or input is Input.Connection:
-        default_ = None if default is PydanticUndefined else default
-        provided_args.update({"default": default_})
-        if default is not PydanticUndefined:
-            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
-            json_schema_extra_.default = default
-            json_schema_extra_.orig_default = default
-    elif default is not PydanticUndefined:
-        default_ = default
-        provided_args.update({"default": default_})
-        json_schema_extra_.orig_default = default_
-
-    return Field(
-        **provided_args,
-        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
-    )
-
-
-def OutputField(
-    # copied from pydantic's Field
-    default: Any = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    ui_type: Optional[UIType] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-) -> Any:
-    """
-    Creates an output field for an invocation output.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
-    """
-    return Field(
-        default=default,
-        title=title,
-        description=description,
-        pattern=pattern,
-        strict=strict,
-        gt=gt,
-        ge=ge,
-        lt=lt,
-        le=le,
-        multiple_of=multiple_of,
-        allow_inf_nan=allow_inf_nan,
-        max_digits=max_digits,
-        decimal_places=decimal_places,
-        min_length=min_length,
-        max_length=max_length,
-        json_schema_extra=OutputFieldJSONSchemaExtra(
-            ui_type=ui_type,
-            ui_hidden=ui_hidden,
-            ui_order=ui_order,
-            field_kind=FieldKind.Output,
-        ).model_dump(exclude_none=True),
-    )
-
-
 class UIConfigBase(BaseModel):
     """
     Provides additional node configuration to the UI.
@@ -460,33 +89,6 @@ class UIConfigBase(BaseModel):
     )
 
 
-class InvocationContext:
-    """Initialized and provided to on execution of invocations."""
-
-    services: InvocationServices
-    graph_execution_state_id: str
-    queue_id: str
-    queue_item_id: int
-    queue_batch_id: str
-    workflow: Optional[WorkflowWithoutID]
-
-    def __init__(
-        self,
-        services: InvocationServices,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        workflow: Optional[WorkflowWithoutID],
-    ):
-        self.services = services
-        self.graph_execution_state_id = graph_execution_state_id
-        self.queue_id = queue_id
-        self.queue_item_id = queue_item_id
-        self.queue_batch_id = queue_batch_id
-        self.workflow = workflow
-
-
 class BaseInvocationOutput(BaseModel):
     """
     Base class for all invocation outputs.
@@ -495,6 +97,7 @@ class BaseInvocationOutput(BaseModel):
     """
 
     _output_classes: ClassVar[set[BaseInvocationOutput]] = set()
+    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def register_output(cls, output: BaseInvocationOutput) -> None:
@@ -507,10 +110,14 @@ class BaseInvocationOutput(BaseModel):
         return cls._output_classes
 
     @classmethod
-    def get_outputs_union(cls) -> UnionType:
-        """Gets a union of all invocation outputs."""
-        outputs_union = Union[tuple(cls._output_classes)]  # type: ignore [valid-type]
-        return outputs_union  # type: ignore [return-value]
+    def get_typeadapter(cls) -> TypeAdapter[Any]:
+        """Gets a pydantc TypeAdapter for the union of all invocation output types."""
+        if not cls._typeadapter:
+            InvocationOutputsUnion = TypeAliasType(
+                "InvocationOutputsUnion", Annotated[Union[tuple(cls._output_classes)], Field(discriminator="type")]
+            )
+            cls._typeadapter = TypeAdapter(InvocationOutputsUnion)
+        return cls._typeadapter
 
     @classmethod
     def get_output_types(cls) -> Iterable[str]:
@@ -559,6 +166,7 @@ class BaseInvocation(ABC, BaseModel):
     """
 
     _invocation_classes: ClassVar[set[BaseInvocation]] = set()
+    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def get_type(cls) -> str:
@@ -571,15 +179,19 @@ class BaseInvocation(ABC, BaseModel):
         cls._invocation_classes.add(invocation)
 
     @classmethod
-    def get_invocations_union(cls) -> UnionType:
-        """Gets a union of all invocation types."""
-        invocations_union = Union[tuple(cls._invocation_classes)]  # type: ignore [valid-type]
-        return invocations_union  # type: ignore [return-value]
+    def get_typeadapter(cls) -> TypeAdapter[Any]:
+        """Gets a pydantc TypeAdapter for the union of all invocation types."""
+        if not cls._typeadapter:
+            InvocationsUnion = TypeAliasType(
+                "InvocationsUnion", Annotated[Union[tuple(cls._invocation_classes)], Field(discriminator="type")]
+            )
+            cls._typeadapter = TypeAdapter(InvocationsUnion)
+        return cls._typeadapter
 
     @classmethod
     def get_invocations(cls) -> Iterable[BaseInvocation]:
         """Gets all invocations, respecting the allowlist and denylist."""
-        app_config = InvokeAIAppConfig.get_config()
+        app_config = get_config()
         allowed_invocations: set[BaseInvocation] = set()
         for sc in cls._invocation_classes:
             invocation_type = sc.get_type()
@@ -632,7 +244,7 @@ class BaseInvocation(ABC, BaseModel):
         """Invoke with provided context and return outputs."""
         pass
 
-    def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
+    def invoke_internal(self, context: InvocationContext, services: "InvocationServices") -> BaseInvocationOutput:
         """
         Internal invoke method, calls `invoke()` after some prep.
         Handles optional fields that are required to call `invoke()` and invocation cache.
@@ -657,23 +269,23 @@ class BaseInvocation(ABC, BaseModel):
                     raise MissingInputException(self.model_fields["type"].default, field_name)
 
         # skip node cache codepath if it's disabled
-        if context.services.configuration.node_cache_size == 0:
+        if services.configuration.node_cache_size == 0:
             return self.invoke(context)
 
         output: BaseInvocationOutput
         if self.use_cache:
-            key = context.services.invocation_cache.create_key(self)
-            cached_value = context.services.invocation_cache.get(key)
+            key = services.invocation_cache.create_key(self)
+            cached_value = services.invocation_cache.get(key)
             if cached_value is None:
-                context.services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
                 output = self.invoke(context)
-                context.services.invocation_cache.save(key, output)
+                services.invocation_cache.save(key, output)
                 return output
             else:
-                context.services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
                 return cached_value
         else:
-            context.services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
+            services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
             return self.invoke(context)
 
     id: str = Field(
@@ -714,9 +326,7 @@ RESERVED_NODE_ATTRIBUTE_FIELD_NAMES = {
     "workflow",
 }
 
-RESERVED_INPUT_FIELD_NAMES = {
-    "metadata",
-}
+RESERVED_INPUT_FIELD_NAMES = {"metadata", "board"}
 
 RESERVED_OUTPUT_FIELD_NAMES = {"type"}
 
@@ -926,37 +536,3 @@ def invocation_output(
         return cls
 
     return wrapper
-
-
-class MetadataField(RootModel):
-    """
-    Pydantic model for metadata with custom root of type dict[str, Any].
-    Metadata is stored without a strict schema.
-    """
-
-    root: dict[str, Any] = Field(description="The metadata")
-
-
-MetadataFieldValidator = TypeAdapter(MetadataField)
-
-
-class WithMetadata(BaseModel):
-    metadata: Optional[MetadataField] = Field(
-        default=None,
-        description=FieldDescriptions.metadata,
-        json_schema_extra=InputFieldJSONSchemaExtra(
-            field_kind=FieldKind.Internal,
-            input=Input.Connection,
-            orig_required=False,
-        ).model_dump(exclude_none=True),
-    )
-
-
-class WithWorkflow:
-    workflow = None
-
-    def __init_subclass__(cls) -> None:
-        logger.warn(
-            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
-        )
-        super().__init_subclass__()

invokeai/app/invocations/collections.py

@@ -5,9 +5,11 @@ import numpy as np
 from pydantic import ValidationInfo, field_validator
 
 from invokeai.app.invocations.primitives import IntegerCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField
 
 
 @invocation(

invokeai/app/invocations/compel.py

@@ -1,40 +1,28 @@
-from dataclasses import dataclass
-from typing import List, Optional, Union
+from typing import Iterator, List, Optional, Tuple, Union, cast
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
+from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
 
-from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIComponent
+from invokeai.app.invocations.primitives import ConditioningOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.ti_utils import generate_ti_list
+from invokeai.backend.lora import LoRAModelRaw
+from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
+    ConditioningFieldData,
     ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
+from invokeai.backend.util.devices import torch_dtype
 
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import ModelNotFoundException, ModelType
-from ...backend.util.devices import torch_dtype
-from ..util.ti_utils import extract_ti_triggers_from_prompt
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
-    invocation,
-    invocation_output,
-)
-from .model import ClipField
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from .model import CLIPField
 
-
-@dataclass
-class ConditioningFieldData:
-    conditionings: List[BasicConditioningInfo]
-    # unconditioned: Optional[torch.Tensor]
+# unconditioned: Optional[torch.Tensor]
 
 
 # class ConditioningAlgo(str, Enum):
@@ -48,7 +36,7 @@ class ConditioningFieldData:
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.0.0",
+    version="1.1.1",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -58,7 +46,7 @@ class CompelInvocation(BaseInvocation):
         description=FieldDescriptions.compel_prompt,
         ui_component=UIComponent.Textarea,
     )
-    clip: ClipField = InputField(
+    clip: CLIPField = InputField(
         title="CLIP",
         description=FieldDescriptions.clip,
         input=Input.Connection,
@@ -66,49 +54,27 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-            context=context,
-        )
+        tokenizer_info = context.models.load(self.clip.tokenizer)
+        tokenizer_model = tokenizer_info.model
+        assert isinstance(tokenizer_model, CLIPTokenizer)
+        text_encoder_info = context.models.load(self.clip.text_encoder)
+        text_encoder_model = text_encoder_info.model
+        assert isinstance(text_encoder_model, CLIPTextModel)
 
-        def _lora_loader():
+        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in self.clip.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
-                yield (lora_info.context.model, lora.weight)
+                lora_info = context.models.load(lora.lora)
+                assert isinstance(lora_info.model, LoRAModelRaw)
+                yield (lora_info.model, lora.weight)
                 del lora_info
             return
 
-        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        ti_list = []
-        for trigger in extract_ti_triggers_from_prompt(self.prompt):
-            name = trigger[1:-1]
-            try:
-                ti_list.append(
-                    (
-                        name,
-                        context.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=self.clip.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                            context=context,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
-                # print(e)
-                # import traceback
-                # print(traceback.format_exc())
-                print(f'Warn: trigger: "{trigger}" not found')
+        ti_list = generate_ti_list(self.prompt, text_encoder_info.config.base, context)
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -116,8 +82,9 @@ class CompelInvocation(BaseInvocation):
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_model, self.clip.skipped_layers),
         ):
+            assert isinstance(text_encoder, CLIPTextModel)
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -128,7 +95,7 @@ class CompelInvocation(BaseInvocation):
 
             conjunction = Compel.parse_prompt_string(self.prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
             c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
@@ -149,45 +116,41 @@ class CompelInvocation(BaseInvocation):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 class SDXLPromptInvocationBase:
+    """Prompt processor for SDXL models."""
+
     def run_clip_compel(
         self,
         context: InvocationContext,
-        clip_field: ClipField,
+        clip_field: CLIPField,
         prompt: str,
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ):
-        tokenizer_info = context.services.model_manager.get_model(
-            **clip_field.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.model_dump(),
-            context=context,
-        )
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[ExtraConditioningInfo]]:
+        tokenizer_info = context.models.load(clip_field.tokenizer)
+        tokenizer_model = tokenizer_info.model
+        assert isinstance(tokenizer_model, CLIPTokenizer)
+        text_encoder_info = context.models.load(clip_field.text_encoder)
+        text_encoder_model = text_encoder_info.model
+        assert isinstance(text_encoder_model, (CLIPTextModel, CLIPTextModelWithProjection))
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
-            cpu_text_encoder = text_encoder_info.context.model
+            cpu_text_encoder = text_encoder_info.model
+            assert isinstance(cpu_text_encoder, torch.nn.Module)
             c = torch.zeros(
                 (
                     1,
                     cpu_text_encoder.config.max_position_embeddings,
                     cpu_text_encoder.config.hidden_size,
                 ),
-                dtype=text_encoder_info.context.cache.precision,
+                dtype=cpu_text_encoder.dtype,
             )
             if get_pooled:
                 c_pooled = torch.zeros(
@@ -198,40 +161,21 @@ class SDXLPromptInvocationBase:
                 c_pooled = None
             return c, c_pooled, None
 
-        def _lora_loader():
+        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in clip_field.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
-                yield (lora_info.context.model, lora.weight)
+                lora_info = context.models.load(lora.lora)
+                lora_model = lora_info.model
+                assert isinstance(lora_model, LoRAModelRaw)
+                yield (lora_model, lora.weight)
                 del lora_info
             return
 
-        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        ti_list = []
-        for trigger in extract_ti_triggers_from_prompt(prompt):
-            name = trigger[1:-1]
-            try:
-                ti_list.append(
-                    (
-                        name,
-                        context.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=clip_field.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                            context=context,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
-                # print(e)
-                # import traceback
-                # print(traceback.format_exc())
-                print(f'Warn: trigger: "{trigger}" not found')
+        ti_list = generate_ti_list(prompt, text_encoder_info.config.base, context)
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -239,8 +183,10 @@ class SDXLPromptInvocationBase:
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_model, clip_field.skipped_layers),
         ):
+            assert isinstance(text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
+            text_encoder = cast(CLIPTextModel, text_encoder)
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -253,7 +199,7 @@ class SDXLPromptInvocationBase:
 
             conjunction = Compel.parse_prompt_string(prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 # TODO: better logging for and syntax
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
@@ -286,7 +232,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.1.1",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -307,8 +253,8 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     crop_left: int = InputField(default=0, description="")
     target_width: int = InputField(default=1024, description="")
     target_height: int = InputField(default=1024, description="")
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
-    clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
+    clip: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
+    clip2: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
@@ -357,6 +303,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 dim=1,
             )
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -368,14 +315,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation(
@@ -383,7 +325,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     title="SDXL Refiner Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.1.1",
 )
 class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -398,7 +340,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
     crop_top: int = InputField(default=0, description="")
     crop_left: int = InputField(default=0, description="")
     aesthetic_score: float = InputField(default=6.0, description=FieldDescriptions.sdxl_aesthetic)
-    clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
+    clip2: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
@@ -410,6 +352,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         add_time_ids = torch.tensor([original_size + crop_coords + (self.aesthetic_score,)])
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -421,21 +364,16 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation_output("clip_skip_output")
-class ClipSkipInvocationOutput(BaseInvocationOutput):
-    """Clip skip node output"""
+class CLIPSkipInvocationOutput(BaseInvocationOutput):
+    """CLIP skip node output"""
 
-    clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
+    clip: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
 @invocation(
@@ -443,25 +381,25 @@ class ClipSkipInvocationOutput(BaseInvocationOutput):
     title="CLIP Skip",
     tags=["clipskip", "clip", "skip"],
     category="conditioning",
-    version="1.0.0",
+    version="1.1.0",
 )
-class ClipSkipInvocation(BaseInvocation):
+class CLIPSkipInvocation(BaseInvocation):
     """Skip layers in clip text_encoder model."""
 
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
-    skipped_layers: int = InputField(default=0, description=FieldDescriptions.skipped_layers)
+    clip: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
+    skipped_layers: int = InputField(default=0, ge=0, description=FieldDescriptions.skipped_layers)
 
-    def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
+    def invoke(self, context: InvocationContext) -> CLIPSkipInvocationOutput:
         self.clip.skipped_layers += self.skipped_layers
-        return ClipSkipInvocationOutput(
+        return CLIPSkipInvocationOutput(
             clip=self.clip,
         )
 
 
 def get_max_token_count(
-    tokenizer,
+    tokenizer: CLIPTokenizer,
     prompt: Union[FlattenedPrompt, Blend, Conjunction],
-    truncate_if_too_long=False,
+    truncate_if_too_long: bool = False,
 ) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt
@@ -473,7 +411,9 @@ def get_max_token_count(
         return len(get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long))
 
 
-def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True) -> List[str]:
+def get_tokens_for_prompt_object(
+    tokenizer: CLIPTokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long: bool = True
+) -> List[str]:
     if type(parsed_prompt) is Blend:
         raise ValueError("Blend is not supported here - you need to get tokens for each of its .children")
 
@@ -486,24 +426,29 @@ def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, trun
         for x in parsed_prompt.children
     ]
     text = " ".join(text_fragments)
-    tokens = tokenizer.tokenize(text)
+    tokens: List[str] = tokenizer.tokenize(text)
     if truncate_if_too_long:
         max_tokens_length = tokenizer.model_max_length - 2  # typically 75
         tokens = tokens[0:max_tokens_length]
     return tokens
 
 
-def log_tokenization_for_conjunction(c: Conjunction, tokenizer, display_label_prefix=None):
+def log_tokenization_for_conjunction(
+    c: Conjunction, tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
+) -> None:
     display_label_prefix = display_label_prefix or ""
     for i, p in enumerate(c.prompts):
         if len(c.prompts) > 1:
             this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
         else:
+            assert display_label_prefix is not None
             this_display_label_prefix = display_label_prefix
         log_tokenization_for_prompt_object(p, tokenizer, display_label_prefix=this_display_label_prefix)
 
 
-def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None):
+def log_tokenization_for_prompt_object(
+    p: Union[Blend, FlattenedPrompt], tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
+) -> None:
     display_label_prefix = display_label_prefix or ""
     if type(p) is Blend:
         blend: Blend = p
@@ -543,7 +488,12 @@ def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokeniz
             log_tokenization_for_text(text, tokenizer, display_label=display_label_prefix)
 
 
-def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
+def log_tokenization_for_text(
+    text: str,
+    tokenizer: CLIPTokenizer,
+    display_label: Optional[str] = None,
+    truncate_if_too_long: Optional[bool] = False,
+) -> None:
     """shows how the prompt is tokenized
     # usually tokens have '</w>' to indicate end-of-word,
     # but for readability it has been replaced with ' '

invokeai/app/invocations/constants.py

@@ -0,0 +1,17 @@
+from typing import Literal
+
+from invokeai.backend.stable_diffusion.schedulers import SCHEDULER_MAP
+
+LATENT_SCALE_FACTOR = 8
+"""
+HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
+be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
+factor is hard-coded to a literal '8' rather than using this constant.
+The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
+"""
+
+SCHEDULER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
+"""A literal type representing the valid scheduler names."""
+
+IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
+"""A literal type for PIL image modes supported by Invoke"""

invokeai/app/invocations/controlnet_image_processors.py

@@ -7,12 +7,8 @@ from typing import Dict, List, Literal, Union
 import cv2
 import numpy as np
 from controlnet_aux import (
-    CannyDetector,
     ContentShuffleDetector,
-    HEDdetector,
     LeresDetector,
-    LineartAnimeDetector,
-    LineartDetector,
     MediapipeFaceDetector,
     MidasDetector,
     MLSDdetector,
@@ -23,27 +19,30 @@ from controlnet_aux import (
 )
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
-from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
-
-from ...backend.model_management import BaseModelType
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
     Input,
     InputField,
-    InvocationContext,
     OutputField,
+    UIType,
+    WithBoard,
     WithMetadata,
-    invocation,
-    invocation_output,
 )
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.image_util.canny import get_canny_edges
+from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
+from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
+from invokeai.backend.image_util.hed import HEDProcessor
+from invokeai.backend.image_util.lineart import LineartProcessor
+from invokeai.backend.image_util.lineart_anime import LineartAnimeProcessor
+
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 
 CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
 CONTROLNET_RESIZE_VALUES = Literal[
@@ -54,18 +53,9 @@ CONTROLNET_RESIZE_VALUES = Literal[
 ]
 
 
-class ControlNetModelField(BaseModel):
-    """ControlNet model field"""
-
-    model_name: str = Field(description="Name of the ControlNet model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
 class ControlField(BaseModel):
     image: ImageField = Field(description="The control image")
-    control_model: ControlNetModelField = Field(description="The ControlNet model to use")
+    control_model: ModelIdentifierField = Field(description="The ControlNet model to use")
     control_weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
@@ -101,7 +91,9 @@ class ControlNetInvocation(BaseInvocation):
     """Collects ControlNet info to pass to other nodes"""
 
     image: ImageField = InputField(description="The control image")
-    control_model: ControlNetModelField = InputField(description=FieldDescriptions.controlnet_model, input=Input.Direct)
+    control_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.controlnet_model, input=Input.Direct, ui_type=UIType.ControlNetModel
+    )
     control_weight: Union[float, List[float]] = InputField(
         default=1.0, ge=-1, le=2, description="The weight given to the ControlNet"
     )
@@ -140,7 +132,7 @@ class ControlNetInvocation(BaseInvocation):
 
 
 # This invocation exists for other invocations to subclass it - do not register with @invocation!
-class ImageProcessorInvocation(BaseInvocation, WithMetadata):
+class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Base class for invocations that preprocess images for ControlNet"""
 
     image: ImageField = InputField(description="The image to process")
@@ -149,23 +141,18 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
         # superclass just passes through image without processing
         return image
 
+    def load_image(self, context: InvocationContext) -> Image.Image:
+        # allows override for any special formatting specific to the preprocessor
+        return context.images.get_pil(self.image.image_name, "RGB")
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        raw_image = context.services.images.get_pil_image(self.image.image_name)
+        raw_image = self.load_image(context)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
         # currently can't see processed image in node UI without a showImage node,
         #    so for now setting image_type to RESULT instead of INTERMEDIATE so will get saved in gallery
-        image_dto = context.services.images.create(
-            image=processed_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.CONTROL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=processed_image)
 
         """Builds an ImageOutput and its ImageField"""
         processed_image_field = ImageField(image_name=image_dto.image_name)
@@ -184,11 +171,13 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
     title="Canny Processor",
     tags=["controlnet", "canny"],
     category="controlnet",
-    version="1.2.0",
+    version="1.3.2",
 )
 class CannyImageProcessorInvocation(ImageProcessorInvocation):
     """Canny edge detection for ControlNet"""
 
+    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
     low_threshold: int = InputField(
         default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)"
     )
@@ -196,9 +185,18 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
         default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)"
     )
 
-    def run_processor(self, image):
-        canny_processor = CannyDetector()
-        processed_image = canny_processor(image, self.low_threshold, self.high_threshold)
+    def load_image(self, context: InvocationContext) -> Image.Image:
+        # Keep alpha channel for Canny processing to detect edges of transparent areas
+        return context.images.get_pil(self.image.image_name, "RGBA")
+
+    def run_processor(self, image: Image.Image) -> Image.Image:
+        processed_image = get_canny_edges(
+            image,
+            self.low_threshold,
+            self.high_threshold,
+            detect_resolution=self.detect_resolution,
+            image_resolution=self.image_resolution,
+        )
         return processed_image
 
 
@@ -207,7 +205,7 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
     title="HED (softedge) Processor",
     tags=["controlnet", "hed", "softedge"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class HedImageProcessorInvocation(ImageProcessorInvocation):
     """Applies HED edge detection to image"""
@@ -218,9 +216,9 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
     # safe: bool = InputField(default=False, description=FieldDescriptions.safe_mode)
     scribble: bool = InputField(default=False, description=FieldDescriptions.scribble_mode)
 
-    def run_processor(self, image):
-        hed_processor = HEDdetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = hed_processor(
+    def run_processor(self, image: Image.Image) -> Image.Image:
+        hed_processor = HEDProcessor()
+        processed_image = hed_processor.run(
             image,
             detect_resolution=self.detect_resolution,
             image_resolution=self.image_resolution,
@@ -236,7 +234,7 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Processor",
     tags=["controlnet", "lineart"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class LineartImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art processing to image"""
@@ -245,9 +243,9 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation):
     image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
     coarse: bool = InputField(default=False, description="Whether to use coarse mode")
 
-    def run_processor(self, image):
-        lineart_processor = LineartDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = lineart_processor(
+    def run_processor(self, image: Image.Image) -> Image.Image:
+        lineart_processor = LineartProcessor()
+        processed_image = lineart_processor.run(
             image, detect_resolution=self.detect_resolution, image_resolution=self.image_resolution, coarse=self.coarse
         )
         return processed_image
@@ -258,7 +256,7 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Anime Processor",
     tags=["controlnet", "lineart", "anime"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art anime processing to image"""
@@ -266,9 +264,9 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
     image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image):
-        processor = LineartAnimeDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = processor(
+    def run_processor(self, image: Image.Image) -> Image.Image:
+        processor = LineartAnimeProcessor()
+        processed_image = processor.run(
             image,
             detect_resolution=self.detect_resolution,
             image_resolution=self.image_resolution,
@@ -281,13 +279,15 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     title="Midas Depth Processor",
     tags=["controlnet", "midas"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.3",
 )
 class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Midas depth processing to image"""
 
     a_mult: float = InputField(default=2.0, ge=0, description="Midas parameter `a_mult` (a = a_mult * PI)")
     bg_th: float = InputField(default=0.1, ge=0, description="Midas parameter `bg_th`")
+    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
     # depth_and_normal not supported in controlnet_aux v0.0.3
     # depth_and_normal: bool = InputField(default=False, description="whether to use depth and normal mode")
 
@@ -297,6 +297,8 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
             image,
             a=np.pi * self.a_mult,
             bg_th=self.bg_th,
+            image_resolution=self.image_resolution,
+            detect_resolution=self.detect_resolution,
             # dept_and_normal not supported in controlnet_aux v0.0.3
             # depth_and_normal=self.depth_and_normal,
         )
@@ -308,7 +310,7 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Normal BAE Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies NormalBae processing to image"""
@@ -325,7 +327,7 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.0"
+    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.2"
 )
 class MlsdImageProcessorInvocation(ImageProcessorInvocation):
     """Applies MLSD processing to image"""
@@ -348,7 +350,7 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.0"
+    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.2"
 )
 class PidiImageProcessorInvocation(ImageProcessorInvocation):
     """Applies PIDI processing to image"""
@@ -375,7 +377,7 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
     title="Content Shuffle Processor",
     tags=["controlnet", "contentshuffle"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     """Applies content shuffle processing to image"""
@@ -405,7 +407,7 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     title="Zoe (Depth) Processor",
     tags=["controlnet", "zoe", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Zoe depth processing to image"""
@@ -421,21 +423,25 @@ class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Mediapipe Face Processor",
     tags=["controlnet", "mediapipe", "face"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.3",
 )
 class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     """Applies mediapipe face processing to image"""
 
     max_faces: int = InputField(default=1, ge=1, description="Maximum number of faces to detect")
     min_confidence: float = InputField(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
+    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
 
     def run_processor(self, image):
-        # MediaPipeFaceDetector throws an error if image has alpha channel
-        #     so convert to RGB if needed
-        if image.mode == "RGBA":
-            image = image.convert("RGB")
         mediapipe_face_processor = MediapipeFaceDetector()
-        processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence)
+        processed_image = mediapipe_face_processor(
+            image,
+            max_faces=self.max_faces,
+            min_confidence=self.min_confidence,
+            image_resolution=self.image_resolution,
+            detect_resolution=self.detect_resolution,
+        )
         return processed_image
 
 
@@ -444,7 +450,7 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     title="Leres (Depth) Processor",
     tags=["controlnet", "leres", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class LeresImageProcessorInvocation(ImageProcessorInvocation):
     """Applies leres processing to image"""
@@ -473,7 +479,7 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
     title="Tile Resample Processor",
     tags=["controlnet", "tile"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     """Tile resampler processor"""
@@ -513,18 +519,23 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     title="Segment Anything Processor",
     tags=["controlnet", "segmentanything"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.3",
 )
 class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     """Applies segment anything processing to image"""
 
+    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+
     def run_processor(self, image):
         # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
         segment_anything_processor = SamDetectorReproducibleColors.from_pretrained(
             "ybelkada/segment-anything", subfolder="checkpoints"
         )
         np_img = np.array(image, dtype=np.uint8)
-        processed_image = segment_anything_processor(np_img)
+        processed_image = segment_anything_processor(
+            np_img, image_resolution=self.image_resolution, detect_resolution=self.detect_resolution
+        )
         return processed_image
 
 
@@ -555,7 +566,7 @@ class SamDetectorReproducibleColors(SamDetector):
     title="Color Map Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.2",
 )
 class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a color map from the provided image"""
@@ -563,7 +574,6 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     color_map_tile_size: int = InputField(default=64, ge=0, description=FieldDescriptions.tile_size)
 
     def run_processor(self, image: Image.Image):
-        image = image.convert("RGB")
         np_image = np.array(image, dtype=np.uint8)
         height, width = np_image.shape[:2]
 
@@ -588,7 +598,7 @@ DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
     title="Depth Anything Processor",
     tags=["controlnet", "depth", "depth anything"],
     category="controlnet",
-    version="1.0.0",
+    version="1.1.1",
 )
 class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a depth map based on the Depth Anything algorithm"""
@@ -597,16 +607,12 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
         default="small", description="The size of the depth model to use"
     )
     resolution: int = InputField(default=512, ge=64, multiple_of=64, description=FieldDescriptions.image_res)
-    offload: bool = InputField(default=False)
 
     def run_processor(self, image: Image.Image):
         depth_anything_detector = DepthAnythingDetector()
         depth_anything_detector.load_model(model_size=self.model_size)
 
-        if image.mode == "RGBA":
-            image = image.convert("RGB")
-
-        processed_image = depth_anything_detector(image=image, resolution=self.resolution, offload=self.offload)
+        processed_image = depth_anything_detector(image=image, resolution=self.resolution)
         return processed_image
 
 
@@ -615,7 +621,7 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     title="DW Openpose Image Processor",
     tags=["controlnet", "dwpose", "openpose"],
     category="controlnet",
-    version="1.0.0",
+    version="1.1.0",
 )
 class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
     """Generates an openpose pose from an image using DWPose"""
@@ -625,7 +631,7 @@ class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
     draw_hands: bool = InputField(default=False)
     image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image):
         dw_openpose = DWOpenposeDetector()
         processed_image = dw_openpose(
             image,

invokeai/app/invocations/custom_nodes/init.py

@@ -3,6 +3,7 @@ Invoke-managed custom node loader. See README.md for more information.
 """
 
 import sys
+import traceback
 from importlib.util import module_from_spec, spec_from_file_location
 from pathlib import Path
 
@@ -41,11 +42,15 @@ for d in Path(__file__).parent.iterdir():
 
     logger.info(f"Loading node pack {module_name}")
 
-    module = module_from_spec(spec)
-    sys.modules[spec.name] = module
-    spec.loader.exec_module(module)
+    try:
+        module = module_from_spec(spec)
+        sys.modules[spec.name] = module
+        spec.loader.exec_module(module)
 
-    loaded_count += 1
+        loaded_count += 1
+    except Exception:
+        full_error = traceback.format_exc()
+        logger.error(f"Failed to load node pack {module_name}:\n{full_error}")
 
     del init, module_name
 

invokeai/app/invocations/cv.py

@@ -5,22 +5,24 @@ import cv2 as cv
 import numpy
 from PIL import Image, ImageOps
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 
 
-@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.0")
-class CvInpaintInvocation(BaseInvocation, WithMetadata):
+@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.3.1")
+class CvInpaintInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Simple inpaint using opencv."""
 
     image: ImageField = InputField(description="The image to inpaint")
     mask: ImageField = InputField(description="The mask to use when inpainting")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        mask = context.services.images.get_pil_image(self.mask.image_name)
+        image = context.images.get_pil(self.image.image_name)
+        mask = context.images.get_pil(self.mask.image_name)
 
         # Convert to cv image/mask
         # TODO: consider making these utility functions
@@ -34,18 +36,6 @@ class CvInpaintInvocation(BaseInvocation, WithMetadata):
         # TODO: consider making a utility function
         image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
 
-        image_dto = context.services.images.create(
-            image=image_inpainted,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=image_inpainted)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/facetools.py

@@ -13,15 +13,13 @@ from pydantic import field_validator
 import invokeai.assets.fonts as font_assets
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 
 @invocation_output("face_mask_output")
@@ -306,37 +304,37 @@ def extract_face(
 
     # Adjust the crop boundaries to stay within the original image's dimensions
     if x_min < 0:
-        context.services.logger.warning("FaceTools --> -X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -X-axis padding reached image edge.")
         x_max -= x_min
         x_min = 0
     elif x_max > mask.width:
-        context.services.logger.warning("FaceTools --> +X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +X-axis padding reached image edge.")
         x_min -= x_max - mask.width
         x_max = mask.width
 
     if y_min < 0:
-        context.services.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
         y_max -= y_min
         y_min = 0
     elif y_max > mask.height:
-        context.services.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
         y_min -= y_max - mask.height
         y_max = mask.height
 
     # Ensure the crop is square and adjust the boundaries if needed
     if x_max - x_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
         diff = crop_size - (x_max - x_min)
         x_min -= diff // 2
         x_max += diff - diff // 2
 
     if y_max - y_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
         diff = crop_size - (y_max - y_min)
         y_min -= diff // 2
         y_max += diff - diff // 2
 
-    context.services.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
+    context.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
 
     # Crop the output image to the specified size with the center of the face mesh as the center.
     mask = mask.crop((x_min, y_min, x_max, y_max))
@@ -368,7 +366,7 @@ def get_faces_list(
 
     # Generate the face box mask and get the center of the face.
     if not should_chunk:
-        context.services.logger.info("FaceTools --> Attempting full image face detection.")
+        context.logger.info("FaceTools --> Attempting full image face detection.")
         result = generate_face_box_mask(
             context=context,
             minimum_confidence=minimum_confidence,
@@ -380,7 +378,7 @@ def get_faces_list(
             draw_mesh=draw_mesh,
         )
     if should_chunk or len(result) == 0:
-        context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
+        context.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
         width, height = image.size
         image_chunks = []
         x_offsets = []
@@ -399,7 +397,7 @@ def get_faces_list(
                 x_offsets.append(x)
                 y_offsets.append(0)
                 fx += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
+                context.logger.info(f"FaceTools --> Chunk starting at x = {x}")
         elif height > width:
             # Portrait - slice the image vertically
             fy = 0.0
@@ -411,10 +409,10 @@ def get_faces_list(
                 x_offsets.append(0)
                 y_offsets.append(y)
                 fy += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
+                context.logger.info(f"FaceTools --> Chunk starting at y = {y}")
 
         for idx in range(len(image_chunks)):
-            context.services.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
+            context.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
             result = result + generate_face_box_mask(
                 context=context,
                 minimum_confidence=minimum_confidence,
@@ -428,7 +426,7 @@ def get_faces_list(
 
         if len(result) == 0:
             # Give up
-            context.services.logger.warning(
+            context.logger.warning(
                 "FaceTools --> No face detected in chunked input image. Passing through original image."
             )
 
@@ -437,7 +435,7 @@ def get_faces_list(
     return all_faces
 
 
-@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.2")
 class FaceOffInvocation(BaseInvocation, WithMetadata):
     """Bound, extract, and mask a face from an image using MediaPipe detection"""
 
@@ -470,11 +468,11 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         )
 
         if len(all_faces) == 0:
-            context.services.logger.warning("FaceOff --> No faces detected. Passing through original image.")
+            context.logger.warning("FaceOff --> No faces detected. Passing through original image.")
             return None
 
         if self.face_id > len(all_faces) - 1:
-            context.services.logger.warning(
+            context.logger.warning(
                 f"FaceOff --> Face ID {self.face_id} is outside of the number of faces detected ({len(all_faces)}). Passing through original image."
             )
             return None
@@ -486,7 +484,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return face_data
 
     def invoke(self, context: InvocationContext) -> FaceOffOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.faceoff(context=context, image=image)
 
         if result is None:
@@ -500,24 +498,9 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
             x = result["x_min"]
             y = result["y_min"]
 
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        mask_dto = context.services.images.create(
-            image=result_mask,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result_mask, image_category=ImageCategory.MASK)
 
         output = FaceOffOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -531,7 +514,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return output
 
 
-@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.2")
 class FaceMaskInvocation(BaseInvocation, WithMetadata):
     """Face mask creation using mediapipe face detection"""
 
@@ -580,7 +563,7 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
             if len(intersected_face_ids) == 0:
                 id_range_str = ",".join([str(id) for id in id_range])
-                context.services.logger.warning(
+                context.logger.warning(
                     f"Face IDs must be in range of detected faces - requested {self.face_ids}, detected {id_range_str}. Passing through original image."
                 )
                 return FaceMaskResult(
@@ -616,27 +599,12 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
         )
 
     def invoke(self, context: InvocationContext) -> FaceMaskOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.facemask(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result["image"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result["image"])
 
-        mask_dto = context.services.images.create(
-            image=result["mask"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result["mask"], image_category=ImageCategory.MASK)
 
         output = FaceMaskOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -649,9 +617,9 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
 
 @invocation(
-    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.0"
+    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.2"
 )
-class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
+class FaceIdentifierInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
 
     image: ImageField = InputField(description="Image to face detect")
@@ -705,21 +673,9 @@ class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
         return image
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result_image = self.faceidentifier(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/fields.py

@@ -0,0 +1,567 @@
+from enum import Enum
+from typing import Any, Callable, Optional, Tuple
+
+from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter
+from pydantic.fields import _Unset
+from pydantic_core import PydanticUndefined
+
+from invokeai.app.util.metaenum import MetaEnum
+from invokeai.backend.util.logging import InvokeAILogger
+
+logger = InvokeAILogger.get_logger()
+
+
+class UIType(str, Enum, metaclass=MetaEnum):
+    """
+    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
+
+    - Model Fields
+    The most common node-author-facing use will be for model fields. Internally, there is no difference
+    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
+    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
+    the field is an SDXL main model field.
+
+    - Any Field
+    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
+    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
+
+    - Scheduler Field
+    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
+
+    - Internal Fields
+    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
+    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
+    should not be used by node authors.
+
+    - DEPRECATED Fields
+    These types are deprecated and should not be used by node authors. A warning will be logged if one is
+    used, and the type will be ignored. They are included here for backwards compatibility.
+    """
+
+    # region Model Field Types
+    MainModel = "MainModelField"
+    SDXLMainModel = "SDXLMainModelField"
+    SDXLRefinerModel = "SDXLRefinerModelField"
+    ONNXModel = "ONNXModelField"
+    VAEModel = "VAEModelField"
+    LoRAModel = "LoRAModelField"
+    ControlNetModel = "ControlNetModelField"
+    IPAdapterModel = "IPAdapterModelField"
+    T2IAdapterModel = "T2IAdapterModelField"
+    # endregion
+
+    # region Misc Field Types
+    Scheduler = "SchedulerField"
+    Any = "AnyField"
+    # endregion
+
+    # region Internal Field Types
+    _Collection = "CollectionField"
+    _CollectionItem = "CollectionItemField"
+    # endregion
+
+    # region DEPRECATED
+    Boolean = "DEPRECATED_Boolean"
+    Color = "DEPRECATED_Color"
+    Conditioning = "DEPRECATED_Conditioning"
+    Control = "DEPRECATED_Control"
+    Float = "DEPRECATED_Float"
+    Image = "DEPRECATED_Image"
+    Integer = "DEPRECATED_Integer"
+    Latents = "DEPRECATED_Latents"
+    String = "DEPRECATED_String"
+    BooleanCollection = "DEPRECATED_BooleanCollection"
+    ColorCollection = "DEPRECATED_ColorCollection"
+    ConditioningCollection = "DEPRECATED_ConditioningCollection"
+    ControlCollection = "DEPRECATED_ControlCollection"
+    FloatCollection = "DEPRECATED_FloatCollection"
+    ImageCollection = "DEPRECATED_ImageCollection"
+    IntegerCollection = "DEPRECATED_IntegerCollection"
+    LatentsCollection = "DEPRECATED_LatentsCollection"
+    StringCollection = "DEPRECATED_StringCollection"
+    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
+    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
+    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
+    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
+    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
+    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
+    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
+    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
+    StringPolymorphic = "DEPRECATED_StringPolymorphic"
+    UNet = "DEPRECATED_UNet"
+    Vae = "DEPRECATED_Vae"
+    CLIP = "DEPRECATED_CLIP"
+    Collection = "DEPRECATED_Collection"
+    CollectionItem = "DEPRECATED_CollectionItem"
+    Enum = "DEPRECATED_Enum"
+    WorkflowField = "DEPRECATED_WorkflowField"
+    IsIntermediate = "DEPRECATED_IsIntermediate"
+    BoardField = "DEPRECATED_BoardField"
+    MetadataItem = "DEPRECATED_MetadataItem"
+    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
+    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
+    MetadataDict = "DEPRECATED_MetadataDict"
+
+
+class UIComponent(str, Enum, metaclass=MetaEnum):
+    """
+    The type of UI component to use for a field, used to override the default components, which are
+    inferred from the field type.
+    """
+
+    None_ = "none"
+    Textarea = "textarea"
+    Slider = "slider"
+
+
+class FieldDescriptions:
+    denoising_start = "When to start denoising, expressed a percentage of total steps"
+    denoising_end = "When to stop denoising, expressed a percentage of total steps"
+    cfg_scale = "Classifier-Free Guidance scale"
+    cfg_rescale_multiplier = "Rescale multiplier for CFG guidance, used for models trained with zero-terminal SNR"
+    scheduler = "Scheduler to use during inference"
+    positive_cond = "Positive conditioning tensor"
+    negative_cond = "Negative conditioning tensor"
+    noise = "Noise tensor"
+    clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
+    unet = "UNet (scheduler, LoRAs)"
+    vae = "VAE"
+    cond = "Conditioning tensor"
+    controlnet_model = "ControlNet model to load"
+    vae_model = "VAE model to load"
+    lora_model = "LoRA model to load"
+    main_model = "Main model (UNet, VAE, CLIP) to load"
+    sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
+    sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
+    onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
+    lora_weight = "The weight at which the LoRA is applied to each model"
+    compel_prompt = "Prompt to be parsed by Compel to create a conditioning tensor"
+    raw_prompt = "Raw prompt text (no parsing)"
+    sdxl_aesthetic = "The aesthetic score to apply to the conditioning tensor"
+    skipped_layers = "Number of layers to skip in text encoder"
+    seed = "Seed for random number generation"
+    steps = "Number of steps to run"
+    width = "Width of output (px)"
+    height = "Height of output (px)"
+    control = "ControlNet(s) to apply"
+    ip_adapter = "IP-Adapter to apply"
+    t2i_adapter = "T2I-Adapter(s) to apply"
+    denoised_latents = "Denoised latents tensor"
+    latents = "Latents tensor"
+    strength = "Strength of denoising (proportional to steps)"
+    metadata = "Optional metadata to be saved with the image"
+    metadata_collection = "Collection of Metadata"
+    metadata_item_polymorphic = "A single metadata item or collection of metadata items"
+    metadata_item_label = "Label for this metadata item"
+    metadata_item_value = "The value for this metadata item (may be any type)"
+    workflow = "Optional workflow to be saved with the image"
+    interp_mode = "Interpolation mode"
+    torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
+    fp32 = "Whether or not to use full float32 precision"
+    precision = "Precision to use"
+    tiled = "Processing using overlapping tiles (reduce memory consumption)"
+    detect_res = "Pixel resolution for detection"
+    image_res = "Pixel resolution for output image"
+    safe_mode = "Whether or not to use safe mode"
+    scribble_mode = "Whether or not to use scribble mode"
+    scale_factor = "The factor by which to scale"
+    blend_alpha = (
+        "Blending factor. 0.0 = use input A only, 1.0 = use input B only, 0.5 = 50% mix of input A and input B."
+    )
+    num_1 = "The first number"
+    num_2 = "The second number"
+    mask = "The mask to use for the operation"
+    board = "The board to save the image to"
+    image = "The image to process"
+    tile_size = "Tile size"
+    inclusive_low = "The inclusive low value"
+    exclusive_high = "The exclusive high value"
+    decimal_places = "The number of decimal places to round to"
+    freeu_s1 = 'Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
+    freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."
+
+
+class ImageField(BaseModel):
+    """An image primitive field"""
+
+    image_name: str = Field(description="The name of the image")
+
+
+class BoardField(BaseModel):
+    """A board primitive field"""
+
+    board_id: str = Field(description="The id of the board")
+
+
+class DenoiseMaskField(BaseModel):
+    """An inpaint mask field"""
+
+    mask_name: str = Field(description="The name of the mask image")
+    masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
+    gradient: bool = Field(default=False, description="Used for gradient inpainting")
+
+
+class LatentsField(BaseModel):
+    """A latents tensor primitive field"""
+
+    latents_name: str = Field(description="The name of the latents")
+    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
+
+
+class ColorField(BaseModel):
+    """A color primitive field"""
+
+    r: int = Field(ge=0, le=255, description="The red component")
+    g: int = Field(ge=0, le=255, description="The green component")
+    b: int = Field(ge=0, le=255, description="The blue component")
+    a: int = Field(ge=0, le=255, description="The alpha component")
+
+    def tuple(self) -> Tuple[int, int, int, int]:
+        return (self.r, self.g, self.b, self.a)
+
+
+class ConditioningField(BaseModel):
+    """A conditioning tensor primitive value"""
+
+    conditioning_name: str = Field(description="The name of conditioning tensor")
+    # endregion
+
+
+class MetadataField(RootModel[dict[str, Any]]):
+    """
+    Pydantic model for metadata with custom root of type dict[str, Any].
+    Metadata is stored without a strict schema.
+    """
+
+    root: dict[str, Any] = Field(description="The metadata")
+
+
+MetadataFieldValidator = TypeAdapter(MetadataField)
+
+
+class Input(str, Enum, metaclass=MetaEnum):
+    """
+    The type of input a field accepts.
+    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
+      are instantiated.
+    - `Input.Connection`: The field must have its value provided by a connection.
+    - `Input.Any`: The field may have its value provided either directly or by a connection.
+    """
+
+    Connection = "connection"
+    Direct = "direct"
+    Any = "any"
+
+
+class FieldKind(str, Enum, metaclass=MetaEnum):
+    """
+    The kind of field.
+    - `Input`: An input field on a node.
+    - `Output`: An output field on a node.
+    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
+    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
+    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
+    allowing "metadata" for that field.
+    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
+    but which are used to store information about the node. For example, the `id` and `type` fields are node
+    attributes.
+
+    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
+    startup, and when generating the OpenAPI schema for the workflow editor.
+    """
+
+    Input = "input"
+    Output = "output"
+    Internal = "internal"
+    NodeAttribute = "node_attribute"
+
+
+class InputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
+    and by the workflow editor during schema parsing and UI rendering.
+    """
+
+    input: Input
+    orig_required: bool
+    field_kind: FieldKind
+    default: Optional[Any] = None
+    orig_default: Optional[Any] = None
+    ui_hidden: bool = False
+    ui_type: Optional[UIType] = None
+    ui_component: Optional[UIComponent] = None
+    ui_order: Optional[int] = None
+    ui_choice_labels: Optional[dict[str, str]] = None
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+class WithMetadata(BaseModel):
+    """
+    Inherit from this class if your node needs a metadata input field.
+    """
+
+    metadata: Optional[MetadataField] = Field(
+        default=None,
+        description=FieldDescriptions.metadata,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Connection,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class WithWorkflow:
+    workflow = None
+
+    def __init_subclass__(cls) -> None:
+        logger.warn(
+            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
+        )
+        super().__init_subclass__()
+
+
+class WithBoard(BaseModel):
+    """
+    Inherit from this class if your node needs a board input field.
+    """
+
+    board: Optional[BoardField] = Field(
+        default=None,
+        description=FieldDescriptions.board,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Direct,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class OutputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
+    during schema parsing and UI rendering.
+    """
+
+    field_kind: FieldKind
+    ui_hidden: bool
+    ui_type: Optional[UIType]
+    ui_order: Optional[int]
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+def InputField(
+    # copied from pydantic's Field
+    # TODO: Can we support default_factory?
+    default: Any = _Unset,
+    default_factory: Callable[[], Any] | None = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    input: Input = Input.Any,
+    ui_type: Optional[UIType] = None,
+    ui_component: Optional[UIComponent] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+    ui_choice_labels: Optional[dict[str, str]] = None,
+) -> Any:
+    """
+    Creates an input field for an invocation.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param Input input: [Input.Any] The kind of input this field requires. \
+      `Input.Direct` means a value must be provided on instantiation. \
+      `Input.Connection` means the value must be provided by a connection. \
+      `Input.Any` means either will do.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
+      The UI will always render a suitable component, but sometimes you want something different than the default. \
+      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
+      For this case, you could provide `UIComponent.Textarea`.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
+
+    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
+    """
+
+    json_schema_extra_ = InputFieldJSONSchemaExtra(
+        input=input,
+        ui_type=ui_type,
+        ui_component=ui_component,
+        ui_hidden=ui_hidden,
+        ui_order=ui_order,
+        ui_choice_labels=ui_choice_labels,
+        field_kind=FieldKind.Input,
+        orig_required=True,
+    )
+
+    """
+    There is a conflict between the typing of invocation definitions and the typing of an invocation's
+    `invoke()` function.
+
+    On instantiation of a node, the invocation definition is used to create the python class. At this time,
+    any number of fields may be optional, because they may be provided by connections.
+
+    On calling of `invoke()`, however, those fields may be required.
+
+    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
+
+    `image` is required during the call to `invoke()`, but when the python class is instantiated,
+    the field may not be present. This is fine, because that image field will be provided by a
+    connection from an ancestor node, which outputs an image.
+
+    This means we want to type the `image` field as optional for the node class definition, but required
+    for the `invoke()` function.
+
+    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
+    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
+    any static type analysis tools will complain.
+
+    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
+    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
+    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
+    """
+
+    if default_factory is not _Unset and default_factory is not None:
+        default = default_factory()
+        logger.warn('"default_factory" is not supported, calling it now to set "default"')
+
+    # These are the args we may wish pass to the pydantic `Field()` function
+    field_args = {
+        "default": default,
+        "title": title,
+        "description": description,
+        "pattern": pattern,
+        "strict": strict,
+        "gt": gt,
+        "ge": ge,
+        "lt": lt,
+        "le": le,
+        "multiple_of": multiple_of,
+        "allow_inf_nan": allow_inf_nan,
+        "max_digits": max_digits,
+        "decimal_places": decimal_places,
+        "min_length": min_length,
+        "max_length": max_length,
+    }
+
+    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
+    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
+
+    # Because we are manually making fields optional, we need to store the original required bool for reference later
+    json_schema_extra_.orig_required = default is PydanticUndefined
+
+    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
+    if input is Input.Any or input is Input.Connection:
+        default_ = None if default is PydanticUndefined else default
+        provided_args.update({"default": default_})
+        if default is not PydanticUndefined:
+            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
+            json_schema_extra_.default = default
+            json_schema_extra_.orig_default = default
+    elif default is not PydanticUndefined:
+        default_ = default
+        provided_args.update({"default": default_})
+        json_schema_extra_.orig_default = default_
+
+    return Field(
+        **provided_args,
+        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
+    )
+
+
+def OutputField(
+    # copied from pydantic's Field
+    default: Any = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    ui_type: Optional[UIType] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+) -> Any:
+    """
+    Creates an output field for an invocation output.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
+    """
+    return Field(
+        default=default,
+        title=title,
+        description=description,
+        pattern=pattern,
+        strict=strict,
+        gt=gt,
+        ge=ge,
+        lt=lt,
+        le=le,
+        multiple_of=multiple_of,
+        allow_inf_nan=allow_inf_nan,
+        max_digits=max_digits,
+        decimal_places=decimal_places,
+        min_length=min_length,
+        max_length=max_length,
+        json_schema_extra=OutputFieldJSONSchemaExtra(
+            ui_type=ui_type,
+            ui_hidden=ui_hidden,
+            ui_order=ui_order,
+            field_kind=FieldKind.Output,
+        ).model_dump(exclude_none=True),
+    )

invokeai/app/invocations/infill.py

@@ -1,164 +1,91 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+from abc import abstractmethod
+from typing import Literal, get_args
 
-import math
-from typing import Literal, Optional, get_args
+from PIL import Image
 
-import numpy as np
-from PIL import Image, ImageOps
-
-from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ColorField, ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
-from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
-from invokeai.backend.image_util.lama import LaMA
-from invokeai.backend.image_util.patchmatch import PatchMatch
+from invokeai.backend.image_util.infill_methods.cv2_inpaint import cv2_inpaint
+from invokeai.backend.image_util.infill_methods.lama import LaMA
+from invokeai.backend.image_util.infill_methods.mosaic import infill_mosaic
+from invokeai.backend.image_util.infill_methods.patchmatch import PatchMatch, infill_patchmatch
+from invokeai.backend.image_util.infill_methods.tile import infill_tile
+from invokeai.backend.util.logging import InvokeAILogger
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
 
+logger = InvokeAILogger.get_logger()
 
-def infill_methods() -> list[str]:
-    methods = ["tile", "solid", "lama", "cv2"]
+
+def get_infill_methods():
+    methods = Literal["tile", "color", "lama", "cv2"]  # TODO: add mosaic back
     if PatchMatch.patchmatch_available():
-        methods.insert(0, "patchmatch")
+        methods = Literal["patchmatch", "tile", "color", "lama", "cv2"]  # TODO: add mosaic back
     return methods
 
 
-INFILL_METHODS = Literal[tuple(infill_methods())]
+INFILL_METHODS = get_infill_methods()
 DEFAULT_INFILL_METHOD = "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
 
 
-def infill_lama(im: Image.Image) -> Image.Image:
-    lama = LaMA()
-    return lama(im)
+class InfillImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Base class for invocations that preprocess images for Infilling"""
+
+    image: ImageField = InputField(description="The image to process")
+
+    @abstractmethod
+    def infill(self, image: Image.Image) -> Image.Image:
+        """Infill the image with the specified method"""
+        pass
+
+    def load_image(self, context: InvocationContext) -> tuple[Image.Image, bool]:
+        """Process the image to have an alpha channel before being infilled"""
+        image = context.images.get_pil(self.image.image_name)
+        has_alpha = True if image.mode == "RGBA" else False
+        return image, has_alpha
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Retrieve and process image to be infilled
+        input_image, has_alpha = self.load_image(context)
+
+        # If the input image has no alpha channel, return it
+        if has_alpha is False:
+            return ImageOutput.build(context.images.get_dto(self.image.image_name))
+
+        # Perform Infill action
+        infilled_image = self.infill(input_image)
+
+        # Create ImageDTO for Infilled Image
+        infilled_image_dto = context.images.save(image=infilled_image)
+
+        # Return Infilled Image
+        return ImageOutput.build(infilled_image_dto)
 
 
-def infill_patchmatch(im: Image.Image) -> Image.Image:
-    if im.mode != "RGBA":
-        return im
-
-    # Skip patchmatch if patchmatch isn't available
-    if not PatchMatch.patchmatch_available():
-        return im
-
-    # Patchmatch (note, we may want to expose patch_size? Increasing it significantly impacts performance though)
-    im_patched_np = PatchMatch.inpaint(im.convert("RGB"), ImageOps.invert(im.split()[-1]), patch_size=3)
-    im_patched = Image.fromarray(im_patched_np, mode="RGB")
-    return im_patched
-
-
-def infill_cv2(im: Image.Image) -> Image.Image:
-    return cv2_inpaint(im)
-
-
-def get_tile_images(image: np.ndarray, width=8, height=8):
-    _nrows, _ncols, depth = image.shape
-    _strides = image.strides
-
-    nrows, _m = divmod(_nrows, height)
-    ncols, _n = divmod(_ncols, width)
-    if _m != 0 or _n != 0:
-        return None
-
-    return np.lib.stride_tricks.as_strided(
-        np.ravel(image),
-        shape=(nrows, ncols, height, width, depth),
-        strides=(height * _strides[0], width * _strides[1], *_strides),
-        writeable=False,
-    )
-
-
-def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int] = None) -> Image.Image:
-    # Only fill if there's an alpha layer
-    if im.mode != "RGBA":
-        return im
-
-    a = np.asarray(im, dtype=np.uint8)
-
-    tile_size_tuple = (tile_size, tile_size)
-
-    # Get the image as tiles of a specified size
-    tiles = get_tile_images(a, *tile_size_tuple).copy()
-
-    # Get the mask as tiles
-    tiles_mask = tiles[:, :, :, :, 3]
-
-    # Find any mask tiles with any fully transparent pixels (we will be replacing these later)
-    tmask_shape = tiles_mask.shape
-    tiles_mask = tiles_mask.reshape(math.prod(tiles_mask.shape))
-    n, ny = (math.prod(tmask_shape[0:2])), math.prod(tmask_shape[2:])
-    tiles_mask = tiles_mask > 0
-    tiles_mask = tiles_mask.reshape((n, ny)).all(axis=1)
-
-    # Get RGB tiles in single array and filter by the mask
-    tshape = tiles.shape
-    tiles_all = tiles.reshape((math.prod(tiles.shape[0:2]), *tiles.shape[2:]))
-    filtered_tiles = tiles_all[tiles_mask]
-
-    if len(filtered_tiles) == 0:
-        return im
-
-    # Find all invalid tiles and replace with a random valid tile
-    replace_count = (tiles_mask == False).sum()  # noqa: E712
-    rng = np.random.default_rng(seed=seed)
-    tiles_all[np.logical_not(tiles_mask)] = filtered_tiles[rng.choice(filtered_tiles.shape[0], replace_count), :, :, :]
-
-    # Convert back to an image
-    tiles_all = tiles_all.reshape(tshape)
-    tiles_all = tiles_all.swapaxes(1, 2)
-    st = tiles_all.reshape(
-        (
-            math.prod(tiles_all.shape[0:2]),
-            math.prod(tiles_all.shape[2:4]),
-            tiles_all.shape[4],
-        )
-    )
-    si = Image.fromarray(st, mode="RGBA")
-
-    return si
-
-
-@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class InfillColorInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
+class InfillColorInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image with a solid color"""
 
-    image: ImageField = InputField(description="The image to infill")
     color: ColorField = InputField(
         default=ColorField(r=127, g=127, b=127, a=255),
         description="The color to use to infill",
     )
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
+    def infill(self, image: Image.Image):
         solid_bg = Image.new("RGBA", image.size, self.color.tuple())
         infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
-
         infilled.paste(image, (0, 0), image.split()[-1])
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return infilled
 
 
-@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
-class InfillTileInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.3")
+class InfillTileInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image with tiles of the image"""
 
-    image: ImageField = InputField(description="The image to infill")
     tile_size: int = InputField(default=32, ge=1, description="The tile size (px)")
     seed: int = InputField(
         default=0,
@@ -167,137 +94,74 @@ class InfillTileInvocation(BaseInvocation, WithMetadata):
         description="The seed to use for tile generation (omit for random)",
     )
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        infilled = tile_fill_missing(image.copy(), seed=self.seed, tile_size=self.tile_size)
-        infilled.paste(image, (0, 0), image.split()[-1])
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+    def infill(self, image: Image.Image):
+        output = infill_tile(image, seed=self.seed, tile_size=self.tile_size)
+        return output.infilled
 
 
 @invocation(
-    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0"
+    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2"
 )
-class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
+class InfillPatchMatchInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
-    image: ImageField = InputField(description="The image to infill")
     downscale: float = InputField(default=2.0, gt=0, description="Run patchmatch on downscaled image to speedup infill")
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name).convert("RGBA")
-
+    def infill(self, image: Image.Image):
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
-        infill_image = image.copy()
         width = int(image.width / self.downscale)
         height = int(image.height / self.downscale)
-        infill_image = infill_image.resize(
+
+        infilled = image.resize(
             (width, height),
             resample=resample_mode,
         )
-
-        if PatchMatch.patchmatch_available():
-            infilled = infill_patchmatch(infill_image)
-        else:
-            raise ValueError("PatchMatch is not available on this system")
-
+        infilled = infill_patchmatch(image)
         infilled = infilled.resize(
             (image.width, image.height),
             resample=resample_mode,
         )
-
         infilled.paste(image, (0, 0), mask=image.split()[-1])
-        # image.paste(infilled, (0, 0), mask=image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return infilled
 
 
-@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class LaMaInfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
+class LaMaInfillInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using the LaMa model"""
 
-    image: ImageField = InputField(description="The image to infill")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        infilled = infill_lama(image.copy())
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+    def infill(self, image: Image.Image):
+        lama = LaMA()
+        return lama(image)
 
 
-@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class CV2InfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
+class CV2InfillInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
+    def infill(self, image: Image.Image):
+        return cv2_inpaint(image)
+
+
+# @invocation(
+#     "infill_mosaic", title="Mosaic Infill", tags=["image", "inpaint", "outpaint"], category="inpaint", version="1.0.0"
+# )
+class MosaicInfillInvocation(InfillImageProcessorInvocation):
+    """Infills transparent areas of an image with a mosaic pattern drawing colors from the rest of the image"""
+
     image: ImageField = InputField(description="The image to infill")
+    tile_width: int = InputField(default=64, description="Width of the tile")
+    tile_height: int = InputField(default=64, description="Height of the tile")
+    min_color: ColorField = InputField(
+        default=ColorField(r=0, g=0, b=0, a=255),
+        description="The min threshold for color",
+    )
+    max_color: ColorField = InputField(
+        default=ColorField(r=255, g=255, b=255, a=255),
+        description="The max threshold for color",
+    )
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        infilled = infill_cv2(image.copy())
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+    def infill(self, image: Image.Image):
+        return infill_mosaic(image, (self.tile_width, self.tile_height), self.min_color.tuple(), self.max_color.tuple())

invokeai/app/invocations/ip_adapter.py

@@ -1,44 +1,28 @@
-import os
 from builtins import float
-from typing import List, Union
+from typing import List, Literal, Union
 
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
+from typing_extensions import Self
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    invocation,
-    invocation_output,
-)
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
+from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.model_management.models.base import BaseModelType, ModelType
-from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
-
-
-class IPAdapterModelField(BaseModel):
-    model_name: str = Field(description="Name of the IP-Adapter model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-class CLIPVisionModelField(BaseModel):
-    model_name: str = Field(description="Name of the CLIP Vision image encoder model")
-    base_model: BaseModelType = Field(description="Base model (usually 'Any')")
-
-    model_config = ConfigDict(protected_namespaces=())
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    IPAdapterCheckpointConfig,
+    IPAdapterInvokeAIConfig,
+    ModelType,
+)
 
 
 class IPAdapterField(BaseModel):
     image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
-    ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
-    image_encoder_model: CLIPVisionModelField = Field(description="The name of the CLIP image encoder model.")
+    ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model to use.")
+    image_encoder_model: ModelIdentifierField = Field(description="The name of the CLIP image encoder model.")
     weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
@@ -49,12 +33,12 @@ class IPAdapterField(BaseModel):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v):
+    def validate_ip_adapter_weight(cls, v: float) -> float:
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self):
+    def validate_begin_end_step_percent(self) -> Self:
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
@@ -65,16 +49,27 @@ class IPAdapterOutput(BaseInvocationOutput):
     ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.1")
+CLIP_VISION_MODEL_MAP = {"ViT-H": "ip_adapter_sd_image_encoder", "ViT-G": "ip_adapter_sdxl_image_encoder"}
+
+
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.2.2")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
     # Inputs
-    image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).")
-    ip_adapter_model: IPAdapterModelField = InputField(
-        description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
+    image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).", ui_order=1)
+    ip_adapter_model: ModelIdentifierField = InputField(
+        description="The IP-Adapter model.",
+        title="IP-Adapter Model",
+        input=Input.Direct,
+        ui_order=-1,
+        ui_type=UIType.IPAdapterModel,
+    )
+    clip_vision_model: Literal["ViT-H", "ViT-G"] = InputField(
+        description="CLIP Vision model to use. Overrides model settings. Mandatory for checkpoint models.",
+        default="auto",
+        ui_order=2,
     )
-
     weight: Union[float, List[float]] = InputField(
         default=1, description="The weight given to the IP-Adapter", title="Weight"
     )
@@ -87,40 +82,59 @@ class IPAdapterInvocation(BaseInvocation):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v):
+    def validate_ip_adapter_weight(cls, v: float) -> float:
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self):
+    def validate_begin_end_step_percent(self) -> Self:
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
     def invoke(self, context: InvocationContext) -> IPAdapterOutput:
         # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
-        ip_adapter_info = context.services.model_manager.model_info(
-            self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
-        )
-        # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
-        # directly, and 2) we are reading from disk every time this invocation is called without caching the result.
-        # A better solution would be to store the image encoder model reference in the IP-Adapter model info, but this
-        # is currently messy due to differences between how the model info is generated when installing a model from
-        # disk vs. downloading the model.
-        image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
-            os.path.join(context.services.configuration.get_config().models_path, ip_adapter_info["path"])
-        )
-        image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
-        image_encoder_model = CLIPVisionModelField(
-            model_name=image_encoder_model_name,
-            base_model=BaseModelType.Any,
-        )
+        ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
+        assert isinstance(ip_adapter_info, (IPAdapterInvokeAIConfig, IPAdapterCheckpointConfig))
+
+        if isinstance(ip_adapter_info, IPAdapterInvokeAIConfig):
+            image_encoder_model_id = ip_adapter_info.image_encoder_model_id
+            image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
+        else:
+            image_encoder_model_name = CLIP_VISION_MODEL_MAP[self.clip_vision_model]
+
+        image_encoder_model = self._get_image_encoder(context, image_encoder_model_name)
+
         return IPAdapterOutput(
             ip_adapter=IPAdapterField(
                 image=self.image,
                 ip_adapter_model=self.ip_adapter_model,
-                image_encoder_model=image_encoder_model,
+                image_encoder_model=ModelIdentifierField.from_config(image_encoder_model),
                 weight=self.weight,
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,
             ),
         )
+
+    def _get_image_encoder(self, context: InvocationContext, image_encoder_model_name: str) -> AnyModelConfig:
+        image_encoder_models = context.models.search_by_attrs(
+            name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
+        )
+
+        if not len(image_encoder_models) > 0:
+            context.logger.warning(
+                f"The image encoder required by this IP Adapter ({image_encoder_model_name}) is not installed. \
+                    Downloading and installing now. This may take a while."
+            )
+
+            installer = context._services.model_manager.install
+            job = installer.heuristic_import(f"InvokeAI/{image_encoder_model_name}")
+            installer.wait_for_job(job, timeout=600)  # Wait for up to 10 minutes
+            image_encoder_models = context.models.search_by_attrs(
+                name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
+            )
+
+            if len(image_encoder_models) == 0:
+                context.logger.error("Error while fetching CLIP Vision Image Encoder")
+                assert len(image_encoder_models) == 1
+
+        return image_encoder_models[0]

invokeai/app/invocations/math.py

@@ -5,13 +5,14 @@ from typing import Literal
 import numpy as np
 from pydantic import ValidationInfo, field_validator
 
+from invokeai.app.invocations.fields import FieldDescriptions, InputField
 from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
 
 
-@invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.0")
+@invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.1")
 class AddInvocation(BaseInvocation):
     """Adds two numbers"""
 
@@ -22,7 +23,7 @@ class AddInvocation(BaseInvocation):
         return IntegerOutput(value=self.a + self.b)
 
 
-@invocation("sub", title="Subtract Integers", tags=["math", "subtract"], category="math", version="1.0.0")
+@invocation("sub", title="Subtract Integers", tags=["math", "subtract"], category="math", version="1.0.1")
 class SubtractInvocation(BaseInvocation):
     """Subtracts two numbers"""
 
@@ -33,7 +34,7 @@ class SubtractInvocation(BaseInvocation):
         return IntegerOutput(value=self.a - self.b)
 
 
-@invocation("mul", title="Multiply Integers", tags=["math", "multiply"], category="math", version="1.0.0")
+@invocation("mul", title="Multiply Integers", tags=["math", "multiply"], category="math", version="1.0.1")
 class MultiplyInvocation(BaseInvocation):
     """Multiplies two numbers"""
 
@@ -44,7 +45,7 @@ class MultiplyInvocation(BaseInvocation):
         return IntegerOutput(value=self.a * self.b)
 
 
-@invocation("div", title="Divide Integers", tags=["math", "divide"], category="math", version="1.0.0")
+@invocation("div", title="Divide Integers", tags=["math", "divide"], category="math", version="1.0.1")
 class DivideInvocation(BaseInvocation):
     """Divides two numbers"""
 
@@ -60,7 +61,7 @@ class DivideInvocation(BaseInvocation):
     title="Random Integer",
     tags=["math", "random"],
     category="math",
-    version="1.0.0",
+    version="1.0.1",
     use_cache=False,
 )
 class RandomIntInvocation(BaseInvocation):
@@ -99,7 +100,7 @@ class RandomFloatInvocation(BaseInvocation):
     title="Float To Integer",
     tags=["math", "round", "integer", "float", "convert"],
     category="math",
-    version="1.0.0",
+    version="1.0.1",
 )
 class FloatToIntegerInvocation(BaseInvocation):
     """Rounds a float number to (a multiple of) an integer."""
@@ -121,7 +122,7 @@ class FloatToIntegerInvocation(BaseInvocation):
             return IntegerOutput(value=int(self.value / self.multiple) * self.multiple)
 
 
-@invocation("round_float", title="Round Float", tags=["math", "round"], category="math", version="1.0.0")
+@invocation("round_float", title="Round Float", tags=["math", "round"], category="math", version="1.0.1")
 class RoundInvocation(BaseInvocation):
     """Rounds a float to a specified number of decimal places."""
 
@@ -175,7 +176,7 @@ INTEGER_OPERATIONS_LABELS = {
         "max",
     ],
     category="math",
-    version="1.0.0",
+    version="1.0.1",
 )
 class IntegerMathInvocation(BaseInvocation):
     """Performs integer math."""
@@ -249,7 +250,7 @@ FLOAT_OPERATIONS_LABELS = {
     title="Float Math",
     tags=["math", "float", "add", "subtract", "multiply", "divide", "power", "root", "absolute value", "min", "max"],
     category="math",
-    version="1.0.0",
+    version="1.0.1",
 )
 class FloatMathInvocation(BaseInvocation):
     """Performs floating point math."""

invokeai/app/invocations/metadata.py

@@ -2,23 +2,18 @@ from typing import Any, Literal, Optional, Union
 
 from pydantic import BaseModel, ConfigDict, Field
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
     InputField,
-    InvocationContext,
     MetadataField,
     OutputField,
     UIType,
-    invocation,
-    invocation_output,
 )
-from invokeai.app.invocations.controlnet_image_processors import ControlField
-from invokeai.app.invocations.ip_adapter import IPAdapterModelField
-from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
-from invokeai.app.invocations.primitives import ImageField
-from invokeai.app.invocations.t2i_adapter import T2IAdapterField
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from ...version import __version__
 
@@ -31,7 +26,7 @@ class MetadataItemField(BaseModel):
 class LoRAMetadataField(BaseModel):
     """LoRA Metadata Field"""
 
-    lora: LoRAModelField = Field(description=FieldDescriptions.lora_model)
+    model: ModelIdentifierField = Field(description=FieldDescriptions.lora_model)
     weight: float = Field(description=FieldDescriptions.lora_weight)
 
 
@@ -39,16 +34,42 @@ class IPAdapterMetadataField(BaseModel):
     """IP Adapter Field, minus the CLIP Vision Encoder model"""
 
     image: ImageField = Field(description="The IP-Adapter image prompt.")
-    ip_adapter_model: IPAdapterModelField = Field(
-        description="The IP-Adapter model.",
-    )
-    weight: Union[float, list[float]] = Field(
-        description="The weight given to the IP-Adapter",
-    )
+    ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model.")
+    clip_vision_model: Literal["ViT-H", "ViT-G"] = Field(description="The CLIP Vision model")
+    weight: Union[float, list[float]] = Field(description="The weight given to the IP-Adapter")
     begin_step_percent: float = Field(description="When the IP-Adapter is first applied (% of total steps)")
     end_step_percent: float = Field(description="When the IP-Adapter is last applied (% of total steps)")
 
 
+class T2IAdapterMetadataField(BaseModel):
+    image: ImageField = Field(description="The control image.")
+    processed_image: Optional[ImageField] = Field(default=None, description="The control image, after processing.")
+    t2i_adapter_model: ModelIdentifierField = Field(description="The T2I-Adapter model to use.")
+    weight: Union[float, list[float]] = Field(default=1, description="The weight given to the T2I-Adapter")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the T2I-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the T2I-Adapter is last applied (% of total steps)"
+    )
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+
+
+class ControlNetMetadataField(BaseModel):
+    image: ImageField = Field(description="The control image")
+    processed_image: Optional[ImageField] = Field(default=None, description="The control image, after processing.")
+    control_model: ModelIdentifierField = Field(description="The ControlNet model to use")
+    control_weight: Union[float, list[float]] = Field(default=1, description="The weight given to the ControlNet")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the ControlNet is last applied (% of total steps)"
+    )
+    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+
+
 @invocation_output("metadata_item_output")
 class MetadataItemOutput(BaseInvocationOutput):
     """Metadata Item Output"""
@@ -56,7 +77,7 @@ class MetadataItemOutput(BaseInvocationOutput):
     item: MetadataItemField = OutputField(description="Metadata Item")
 
 
-@invocation("metadata_item", title="Metadata Item", tags=["metadata"], category="metadata", version="1.0.0")
+@invocation("metadata_item", title="Metadata Item", tags=["metadata"], category="metadata", version="1.0.1")
 class MetadataItemInvocation(BaseInvocation):
     """Used to create an arbitrary metadata item. Provide "label" and make a connection to "value" to store that data as the value."""
 
@@ -72,7 +93,7 @@ class MetadataOutput(BaseInvocationOutput):
     metadata: MetadataField = OutputField(description="Metadata Dict")
 
 
-@invocation("metadata", title="Metadata", tags=["metadata"], category="metadata", version="1.0.0")
+@invocation("metadata", title="Metadata", tags=["metadata"], category="metadata", version="1.0.1")
 class MetadataInvocation(BaseInvocation):
     """Takes a MetadataItem or collection of MetadataItems and outputs a MetadataDict."""
 
@@ -93,7 +114,7 @@ class MetadataInvocation(BaseInvocation):
         return MetadataOutput(metadata=MetadataField.model_validate(data))
 
 
-@invocation("merge_metadata", title="Metadata Merge", tags=["metadata"], category="metadata", version="1.0.0")
+@invocation("merge_metadata", title="Metadata Merge", tags=["metadata"], category="metadata", version="1.0.1")
 class MergeMetadataInvocation(BaseInvocation):
     """Merged a collection of MetadataDict into a single MetadataDict."""
 
@@ -112,7 +133,7 @@ GENERATION_MODES = Literal[
 ]
 
 
-@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.0.1")
+@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="2.0.0")
 class CoreMetadataInvocation(BaseInvocation):
     """Collects core generation metadata into a MetadataField"""
 
@@ -138,14 +159,14 @@ class CoreMetadataInvocation(BaseInvocation):
         default=None,
         description="The number of skipped CLIP layers",
     )
-    model: Optional[MainModelField] = InputField(default=None, description="The main model used for inference")
-    controlnets: Optional[list[ControlField]] = InputField(
+    model: Optional[ModelIdentifierField] = InputField(default=None, description="The main model used for inference")
+    controlnets: Optional[list[ControlNetMetadataField]] = InputField(
         default=None, description="The ControlNets used for inference"
     )
     ipAdapters: Optional[list[IPAdapterMetadataField]] = InputField(
         default=None, description="The IP Adapters used for inference"
     )
-    t2iAdapters: Optional[list[T2IAdapterField]] = InputField(
+    t2iAdapters: Optional[list[T2IAdapterMetadataField]] = InputField(
         default=None, description="The IP Adapters used for inference"
     )
     loras: Optional[list[LoRAMetadataField]] = InputField(default=None, description="The LoRAs used for inference")
@@ -157,7 +178,7 @@ class CoreMetadataInvocation(BaseInvocation):
         default=None,
         description="The name of the initial image",
     )
-    vae: Optional[VAEModelField] = InputField(
+    vae: Optional[ModelIdentifierField] = InputField(
         default=None,
         description="The VAE used for decoding, if the main model's default was not used",
     )
@@ -188,7 +209,7 @@ class CoreMetadataInvocation(BaseInvocation):
     )
 
     # SDXL Refiner
-    refiner_model: Optional[MainModelField] = InputField(
+    refiner_model: Optional[ModelIdentifierField] = InputField(
         default=None,
         description="The SDXL Refiner model used",
     )
@@ -220,10 +241,9 @@ class CoreMetadataInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> MetadataOutput:
         """Collects and outputs a CoreMetadata object"""
 
-        return MetadataOutput(
-            metadata=MetadataField.model_validate(
-                self.model_dump(exclude_none=True, exclude={"id", "type", "is_intermediate", "use_cache"})
-            )
-        )
+        as_dict = self.model_dump(exclude_none=True, exclude={"id", "type", "is_intermediate", "use_cache"})
+        as_dict["app_version"] = __version__
+
+        return MetadataOutput(metadata=MetadataField.model_validate(as_dict))
 
     model_config = ConfigDict(extra="allow")