Path->str in call to expand_prompts

- Previous PR to truncate long filenames won't work on windows due to
lack of support for os.pathconf(). This works around the limitation by
hardcoding the value for PC_NAME_MAX when pathconf is unavailable.
- The `multiprocessing` send() and recv() methods weren't working
properly on Windows due to issues involving `utf-8` encoding and
pickling/unpickling. Changed these calls to `send_bytes()` and
`recv_bytes()` , which seems to fix the issue.

Not fully tested on Windows since I lack a GPU machine to test on, but
is working on CPU.

.coveragerc

@@ -0,0 +1,6 @@
+[run]
+omit='.env/*'
+source='.'
+
+[report]
+show_missing = true

.dockerignore

@@ -1,9 +1,25 @@
+# use this file as a whitelist
 *
 !invokeai
+!ldm
 !pyproject.toml
-!docker/docker-entrypoint.sh
-!LICENSE
 
-**/node_modules
-**/__pycache__
-**/*.egg-info
+# Guard against pulling in any models that might exist in the directory tree
+**/*.pt*
+**/*.ckpt
+
+# ignore frontend but whitelist dist
+invokeai/frontend/
+!invokeai/frontend/dist/
+
+# ignore invokeai/assets but whitelist invokeai/assets/web
+invokeai/assets/
+!invokeai/assets/web/
+
+# Byte-compiled / optimized / DLL files
+**/__pycache__/
+**/*.py[cod]
+
+# Distribution / packaging
+*.egg-info/
+*.egg

.editorconfig

@@ -1,5 +1,8 @@
+root = true
+
 # All files
 [*]
+max_line_length = 80
 charset = utf-8
 end_of_line = lf
 indent_size = 2
@@ -10,3 +13,18 @@ trim_trailing_whitespace = true
 # Python
 [*.py]
 indent_size = 4
+max_line_length = 120
+
+# css
+[*.css]
+indent_size = 4
+
+# flake8
+[.flake8]
+indent_size = 4
+
+# Markdown MkDocs
+[docs/**/*.md]
+max_line_length = 80
+indent_size = 4
+indent_style = unset

.flake8

@@ -0,0 +1,37 @@
+[flake8]
+max-line-length = 120
+extend-ignore =
+    # See https://github.com/PyCQA/pycodestyle/issues/373
+    E203,
+    # use Bugbear's B950 instead
+    E501,
+    # from black repo https://github.com/psf/black/blob/main/.flake8
+    E266, W503, B907
+extend-select =
+    # Bugbear line length
+    B950
+extend-exclude =
+    scripts/orig_scripts/*
+    ldm/models/*
+    ldm/modules/*
+    ldm/data/*
+    ldm/generate.py
+    ldm/util.py
+    ldm/simplet2i.py
+per-file-ignores =
+    # B950 line too long
+    # W605 invalid escape sequence
+    # F841 assigned to but never used
+    # F401 imported but unused
+    tests/test_prompt_parser.py: B950, W605, F401
+    tests/test_textual_inversion.py: F841, B950
+    # B023 Function definition does not bind loop variable
+    scripts/legacy_api.py: F401, B950, B023, F841
+    ldm/invoke/__init__.py: F401
+    # B010 Do not call setattr with a constant attribute value
+    ldm/invoke/server_legacy.py: B010
+# =====================
+# flake-quote settings:
+# =====================
+# Set this to match black style:
+inline-quotes = double

.git-blame-ignore-revs

@@ -1 +0,0 @@
-b3dccfaeb636599c02effc377cdd8a87d658256c

.github/CODEOWNERS

@@ -1,34 +1,61 @@
 # continuous integration
-/.github/workflows/  @lstein @blessedcoolant
+/.github/workflows/ @mauwii @lstein @blessedcoolant
 
 # documentation
-/docs/ @lstein @blessedcoolant @hipsterusername
-/mkdocs.yml @lstein  @blessedcoolant
-
-# nodes
-/invokeai/app/ @Kyle0654 @blessedcoolant @psychedelicious @brandonrising 
+/docs/ @lstein @mauwii @blessedcoolant
+mkdocs.yml @mauwii @lstein
 
 # installation and configuration
-/pyproject.toml  @lstein @blessedcoolant
-/docker/  @lstein @blessedcoolant
-/scripts/ @ebr @lstein
-/installer/ @lstein @ebr
-/invokeai/assets @lstein @ebr
-/invokeai/configs @lstein
-/invokeai/version @lstein @blessedcoolant
+/pyproject.toml @mauwii @lstein @ebr
+/docker/ @mauwii
+/scripts/ @ebr @lstein @blessedcoolant
+/installer/ @ebr @lstein 
+ldm/invoke/config @lstein @ebr
+invokeai/assets @lstein @blessedcoolant
+invokeai/configs @lstein @ebr  @blessedcoolant
+/ldm/invoke/_version.py @lstein @blessedcoolant
 
 # web ui
-/invokeai/frontend @blessedcoolant @psychedelicious @lstein @maryhipp
-/invokeai/backend @blessedcoolant @psychedelicious @lstein @maryhipp
+/invokeai/frontend @blessedcoolant @psychedelicious
+/invokeai/backend @blessedcoolant @psychedelicious
 
-# generation, model management, postprocessing
-/invokeai/backend  @damian0815 @lstein @blessedcoolant @gregghelt2 @StAlKeR7779 @brandonrising
+# generation and model management
+/ldm/*.py @lstein @blessedcoolant
+/ldm/generate.py @lstein @keturn
+/ldm/invoke/args.py @lstein @blessedcoolant
+/ldm/invoke/ckpt* @lstein @blessedcoolant
+/ldm/invoke/ckpt_generator @lstein @blessedcoolant
+/ldm/invoke/CLI.py @lstein @blessedcoolant
+/ldm/invoke/config @lstein @ebr @mauwii @blessedcoolant
+/ldm/invoke/generator @keturn @damian0815
+/ldm/invoke/globals.py @lstein @blessedcoolant 
+/ldm/invoke/merge_diffusers.py @lstein @blessedcoolant
+/ldm/invoke/model_manager.py @lstein @blessedcoolant
+/ldm/invoke/txt2mask.py @lstein @blessedcoolant
+/ldm/invoke/patchmatch.py @Kyle0654 @lstein
+/ldm/invoke/restoration @lstein @blessedcoolant
 
-# front ends
-/invokeai/frontend/CLI @lstein
-/invokeai/frontend/install @lstein @ebr  
-/invokeai/frontend/merge @lstein @blessedcoolant 
-/invokeai/frontend/training @lstein @blessedcoolant 
-/invokeai/frontend/web @psychedelicious @blessedcoolant @maryhipp 
+# attention, textual inversion, model configuration
+/ldm/models @damian0815 @keturn @blessedcoolant
+/ldm/modules/textual_inversion_manager.py @lstein @blessedcoolant
+/ldm/modules/attention.py @damian0815 @keturn
+/ldm/modules/diffusionmodules @damian0815 @keturn
+/ldm/modules/distributions @damian0815 @keturn
+/ldm/modules/ema.py  @damian0815 @keturn
+/ldm/modules/embedding_manager.py @lstein
+/ldm/modules/encoders @damian0815 @keturn
+/ldm/modules/image_degradation @damian0815 @keturn
+/ldm/modules/losses  @damian0815 @keturn
+/ldm/modules/x_transformer.py @damian0815 @keturn
+
+# Nodes
+apps/ @Kyle0654 @jpphoto
+
+# legacy REST API
+# these are dead code
+#/ldm/invoke/pngwriter.py @CapableWeb
+#/ldm/invoke/server_legacy.py @CapableWeb
+#/scripts/legacy_api.py @CapableWeb
+#/tests/legacy_tests.sh @CapableWeb
 
 

.github/ISSUE_TEMPLATE/BUG_REPORT.yml

@@ -65,16 +65,6 @@ body:
       placeholder: 8GB
     validations:
       required: false
-      
-  - type: input
-    id: version-number
-    attributes:
-      label: What version did you experience this issue on?
-      description: |
-        Please share the version of Invoke AI that you experienced the issue on. If this is not the latest version, please update first to confirm the issue still exists. If you are testing main, please include the commit hash instead.
-      placeholder: X.X.X
-    validations:
-      required: true
 
   - type: textarea
     id: what-happened

.github/stale.yaml

@@ -1,19 +0,0 @@
-# Number of days of inactivity before an issue becomes stale
-daysUntilStale: 28
-# Number of days of inactivity before a stale issue is closed
-daysUntilClose: 14
-# Issues with these labels will never be considered stale
-exemptLabels:
-  - pinned
-  - security
-# Label to use when marking an issue as stale
-staleLabel: stale
-# Comment to post when marking an issue as stale. Set to `false` to disable
-markComment: >
-  This issue has been automatically marked as stale because it has not had
-  recent activity. It will be closed if no further activity occurs. Please
-  update the ticket if this is still a problem on the latest release.
-# Comment to post when closing a stale issue. Set to `false` to disable
-closeComment: >
-  Due to inactivity, this issue has been automatically closed. If this is
-  still a problem on the latest release, please recreate the issue.

.github/workflows/build-container.yml

@@ -3,20 +3,19 @@ on:
   push:
     branches:
       - 'main'
+      - 'update/ci/docker/*'
+      - 'update/docker/*'
     paths:
       - 'pyproject.toml'
-      - '.dockerignore'
-      - 'invokeai/**'
+      - 'ldm/**'
+      - 'invokeai/backend/**'
+      - 'invokeai/configs/**'
+      - 'invokeai/frontend/dist/**'
       - 'docker/Dockerfile'
-      - 'docker/docker-entrypoint.sh'
-      - 'workflows/build-container.yml'
     tags:
-      - 'v*'
+      - 'v*.*.*'
   workflow_dispatch:
 
-permissions:
-  contents: write
-  packages: write
 
 jobs:
   docker:
@@ -24,27 +23,23 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        gpu-driver:
-        - cuda
-        - cpu
-        - rocm
+        flavor:
+          - amd
+          - cuda
+          - cpu
+        include:
+          - flavor: amd
+            pip-extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
+          - flavor: cuda
+            pip-extra-index-url: ''
+          - flavor: cpu
+            pip-extra-index-url: 'https://download.pytorch.org/whl/cpu'
     runs-on: ubuntu-latest
-    name: ${{ matrix.gpu-driver }}
+    name: ${{ matrix.flavor }}
     env:
-      # torch/arm64 does not support GPU currently, so arm64 builds
-      # would not be GPU-accelerated.
-      # re-enable arm64 if there is sufficient demand.
-      # PLATFORMS: 'linux/amd64,linux/arm64'
-      PLATFORMS: 'linux/amd64'
+      PLATFORMS: 'linux/amd64,linux/arm64'
+      DOCKERFILE: 'docker/Dockerfile'
     steps:
-      - name: Free up more disk space on the runner
-        # https://github.com/actions/runner-images/issues/2840#issuecomment-1284059930
-        run: |
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
-          sudo swapoff /mnt/swapfile
-          sudo rm -rf /mnt/swapfile
-
       - name: Checkout
         uses: actions/checkout@v3
 
@@ -55,17 +50,17 @@ jobs:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           images: |
             ghcr.io/${{ github.repository }}
-            ${{ env.DOCKERHUB_REPOSITORY }}
+            ${{ vars.DOCKERHUB_REPOSITORY }}
           tags: |
             type=ref,event=branch
             type=ref,event=tag
-            type=pep440,pattern={{version}}
-            type=pep440,pattern={{major}}.{{minor}}
-            type=pep440,pattern={{major}}
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{major}}
             type=sha,enable=true,prefix=sha-,format=short
           flavor: |
-            latest=${{ matrix.gpu-driver == 'cuda' && github.ref == 'refs/heads/main' }}
-            suffix=-${{ matrix.gpu-driver }},onlatest=false
+            latest=${{ matrix.flavor == 'cuda' && github.ref == 'refs/heads/main' }}
+            suffix=-${{ matrix.flavor }},onlatest=false
 
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v2
@@ -83,33 +78,34 @@ jobs:
           username: ${{ github.repository_owner }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
-      # - name: Login to Docker Hub
-      #   if: github.event_name != 'pull_request' && vars.DOCKERHUB_REPOSITORY != ''
-      #   uses: docker/login-action@v2
-      #   with:
-      #     username: ${{ secrets.DOCKERHUB_USERNAME }}
-      #     password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Login to Docker Hub
+        if: github.event_name != 'pull_request' && vars.DOCKERHUB_REPOSITORY != ''
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Build container
         id: docker_build
         uses: docker/build-push-action@v4
         with:
           context: .
-          file: docker/Dockerfile
+          file: ${{ env.DOCKERFILE }}
           platforms: ${{ env.PLATFORMS }}
-          push: ${{ github.ref == 'refs/heads/main' || github.ref_type == 'tag' }}
+          push: ${{ github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' }}
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
+          build-args: PIP_EXTRA_INDEX_URL=${{ matrix.pip-extra-index-url }}
           cache-from: |
-            type=gha,scope=${{ github.ref_name }}-${{ matrix.gpu-driver }}
-            type=gha,scope=main-${{ matrix.gpu-driver }}
-          cache-to: type=gha,mode=max,scope=${{ github.ref_name }}-${{ matrix.gpu-driver }}
+            type=gha,scope=${{ github.ref_name }}-${{ matrix.flavor }}
+            type=gha,scope=main-${{ matrix.flavor }}
+          cache-to: type=gha,mode=max,scope=${{ github.ref_name }}-${{ matrix.flavor }}
 
-      # - name: Docker Hub Description
-      #   if: github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' && vars.DOCKERHUB_REPOSITORY != ''
-      #   uses: peter-evans/dockerhub-description@v3
-      #   with:
-      #     username: ${{ secrets.DOCKERHUB_USERNAME }}
-      #     password: ${{ secrets.DOCKERHUB_TOKEN }}
-      #     repository: ${{ vars.DOCKERHUB_REPOSITORY }}
-      #     short-description: ${{ github.event.repository.description }}
+      - name: Docker Hub Description
+        if: github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' && vars.DOCKERHUB_REPOSITORY != ''
+        uses: peter-evans/dockerhub-description@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          repository: ${{ vars.DOCKERHUB_REPOSITORY }}
+          short-description: ${{ github.event.repository.description }}

.github/workflows/close-inactive-issues.yml

@@ -1,27 +0,0 @@
-name: Close inactive issues
-on:
-  schedule:
-    - cron: "00 6 * * *"
-
-env:
-  DAYS_BEFORE_ISSUE_STALE: 14
-  DAYS_BEFORE_ISSUE_CLOSE: 28
-
-jobs:
-  close-issues:
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-      pull-requests: write
-    steps:
-      - uses: actions/stale@v5
-        with:
-          days-before-issue-stale: ${{ env.DAYS_BEFORE_ISSUE_STALE }}
-          days-before-issue-close: ${{ env.DAYS_BEFORE_ISSUE_CLOSE }}
-          stale-issue-label: "Inactive Issue"
-          stale-issue-message: "There has been no activity in this issue for ${{ env.DAYS_BEFORE_ISSUE_STALE }} days. If this issue is still being experienced, please reply with an updated confirmation that the issue is still being experienced with the latest release."
-          close-issue-message: "Due to inactivity, this issue was automatically closed. If you are still experiencing the issue, please recreate the issue."
-          days-before-pr-stale: -1
-          days-before-pr-close: -1
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-          operations-per-run: 500

.github/workflows/lint-frontend.yml

@@ -3,22 +3,14 @@ name: Lint frontend
 on:
   pull_request:
     paths:
-      - 'invokeai/frontend/web/**'
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
+      - 'invokeai/frontend/**'
   push:
-    branches:
-      - 'main'
     paths:
-      - 'invokeai/frontend/web/**'
-  merge_group:
-  workflow_dispatch:
+      - 'invokeai/frontend/**'
 
 defaults:
   run:
-    working-directory: invokeai/frontend/web
+    working-directory: invokeai/frontend
 
 jobs:
   lint-frontend:
@@ -31,7 +23,7 @@ jobs:
           node-version: '18'
       - uses: actions/checkout@v3
       - run: 'yarn install --frozen-lockfile'
-      - run: 'yarn run lint:tsc'
-      - run: 'yarn run lint:madge'
-      - run: 'yarn run lint:eslint'
-      - run: 'yarn run lint:prettier'
+      - run: 'yarn tsc'
+      - run: 'yarn run madge'
+      - run: 'yarn run lint --max-warnings=0'
+      - run: 'yarn run prettier --check'

.github/workflows/mkdocs-material.yml

@@ -2,10 +2,8 @@ name: mkdocs-material
 on:
   push:
     branches:
-      - 'refs/heads/v2.3'
-
-permissions:
-    contents: write
+      - 'main'
+      - 'development'
 
 jobs:
   mkdocs-material:
@@ -43,7 +41,7 @@ jobs:
             --verbose
 
       - name: deploy to gh-pages
-        if: ${{ github.ref == 'refs/heads/v2.3' }}
+        if: ${{ github.ref == 'refs/heads/main' }}
         run: |
           python -m \
             mkdocs gh-deploy \

.github/workflows/pypi-release.yml

@@ -3,7 +3,7 @@ name: PyPI Release
 on:
   push:
     paths:
-      - 'invokeai/version/invokeai_version.py'
+      - 'ldm/invoke/_version.py'
   workflow_dispatch:
 
 jobs:

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

@@ -1,17 +1,12 @@
 name: Test invoke.py pip
-
-# This is a dummy stand-in for the actual tests
-# we don't need to run python tests on non-Python changes
-# But PRs require passing tests to be mergeable
-
 on:
   pull_request:
-    paths:
-      - '**'
-      - '!pyproject.toml'
-      - '!invokeai/**'
-      - '!tests/**'
-      - 'invokeai/frontend/web/**'
+    paths-ignore:
+      - 'pyproject.toml'
+      - 'ldm/**'
+      - 'invokeai/backend/**'
+      - 'invokeai/configs/**'
+      - 'invokeai/frontend/dist/**'
   merge_group:
   workflow_dispatch:
 
@@ -25,26 +20,48 @@ jobs:
     strategy:
       matrix:
         python-version:
+          # - '3.9'
           - '3.10'
         pytorch:
+          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
+          # - windows-cuda-11_6
+          # - windows-cuda-11_7
         include:
+          # - pytorch: linux-cuda-11_6
+          #   os: ubuntu-22.04
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $GITHUB_ENV
           - 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
+          # - pytorch: windows-cuda-11_6
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_7
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
+          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     steps:
-      - name: skip
-        run: echo "no build required"
+      - run: 'echo "No build required"'

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

@@ -5,14 +5,17 @@ on:
       - 'main'
     paths:
       - 'pyproject.toml'
-      - 'invokeai/**'
-      - '!invokeai/frontend/web/**'
+      - 'ldm/**'
+      - 'invokeai/backend/**'
+      - 'invokeai/configs/**'
+      - 'invokeai/frontend/dist/**'
   pull_request:
     paths:
       - 'pyproject.toml'
-      - 'invokeai/**'
-      - 'tests/**'
-      - '!invokeai/frontend/web/**'
+      - 'ldm/**'
+      - 'invokeai/backend/**'
+      - 'invokeai/configs/**'
+      - 'invokeai/frontend/dist/**'
     types:
       - 'ready_for_review'
       - 'opened'
@@ -33,12 +36,19 @@ jobs:
           # - '3.9'
           - '3.10'
         pytorch:
+          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
+          # - windows-cuda-11_6
+          # - windows-cuda-11_7
         include:
+          # - pytorch: linux-cuda-11_6
+          #   os: ubuntu-22.04
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $GITHUB_ENV
           - pytorch: linux-cuda-11_7
             os: ubuntu-22.04
             github-env: $GITHUB_ENV
@@ -56,6 +66,14 @@ jobs:
           - pytorch: windows-cpu
             os: windows-2022
             github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_6
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_7
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
+          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     env:
@@ -66,6 +84,11 @@ jobs:
         uses: actions/checkout@v3
 
       - name: set test prompt to main branch validation
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> ${{ matrix.github-env }}
+
+      - name: set test prompt to Pull Request validation
+        if: ${{ github.ref != 'refs/heads/main' }}
         run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
 
       - name: setup python
@@ -86,38 +109,40 @@ jobs:
         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: set INVOKEAI_OUTDIR
+        run: >
+          python -c
+          "import os;from ldm.invoke.globals import Globals;OUTDIR=os.path.join(Globals.root,str('outputs'));print(f'INVOKEAI_OUTDIR={OUTDIR}')"
+          >> ${{ matrix.github-env }}
 
-      # - 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: run invokeai-configure
+        id: run-preload-models
+        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: Archive results
-      #   env:
-      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-      #   uses: actions/upload-artifact@v3
-      #   with:
-      #     name: results
-      #     path: ${{ env.INVOKEAI_OUTDIR }}
+      - 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
+        run: >
+          invokeai
+          --no-patchmatch
+          --no-nsfw_checker
+          --from_file ${{ env.TEST_PROMPTS }}
+          --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+
+      - name: Archive results
+        id: archive-results
+        uses: actions/upload-artifact@v3
+        with:
+          name: results
+          path: ${{ env.INVOKEAI_OUTDIR }}

.gitignore

@@ -9,8 +9,6 @@ models/ldm/stable-diffusion-v1/model.ckpt
 configs/models.user.yaml
 config/models.user.yml
 invokeai.init
-.version
-.last_model
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -34,7 +32,7 @@ __pycache__/
 .Python
 build/
 develop-eggs/
-# dist/
+dist/
 downloads/
 eggs/
 .eggs/
@@ -65,7 +63,6 @@ pip-delete-this-directory.txt
 htmlcov/
 .tox/
 .nox/
-.coveragerc
 .coverage
 .coverage.*
 .cache
@@ -76,10 +73,8 @@ cov.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.pytest.ini
 cover/
 junit/
-notes/
 
 # Translations
 *.mo
@@ -202,11 +197,8 @@ checkpoints
 # If it's a Mac
 .DS_Store
 
-invokeai/frontend/yarn.lock
-invokeai/frontend/node_modules
-
 # Let the frontend manage its own gitignore
-!invokeai/frontend/web/*
+!invokeai/frontend/*
 
 # Scratch folder
 .scratch/
@@ -221,6 +213,11 @@ gfpgan/
 # config file (will be created by installer)
 configs/models.yaml
 
+# weights (will be created by installer)
+models/ldm/stable-diffusion-v1/*.ckpt
+models/clipseg
+models/gfpgan
+
 # ignore initfile
 .invokeai
 
@@ -235,3 +232,6 @@ installer/install.bat
 installer/install.sh
 installer/update.bat
 installer/update.sh
+
+# no longer stored in source directory
+models

.pre-commit-config.yaml

@@ -0,0 +1,41 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/psf/black
+    rev: 23.1.0
+    hooks:
+      - id: black
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+
+  - repo: https://github.com/PyCQA/flake8
+    rev: 6.0.0
+    hooks:
+      - id: flake8
+        additional_dependencies:
+          - flake8-black
+          - flake8-bugbear
+          - flake8-comprehensions
+          - flake8-simplify
+
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: 'v3.0.0-alpha.4'
+    hooks:
+      - id: prettier
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-executables-have-shebangs
+      - id: check-shebang-scripts-are-executable
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: check-toml
+      - id: end-of-file-fixer
+      - id: no-commit-to-branch
+        args: ['--branch', 'main']
+      - id: trailing-whitespace

.prettierignore

@@ -0,0 +1,14 @@
+invokeai/frontend/.husky
+invokeai/frontend/patches
+
+# Ignore artifacts:
+build
+coverage
+static
+invokeai/frontend/dist
+
+# Ignore all HTML files:
+*.html
+
+# Ignore deprecated docs
+docs/installation/deprecated_documentation

.prettierrc.yaml

@@ -1,9 +1,9 @@
-endOfLine: lf
-tabWidth: 2
-useTabs: false
-singleQuote: true
-quoteProps: as-needed
 embeddedLanguageFormatting: auto
+endOfLine: lf
+singleQuote: true
+semi: true
+trailingComma: es5
+useTabs: false
 overrides:
   - files: '*.md'
     options:
@@ -11,3 +11,9 @@ overrides:
       printWidth: 80
       parser: markdown
       cursorOffset: -1
+  - files: docs/**/*.md
+    options:
+      tabWidth: 4
+  - files: 'invokeai/frontend/public/locales/*.json'
+    options:
+      tabWidth: 4

.pytest.ini

@@ -0,0 +1,5 @@
+[pytest]
+DJANGO_SETTINGS_MODULE = webtas.settings
+; python_files = tests.py test_*.py *_tests.py
+
+addopts = --cov=. --cov-config=.coveragerc --cov-report xml:cov.xml

LICENSE

@@ -1,176 +1,21 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
+MIT License
 
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+Copyright (c) 2022 InvokeAI Team
 
-   1. Definitions.
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
 
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
 
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,11 +1,8 @@
 <div align="center">
 
-![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/1a917d94-e099-4fa1-a70f-7dd8d0691018)
-
-# Invoke AI - Generative AI for Professional Creatives
-## Professional Creative Tools for Stable Diffusion, Custom-Trained Models, and more. 
-  To learn more about Invoke AI, get started instantly, or implement our Business solutions, visit [invoke.ai](https://invoke.ai)
+![project logo](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/invoke_ai_banner.png)
 
+# InvokeAI: A Stable Diffusion Toolkit
 
 [![discord badge]][discord link]
 
@@ -36,32 +33,13 @@
 
 </div>
 
-_**Note: This is an alpha release. Bugs are expected and not all
-features are fully implemented. Please use the GitHub [Issues
-pages](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen)
-to report unexpected problems. Also note that InvokeAI root directory
-which contains models, outputs and configuration files, has changed
-between the 2.x and 3.x release. If you wish to use your v2.3 root
-directory with v3.0, please follow the directions in [Migrating a 2.3
-root directory to 3.0](#migrating-to-3).**_
+InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
 
-InvokeAI is a leading creative engine built to empower professionals
-and enthusiasts alike. Generate and create stunning visual media using
-the latest AI-driven technologies. InvokeAI offers an industry leading
-Web Interface, interactive Command Line Interface, and also serves as
-the foundation for multiple commercial products.
+**Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
 
-**Quick links**: [[How to
-  Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a
-  href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a
-  href="https://invoke-ai.github.io/InvokeAI/">Documentation and
-  Tutorials</a>] [<a
-  href="https://github.com/invoke-ai/InvokeAI/">Code and
-  Downloads</a>] [<a
-  href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>]
-  [<a
-  href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion,
-  Ideas & Q&A</a>]
+_Note: InvokeAI is rapidly evolving. Please use the
+[Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
+requests. Be sure to use the provided templates. They will help us diagnose issues faster._
 
 <div align="center">
 
@@ -71,30 +49,22 @@ the foundation for multiple commercial products.
 
 ## Table of Contents
 
-Table of Contents 📝
+1. [Quick Start](#getting-started-with-invokeai)
+2. [Installation](#detailed-installation-instructions)
+3. [Hardware Requirements](#hardware-requirements)
+4. [Features](#features)
+5. [Latest Changes](#latest-changes)
+6. [Troubleshooting](#troubleshooting)
+7. [Contributing](#contributing)
+8. [Contributors](#contributors)
+9. [Support](#support)
+10. [Further Reading](#further-reading)
 
-**Getting Started**
-1. 🏁 [Quick Start](#quick-start) 
-3. 🖥️ [Hardware Requirements](#hardware-requirements) 
-
-**More About Invoke**
-1. 🌟 [Features](#features) 
-2. 📣 [Latest Changes](#latest-changes) 
-3. 🛠️ [Troubleshooting](#troubleshooting) 
-
-**Supporting the Project**
-1. 🤝 [Contributing](#contributing) 
-2. 👥 [Contributors](#contributors) 
-3. 💕 [Support](#support) 
-
-## Quick Start
+## Getting Started with InvokeAI
 
 For full installation and upgrade instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
 
-If upgrading from version 2.3, please read [Migrating a 2.3 root
-directory to 3.0](#migrating-to-3) first.
-
 ### Automatic Installer (suggested for 1st time users)
 
 1. Go to the bottom of the [Latest Release Page](https://github.com/invoke-ai/InvokeAI/releases/latest)
@@ -103,8 +73,9 @@ directory to 3.0](#migrating-to-3) first.
 
 3. Unzip the file.
 
-4. **Windows:** double-click on the `install.bat` script. **macOS:** Open a Terminal window, drag the file `install.sh` from Finder
-into the Terminal, and press return. **Linux:** run `install.sh`.
+4. If you are on Windows, double-click on the `install.bat` script. On
+macOS, open a Terminal window, drag the file `install.sh` from Finder
+into the Terminal, and press return. On Linux, run `install.sh`.
 
 5. You'll be asked to confirm the location of the folder in which
 to install InvokeAI and its image generation model files. Pick a
@@ -113,7 +84,7 @@ installing lots of models.
 
 6. Wait while the installer does its thing. After installing the software,
 the installer will launch a script that lets you configure InvokeAI and
-select a set of starting image generation models.
+select a set of starting image generaiton models.
 
 7. Find the folder that InvokeAI was installed into (it is not the
 same as the unpacked zip file directory!) The default location of this
@@ -130,12 +101,10 @@ and go to http://localhost:9090.
 
 10. Type `banana sushi` in the box on the top left and click `Invoke`
 
-### Command-Line Installation (for developers and users familiar with Terminals)
+### Command-Line Installation (for users familiar with Terminals)
 
-You must have Python 3.9 or 3.10 installed on your machine. Earlier or
-later versions are not supported.
-Node.js also needs to be installed along with yarn (can be installed with
-the command `npm install -g yarn` if needed)
+You must have Python 3.9 or 3.10 installed on your machine. Earlier or later versions are
+not supported.
 
 1. Open a command-line window on your machine. The PowerShell is recommended for Windows.
 2. Create a directory to install InvokeAI into. You'll need at least 15 GB of free space:
@@ -170,7 +139,7 @@ the command `npm install -g yarn` if needed)
     _For Windows/Linux with an NVIDIA GPU:_
 
     ```terminal
-    pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+    pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
     ```
 
     _For Linux with an AMD GPU:_
@@ -179,11 +148,6 @@ the command `npm install -g yarn` if needed)
     pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
     ```
 
-    _For non-GPU systems:_
-    ```terminal
-    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
-    ``` 
-
     _For Macintoshes, either Intel or M1/M2:_
 
     ```sh
@@ -199,23 +163,16 @@ the command `npm install -g yarn` if needed)
 7. Launch the web server (do it every time you run InvokeAI):
 
     ```terminal
-    invokeai-web
+    invokeai --web
     ```
 
-8. Build Node.js assets
-
-  ```terminal
-  cd invokeai/frontend/web/
-  yarn vite build
-  ```
-
-9. Point your browser to http://localhost:9090 to bring up the web interface.
-10. Type `banana sushi` in the box on the top left and click `Invoke`.
+8. Point your browser to http://localhost:9090 to bring up the web interface.
+9. Type `banana sushi` in the box on the top left and click `Invoke`.
 
 Be sure to activate the virtual environment each time before re-launching InvokeAI,
 using `source .venv/bin/activate` or `.venv\Scripts\activate`.
 
-## Detailed Installation Instructions
+### Detailed Installation Instructions
 
 This fork is supported across Linux, Windows and Macintosh. Linux
 users can use either an Nvidia-based card (with CUDA support) or an
@@ -223,87 +180,6 @@ AMD card (using the ROCm driver). For full installation and upgrade
 instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_SOURCE/)
 
-<a name="migrating-to-3"></a>
-### Migrating a v2.3 InvokeAI root directory
-
-The InvokeAI root directory is where the InvokeAI startup file,
-installed models, and generated images are stored. It is ordinarily
-named `invokeai` and located in your home directory. The contents and
-layout of this directory has changed between versions 2.3 and 3.0 and
-cannot be used directly.
-
-We currently recommend that you use the installer to create a new root
-directory named differently from the 2.3 one, e.g. `invokeai-3` and
-then use a migration script to copy your 2.3 models into the new
-location. However, if you choose, you can upgrade this directory in
-place.  This section gives both recipes.
-
-#### Creating a new root directory and migrating old models
-
-This is the safer recipe because it leaves your old root directory in
-place to fall back on.
-
-1. Follow the instructions above to create and install InvokeAI in a
-directory that has a different name from the 2.3 invokeai directory.
-In this example, we will use "invokeai-3"
-
-2. When you are prompted to select models to install, select a minimal
-set of models, such as stable-diffusion-v1.5 only.
-
-3. After installation is complete launch `invokeai.sh` (Linux/Mac) or
-`invokeai.bat` and select option 8 "Open the developers console". This
-will take you to the command line.
-
-4. Issue the command `invokeai-migrate3 --from /path/to/v2.3-root --to
-/path/to/invokeai-3-root`. Provide the correct `--from` and `--to`
-paths for your v2.3 and v3.0 root directories respectively.
-
-This will copy and convert your old models from 2.3 format to 3.0
-format and create a new `models` directory in the 3.0 directory. The
-old models directory (which contains the models selected at install
-time) will be renamed `models.orig` and can be deleted once you have
-confirmed that the migration was successful.
-
-#### Migrating in place
-
-For the adventurous, you may do an in-place upgrade from 2.3 to 3.0
-without touching the command line. The recipe is as follows>
-
-1. Launch the InvokeAI launcher script in your current v2.3 root directory.
-
-2. Select option [9] "Update InvokeAI" to bring up the updater dialog.
-
-3a. During the alpha release phase, select option [3] and manually
-enter the tag name `v3.0.0+a2`.
-
-3b. Once 3.0 is released, select option [1] to upgrade to the latest release.
-
-4. Once the upgrade is finished you will be returned to the launcher
-menu. Select option [7] "Re-run the configure script to fix a broken
-install or to complete a major upgrade".
-
-This will run the configure script against the v2.3 directory and
-update it to the 3.0 format. The following files will be replaced:
-
-  - The invokeai.init file, replaced by invokeai.yaml
-  - The models directory
-  - The configs/models.yaml model index
-  
-The original versions of these files will be saved with the suffix
-".orig" appended to the end. Once you have confirmed that the upgrade
-worked, you can safely remove these files. Alternatively you can
-restore a working v2.3 directory by removing the new files and
-restoring the ".orig" files' original names.
-
-#### Migration Caveats
-
-The migration script will migrate your invokeai settings and models,
-including textual inversion models, LoRAs and merges that you may have
-installed previously. However it does **not** migrate the generated
-images stored in your 2.3-format outputs directory. The released
-version of 3.0 is expected to have an interface for importing an
-entire directory of image files as a batch.
-
 ## Hardware Requirements
 
 InvokeAI is supported across Linux, Windows and macOS. Linux
@@ -322,9 +198,13 @@ We do not recommend the GTX 1650 or 1660 series video cards. They are
 unable to run in half-precision mode and do not have sufficient VRAM
 to render 512x512 images.
 
-**Memory** - At least 12 GB Main Memory RAM.
+### Memory
 
-**Disk** - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
+- At least 12 GB Main Memory RAM.
+
+### Disk
+
+- At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
 ## Features
 
@@ -338,24 +218,28 @@ InvokeAI offers a locally hosted Web Server & React Frontend, with an industry l
 
 The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/outpainting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.
 
-### *Node Architecture & Editor (Beta)*
+### *Advanced Prompt Syntax*
 
-Invoke AI's backend is built on a graph-based execution architecture. This allows for customizable generation pipelines to be developed by professional users looking to create specific workflows to support their production use-cases, and will be extended in the future with additional capabilities.
+InvokeAI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space.
 
-### *Board & Gallery Management*
+### *Command Line Interface*
 
-Invoke AI provides an organized gallery system for easily storing, accessing, and remixing your content in the Invoke workspace. Images can be dragged/dropped onto any Image-base UI element in the application, and rich metadata within the Image allows for easy recall of key prompts or settings used in your workflow. 
+For users utilizing a terminal-based environment, or who want to take advantage of CLI features, InvokeAI offers an extensive and actively supported command-line interface that provides the full suite of generation functionality available in the tool.
 
 ### Other features
 
 - *Support for both ckpt and diffusers models*
 - *SD 2.0, 2.1 support*
-- *Upscaling Tools*
+- *Noise Control & Tresholding*
+- *Popular Sampler Support*
+- *Upscaling & Face Restoration Tools*
 - *Embedding Manager & Support*
 - *Model Manager & Support*
-- *Node-Based Architecture*
-- *Node-Based Plug-&-Play UI (Beta)*
-- *SDXL Support* (Coming soon)
+
+### Coming Soon
+
+- *Node-Based Architecture & UI*
+- And more...
 
 ### Latest Changes
 
@@ -363,7 +247,7 @@ For our latest changes, view our [Release
 Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
 [CHANGELOG](docs/CHANGELOG.md).
 
-### Troubleshooting
+## Troubleshooting
 
 Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
 problems and other issues.
@@ -393,6 +277,8 @@ This fork is a combined effort of various people from across the world.
 [Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
 their time, hard work and effort.
 
+Thanks to [Weblate](https://weblate.org/) for generously providing translation services to this project.
+
 ### Support
 
 For support, please use this repository's GitHub Issues tracking service, or join the Discord.

coverage/.gitignore

@@ -1,4 +0,0 @@
-# Ignore everything in this directory
-*
-# Except this file
-!.gitignore

docker/.env.sample

@@ -1,13 +0,0 @@
-## Make a copy of this file named `.env` and fill in the values below.
-## Any environment variables supported by InvokeAI can be specified here.
-
-# INVOKEAI_ROOT is the path to a path on the local filesystem where InvokeAI will store data.
-# Outputs will also be stored here by default.
-# This **must** be an absolute path.
-INVOKEAI_ROOT=
-
-HUGGINGFACE_TOKEN=
-
-## optional variables specific to the docker setup
-# GPU_DRIVER=cuda
-# CONTAINER_UID=1000

docker/Dockerfile

@@ -1,129 +1,103 @@
-# syntax=docker/dockerfile:1.4
+# syntax=docker/dockerfile:1
 
-## Builder stage
+ARG PYTHON_VERSION=3.9
+##################
+##  base image  ##
+##################
+FROM python:${PYTHON_VERSION}-slim AS python-base
 
-FROM library/ubuntu:22.04 AS builder
+LABEL org.opencontainers.image.authors="mauwii@outlook.de"
 
-ARG DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
-    --mount=type=cache,target=/var/lib/apt,sharing=locked \
-    apt update && apt-get install -y \
-        git \
-        python3.10-venv \
-        python3-pip \
-        build-essential
+# prepare for buildkit cache
+RUN rm -f /etc/apt/apt.conf.d/docker-clean \
+  && echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' >/etc/apt/apt.conf.d/keep-cache
 
-ENV INVOKEAI_SRC=/opt/invokeai
-ENV VIRTUAL_ENV=/opt/venv/invokeai
+# Install necessary packages
+RUN \
+  --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt,sharing=locked \
+  apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    libgl1-mesa-glx=20.3.* \
+    libglib2.0-0=2.66.* \
+    libopencv-dev=4.5.*
 
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-ARG TORCH_VERSION=2.0.1
-ARG TORCHVISION_VERSION=0.15.2
-ARG GPU_DRIVER=cuda
-ARG TARGETPLATFORM="linux/amd64"
-# unused but available
-ARG BUILDPLATFORM
+# set working directory and env
+ARG APPDIR=/usr/src
+ARG APPNAME=InvokeAI
+WORKDIR ${APPDIR}
+ENV PATH ${APPDIR}/${APPNAME}/bin:$PATH
+# Keeps Python from generating .pyc files in the container
+ENV PYTHONDONTWRITEBYTECODE 1
+# Turns off buffering for easier container logging
+ENV PYTHONUNBUFFERED 1
+# don't fall back to legacy build system
+ENV PIP_USE_PEP517=1
 
-WORKDIR ${INVOKEAI_SRC}
+#######################
+##  build pyproject  ##
+#######################
+FROM python-base AS pyproject-builder
 
-# Install pytorch before all other pip packages
-# NOTE: there are no pytorch builds for arm64 + cuda, only cpu
-# x86_64/CUDA is default
-RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m venv ${VIRTUAL_ENV} &&\
-    if [ "$TARGETPLATFORM" = "linux/arm64" ] || [ "$GPU_DRIVER" = "cpu" ]; then \
-        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cpu"; \
-    elif [ "$GPU_DRIVER" = "rocm" ]; then \
-        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm5.4.2"; \
-    else \
-        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu118"; \
-    fi &&\
-    pip install $extra_index_url_arg \
-        torch==$TORCH_VERSION \
-        torchvision==$TORCHVISION_VERSION
+# Install dependencies
+RUN \
+  --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt,sharing=locked \
+  apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    build-essential=12.9 \
+    gcc=4:10.2.* \
+    python3-dev=3.9.*
 
-# 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]"; \
-    else \
-        pip install -e "."; \
-    fi
+# prepare pip for buildkit cache
+ARG PIP_CACHE_DIR=/var/cache/buildkit/pip
+ENV PIP_CACHE_DIR ${PIP_CACHE_DIR}
+RUN mkdir -p ${PIP_CACHE_DIR}
 
-# #### Build the Web UI ------------------------------------
+# create virtual environment
+RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+  python3 -m venv "${APPNAME}" \
+  --upgrade-deps
 
-FROM node:18 AS web-builder
-WORKDIR /build
-COPY invokeai/frontend/web/ ./
-RUN --mount=type=cache,target=/usr/lib/node_modules \
-    npm install --include dev
-RUN --mount=type=cache,target=/usr/lib/node_modules \
-    yarn vite build
+# copy sources
+COPY --link . .
 
-
-#### Runtime stage ---------------------------------------
-
-FROM library/ubuntu:22.04 AS runtime
-
-ARG DEBIAN_FRONTEND=noninteractive
-ENV PYTHONUNBUFFERED=1
-ENV PYTHONDONTWRITEBYTECODE=1
-
-RUN apt update && apt install -y --no-install-recommends \
-        git \
-        curl \
-        vim \
-        tmux \
-        ncdu \
-        iotop \
-        bzip2 \
-        gosu \
-        libglib2.0-0 \
-        libgl1-mesa-glx \
-        python3-venv \
-        python3-pip \
-        build-essential \
-        libopencv-dev \
-        libstdc++-10-dev &&\
-    apt-get clean && apt-get autoclean
-
-# globally add magic-wormhole
-# for ease of transferring data to and from the container
-# when running in sandboxed cloud environments; e.g. Runpod etc.
-RUN pip install magic-wormhole
-
-ENV INVOKEAI_SRC=/opt/invokeai
-ENV VIRTUAL_ENV=/opt/venv/invokeai
-ENV INVOKEAI_ROOT=/invokeai
-ENV PATH="$VIRTUAL_ENV/bin:$INVOKEAI_SRC:$PATH"
-
-# --link requires buldkit w/ dockerfile syntax 1.4
-COPY --link --from=builder ${INVOKEAI_SRC} ${INVOKEAI_SRC}
-COPY --link --from=builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
-COPY --link --from=web-builder /build/dist ${INVOKEAI_SRC}/invokeai/frontend/web/dist
-
-# Link amdgpu.ids for ROCm builds
-# contributed by https://github.com/Rubonnek
-RUN mkdir -p "/opt/amdgpu/share/libdrm" &&\
-  ln -s "/usr/share/libdrm/amdgpu.ids" "/opt/amdgpu/share/libdrm/amdgpu.ids"
-
-WORKDIR ${INVOKEAI_SRC}
+# install pyproject.toml
+ARG PIP_EXTRA_INDEX_URL
+ENV PIP_EXTRA_INDEX_URL ${PIP_EXTRA_INDEX_URL}
+RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+  "${APPNAME}/bin/pip" install .
 
 # build patchmatch
-RUN cd /usr/lib/$(uname -p)-linux-gnu/pkgconfig/ && ln -sf opencv4.pc opencv.pc
 RUN python3 -c "from patchmatch import patch_match"
 
-# Create unprivileged user and make the local dir
-RUN useradd --create-home --shell /bin/bash -u 1000 --comment "container local user" invoke
-RUN mkdir -p ${INVOKEAI_ROOT} && chown -R invoke:invoke ${INVOKEAI_ROOT}
+#####################
+##  runtime image  ##
+#####################
+FROM python-base AS runtime
 
-COPY docker/docker-entrypoint.sh ./
-ENTRYPOINT ["/opt/invokeai/docker-entrypoint.sh"]
-CMD ["invokeai-web", "--host", "0.0.0.0"]
+# Create a new user
+ARG UNAME=appuser
+RUN useradd \
+  --no-log-init \
+  -m \
+  -U \
+  "${UNAME}"
+
+# create volume directory
+ARG VOLUME_DIR=/data
+RUN mkdir -p "${VOLUME_DIR}" \
+  && chown -R "${UNAME}" "${VOLUME_DIR}"
+
+# setup runtime environment
+USER ${UNAME}
+COPY --chown=${UNAME} --from=pyproject-builder ${APPDIR}/${APPNAME} ${APPNAME}
+ENV INVOKEAI_ROOT ${VOLUME_DIR}
+ENV TRANSFORMERS_CACHE ${VOLUME_DIR}/.cache
+ENV INVOKE_MODEL_RECONFIGURE "--yes --default_only"
+EXPOSE 9090
+ENTRYPOINT [ "invokeai" ]
+CMD [ "--web", "--host", "0.0.0.0", "--port", "9090" ]
+VOLUME [ "${VOLUME_DIR}" ]

docker/README.md

@@ -1,77 +0,0 @@
-# InvokeAI Containerized
-
-All commands are to be run from the `docker` directory: `cd docker`
-
-#### Linux
-
-1. Ensure builkit is enabled in the Docker daemon settings (`/etc/docker/daemon.json`)
-2. Install the `docker compose` plugin using your package manager, or follow a [tutorial](https://www.digitalocean.com/community/tutorials/how-to-install-and-use-docker-compose-on-ubuntu-22-04).
-    - The deprecated `docker-compose` (hyphenated) CLI continues to work for now.
-3. Ensure docker daemon is able to access the GPU.
-    - You may need to install [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
-
-#### macOS
-
-1. Ensure Docker has at least 16GB RAM
-2. Enable VirtioFS for file sharing
-3. Enable `docker compose` V2 support
-
-This is done via Docker Desktop preferences
-
-## Quickstart
-
-
-1. Make a copy of `env.sample` and name it `.env` (`cp env.sample .env` (Mac/Linux) or `copy example.env .env` (Windows)). Make changes as necessary. Set `INVOKEAI_ROOT` to an absolute path to:
-    a. the desired location of the InvokeAI runtime directory, or
-    b. an existing, v3.0.0 compatible runtime directory.
-1. `docker compose up`
-
-The image will be built automatically if needed.
-
-The runtime directory (holding models and outputs) will be created in the location specified by `INVOKEAI_ROOT`. The default location is `~/invokeai`. The runtime directory will be populated with the base configs and models necessary to start generating.
-
-### Use a GPU
-
-- Linux is *recommended* for GPU support in Docker.
-- WSL2 is *required* for Windows.
-- only `x86_64` architecture is supported.
-
-The Docker daemon on the system must be already set up to use the GPU. In case of Linux, this involves installing `nvidia-docker-runtime` and configuring the `nvidia` runtime as default. Steps will be different for AMD. Please see Docker documentation for the most up-to-date instructions for using your GPU with Docker.
-
-## Customize
-
-Check the `.env.sample` file. It contains some environment variables for running in Docker. Copy it, name it `.env`, and fill it in with your own values. Next time you run `docker compose up`, your custom values will be used.
-
-You can also set these values in `docker compose.yml` directly, but `.env` will help avoid conflicts when code is updated.
-
-Example (most values are optional):
-
-```
-INVOKEAI_ROOT=/Volumes/WorkDrive/invokeai
-HUGGINGFACE_TOKEN=the_actual_token
-CONTAINER_UID=1000
-GPU_DRIVER=cuda
-```
-
-## Even Moar Customizing!
-
-See the `docker compose.yaml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
-
-### Reconfigure the runtime directory
-
-Can be used to download additional models from the supported model list
-
-In conjunction with `INVOKEAI_ROOT` can be also used to initialize a runtime directory
-
-```
-command:
-  - invokeai-configure
-  - --yes
-```
-
-Or install models:
-
-```
-command:
-  - invokeai-model-install
-```

docker/build.sh

@@ -1,11 +1,51 @@
 #!/usr/bin/env bash
 set -e
 
-build_args=""
+# If you want to build a specific flavor, set the CONTAINER_FLAVOR environment variable
+#   e.g. CONTAINER_FLAVOR=cpu ./build.sh
+#   Possible Values are:
+#     - cpu
+#     - cuda
+#     - rocm
+#   Don't forget to also set it when executing run.sh
+#   if it is not set, the script will try to detect the flavor by itself.
+#
+# Doc can be found here:
+#   https://invoke-ai.github.io/InvokeAI/installation/040_INSTALL_DOCKER/
 
-[[ -f ".env" ]] && build_args=$(awk '$1 ~ /\=[^$]/ {print "--build-arg " $0 " "}' .env)
+SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
+cd "$SCRIPTDIR" || exit 1
 
-echo "docker-compose build args:"
-echo $build_args
+source ./env.sh
 
-docker-compose build $build_args
+DOCKERFILE=${INVOKE_DOCKERFILE:-./Dockerfile}
+
+# print the settings
+echo -e "You are using these values:\n"
+echo -e "Dockerfile:\t\t${DOCKERFILE}"
+echo -e "index-url:\t\t${PIP_EXTRA_INDEX_URL:-none}"
+echo -e "Volumename:\t\t${VOLUMENAME}"
+echo -e "Platform:\t\t${PLATFORM}"
+echo -e "Container Registry:\t${CONTAINER_REGISTRY}"
+echo -e "Container Repository:\t${CONTAINER_REPOSITORY}"
+echo -e "Container Tag:\t\t${CONTAINER_TAG}"
+echo -e "Container Flavor:\t${CONTAINER_FLAVOR}"
+echo -e "Container Image:\t${CONTAINER_IMAGE}\n"
+
+# Create docker volume
+if [[ -n "$(docker volume ls -f name="${VOLUMENAME}" -q)" ]]; then
+    echo -e "Volume already exists\n"
+else
+    echo -n "creating docker volume "
+    docker volume create "${VOLUMENAME}"
+fi
+
+# Build Container
+DOCKER_BUILDKIT=1 docker build \
+    --platform="${PLATFORM:-linux/amd64}" \
+    --tag="${CONTAINER_IMAGE:-invokeai}" \
+    ${CONTAINER_FLAVOR:+--build-arg="CONTAINER_FLAVOR=${CONTAINER_FLAVOR}"} \
+    ${PIP_EXTRA_INDEX_URL:+--build-arg="PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}"} \
+    ${PIP_PACKAGE:+--build-arg="PIP_PACKAGE=${PIP_PACKAGE}"} \
+    --file="${DOCKERFILE}" \
+    ..

docker/docker-compose.yml

@@ -1,48 +0,0 @@
-# Copyright (c) 2023 Eugene Brodsky https://github.com/ebr
-
-version: '3.8'
-
-services:
-  invokeai:
-    image: "local/invokeai:latest"
-    # edit below to run on a container runtime other than nvidia-container-runtime.
-    # not yet tested with rocm/AMD GPUs
-    # Comment out the "deploy" section to run on CPU only
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: 1
-              capabilities: [gpu]
-    build:
-      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
-
-    ports:
-      - "${INVOKEAI_PORT:-9090}:9090"
-    volumes:
-      - ${INVOKEAI_ROOT:-~/invokeai}:${INVOKEAI_ROOT:-/invokeai}
-      - ${HF_HOME:-~/.cache/huggingface}:${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

docker/docker-entrypoint.sh

@@ -1,65 +0,0 @@
-#!/bin/bash
-set -e -o pipefail
-
-### Container entrypoint
-# Runs the CMD as defined by the Dockerfile or passed to `docker run`
-# Can be used to configure the runtime dir
-# Bypass by using ENTRYPOINT or `--entrypoint`
-
-### 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=$(id -u) <this image>
-# Default UID: 1000 chosen due to popularity on Linux systems. Possibly 501 on MacOS.
-
-USER_ID=${CONTAINER_UID:-1000}
-USER=invoke
-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 $PUBLIC_KEY env var to enable SSH access.
-# We do not install openssh-server in the image by default to avoid bloat.
-# but it is useful to have the full SSH server e.g. on Runpod.
-# (use SCP to copy files to/from the image, etc)
-if [[ -v "PUBLIC_KEY" ]] && [[ ! -d "${HOME}/.ssh" ]]; then
-    apt-get update
-    apt-get install -y openssh-server
-    pushd $HOME
-    mkdir -p .ssh
-    echo ${PUBLIC_KEY} > .ssh/authorized_keys
-    chmod -R 700 .ssh
-    popd
-    service ssh start
-fi
-
-
-cd ${INVOKEAI_ROOT}
-
-# Run the CMD as the Container User (not root).
-exec gosu ${USER} "$@"

docker/env.sh

@@ -0,0 +1,51 @@
+#!/usr/bin/env bash
+
+# This file is used to set environment variables for the build.sh and run.sh scripts.
+
+# Try to detect the container flavor if no PIP_EXTRA_INDEX_URL got specified
+if [[ -z "$PIP_EXTRA_INDEX_URL" ]]; then
+
+  # Activate virtual environment if not already activated and exists
+  if [[ -z $VIRTUAL_ENV ]]; then
+    [[ -e "$(dirname "${BASH_SOURCE[0]}")/../.venv/bin/activate" ]] \
+      && source "$(dirname "${BASH_SOURCE[0]}")/../.venv/bin/activate" \
+      && echo "Activated virtual environment: $VIRTUAL_ENV"
+  fi
+
+  # Decide which container flavor to build if not specified
+  if [[ -z "$CONTAINER_FLAVOR" ]] && python -c "import torch" &>/dev/null; then
+    # Check for CUDA and ROCm
+    CUDA_AVAILABLE=$(python -c "import torch;print(torch.cuda.is_available())")
+    ROCM_AVAILABLE=$(python -c "import torch;print(torch.version.hip is not None)")
+    if [[ "${CUDA_AVAILABLE}" == "True" ]]; then
+      CONTAINER_FLAVOR="cuda"
+    elif [[ "${ROCM_AVAILABLE}" == "True" ]]; then
+      CONTAINER_FLAVOR="rocm"
+    else
+      CONTAINER_FLAVOR="cpu"
+    fi
+  fi
+
+  # Set PIP_EXTRA_INDEX_URL based on container flavor
+  if [[ "$CONTAINER_FLAVOR" == "rocm" ]]; then
+    PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/rocm"
+  elif [[ "$CONTAINER_FLAVOR" == "cpu" ]]; then
+    PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
+  # elif [[ -z "$CONTAINER_FLAVOR" || "$CONTAINER_FLAVOR" == "cuda" ]]; then
+  #   PIP_PACKAGE=${PIP_PACKAGE-".[xformers]"}
+  fi
+fi
+
+# Variables shared by build.sh and run.sh
+REPOSITORY_NAME="${REPOSITORY_NAME-$(basename "$(git rev-parse --show-toplevel)")}"
+REPOSITORY_NAME="${REPOSITORY_NAME,,}"
+VOLUMENAME="${VOLUMENAME-"${REPOSITORY_NAME}_data"}"
+ARCH="${ARCH-$(uname -m)}"
+PLATFORM="${PLATFORM-linux/${ARCH}}"
+INVOKEAI_BRANCH="${INVOKEAI_BRANCH-$(git branch --show)}"
+CONTAINER_REGISTRY="${CONTAINER_REGISTRY-"ghcr.io"}"
+CONTAINER_REPOSITORY="${CONTAINER_REPOSITORY-"$(whoami)/${REPOSITORY_NAME}"}"
+CONTAINER_FLAVOR="${CONTAINER_FLAVOR-cuda}"
+CONTAINER_TAG="${CONTAINER_TAG-"${INVOKEAI_BRANCH##*/}-${CONTAINER_FLAVOR}"}"
+CONTAINER_IMAGE="${CONTAINER_REGISTRY}/${CONTAINER_REPOSITORY}:${CONTAINER_TAG}"
+CONTAINER_IMAGE="${CONTAINER_IMAGE,,}"

docker/run.sh

@@ -1,8 +1,41 @@
 #!/usr/bin/env bash
 set -e
 
+# How to use: https://invoke-ai.github.io/InvokeAI/installation/040_INSTALL_DOCKER/
+
 SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
 cd "$SCRIPTDIR" || exit 1
 
-docker-compose up --build -d
-docker-compose logs -f
+source ./env.sh
+
+# Create outputs directory if it does not exist
+[[ -d ./outputs ]] || mkdir ./outputs
+
+echo -e "You are using these values:\n"
+echo -e "Volumename:\t${VOLUMENAME}"
+echo -e "Invokeai_tag:\t${CONTAINER_IMAGE}"
+echo -e "local Models:\t${MODELSPATH:-unset}\n"
+
+docker run \
+  --interactive \
+  --tty \
+  --rm \
+  --platform="${PLATFORM}" \
+  --name="${REPOSITORY_NAME,,}" \
+  --hostname="${REPOSITORY_NAME,,}" \
+  --mount=source="${VOLUMENAME}",target=/data \
+  --mount type=bind,source="$(pwd)"/outputs,target=/data/outputs \
+  ${MODELSPATH:+--mount="type=bind,source=${MODELSPATH},target=/data/models"} \
+  ${HUGGING_FACE_HUB_TOKEN:+--env="HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN}"} \
+  --publish=9090:9090 \
+  --cap-add=sys_nice \
+  ${GPU_FLAGS:+--gpus="${GPU_FLAGS}"} \
+  "${CONTAINER_IMAGE}" ${@:+$@}
+
+# Remove Trash folder
+for f in outputs/.Trash*; do
+  if [ -e "$f" ]; then
+    rm -Rf "$f"
+    break
+  fi
+done

docker/runpod-readme.md

@@ -1,60 +0,0 @@
-# InvokeAI - A Stable Diffusion Toolkit
-
-Stable Diffusion distribution by InvokeAI: https://github.com/invoke-ai
-
-The Docker image tracks the `main` branch of the InvokeAI project, which means it includes the latest features, but may contain some bugs.
-
-Your working directory is mounted under the `/workspace` path inside the pod. The models are in `/workspace/invokeai/models`, and outputs are in `/workspace/invokeai/outputs`.
-
-> **Only the /workspace directory will persist between pod restarts!**
-
-> **If you _terminate_ (not just _stop_) the pod, the /workspace will be lost.**
-
-## Quickstart
-
-1. Launch a pod from this template. **It will take about 5-10 minutes to run through the initial setup**. Be patient.
-1. Wait for the application to load.
-    - TIP: you know it's ready when the CPU usage goes idle
-    - You can also check the logs for a line that says "_Point your browser at..._"
-1. Open the Invoke AI web UI: click the `Connect` => `connect over  HTTP` button.
-1. Generate some art!
-
-## Other things you can do
-
-At any point you may edit the pod configuration and set an arbitrary Docker command. For example, you could run a command to downloads some models using `curl`, or fetch some images and place them into your outputs to continue a working session.
-
-If you need to run *multiple commands*, define them in the Docker Command field like this:
-
-`bash -c "cd ${INVOKEAI_ROOT}/outputs; wormhole receive 2-foo-bar; invoke.py --web --host 0.0.0.0"`
-
-### Copying your data in and out of the pod
-
-This image includes a couple of handy tools to help you get the data into the pod (such as your custom models or embeddings), and out of the pod (such as downloading your outputs). Here are your options for getting your data in and out of the pod:
-
-- **SSH server**:
-    1. Make sure to create and set your Public Key in the RunPod settings (follow the official instructions)
-    1. Add an exposed port 22 (TCP) in the pod settings!
-    1. When your pod restarts, you will see a new entry in the `Connect` dialog. Use this SSH server to `scp` or `sftp` your files as necessary, or SSH into the pod using the fully fledged SSH server.
-
-- [**Magic Wormhole**](https://magic-wormhole.readthedocs.io/en/latest/welcome.html):
-    1. On your computer, `pip install magic-wormhole` (see above instructions for details)
-    1. Connect to the command line **using the "light" SSH client** or the browser-based console. _Currently there's a bug where `wormhole` isn't available when connected to "full" SSH server, as described above_.
-    1. `wormhole send /workspace/invokeai/outputs` will send the entire `outputs` directory. You can also send individual files.
-    1. Once packaged, you will see a `wormhole receive <123-some-words>` command. Copy it
-    1. Paste this command into the terminal on your local machine to securely download the payload.
-    1. It works the same in reverse: you can `wormhole send` some models from your computer to the pod. Again, save your files somewhere in `/workspace` or they will be lost when the pod is stopped.
-
-- **RunPod's Cloud Sync feature** may be used to sync the persistent volume to cloud storage. You could, for example, copy the entire `/workspace` to S3, add some custom models to it, and copy it back from S3 when launching new pod configurations. Follow the Cloud Sync instructions.
-
-
-### Disable the NSFW checker
-
-The NSFW checker is enabled by default. To disable it, edit the pod configuration and set the following command:
-
-```
-invoke --web --host 0.0.0.0 --no-nsfw_checker
-```
-
----
-
-Template ©2023 Eugene Brodsky [ebr](https://github.com/ebr)

docs/.markdownlint.jsonc

@@ -0,0 +1,5 @@
+{
+  "MD046": false,
+  "MD007": false,
+  "MD030": false
+}

docs/CHANGELOG.md

@@ -4,236 +4,6 @@ title: Changelog
 
 # :octicons-log-16: **Changelog**
 
-## v2.3.5 <small>(22 May 2023)</small>
-
-This release (along with the post1 and post2 follow-on releases) expands support for additional LoRA and LyCORIS models, upgrades diffusers versions, and fixes a few bugs.
-
-### LoRA and LyCORIS Support Improvement
-
-    A number of LoRA/LyCORIS fine-tune files (those which alter the text encoder as well as the unet model) were not having the desired effect in InvokeAI. This bug has now been fixed. Full documentation of LoRA support is available at InvokeAI LoRA Support.
-    Previously, InvokeAI did not distinguish between LoRA/LyCORIS models based on Stable Diffusion v1.5 vs those based on v2.0 and 2.1, leading to a crash when an incompatible model was loaded. This has now been fixed. In addition, the web pulldown menus for LoRA and Textual Inversion selection have been enhanced to show only those files that are compatible with the currently-selected Stable Diffusion model.
-    Support for the newer LoKR LyCORIS files has been added.
-
-### Library Updates and Speed/Reproducibility Advancements
-The major enhancement in this version is that NVIDIA users no longer need to decide between speed and reproducibility. Previously, if you activated the Xformers library, you would see improvements in speed and memory usage, but multiple images generated with the same seed and other parameters would be slightly different from each other. This is no longer the case. Relative to 2.3.5 you will see improved performance when running without Xformers, and even better performance when Xformers is activated. In both cases, images generated with the same settings will be identical.
-
-Here are the new library versions:
-Library 	Version
-Torch 	2.0.0
-Diffusers 	0.16.1
-Xformers 	0.0.19
-Compel 	1.1.5
-Other Improvements
-
-### Performance Improvements
-
-    When a model is loaded for the first time, InvokeAI calculates its checksum for incorporation into the PNG metadata. This process could take up to a minute on network-mounted disks and WSL mounts. This release noticeably speeds up the process.
-
-### Bug Fixes
-
-    The "import models from directory" and "import from URL" functionality in the console-based model installer has now been fixed.
-    When running the WebUI, we have reduced the number of times that InvokeAI reaches out to HuggingFace to fetch the list of embeddable Textual Inversion models. We have also caught and fixed a problem with the updater not correctly detecting when another instance of the updater is running 
-
-
-## v2.3.4 <small>(7 April 2023)</small>
-
-What's New in 2.3.4
-
-This features release adds support for LoRA (Low-Rank Adaptation) and LyCORIS (Lora beYond Conventional) models, as well as some minor bug fixes.
-### LoRA and LyCORIS Support
-
-LoRA files contain fine-tuning weights that enable particular styles, subjects or concepts to be applied to generated images. LyCORIS files are an extended variant of LoRA. InvokeAI supports the most common LoRA/LyCORIS format, which ends in the suffix .safetensors. You will find numerous LoRA and LyCORIS models for download at Civitai, and a small but growing number at Hugging Face. Full documentation of LoRA support is available at InvokeAI LoRA Support.( Pre-release note: this page will only be available after release)
-
-To use LoRA/LyCORIS models in InvokeAI:
-
-    Download the .safetensors files of your choice and place in /path/to/invokeai/loras. This directory was not present in earlier version of InvokeAI but will be created for you the first time you run the command-line or web client. You can also create the directory manually.
-
-    Add withLora(lora-file,weight) to your prompts. The weight is optional and will default to 1.0. A few examples, assuming that a LoRA file named loras/sushi.safetensors is present:
-
-family sitting at dinner table eating sushi withLora(sushi,0.9)
-family sitting at dinner table eating sushi withLora(sushi, 0.75)
-family sitting at dinner table eating sushi withLora(sushi)
-
-Multiple withLora() prompt fragments are allowed. The weight can be arbitrarily large, but the useful range is roughly 0.5 to 1.0. Higher weights make the LoRA's influence stronger. Negative weights are also allowed, which can lead to some interesting effects.
-
-    Generate as you usually would! If you find that the image is too "crisp" try reducing the overall CFG value or reducing individual LoRA weights. As is the case with all fine-tunes, you'll get the best results when running the LoRA on top of the model similar to, or identical with, the one that was used during the LoRA's training. Don't try to load a SD 1.x-trained LoRA into a SD 2.x model, and vice versa. This will trigger a non-fatal error message and generation will not proceed.
-
-    You can change the location of the loras directory by passing the --lora_directory option to `invokeai.
-
-### New WebUI LoRA and Textual Inversion Buttons
-
-This version adds two new web interface buttons for inserting LoRA and Textual Inversion triggers into the prompt as shown in the screenshot below.
-
-Clicking on one or the other of the buttons will bring up a menu of available LoRA/LyCORIS or Textual Inversion trigger terms. Select a menu item to insert the properly-formatted withLora() or <textual-inversion> prompt fragment into the positive prompt. The number in parentheses indicates the number of trigger terms currently in the prompt. You may click the button again and deselect the LoRA or trigger to remove it from the prompt, or simply edit the prompt directly.
-
-Currently terms are inserted into the positive prompt textbox only. However, some textual inversion embeddings are designed to be used with negative prompts. To move a textual inversion trigger into the negative prompt, simply cut and paste it.
-
-By default the Textual Inversion menu only shows locally installed models found at startup time in /path/to/invokeai/embeddings. However, InvokeAI has the ability to dynamically download and install additional Textual Inversion embeddings from the HuggingFace Concepts Library. You may choose to display the most popular of these (with five or more likes) in the Textual Inversion menu by going to Settings and turning on "Show Textual Inversions from HF Concepts Library." When this option is activated, the locally-installed TI embeddings will be shown first, followed by uninstalled terms from Hugging Face. See The Hugging Face Concepts Library and Importing Textual Inversion files for more information.
-### Minor features and fixes
-
-This release changes model switching behavior so that the command-line and Web UIs save the last model used and restore it the next time they are launched. It also improves the behavior of the installer so that the pip utility is kept up to date.
-  
-### Known Bugs in 2.3.4
-
-These are known bugs in the release.
-
-    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
-    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
-
-
-## v2.3.3 <small>(28 March 2023)</small>
-
-This is a bugfix and minor feature release.
-### Bugfixes
-
-Since version 2.3.2 the following bugs have been fixed:
-Bugs
-
-    When using legacy checkpoints with an external VAE, the VAE file is now scanned for malware prior to loading. Previously only the main model weights file was scanned.
-    Textual inversion will select an appropriate batchsize based on whether xformers is active, and will default to xformers enabled if the library is detected.
-    The batch script log file names have been fixed to be compatible with Windows.
-    Occasional corruption of the .next_prefix file (which stores the next output file name in sequence) on Windows systems is now detected and corrected.
-    Support loading of legacy config files that have no personalization (textual inversion) section.
-    An infinite loop when opening the developer's console from within the invoke.sh script has been corrected.
-    Documentation fixes, including a recipe for detecting and fixing problems with the AMD GPU ROCm driver.
-
-Enhancements
-
-    It is now possible to load and run several community-contributed SD-2.0 based models, including the often-requested "Illuminati" model.
-    The "NegativePrompts" embedding file, and others like it, can now be loaded by placing it in the InvokeAI embeddings directory.
-    If no --model is specified at launch time, InvokeAI will remember the last model used and restore it the next time it is launched.
-    On Linux systems, the invoke.sh launcher now uses a prettier console-based interface. To take advantage of it, install the dialog package using your package manager (e.g. sudo apt install dialog).
-    When loading legacy models (safetensors/ckpt) you can specify a custom config file and/or a VAE by placing like-named files in the same directory as the model following this example:
-
-my-favorite-model.ckpt
-my-favorite-model.yaml
-my-favorite-model.vae.pt      # or my-favorite-model.vae.safetensors
-
-### Known Bugs in 2.3.3
-
-These are known bugs in the release.
-
-    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
-    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
-
-
-## v2.3.2 <small>(11 March 2023)</small>
-This is a bugfix and minor feature release.
-
-### Bugfixes
-
-Since version 2.3.1 the following bugs have been fixed:
-
-    Black images appearing for potential NSFW images when generating with legacy checkpoint models and both --no-nsfw_checker and --ckpt_convert turned on.
-    Black images appearing when generating from models fine-tuned on Stable-Diffusion-2-1-base. When importing V2-derived models, you may be asked to select whether the model was derived from a "base" model (512 pixels) or the 768-pixel SD-2.1 model.
-    The "Use All" button was not restoring the Hi-Res Fix setting on the WebUI
-    When using the model installer console app, models failed to import correctly when importing from directories with spaces in their names. A similar issue with the output directory was also fixed.
-    Crashes that occurred during model merging.
-    Restore previous naming of Stable Diffusion base and 768 models.
-    Upgraded to latest versions of diffusers, transformers, safetensors and accelerate libraries upstream. We hope that this will fix the assertion NDArray > 2**32 issue that MacOS users have had when generating images larger than 768x768 pixels. Please report back.
-
-As part of the upgrade to diffusers, the location of the diffusers-based models has changed from models/diffusers to models/hub. When you launch InvokeAI for the first time, it will prompt you to OK a one-time move. This should be quick and harmless, but if you have modified your models/diffusers directory in some way, for example using symlinks, you may wish to cancel the migration and make appropriate adjustments.
-New "Invokeai-batch" script
-
-### Invoke AI Batch
-2.3.2 introduces a new command-line only script called invokeai-batch that can be used to generate hundreds of images from prompts and settings that vary systematically. This can be used to try the same prompt across multiple combinations of models, steps, CFG settings and so forth. It also allows you to template prompts and generate a combinatorial list like:
-
-a shack in the mountains, photograph
-a shack in the mountains, watercolor
-a shack in the mountains, oil painting
-a chalet in the mountains, photograph
-a chalet in the mountains, watercolor
-a chalet in the mountains, oil painting
-a shack in the desert, photograph
-...
-
-If you have a system with multiple GPUs, or a single GPU with lots of VRAM, you can parallelize generation across the combinatorial set, reducing wait times and using your system's resources efficiently (make sure you have good GPU cooling).
-
-To try invokeai-batch out. Launch the "developer's console" using the invoke launcher script, or activate the invokeai virtual environment manually. From the console, give the command invokeai-batch --help in order to learn how the script works and create your first template file for dynamic prompt generation.
-
-
-### Known Bugs in 2.3.2
-
-These are known bugs in the release.
-
-    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
-    Windows Defender will sometimes raise a Trojan alert for the codeformer.pth face restoration model. As far as we have been able to determine, this is a false positive and can be safely whitelisted.
-
-
-## v2.3.1 <small>(22 February 2023)</small>
-This is primarily a bugfix release, but it does provide several new features that will improve the user experience.
-
-### Enhanced support for model management
-
-InvokeAI now makes it convenient to add, remove and modify models. You can individually import models that are stored on your local system, scan an entire folder and its subfolders for models and import them automatically, and even directly import models from the internet by providing their download URLs. You also have the option of designating a local folder to scan for new models each time InvokeAI is restarted.
-
-There are three ways of accessing the model management features:
-
-    From the WebUI, click on the cube to the right of the model selection menu. This will bring up a form that allows you to import models individually from your local disk or scan a directory for models to import.
-
-    Using the Model Installer App
-
-Choose option (5) download and install models from the invoke launcher script to start a new console-based application for model management. You can use this to select from a curated set of starter models, or import checkpoint, safetensors, and diffusers models from a local disk or the internet. The example below shows importing two checkpoint URLs from popular SD sites and a HuggingFace diffusers model using its Repository ID. It also shows how to designate a folder to be scanned at startup time for new models to import.
-
-Command-line users can start this app using the command invokeai-model-install.
-
-    Using the Command Line Client (CLI)
-
-The !install_model and !convert_model commands have been enhanced to allow entering of URLs and local directories to scan and import. The first command installs .ckpt and .safetensors files as-is. The second one converts them into the faster diffusers format before installation.
-
-Internally InvokeAI is able to probe the contents of a .ckpt or .safetensors file to distinguish among v1.x, v2.x and inpainting models. This means that you do not need to include "inpaint" in your model names to use an inpainting model. Note that Stable Diffusion v2.x models will be autoconverted into a diffusers model the first time you use it.
-
-Please see INSTALLING MODELS for more information on model management.
-
-### An Improved Installer Experience
-
-The installer now launches a console-based UI for setting and changing commonly-used startup options:
-
-After selecting the desired options, the installer installs several support models needed by InvokeAI's face reconstruction and upscaling features and then launches the interface for selecting and installing models shown earlier. At any time, you can edit the startup options by launching invoke.sh/invoke.bat and entering option (6) change InvokeAI startup options
-
-Command-line users can launch the new configure app using invokeai-configure.
-
-This release also comes with a renewed updater. To do an update without going through a whole reinstallation, launch invoke.sh or invoke.bat and choose option (9) update InvokeAI . This will bring you to a screen that prompts you to update to the latest released version, to the most current development version, or any released or unreleased version you choose by selecting the tag or branch of the desired version.
-
-Command-line users can run this interface by typing invokeai-configure
-
-### Image Symmetry Options
-
-There are now features to generate horizontal and vertical symmetry during generation. The way these work is to wait until a selected step in the generation process and then to turn on a mirror image effect. In addition to generating some cool images, you can also use this to make side-by-side comparisons of how an image will look with more or fewer steps. Access this option from the WebUI by selecting Symmetry from the image generation settings, or within the CLI by using the options --h_symmetry_time_pct and --v_symmetry_time_pct (these can be abbreviated to --h_sym and --v_sym like all other options).
-
-### A New Unified Canvas Look
-
-This release introduces a beta version of the WebUI Unified Canvas. To try it out, open up the settings dialogue in the WebUI (gear icon) and select Use Canvas Beta Layout:
-
-Refresh the screen and go to to Unified Canvas (left side of screen, third icon from the top). The new layout is designed to provide more space to work in and to keep the image controls close to the image itself:
-
-Model conversion and merging within the WebUI
-
-The WebUI now has an intuitive interface for model merging, as well as for permanent conversion of models from legacy .ckpt/.safetensors formats into diffusers format. These options are also available directly from the invoke.sh/invoke.bat scripts.
-An easier way to contribute translations to the WebUI
-
-We have migrated our translation efforts to Weblate, a FOSS translation product. Maintaining the growing project's translations is now far simpler for the maintainers and community. Please review our brief translation guide for more information on how to contribute.
-Numerous internal bugfixes and performance issues
-
-### Bug Fixes
-This releases quashes multiple bugs that were reported in 2.3.0. Major internal changes include upgrading to diffusers 0.13.0, and using the compel library for prompt parsing. See Detailed Change Log for a detailed list of bugs caught and squished.
-Summary of InvokeAI command line scripts (all accessible via the launcher menu)
-Command 	Description
-invokeai 	Command line interface
-invokeai --web 	Web interface
-invokeai-model-install 	Model installer with console forms-based front end
-invokeai-ti --gui 	Textual inversion, with a console forms-based front end
-invokeai-merge --gui 	Model merging, with a console forms-based front end
-invokeai-configure 	Startup configuration; can also be used to reinstall support models
-invokeai-update 	InvokeAI software updater
-
-### Known Bugs in 2.3.1
-
-These are known bugs in the release.
-    MacOS users generating 768x768 pixel images or greater using diffusers models may experience a hard crash with assertion NDArray > 2**32 This appears to be an issu...
-
-
-
 ## v2.3.0 <small>(15 January 2023)</small>
 
 **Transition to diffusers
@@ -494,7 +264,7 @@ sections describe what's new for InvokeAI.
   [Manual Installation](installation/020_INSTALL_MANUAL.md).
 - The ability to save frequently-used startup options (model to load, steps,
   sampler, etc) in a `.invokeai` file. See
-  [Client](deprecated/CLI.md)
+  [Client](features/CLI.md)
 - Support for AMD GPU cards (non-CUDA) on Linux machines.
 - Multiple bugs and edge cases squashed.
 
@@ -617,7 +387,7 @@ sections describe what's new for InvokeAI.
 - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for
   backward compatibility.
 - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
-- Support for [inpainting](deprecated/INPAINTING.md) and
+- Support for [inpainting](features/INPAINTING.md) and
   [outpainting](features/OUTPAINTING.md)
 - img2img runs on all k\* samplers
 - Support for
@@ -629,7 +399,7 @@ sections describe what's new for InvokeAI.
   using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E
   infinite canvas), and "embiggen" upscaling. See the `!fix` command.
 - New `--hires` option on `invoke>` line allows
-  [larger images to be created without duplicating elements](deprecated/CLI.md#this-is-an-example-of-txt2img),
+  [larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img),
   at the cost of some performance.
 - New `--perlin` and `--threshold` options allow you to add and control
   variation during image generation (see
@@ -638,7 +408,7 @@ sections describe what's new for InvokeAI.
   of images and tweaking of previous settings.
 - Command-line completion in `invoke.py` now works on Windows, Linux and Mac
   platforms.
-- Improved [command-line completion behavior](deprecated/CLI.md) New commands
+- Improved [command-line completion behavior](features/CLI.md) New commands
   added:
   - List command-line history with `!history`
   - Search command-line history with `!search`

docs/contributing/CONTRIBUTING.md

@@ -1,54 +0,0 @@
-## Welcome to Invoke AI
-
-We're thrilled to have you here and we're excited for you to contribute. 
-
-Invoke AI originated as a project built by the community, and that vision carries forward today as we aim to build the best pro-grade tools available. We work together to incorporate the latest in AI/ML research, making these tools available in over 20 languages to artists and creatives around the world as part of our fully permissive OSS project designed for individual users to self-host and use.
-
-Here are some guidelines to help you get started:
-
-### Technical Prerequisites
-
-Front-end: You'll need a working knowledge of React and TypeScript.
-
-Back-end: Depending on the scope of your contribution, you may need to know SQLite, FastAPI, Python, and Socketio. Also, a good majority of the backend logic involved in processing images is built in a modular way using a concept called "Nodes", which are isolated functions that carry out individual, discrete operations. This design allows for easy contributions of novel pipelines and capabilities.
-
-### How to Submit Contributions
-
-To start contributing, please follow these steps:
-
-1. Familiarize yourself with our roadmap and open projects to see where your skills and interests align. These documents can serve as a source of inspiration.
-2. Open a Pull Request (PR) with a clear description of the feature you're adding or the problem you're solving. Make sure your contribution aligns with the project's vision.
-3. Adhere to general best practices. This includes assuming interoperability with other nodes, keeping the scope of your functions as small as possible, and organizing your code according to our architecture documents.
-
-### Types of Contributions We're Looking For
-
-We welcome all contributions that improve the project. Right now, we're especially looking for:
-
-1. Quality of life (QOL) enhancements on the front-end.
-2. New backend capabilities added through nodes.
-3. Incorporating additional optimizations from the broader open-source software community.
-
-### Communication and Decision-making Process
-
-Project maintainers and code owners review PRs to ensure they align with the project's goals. They may provide design or architectural guidance, suggestions on user experience, or provide more significant feedback on the contribution itself. Expect to receive feedback on your submissions, and don't hesitate to ask questions or propose changes.
-
-For more robust discussions, or if you're planning to add capabilities not currently listed on our roadmap, please reach out to us on our Discord server. That way, we can ensure your proposed contribution aligns with the project's direction before you start writing code.
-
-### Code of Conduct and Contribution Expectations
-
-We want everyone in our community to have a positive experience. To facilitate this, we've established a code of conduct and a statement of values that we expect all contributors to adhere to. Please take a moment to review these documents—they're essential to maintaining a respectful and inclusive environment.
-
-By making a contribution to this project, you certify that:
-
-1. The contribution was created in whole or in part by you and you have the right to submit it under the open-source license indicated in this project’s GitHub repository; or
-2. The contribution is based upon previous work that, to the best of your knowledge, is covered under an appropriate open-source license and you have the right under that license to submit that work with modifications, whether created in whole or in part by you, under the same open-source license (unless you are permitted to submit under a different license); or
-3. The contribution was provided directly to you by some other person who certified (1) or (2) and you have not modified it; or
-4. You understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information you submit with it, including your sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open-source license(s) involved.
-
-This disclaimer is not a license and does not grant any rights or permissions. You must obtain necessary permissions and licenses, including from third parties, before contributing to this project.
-
-This disclaimer is provided "as is" without warranty of any kind, whether expressed or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, or non-infringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the contribution or the use or other dealings in the contribution.
-
----
-
-Remember, your contributions help make this project great. We're excited to see what you'll bring to our community!

docs/contributing/INVOCATIONS.md

@@ -1,790 +1,105 @@
 # Invocations
 
-Features in InvokeAI are added in the form of modular node-like systems called
-**Invocations**.
-
-An Invocation is simply a single operation that takes in some inputs and gives
-out some outputs. We can then chain multiple Invocations together to create more
-complex functionality.
-
-## Invocations Directory
-
-InvokeAI Invocations can be found in the `invokeai/app/invocations` directory.
-
-You can add your new functionality to one of the existing Invocations in this
-directory or create a new file in this directory as per your needs.
-
-**Note:** _All Invocations must be inside this directory for InvokeAI to
-recognize them as valid Invocations._
-
-## Creating A New Invocation
-
-In order to understand the process of creating a new Invocation, let us actually
-create one.
-
-In our example, let us create an Invocation that will take in an image, resize
-it and output the resized image.
-
-The first set of things we need to do when creating a new Invocation are -
-
-- Create a new class that derives from a predefined parent class called
-  `BaseInvocation`.
-- The name of every Invocation must end with the word `Invocation` in order for
-  it to be recognized as an Invocation.
-- Every Invocation must have a `docstring` that describes what this Invocation
-  does.
-- Every Invocation must have a unique `type` field defined which becomes its
-  indentifier.
-- Invocations are strictly typed. We make use of the native
-  [typing](https://docs.python.org/3/library/typing.html) library and the
-  installed [pydantic](https://pydantic-docs.helpmanual.io/) library for
-  validation.
-
-So let us do that.
-
-```python
-from typing import Literal
-from .baseinvocation import BaseInvocation
-
-class ResizeInvocation(BaseInvocation):
-    '''Resizes an image'''
-    type: Literal['resize'] = 'resize'
-```
-
-That's great.
-
-Now we have setup the base of our new Invocation. Let us think about what inputs
-our Invocation takes.
-
-- We need an `image` that we are going to resize.
-- We will need new `width` and `height` values to which we need to resize the
-  image to.
-
-### **Inputs**
-
-Every Invocation input is a pydantic `Field` and like everything else should be
-strictly typed and defined.
-
-So let us create these inputs for our Invocation. First up, the `image` input we
-need. Generally, we can use standard variable types in Python but InvokeAI
-already has a custom `ImageField` type that handles all the stuff that is needed
-for image inputs.
-
-But what is this `ImageField` ..? It is a special class type specifically
-written to handle how images are dealt with in InvokeAI. We will cover how to
-create your own custom field types later in this guide. For now, let's go ahead
-and use it.
-
-```python
-from typing import Literal, Union
-from pydantic import Field
-
-from .baseinvocation import BaseInvocation
-from ..models.image import ImageField
-
-class ResizeInvocation(BaseInvocation):
-    '''Resizes an image'''
-    type: Literal['resize'] = 'resize'
-
-    # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
-```
-
-Let us break down our input code.
-
-```python
-image: Union[ImageField, None] = Field(description="The input image", default=None)
-```
-
-| Part      | Value                                                | Description                                                                                        |
-| --------- | ---------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
-| Name      | `image`                                              | The variable that will hold our image                                                              |
-| Type Hint | `Union[ImageField, None]`                            | The types for our field. Indicates that the image can either be an `ImageField` type or `None`     |
-| Field     | `Field(description="The input image", default=None)` | The image variable is a field which needs a description and a default value that we set to `None`. |
-
-Great. Now let us create our other inputs for `width` and `height`
-
-```python
-from typing import Literal, Union
-from pydantic import Field
-
-from .baseinvocation import BaseInvocation
-from ..models.image import ImageField
-
-class ResizeInvocation(BaseInvocation):
-    '''Resizes an image'''
-    type: Literal['resize'] = 'resize'
-
-    # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
-    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
-```
-
-As you might have noticed, we added two new parameters to the field type for
-`width` and `height` called `gt` and `le`. These basically stand for _greater
-than or equal to_ and _less than or equal to_. There are various other param
-types for field that you can find on the **pydantic** documentation.
-
-**Note:** _Any time it is possible to define constraints for our field, we
-should do it so the frontend has more information on how to parse this field._
-
-Perfect. We now have our inputs. Let us do something with these.
-
-### **Invoke Function**
-
-The `invoke` function is where all the magic happens. This function provides you
-the `context` parameter that is of the type `InvocationContext` which will give
-you access to the current context of the generation and all the other services
-that are provided by it by InvokeAI.
-
-Let us create this function first.
-
-```python
-from typing import Literal, Union
-from pydantic import Field
-
-from .baseinvocation import BaseInvocation, InvocationContext
-from ..models.image import ImageField
-
-class ResizeInvocation(BaseInvocation):
-    '''Resizes an image'''
-    type: Literal['resize'] = 'resize'
-
-    # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
-    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
-
-    def invoke(self, context: InvocationContext):
-        pass
-```
-
-### **Outputs**
-
-The output of our Invocation will be whatever is returned by this `invoke`
-function. Like with our inputs, we need to strongly type and define our outputs
-too.
-
-What is our output going to be? Another image. Normally you'd have to create a
-type for this but InvokeAI already offers you an `ImageOutput` type that handles
-all the necessary info related to image outputs. So let us use that.
-
-We will cover how to create your own output types later in this guide.
-
-```python
-from typing import Literal, Union
-from pydantic import Field
-
-from .baseinvocation import BaseInvocation, InvocationContext
-from ..models.image import ImageField
-from .image import ImageOutput
-
-class ResizeInvocation(BaseInvocation):
-    '''Resizes an image'''
-    type: Literal['resize'] = 'resize'
-
-    # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
-    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        pass
-```
-
-Perfect. Now that we have our Invocation setup, let us do what we want to do.
-
-- We will first load the image. Generally we do this using the `PIL` library but
-  we can use one of the services provided by InvokeAI to load the image.
-- We will resize the image using `PIL` to our input data.
-- We will output this image in the format we set above.
-
-So let's do that.
-
-```python
-from typing import Literal, Union
-from pydantic import Field
-
-from .baseinvocation import BaseInvocation, InvocationContext
-from ..models.image import ImageField, ResourceOrigin, ImageCategory
-from .image import ImageOutput
-
-class ResizeInvocation(BaseInvocation):
-    '''Resizes an image'''
-    type: Literal['resize'] = 'resize'
-
-    # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
-    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = Field(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.
-        image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
-
-        # Resizing the image
-        # Because we used the above service, we already have a PIL image. So we can simply resize.
-        resized_image = image.resize((self.width, self.height))
-
-        # Preparing the image for output using InvokeAI's predefined Image Service.
-        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,
-        )
-
-        # Returning the Image
-        return ImageOutput(
-            image=ImageField(
-                image_name=output_image.image_name,
-                image_origin=output_image.image_origin,
-            ),
-            width=output_image.width,
-            height=output_image.height,
-        )
-```
-
-**Note:** Do not be overwhelmed by the `ImageOutput` process. InvokeAI has a
-certain way that the images need to be dispatched in order to be stored and read
-correctly. In 99% of the cases when dealing with an image output, you can simply
-copy-paste the template above.
-
-That's it. You made your own **Resize Invocation**.
-
-## Result
-
-Once you make your Invocation correctly, the rest of the process is fully
-automated for you.
-
-When you launch InvokeAI, you can go to `http://localhost:9090/docs` and see
-your new Invocation show up there with all the relevant info.
-
-![resize invocation](../assets/contributing/resize_invocation.png)
-
-When you launch the frontend UI, you can go to the Node Editor tab and find your
-new Invocation ready to be used.
-
-![resize node editor](../assets/contributing/resize_node_editor.png)
-
-# Advanced
-
-## 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.
-
-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**
-
-- 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.
-- Keep your field in the same file as the Invocation that it is made for or in
-  another file where it is relevant.
-
-All input types a class that derive from the `BaseModel` type from `pydantic`.
-So let's create one.
-
-```python
-from pydantic import BaseModel
-
-class ColorField(BaseModel):
-    '''A field that holds the rgba values of a color'''
-    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.
-
-```python
-class ColorField(BaseModel):
-    '''A field that holds the rgba values of a color'''
-    r: int = Field(ge=0, le=255, description="The red channel")
-    g: int = Field(ge=0, le=255, description="The green channel")
-    b: int = Field(ge=0, le=255, description="The blue channel")
-    a: int = Field(ge=0, le=255, description="The alpha channel")
-```
-
-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')
-```
-
-**Extra Config**
-
-All input fields also take an additional `Config` class that you can use to do
-various advanced things like setting required parameters and etc.
-
-Let us do that for our _ColorField_ and enforce all the values because we did
-not define any defaults for our fields.
-
-```python
-class ColorField(BaseModel):
-    '''A field that holds the rgba values of a color'''
-    r: int = Field(ge=0, le=255, description="The red channel")
-    g: int = Field(ge=0, le=255, description="The green channel")
-    b: int = Field(ge=0, le=255, description="The blue channel")
-    a: int = Field(ge=0, le=255, description="The alpha channel")
-
-    class Config:
-        schema_extra = {"required": ["r", "g", "b", "a"]}
-```
-
-Now it becomes mandatory for the user to supply all the values required by our
-input field.
-
-We will discuss the `Config` class in extra detail later in this guide and how
-you can use it to make your Invocations more robust.
-
-## Custom Output Types
-
-Like with custom inputs, sometimes you might find yourself needing custom
-outputs that InvokeAI does not provide. We can easily set one up.
-
-Now that you are familiar with Invocations and Inputs, let us use that knowledge
-to put together a custom output type for an Invocation that returns _width_,
-_height_ and _background_color_ that we need to create a blank image.
-
-- A custom output type is a class that derives from the parent class of
-  `BaseInvocationOutput`.
-- It is not mandatory but we recommend using names ending with `Output` for
-  output types. So we'll call our class `BlankImageOutput`
-- It is not mandatory but we highly recommend adding a `docstring` to describe
-  what your output type is for.
-- Like Invocations, each output type should have a `type` variable that is
-  **unique**
-
-Now that we know the basic rules for creating a new output type, let us go ahead
-and make it.
-
-```python
-from typing import Literal
-from pydantic import Field
-
-from .baseinvocation import BaseInvocationOutput
-
-class BlankImageOutput(BaseInvocationOutput):
-    '''Base output type for creating a blank image'''
-    type: Literal['blank_image_output'] = 'blank_image_output'
-
-    # Inputs
-    width: int = Field(description='Width of blank image')
-    height: int = Field(description='Height of blank image')
-    bg_color: ColorField = Field(description='Background color of blank image')
-
-    class Config:
-        schema_extra = {"required": ["type", "width", "height", "bg_color"]}
-```
-
-All set. We now have an output type that requires what we need to create a
-blank_image. And if you noticed it, we even used the `Config` class to ensure
-the fields are required.
-
-## Custom Configuration
-
-As you might have noticed when making inputs and outputs, we used a class called
-`Config` from _pydantic_ to further customize them. Because our inputs and
-outputs essentially inherit from _pydantic_'s `BaseModel` class, all
-[configuration options](https://docs.pydantic.dev/latest/usage/schema/#schema-customization)
-that are valid for _pydantic_ classes are also valid for our inputs and outputs.
-You can do the same for your Invocations too but InvokeAI makes our life a
-little bit easier on that end.
-
-InvokeAI provides a custom configuration class called `InvocationConfig`
-particularly for configuring Invocations. This is exactly the same as the raw
-`Config` class from _pydantic_ with some extra stuff on top to help faciliate
-parsing of the scheme in the frontend UI.
-
-At the current moment, tihs `InvocationConfig` class is further improved with
-the following features related the `ui`.
-
-| Config Option | Field Type                                                                                                    | Example                                                                                                               |
-| ------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- |
-| type_hints    | `Dict[str, Literal["integer", "float", "boolean", "string", "enum", "image", "latents", "model", "control"]]` | `type_hint: "model"` provides type hints related to the model like displaying a list of available models              |
-| tags          | `List[str]`                                                                                                   | `tags: ['resize', 'image']` will classify your invocation under the tags of resize and image.                         |
-| title         | `str`                                                                                                         | `title: 'Resize Image` will rename your to this custom title rather than infer from the name of the Invocation class. |
-
-So let us update your `ResizeInvocation` with some extra configuration and see
-how that works.
-
-```python
-from typing import Literal, Union
-from pydantic import Field
-
-from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from ..models.image import ImageField, ResourceOrigin, ImageCategory
-from .image import ImageOutput
-
-class ResizeInvocation(BaseInvocation):
-    '''Resizes an image'''
-    type: Literal['resize'] = 'resize'
-
-    # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
-    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
-
-    class Config(InvocationConfig):
-        schema_extra: {
-            ui: {
-                tags: ['resize', 'image'],
-                title: ['My Custom Resize']
-            }
-        }
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Load the image using InvokeAI's predefined Image Service.
-        image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
-
-        # Resizing the image
-        # Because we used the above service, we already have a PIL image. So we can simply resize.
-        resized_image = image.resize((self.width, self.height))
-
-        # Preparing the image for output using InvokeAI's predefined Image Service.
-        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,
-        )
-
-        # Returning the Image
-        return ImageOutput(
-            image=ImageField(
-                image_name=output_image.image_name,
-                image_origin=output_image.image_origin,
-            ),
-            width=output_image.width,
-            height=output_image.height,
-        )
-```
-
-We now customized our code to let the frontend know that our Invocation falls
-under `resize` and `image` categories. So when the user searches for these
-particular words, our Invocation will show up too.
-
-We also set a custom title for our Invocation. So instead of being called
-`Resize`, it will be called `My Custom Resize`.
-
-As simple as that.
-
-As time goes by, InvokeAI will further improve and add more customizability for
-Invocation configuration. We will have more documentation regarding this at a
-later time.
-
-# **[TODO]**
-
-## Custom Components For Frontend
-
-Every backend input type should have a corresponding frontend component so the
-UI knows what to render when you use a particular field type.
-
-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.
-
----
-
-# OLD -- TO BE DELETED OR MOVED LATER
-
----
+Invocations represent a single operation, its inputs, and its outputs. These operations and their outputs can be chained together to generate and modify images.
 
 ## Creating a new invocation
 
-To create a new invocation, either find the appropriate module file in
-`/ldm/invoke/app/invocations` to add your invocation to, or create a new one in
-that folder. All invocations in that folder will be discovered and made
-available to the CLI and API automatically. Invocations make use of
-[typing](https://docs.python.org/3/library/typing.html) and
-[pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration
-into the CLI and API.
+To create a new invocation, either find the appropriate module file in `/ldm/invoke/app/invocations` to add your invocation to, or create a new one in that folder. All invocations in that folder will be discovered and made available to the CLI and API automatically. Invocations make use of [typing](https://docs.python.org/3/library/typing.html) and [pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration into the CLI and API.
 
 An invocation looks like this:
 
 ```py
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
-
-    # fmt: off
-    type: Literal["upscale"] = "upscale"
+    type: Literal['upscale'] = 'upscale'
 
     # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
-    strength: float                = Field(default=0.75, gt=0, le=1, description="The strength")
-    level: Literal[2, 4]           = Field(default=2, description="The upscale level")
-    # fmt: on
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["upscaling", "image"],
-            },
-        }
+    image: Union[ImageField,None] = Field(description="The input image")
+    strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2,4]           = Field(default=2, description = "The upscale level")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
-        results = context.services.restoration.upscale_and_reconstruct(
-            image_list=[[image, 0]],
-            upscale=(self.level, self.strength),
-            strength=0.0,  # GFPGAN strength
-            save_original=False,
-            image_callback=None,
+        image = context.services.images.get(self.image.image_type, self.image.image_name)
+        results = context.services.generate.upscale_and_reconstruct(
+            image_list     = [[image, 0]],
+            upscale        = (self.level, self.strength),
+            strength       = 0.0, # GFPGAN strength
+            save_original  = False,
+            image_callback = None,
         )
 
         # Results are image and seed, unwrap for now
         # TODO: can this return multiple results?
-        image_dto = context.services.images.create(
-            image=results[0][0],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
+        context.services.images.save(image_type, image_name, results[0][0])
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
-            width=image_dto.width,
-            height=image_dto.height,
+            image = ImageField(image_type = image_type, image_name = image_name)
         )
-
 ```
 
 Each portion is important to implement correctly.
 
 ### Class definition and type
-
 ```py
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
     type: Literal['upscale'] = 'upscale'
 ```
-
-All invocations must derive from `BaseInvocation`. They should have a docstring
-that declares what they do in a single, short line. They should also have a
-`type` with a type hint that's `Literal["command_name"]`, where `command_name`
-is what the user will type on the CLI or use in the API to create this
-invocation. The `command_name` must be unique. The `type` must be assigned to
-the value of the literal in the type hint.
+All invocations must derive from `BaseInvocation`. They should have a docstring that declares what they do in a single, short line. They should also have a `type` with a type hint that's `Literal["command_name"]`, where `command_name` is what the user will type on the CLI or use in the API to create this invocation. The `command_name` must be unique. The `type` must be assigned to the value of the literal in the type hint.
 
 ### Inputs
-
 ```py
     # Inputs
     image: Union[ImageField,None] = Field(description="The input image")
     strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
     level: Literal[2,4]           = Field(default=2, description="The upscale level")
 ```
+Inputs consist of three parts: a name, a type hint, and a `Field` with default, description, and validation information. For example:
+| Part | Value | Description |
+| ---- | ----- | ----------- |
+| Name | `strength` | This field is referred to as `strength` |
+| Type Hint | `float` | This field must be of type `float` |
+| Field | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
 
-Inputs consist of three parts: a name, a type hint, and a `Field` with default,
-description, and validation information. For example:
+Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this field to be parsed with `None` as a value, which enables linking to previous invocations. All fields should either provide a default value or allow `None` as a value, so that they can be overwritten with a linked output from another invocation.
 
-| Part      | Value                                                         | Description                                                                                                               |
-| --------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
-| Name      | `strength`                                                    | This field is referred to as `strength`                                                                                   |
-| Type Hint | `float`                                                       | This field must be of type `float`                                                                                        |
-| Field     | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
+The special type `ImageField` is also used here. All images are passed as `ImageField`, which protects them from pydantic validation errors (since images only ever come from links).
 
-Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this
-field to be parsed with `None` as a value, which enables linking to previous
-invocations. All fields should either provide a default value or allow `None` as
-a value, so that they can be overwritten with a linked output from another
-invocation.
-
-The special type `ImageField` is also used here. All images are passed as
-`ImageField`, which protects them from pydantic validation errors (since images
-only ever come from links).
-
-Finally, note that for all linking, the `type` of the linked fields must match.
-If the `name` also matches, then the field can be **automatically linked** to a
-previous invocation by name and matching.
-
-### Config
-
-```py
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["upscaling", "image"],
-            },
-        }
-```
-
-This is an optional configuration for the invocation. It inherits from
-pydantic's model `Config` class, and it used primarily to customize the
-autogenerated OpenAPI schema.
-
-The UI relies on the OpenAPI schema in two ways:
-
-- An API client & Typescript types are generated from it. This happens at build
-  time.
-- The node editor parses the schema into a template used by the UI to create the
-  node editor UI. This parsing happens at runtime.
-
-In this example, a `ui` key has been added to the `schema_extra` dict to provide
-some tags for the UI, to facilitate filtering nodes.
-
-See the Schema Generation section below for more information.
+Finally, note that for all linking, the `type` of the linked fields must match. If the `name` also matches, then the field can be **automatically linked** to a previous invocation by name and matching.
 
 ### Invoke Function
-
 ```py
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
-        results = context.services.restoration.upscale_and_reconstruct(
-            image_list=[[image, 0]],
-            upscale=(self.level, self.strength),
-            strength=0.0,  # GFPGAN strength
-            save_original=False,
-            image_callback=None,
+        image = context.services.images.get(self.image.image_type, self.image.image_name)
+        results = context.services.generate.upscale_and_reconstruct(
+            image_list     = [[image, 0]],
+            upscale        = (self.level, self.strength),
+            strength       = 0.0, # GFPGAN strength
+            save_original  = False,
+            image_callback = None,
         )
 
         # Results are image and seed, unwrap for now
-        # TODO: can this return multiple results?
-        image_dto = context.services.images.create(
-            image=results[0][0],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
+        context.services.images.save(image_type, image_name, results[0][0])
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
-            width=image_dto.width,
-            height=image_dto.height,
+            image = ImageField(image_type = image_type, image_name = image_name)
         )
 ```
+The `invoke` function is the last portion of an invocation. It is provided an `InvocationContext` which contains services to perform work as well as a `session_id` for use as needed. It should return a class with output values that derives from `BaseInvocationOutput`.
 
-The `invoke` function is the last portion of an invocation. It is provided an
-`InvocationContext` which contains services to perform work as well as a
-`session_id` for use as needed. It should return a class with output values that
-derives from `BaseInvocationOutput`.
+Before being called, the invocation will have all of its fields set from defaults, inputs, and finally links (overriding in that order).
 
-Before being called, the invocation will have all of its fields set from
-defaults, inputs, and finally links (overriding in that order).
-
-Assume that this invocation may be running simultaneously with other
-invocations, may be running on another machine, or in other interesting
-scenarios. If you need functionality, please provide it as a service in the
-`InvocationServices` class, and make sure it can be overridden.
+Assume that this invocation may be running simultaneously with other invocations, may be running on another machine, or in other interesting scenarios. If you need functionality, please provide it as a service in the `InvocationServices` class, and make sure it can be overridden.
 
 ### Outputs
-
 ```py
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
+    type: Literal['image'] = 'image'
 
-    # fmt: off
-    type: Literal["image_output"] = "image_output"
-    image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
-    # fmt: on
-
-    class Config:
-        schema_extra = {"required": ["type", "image", "width", "height"]}
+    image: ImageField = Field(default=None, description="The output image")
 ```
-
-Output classes look like an invocation class without the invoke method. Prefer
-to use an existing output class if available, and prefer to name inputs the same
-as outputs when possible, to promote automatic invocation linking.
-
-## Schema Generation
-
-Invocation, output and related classes are used to generate an OpenAPI schema.
-
-### Required Properties
-
-The schema generation treat all properties with default values as optional. This
-makes sense internally, but when when using these classes via the generated
-schema, we end up with e.g. the `ImageOutput` class having its `image` property
-marked as optional.
-
-We know that this property will always be present, so the additional logic
-needed to always check if the property exists adds a lot of extraneous cruft.
-
-To fix this, we can leverage `pydantic`'s
-[schema customisation](https://docs.pydantic.dev/usage/schema/#schema-customization)
-to mark properties that we know will always be present as required.
-
-Here's that `ImageOutput` class, without the needed schema customisation:
-
-```python
-class ImageOutput(BaseInvocationOutput):
-    """Base class for invocations that output an image"""
-
-    # fmt: off
-    type: Literal["image_output"] = "image_output"
-    image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
-    # fmt: on
-```
-
-The OpenAPI schema that results from this `ImageOutput` will have the `type`,
-`image`, `width` and `height` properties marked as optional, even though we know
-they will always have a value.
-
-```python
-class ImageOutput(BaseInvocationOutput):
-    """Base class for invocations that output an image"""
-
-    # fmt: off
-    type: Literal["image_output"] = "image_output"
-    image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
-    # fmt: on
-
-    # Add schema customization
-    class Config:
-        schema_extra = {"required": ["type", "image", "width", "height"]}
-```
-
-With the customization in place, the schema will now show these properties as
-required, obviating the need for extensive null checks in client code.
-
-See this `pydantic` issue for discussion on this solution:
-<https://github.com/pydantic/pydantic/discussions/4577>
+Output classes look like an invocation class without the invoke method. Prefer to use an existing output class if available, and prefer to name inputs the same as outputs when possible, to promote automatic invocation linking.

docs/contributing/LOCAL_DEVELOPMENT.md

@@ -1,83 +0,0 @@
-# Local Development
-
-If you are looking to contribute you will need to have a local development
-environment. See the
-[Developer Install](../installation/020_INSTALL_MANUAL.md#developer-install) for
-full details.
-
-Broadly this involves cloning the repository, installing the pre-reqs, and
-InvokeAI (in editable form). Assuming this is working, choose your area of
-focus.
-
-## Documentation
-
-We use [mkdocs](https://www.mkdocs.org) for our documentation with the
-[material theme](https://squidfunk.github.io/mkdocs-material/). Documentation is
-written in markdown files under the `./docs` folder and then built into a static
-website for hosting with GitHub Pages at
-[invoke-ai.github.io/InvokeAI](https://invoke-ai.github.io/InvokeAI).
-
-To contribute to the documentation you'll need to install the dependencies. Note
-the use of `"`.
-
-```zsh
-pip install ".[docs]"
-```
-
-Now, to run the documentation locally with hot-reloading for changes made.
-
-```zsh
-mkdocs serve
-```
-
-You'll then be prompted to connect to `http://127.0.0.1:8080` in order to
-access.
-
-## Backend
-
-The backend is contained within the `./invokeai/backend` folder structure. To
-get started however please install the development dependencies.
-
-From the root of the repository run the following command. Note the use of `"`.
-
-```zsh
-pip install ".[test]"
-```
-
-This in an optional group of packages which is defined within the
-`pyproject.toml` and will be required for testing the changes you make the the
-code.
-
-### Running Tests
-
-We use [pytest](https://docs.pytest.org/en/7.2.x/) for our test suite. Tests can
-be found under the `./tests` folder and can be run with a single `pytest`
-command. Optionally, to review test coverage you can append `--cov`.
-
-```zsh
-pytest --cov
-```
-
-Test outcomes and coverage will be reported in the terminal. In addition a more
-detailed report is created in both XML and HTML format in the `./coverage`
-folder. The HTML one in particular can help identify missing statements
-requiring tests to ensure coverage. This can be run by opening
-`./coverage/html/index.html`.
-
-For example.
-
-```zsh
-pytest --cov; open ./coverage/html/index.html
-```
-
-??? info "HTML coverage report output"
-
-    ![html-overview](../assets/contributing/html-overview.png)
-
-    ![html-detail](../assets/contributing/html-detail.png)
-
-## Front End
-
-<!--#TODO: get input from blessedcoolant here, for the moment inserted the frontend README via snippets extension.-->
-
---8<-- "invokeai/frontend/web/README.md"

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](../features/VARIATIONS.md). |
-| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](../features/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/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/features/CLI.md

@@ -0,0 +1,589 @@
+---
+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](./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](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/features/CONCEPTS.md

@@ -1,12 +1,9 @@
 ---
-title: Concepts 
+title: Styles and Subjects
 ---
 
 # :material-library-shelves: The Hugging Face Concepts Library and Importing Textual Inversion files
 
-With the advances in research, many new capabilities are available to customize the knowledge and understanding of novel concepts not originally contained in the base model. 
-
-
 ## Using Textual Inversion Files
 
 Textual inversion (TI) files are small models that customize the output of
@@ -15,21 +12,27 @@ and artistic styles. They are also known as "embeds" in the machine learning
 world.
 
 Each TI file introduces one or more vocabulary terms to the SD model. These are
-known in InvokeAI as "triggers." Triggers are denoted using angle brackets 
-as in "<trigger-phrase>". The two most common type of
+known in InvokeAI as "triggers." Triggers are often, but not always, denoted
+using angle brackets as in "<trigger-phrase>". The two most common type of
 TI files that you'll encounter are `.pt` and `.bin` files, which are produced by
 different TI training packages. InvokeAI supports both formats, but its
-[built-in TI training system](TRAINING.md) produces `.pt`.
+[built-in TI training system](TEXTUAL_INVERSION.md) produces `.pt`.
 
 The [Hugging Face company](https://huggingface.co/sd-concepts-library) has
 amassed a large ligrary of >800 community-contributed TI files covering a
-broad range of subjects and styles. You can also install your own or others' TI files 
-by placing them in the designated directory for the compatible model type
+broad range of subjects and styles. InvokeAI has built-in support for this
+library which downloads and merges TI files automatically upon request. You can
+also install your own or others' TI files by placing them in a designated
+directory.
+
+You may also be interested in using [LoRA Models](LORAS.md) to
+generate images with specialized styles and subjects.
 
 ### An Example
 
-Here are a few examples to illustrate how it works. All these images were
-generated using the command-line client and the Stable Diffusion 1.5 model:
+Here are a few examples to illustrate how Textual Inversion works. All
+these images were generated using the command-line client and the
+Stable Diffusion 1.5 model:
 
 |         Japanese gardener          | Japanese gardener <ghibli-face> | Japanese gardener <hoi4-leaders> | Japanese gardener <cartoona-animals> |
 | :--------------------------------: | :-----------------------------------: | :------------------------------------: | :----------------------------------------: |
@@ -42,43 +45,120 @@ You can also combine styles and concepts:
   | :--------------------------------------------------------: |
   | ![](../assets/concepts/image5.png)                         |
 </figure>
+## Using a Hugging Face Concept
 
+!!! warning "Authenticating to HuggingFace"
+
+    Some concepts require valid authentication to HuggingFace. Without it, they will not be downloaded
+    and will be silently ignored.
+
+    If you used an installer to install InvokeAI, you may have already set a HuggingFace token.
+    If you skipped this step, you can:
+
+    - run the InvokeAI configuration script again (if you used a manual installer): `invokeai-configure`
+    - set one of the `HUGGINGFACE_TOKEN` or `HUGGING_FACE_HUB_TOKEN` environment variables to contain your token
+
+    Finally, if you already used any HuggingFace library on your computer, you might already have a token
+    in your local cache. Check for a hidden `.huggingface` directory in your home folder. If it
+    contains a `token` file, then you are all set.
+
+
+Hugging Face TI concepts are downloaded and installed automatically as you
+require them. This requires your machine to be connected to the Internet. To
+find out what each concept is for, you can browse the
+[Hugging Face concepts library](https://huggingface.co/sd-concepts-library) and
+look at examples of what each concept produces.
+
+When you have an idea of a concept you wish to try, go to the command-line
+client (CLI) and type a `<` character and the beginning of the Hugging Face
+concept name you wish to load. Press ++tab++, and the CLI will show you all
+matching concepts. You can also type `<` and hit ++tab++ to get a listing of all
+~800 concepts, but be prepared to scroll up to see them all! If there is more
+than one match you can continue to type and ++tab++ until the concept is
+completed.
+
+!!! example
+
+    if you type in `<x` and hit ++tab++, you'll be prompted with the completions:
+
+    ```py
+    <xatu2>        <xatu>         <xbh>          <xi>           <xidiversity>  <xioboma>      <xuna>         <xyz>
+    ```
+
+    Now type `id` and press ++tab++. It will be autocompleted to `<xidiversity>`
+    because this is a unique match.
+
+    Finish your prompt and generate as usual. You may include multiple concept terms
+    in the prompt.
+
+If you have never used this concept before, you will see a message that the TI
+model is being downloaded and installed. After this, the concept will be saved
+locally (in the `models/sd-concepts-library` directory) for future use.
+
+Several steps happen during downloading and installation, including a scan of
+the file for malicious code. Should any errors occur, you will be warned and the
+concept will fail to load. Generation will then continue treating the trigger
+term as a normal string of characters (e.g. as literal `<ghibli-face>`).
+
+You can also use `<concept-names>` in the WebGUI's prompt textbox. There is no
+autocompletion at this time.
 
 ## Installing your Own TI Files
 
 You may install any number of `.pt` and `.bin` files simply by copying them into
-the `embedding` directory of the corresponding InvokeAI models directory (usually `invokeai`
-in your home directory). For example, you can simply move a Stable Diffusion 1.5 embedding file to
-the `sd-1/embedding` folder. Be careful not to overwrite one file with another.
+the `embeddings` directory of the InvokeAI runtime directory (usually `invokeai`
+in your home directory). You may create subdirectories in order to organize the
+files in any way you wish. Be careful not to overwrite one file with another.
 For example, TI files generated by the Hugging Face toolkit share the named
-`learned_embedding.bin`. You can rename these, or use subdirectories to keep them distinct.
+`learned_embedding.bin`. You can use subdirectories to keep them distinct.
 
-At startup time, InvokeAI will scan the various `embedding` directories and load any TI
-files it finds there for compatible models. At startup you will see a message similar to this one:
+At startup time, InvokeAI will scan the `embeddings` directory and load any TI
+files it finds there. At startup you will see messages similar to these:
 
 ```bash
->> Current embedding manager terms: <HOI4-Leader>, <princess-knight>
+>> Loading embeddings from /data/lstein/invokeai-2.3/embeddings
+   | Loading v1 embedding file: style-hamunaptra
+   | Loading v4 embedding file: embeddings/learned_embeds-steps-500.bin
+   | Loading v2 embedding file: lfa
+   | Loading v3 embedding file: easynegative
+   | Loading v1 embedding file: rem_rezero
+   | Loading v2 embedding file: midj-strong
+   | Loading v4 embedding file: anime-background-style-v2/learned_embeds.bin
+   | Loading v4 embedding file: kamon-style/learned_embeds.bin
+   ** Notice: kamon-style/learned_embeds.bin was trained on a model with an incompatible token dimension: 768 vs 1024.
+>> Textual inversion triggers: <anime-background-style-v2>, <easynegative>, <lfa>, <midj-strong>, <milo>, Rem3-2600, Style-Hamunaptra
 ```
-To use these when generating, simply type the `<` key in your prompt to open the Textual Inversion WebUI and 
-select the embedding you'd like to use. This UI has type-ahead support, so you can easily find supported embeddings.
 
-## Using LoRAs
+Textual Inversion embeddings trained on version 1.X stable diffusion
+models are incompatible with version 2.X models and vice-versa.
 
-LoRA files are models that customize the output of Stable Diffusion image generation.
-Larger than embeddings, but much smaller than full models, they augment SD with improved
-understanding of subjects and artistic styles.
+After the embeddings load, InvokeAI will print out a list of all the
+recognized trigger terms. To trigger the term, include it in the
+prompt exactly as written, including angle brackets if any and
+respecting the capitalization.
 
-Unlike TI files, LoRAs do not introduce novel vocabulary into the model's known tokens. Instead,
-LoRAs augment the model's weights that are applied to generate imagery. LoRAs may be supplied
-with a "trigger" word that they have been explicitly trained on, or may simply apply their 
-effect without being triggered.
+There are at least four different embedding file formats, and each uses
+a different convention for the trigger terms. In some cases, the
+trigger term is specified in the file contents and may or may not be
+surrounded by angle brackets. In the example above, `Rem3-2600`,
+`Style-Hamunaptra`, and `<midj-strong>` were specified this way and
+there is no easy way to change the term.
 
-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 `lora` directory of the corresponding InvokeAI models directory (usually `invokeai`
-in your home directory). For example, you can simply move a Stable Diffusion 1.5 LoRA file to
-the `sd-1/lora` folder.
+In other cases the trigger term is not contained within the embedding
+file. In this case, InvokeAI constructs a trigger term consisting of
+the base name of the file (without the file extension) surrounded by
+angle brackets. In the example above `<easynegative`> is such a file
+(the filename was `easynegative.safetensors`). In such cases, you can
+change the trigger term simply by renaming the file.
 
-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 the appropriate weight recommended by the model provider. Typically, most LoRAs perform best at a weight of .75-1. 
+## Training your own Textual Inversion models
 
+InvokeAI provides a script that lets you train your own Textual
+Inversion embeddings using a small number (about a half-dozen) images
+of your desired style or subject. Please see [Textual
+Inversion](TEXTUAL_INVERSION.md) for details.
+
+## Further Reading
+
+Please see [the repository](https://github.com/rinongal/textual_inversion) and
+associated paper for details and limitations.

docs/features/CONFIGURATION.md

@@ -1,287 +0,0 @@
----
-title: Configuration
----
-
-# :material-tune-variant: InvokeAI 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:
-
-1. By editing settings in the `invokeai.yaml` file.
-2. By setting environment variables.
-3. On the command-line, when InvokeAI is launched.
-
-In addition, the most commonly changed settings are accessible
-graphically via the `invokeai-configure` script.
-
-### How the Configuration System Works
-
-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.
-
-#### Finding the Root Directory
-
-To find its root directory, InvokeAI uses the following recipe:
-
-1. It first looks for the argument `--root <path>` on the command line
-it was launched from, and uses the indicated path if present.
-
-2. Next it looks for the environment variable INVOKEAI_ROOT, and uses
-the directory path found there if present.
-
-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.
-
-4. Finally, InvokeAI looks for a directory in the current user's home
-directory named `invokeai`.
-
-#### 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
-    nsfw_checker: false
-    patchmatch: true
-    restore: true
-...
-```
-
-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.
-
-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/).
-
-You can fix a broken `invokeai.yaml` by deleting it and running the
-configuration script again -- option [7] in the launcher, "Re-run the
-configure script".
-
-#### Reading Environment Variables
-
-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:
-
-```
-export INVOKEAI_port=8000
-invokeai-web
-```
-
-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.
-
-#### Reading the Command Line
-
-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`.
-
-If you are using the launcher (`invoke.sh` or `invoke.bat`) to launch
-InvokeAI, then just pass the command-line arguments to the launcher:
-
-```
-invoke.bat --port 8000 --host 0.0.0.0
-```
-
-The arguments will be applied when you select the web server option
-(and the other options as well).
-
-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`:
-
-```
-> C:\Users\Fred\invokeai\.venv\scripts\activate
-(.venv) > invokeai-web --port 8000 --host 0.0.0.0
-```
-
-You can get a listing and brief instructions for each of the
-command-line options by giving the `--help` argument:
-
-```
-(.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]
-                [--nsfw_checker | --no-nsfw_checker] [--patchmatch | --no-patchmatch] [--restore | --no-restore]
-                [--always_use_cpu | --no-always_use_cpu] [--free_gpu_mem | --no-free_gpu_mem] [--max_cache_size MAX_CACHE_SIZE]
-                [--max_vram_cache_size MAX_VRAM_CACHE_SIZE] [--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}]
-...
-```
-
-## The Configuration Settings
-
-The configuration settings are divided into several distinct
-groups in `invokeia.yaml`:
-
-### Web Server
-
-| 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  |
-
-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 |
-| `nsfw_checker` | `true`     | Activate the NSFW checker to blur out risque images |
-| `patchmatch` | `true`     | Activate the "patchmatch" algorithm for improved inpainting |
-| `restore`    | `true`     | Activate the facial restoration features (DEPRECATED; restoration features will be removed in 3.0.0) |
-
-### Memory/Performance
-
-These options tune InvokeAI's memory and performance characteristics.
-
-| Setting  | Default Value  |  Description |
-|----------|----------------|--------------|
-| `always_use_cpu`     | `false`      | Use the CPU to generate images, even if a GPU is available |
-| `free_gpu_mem`       | `false`      | Aggressively free up GPU memory after each operation; this will allow you to run in low-VRAM environments with some performance penalties |
-| `max_cache_size`       | `6`      | Amount of CPU RAM (in GB) to reserve for caching models in memory; more cache allows you to keep models in memory and switch among them quickly |
-| `max_vram_cache_size`  | `2.75`   | Amount of GPU VRAM (in GB) to reserve for caching models in VRAM; more cache speeds up generation but reduces the size of the images that can be generated. This can be set to zero to maximize the amount of memory available for generation. |
-| `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 |
-| `sequential_guidance`     | `false`      | Calculate guidance in serial rather than in parallel, lowering memory requirements at the cost of some performance loss |
-| `xformers_enabled`        | `true`      | If the x-formers memory-efficient attention module is installed, activate it for better memory usage and generation speed|
-| `tiled_decode`            | `false`     | If true, then during the VAE decoding phase the image will be decoded a section at a time, reducing memory consumption at the cost of a performance hit |
-
-### 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 |
-
-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
-```
-
-* `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
-  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:
-
-```
-  syslog=/dev/log`      - log to the /dev/log device
-  syslog=localhost`     - log to the network logger running on the local machine
-  syslog=localhost:512` - same as above, but using a non-standard port
-  syslog=fredserver,facility=LOG_USER,socktype=SOCK_DRAM`
-                        - 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
-  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
-  POST method.
-
-```
- http=http://my.server/path/to/logger,method=POST
-```
-
-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.

docs/features/CONTROLNET.md

@@ -1,92 +0,0 @@
----
-title: ControlNet
----
-
-# :material-loupe: ControlNet
-
-## ControlNet
-
-ControlNet
-
-ControlNet is a powerful set of features developed by the open-source community (notably, Stanford researcher [**@ilyasviel**](https://github.com/lllyasviel)) that allows you to apply a secondary neural network model to your image generation process in Invoke.
-
-With ControlNet, you can get more control over the output of your image generation, providing you with a way to direct the network towards generating images that better fit your desired style or outcome.
-
-
-### How it works
-
-ControlNet works by analyzing an input image, pre-processing that image to identify relevant information that can be interpreted by each specific ControlNet model, and then inserting that control information into the generation process. This can be used to adjust the style, composition, or other aspects of the image to better achieve a specific result.
-
-
-### Models
-
-As part of the model installation, ControlNet models can be selected including a variety of pre-trained models that have been added to achieve different effects or styles in your generated images. Further ControlNet models may require additional code functionality to also be incorporated into Invoke's Invocations folder. You should expect to follow any installation instructions for ControlNet models loaded  outside the default models provided by Invoke. The default models include:
-
-
-**Canny**:
-
-When the Canny model is used in ControlNet, Invoke will attempt to generate images that match the edges detected. 
-
-Canny edge detection works by detecting the edges in an image by looking for abrupt changes in intensity. It is known for its ability to detect edges accurately while reducing noise and false edges, and the preprocessor can identify more information by decreasing the thresholds.
-
-**M-LSD**: 
-
-M-LSD is another edge detection algorithm used in ControlNet. It stands for Multi-Scale Line Segment Detector. 
-
-It detects straight line segments in an image by analyzing the local structure of the image at multiple scales.  It can be useful for architectural imagery, or anything where straight-line structural information is needed for the resulting output. 
-
-**Lineart**: 
-
-The Lineart model in ControlNet generates line drawings from an input image. The resulting pre-processed image is a simplified version of the original, with only the outlines of objects visible.The Lineart model in ControlNet is known for its ability to accurately capture the contours of the objects in an input sketch. 
-
-**Lineart Anime**: 
-
-A variant of the Lineart model that generates line drawings with a distinct style inspired by anime and manga art styles.
-
-**Depth**: 
-A model that generates depth maps of images, allowing you to create more realistic 3D models or to simulate depth effects in post-processing.
-
-**Normal Map (BAE):** 
-A model that generates normal maps from input images, allowing for more realistic lighting effects in 3D rendering.
-		
-**Image Segmentation**: 
-A model that divides input images into segments or regions, each of which corresponds to a different object or part of the image. (More details coming soon)
-
-
-**Openpose**: 
-The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
-
-**Mediapipe Face**:
-
-The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.
-
-**Tile (experimental)**:
-
-The Tile model fills out details in the image to match the image, rather than the prompt. The Tile Model is a versatile tool that offers a range of functionalities. Its primary capabilities can be boiled down to two main behaviors:
-
-- It can reinterpret specific details within an image and create fresh, new elements.
-- It has the ability to disregard global instructions if there's a discrepancy between them and the local context or specific parts of the image. In such cases, it uses the local context to guide the process.
-
-The Tile Model can be a powerful tool in your arsenal for enhancing image quality and details. If there are undesirable elements in your images, such as blurriness caused by resizing, this model can effectively eliminate these issues, resulting in cleaner, crisper images. Moreover, it can generate and add refined details to your images, improving their overall quality and appeal. 
-
-**Pix2Pix (experimental)**
-
-With Pix2Pix, you can input an image into the controlnet, and then "instruct" the model to change it using your prompt. For example, you can say "Make it winter" to add more wintry elements to a scene.
-
-**Inpaint**: Coming Soon - Currently this model is available but not functional on the Canvas. An upcoming release will provide additional capabilities for using this model when inpainting.
-
-Each of these models can be adjusted and combined with other ControlNet models to achieve different results, giving you even more control over your image generation process.
-
-
-## Using ControlNet
-
-To use ControlNet, you can simply select the desired model and adjust both the ControlNet and Pre-processor settings to achieve the desired result. You can also use multiple ControlNet models at the same time, allowing you to achieve even more complex effects or styles in your generated images.
-
-
-Each ControlNet has two settings that are applied to the ControlNet.
-
-Weight - Strength of the Controlnet model applied to the generation for the section, defined by start/end.
-
-Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
-
-Additionally, each ControlNet section can be expanded in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in when you Invoke.

docs/features/IMG2IMG.md

@@ -4,13 +4,86 @@ title: Image-to-Image
 
 # :material-image-multiple: Image-to-Image
 
-InvokeAI provides an "img2img" feature that lets you seed your
-creations with an initial drawing or photo. This is a really cool
-feature that tells stable diffusion to build the prompt on top of the
-image you provide, preserving the original's basic shape and layout.
+Both the Web and command-line interfaces provide an "img2img" feature
+that lets you seed your creations with an initial drawing or
+photo. This is a really cool feature that tells stable diffusion to
+build the prompt on top of the image you provide, preserving the
+original's basic shape and layout.
 
-For a walkthrough of using Image-to-Image in the Web UI, see [InvokeAI
-Web Server](./WEB.md#image-to-image).
+See the [WebUI Guide](WEB.md) for a walkthrough of the img2img feature
+in the InvokeAI web server. This document describes how to use img2img
+in the command-line tool.
+
+## Basic Usage
+
+Launch the command-line client by launching `invoke.sh`/`invoke.bat`
+and choosing option (1). Alternative, activate the InvokeAI
+environment and issue the command `invokeai`.
+
+Once the `invoke> ` prompt appears, you can start an img2img render by
+pointing to a seed file with the `-I` option as shown here:
+
+!!! example ""
+
+    ```commandline
+    tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
+    ```
+
+    <figure markdown>
+
+    | original image | generated image |
+    | :------------: | :-------------: |
+    | ![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 } | ![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 } |
+
+    </figure>
+
+The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
+(`-f`) controls how much the original will be modified, ranging from `0.0` (keep
+the original intact), to `1.0` (ignore the original completely). The default is
+`0.75`, and ranges from `0.25-0.90` give interesting results. Other relevant
+options include `-C` (classification free guidance scale), and `-s` (steps).
+Unlike `txt2img`, adding steps will continuously change the resulting image and
+it will not converge.
+
+You may also pass a `-v<variation_amount>` option to generate `-n<iterations>`
+count variants on the original image. This is done by passing the first
+generated image back into img2img the requested number of times. It generates
+interesting variants.
+
+Note that the prompt makes a big difference. For example, this slight variation
+on the prompt produces a very different image:
+
+<figure markdown>
+![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png){ width=320 }
+<caption markdown>photograph of a tree on a hill with a river</caption>
+</figure>
+
+!!! tip
+
+    When designing prompts, think about how the images scraped from the internet were
+    captioned. Very few photographs will be labeled "photograph" or "photorealistic."
+    They will, however, be captioned with the publication, photographer, camera model,
+    or film settings.
+
+If the initial image contains transparent regions, then Stable Diffusion will
+only draw within the transparent regions, a process called
+[`inpainting`](./INPAINTING.md#creating-transparent-regions-for-inpainting).
+However, for this to work correctly, the color information underneath the
+transparent needs to be preserved, not erased.
+
+!!! warning "**IMPORTANT ISSUE** "
+
+    `img2img` does not work properly on initial images smaller
+    than 512x512. Please scale your image to at least 512x512 before using it.
+    Larger images are not a problem, but may run out of VRAM on your GPU card. To
+    fix this, use the --fit option, which downscales the initial image to fit within
+    the box specified by width x height:
+
+    ```
+    tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
+    ```
+
+## How does it actually work, though?
 
 The main difference between `img2img` and `prompt2img` is the starting point.
 While `prompt2img` always starts with pure gaussian noise and progressively
@@ -26,6 +99,10 @@ seed `1592514025` develops something like this:
 
 !!! example ""
 
+    ```bash
+    invoke> "fire" -s10 -W384 -H384 -S1592514025
+    ```
+
     <figure markdown>
     ![latent steps](../assets/img2img/000019.steps.png){ width=720 }
     </figure>
@@ -80,8 +157,17 @@ Diffusion has less chance to refine itself, so the result ends up inheriting all
 the problems of my bad drawing.
 
 If you want to try this out yourself, all of these are using a seed of
-`1592514025` with a width/height of `384`, step count `10`, the
-`k_lms` sampler, and the single-word prompt `"fire"`.
+`1592514025` with a width/height of `384`, step count `10`, the default sampler
+(`k_lms`), and the single-word prompt `"fire"`:
+
+```bash
+invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
+```
+
+The code for rendering intermediates is on my (damian0815's) branch
+[document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) -
+run `invoke.py` and check your `outputs/img-samples/intermediates` folder while
+generating an image.
 
 ### Compensating for the reduced step count
 
@@ -94,6 +180,10 @@ give each generation 20 steps.
 Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD
 does `20` steps from my image):
 
+```bash
+invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
+```
+
 <figure markdown>
 ![000035.1592514025](../assets/img2img/000035.1592514025.png)
 </figure>
@@ -101,6 +191,10 @@ does `20` steps from my image):
 and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to
 make sure SD does `20` steps from my image):
 
+```commandline
+invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
+```
+
 <figure markdown>
 ![000046.1592514025](../assets/img2img/000046.1592514025.png)
 </figure>

docs/features/INPAINTING.md

@@ -0,0 +1,306 @@
+---
+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:
+
+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/features/LOGGING.md

@@ -1,171 +0,0 @@
----
-title: Controlling Logging
----
-
-# :material-image-off: Controlling Logging
-
-## Controlling How InvokeAI Logs Status Messages
-
-InvokeAI logs status messages using a configurable logging system. You
-can log to the terminal window, to a designated file on the local
-machine, to the syslog facility on a Linux or Mac, or to a properly
-configured web server. You can configure several logs at the same
-time, and control the level of message logged and the logging format
-(to a limited extent).
-
-Three command-line options control logging:
-
-### `--log_handlers <handler1> <handler2> ...`
-
-This option activates one or more log handlers. Options are "console",
-"file", "syslog" and "http". To specify more than one, separate them
-by spaces:
-
-```bash
-invokeai-web --log_handlers console syslog=/dev/log file=C:\Users\fred\invokeai.log
-```
-
-The format of these options is described below.
-
-### `--log_format {plain|color|legacy|syslog}`
-
-This controls the format of log messages written to the console. Only
-the "console" log handler is currently affected by this setting.
-
-* "plain" provides formatted messages like this:
-
-```bash
-
-[2023-05-24 23:18:2[2023-05-24 23:18:50,352]::[InvokeAI]::DEBUG --> this is a debug message
-[2023-05-24 23:18:50,352]::[InvokeAI]::INFO --> this is an informational messages
-[2023-05-24 23:18:50,352]::[InvokeAI]::WARNING --> this is a warning
-[2023-05-24 23:18:50,352]::[InvokeAI]::ERROR --> this is an error
-[2023-05-24 23:18:50,352]::[InvokeAI]::CRITICAL --> this is a critical error
-```
-
-* "color" produces similar output, but the text will be color coded to
-indicate the severity of the message.
-
-* "legacy" produces output similar to InvokeAI versions 2.3 and earlier:
-
-```bash
-### this is a critical error
-*** this is an error
-** this is a warning
->> this is an informational messages
-   | this is a debug message
-```
-
-* "syslog" produces messages suitable for syslog entries:
-
-```bash
-InvokeAI [2691178] <CRITICAL> this is a critical error
-InvokeAI [2691178] <ERROR> this is an error
-InvokeAI [2691178] <WARNING> this is a warning
-InvokeAI [2691178] <INFO> this is an informational messages
-InvokeAI [2691178] <DEBUG> this is a debug message
-```
-
-(note that the date, time and hostname will be added by the syslog
-system)
-
-### `--log_level {debug|info|warning|error|critical}`
-
-Providing this command-line option will cause only messages at the
-specified level or above to be emitted.
-
-## Console logging
-
-When "console" is provided to `--log_handlers`, messages will be
-written to the command line window in which InvokeAI was launched. By
-default, the color formatter will be used unless overridden by
-`--log_format`.
-
-## File logging
-
-When "file" is provided to `--log_handlers`, entries will be written
-to the file indicated in the path argument. By default, the "plain"
-format will be used:
-
-```bash
-invokeai-web --log_handlers file=/var/log/invokeai.log
-```
-
-## Syslog logging
-
-When "syslog" is requested, entries will be sent to the syslog
-system. There are a variety of ways to control where the log message
-is sent:
-
-* Send to the local machine using the `/dev/log` socket:
-
-```
-invokeai-web --log_handlers syslog=/dev/log
-```
-
-* Send to the local machine using a UDP message:
-
-```
-invokeai-web --log_handlers syslog=localhost
-```
-
-* Send to the local machine using a UDP message on a nonstandard
-  port:
-
-```
-invokeai-web --log_handlers syslog=localhost:512
-```
-
-* Send to a remote machine named "loghost" on the local LAN using
-  facility LOG_USER and UDP packets:
-
-```
-invokeai-web --log_handlers syslog=loghost,facility=LOG_USER,socktype=SOCK_DGRAM
-```
-
-This can be abbreviated `syslog=loghost`, as LOG_USER and SOCK_DGRAM
-are defaults.
-
-* Send to a remote machine named "loghost" using the facility LOCAL0
-  and using a TCP socket:
-
-```
-invokeai-web --log_handlers syslog=loghost,facility=LOG_LOCAL0,socktype=SOCK_STREAM
-```
-
-If no arguments are specified (just a bare "syslog"), then the logging
-system will look for a UNIX socket named `/dev/log`, and if not found
-try to send a UDP message to `localhost`. The Macintosh OS used to
-support logging to a socket named `/var/run/syslog`, but this feature
-has since been disabled.
-
-## Web logging
-
-If you have access to a web server that is configured to log messages
-when a particular URL is requested, you can log using the "http"
-method:
-
-```
-invokeai-web --log_handlers http=http://my.server/path/to/logger,method=POST
-```
-
-The optional [,method=] part can be used to specify whether the URL
-accepts GET (default) or POST messages.
-
-Currently password authentication and SSL are not supported.
-
-## Using the configuration file
-
-You can set and forget logging options by adding a "Logging" section
-to `invokeai.yaml`:
-
-```
-InvokeAI:
-  [... other settings...]
-  Logging:
-    log_handlers:
-       - console
-       - syslog=/dev/log
-    log_level: info
-    log_format: color
-```

docs/features/LORAS.md

@@ -0,0 +1,100 @@
+---
+title: Low-Rank Adaptation (LoRA) Models
+---
+
+# :material-library-shelves: Using Low-Rank Adaptation (LoRA) Models
+
+## Introduction
+
+LoRA is a technique for fine-tuning Stable Diffusion models using much
+less time and memory than traditional training techniques. The
+resulting model files are much smaller than full model files, and can
+be used to generate specialized styles and subjects.
+
+LoRAs are built on top of Stable Diffusion v1.x or 2.x checkpoint or
+diffusers models. To load a LoRA, you include its name in the text
+prompt using a simple syntax described below. While you will generally
+get the best results when you use the same model the LoRA was trained
+on, they will work to a greater or lesser extent with other models.
+The major caveat is that a LoRA built on top of a SD v1.x model cannot
+be used with a v2.x model, and vice-versa. If you try, you will get an
+error! You may refer to multiple LoRAs in your prompt.
+
+When you apply a LoRA in a prompt you can specify a weight. The higher
+the weight, the more influence it will have on the image. Useful
+ranges for weights are usually in the 0.0 to 1.0 range (with ranges
+between 0.5 and 1.0 being most typical). However you can specify a
+higher weight if you wish. Like models, each LoRA has a slightly
+different useful weight range and will interact with other generation
+parameters such as the CFG, step count and sampler. The author of the
+LoRA will often provide guidance on the best settings, but feel free
+to experiment. Be aware that it often helps to reduce the CFG value
+when using LoRAs.
+
+## Installing LoRAs
+
+This is very easy! Download a LoRA model file from your favorite site
+(e.g. [CIVITAI](https://civitai.com) and place it in the `loras`
+folder in the InvokeAI root directory (usually `~invokeai/loras` on
+Linux/Macintosh machines, and `C:\Users\your-name\invokeai/loras` on
+Windows systems). If the `loras` folder does not already exist, just
+create it. The vast majority of LoRA models use the Kohya file format,
+which is a type of `.safetensors` file.
+
+You may change where InvokeAI looks for the `loras` folder by passing the
+`--lora_directory` option to the `invoke.sh`/`invoke.bat` launcher, or
+by placing the option in `invokeai.init`. For example:
+
+```
+invoke.sh --lora_directory=C:\Users\your-name\SDModels\lora
+```
+
+## Using a LoRA in your prompt
+
+To activate a LoRA use the syntax `withLora(my-lora-name,weight)`
+somewhere in the text of the prompt. The position doesn't matter; use
+whatever is most comfortable for you.
+
+For example, if you have a LoRA named `parchment_people.safetensors`
+in your `loras` directory, you can load it with a weight of 0.9 with a
+prompt like this one:
+
+```
+family sitting at dinner table withLora(parchment_people,0.9)
+```
+
+Add additional `withLora()` phrases to load more LoRAs.
+
+You may omit the weight entirely to default to a weight of 1.0:
+
+```
+family sitting at dinner table withLora(parchment_people)
+```
+
+If you watch the console as your prompt executes, you will see
+messages relating to the loading and execution of the LoRA. If things
+don't work as expected, note down the console messages and report them
+on the InvokeAI Issues pages or Discord channel.
+
+That's pretty much all you need to know!
+
+## Training Kohya Models
+
+InvokeAI cannot currently train LoRA models, but it can load and use
+existing LoRA ones to generate images. While there are several LoRA
+model file formats, the predominant one is ["Kohya"
+format](https://github.com/kohya-ss/sd-scripts), written by [Kohya
+S.](https://github.com/kohya-ss). InvokeAI provides support for this
+format. For creating your own Kohya models, we recommend the Windows
+GUI written by former InvokeAI-team member
+[bmaltais](https://github.com/bmaltais), which can be found at
+[kohya_ss](https://github.com/bmaltais/kohya_ss).
+
+We can also recommend the [HuggingFace DreamBooth Training
+UI](https://huggingface.co/spaces/lora-library/LoRA-DreamBooth-Training-UI),
+a paid service that supports both Textual Inversion and LoRA training.
+
+You may also be interested in [Textual
+Inversion](TEXTUAL_INVERSION.md) training, which is supported by
+InvokeAI as a text console and command-line tool.
+

docs/features/MODEL_MERGING.md

@@ -71,3 +71,6 @@ under the selected name and register it with InvokeAI.
   use InvokeAI conventions - only alphanumeric letters and the
   characters ".+-".
 
+## Caveats
+
+This is a new script and may contain bugs.

docs/features/NODES.md

@@ -1,206 +0,0 @@
-# Nodes Editor (Experimental)
-
-🚨
-*The node editor is experimental. We've made it accessible because we use it to develop the application, but we have not addressed the many known rough edges. It's very easy to shoot yourself in the foot, and we cannot offer support for it until it sees full release (ETA v3.1). Everything is subject to change without warning.* 
-🚨
-
-The nodes editor is a blank canvas allowing for the use of individual functions and image transformations to control the image generation workflow. The node processing flow is usually done from left (inputs) to right (outputs), though linearity can become abstracted the more complex the node graph becomes. Nodes inputs and outputs are connected by dragging connectors from node to node.
-
-To better understand how nodes are used, think of how an electric power bar works. It takes in one input (electricity from a wall outlet) and passes it to multiple devices through multiple outputs. Similarly, a node could have multiple inputs and outputs functioning at the same (or different) time, but all node outputs pass information onward like a power bar passes electricity. Not all outputs are compatible with all inputs, however - Each node has different constraints on how it is expecting to input/output information. In general, node outputs are colour-coded to match compatible inputs of other nodes.
-
-## Anatomy of a Node
-
-Individual nodes are made up of the following:
-
-- Inputs: Edge points on the left side of the node window where you connect outputs from other nodes.
-- Outputs: Edge points on the right side of the node window where you connect to inputs on other nodes.
-- Options: Various options which are either manually configured, or overridden by connecting an output from another node to the input.
-
-## Diffusion Overview
-
-Taking the time to understand the diffusion process will help you to understand how to set up your nodes in the nodes editor. 
-
-There are two main spaces Stable Diffusion works in: image space and latent space.
-
-Image space represents images in pixel form that you look at. Latent space represents compressed inputs. It’s in latent space that Stable Diffusion processes images. A VAE (Variational Auto Encoder) is responsible for compressing and encoding inputs into latent space, as well as decoding outputs back into image space.
-
-When you generate an image using text-to-image, multiple steps occur in latent space:
-1. Random noise is generated at the chosen height and width. The noise’s characteristics are dictated by the chosen (or not chosen) seed. This noise tensor is passed into latent space. We’ll call this noise A.
-1. Using a model’s U-Net, a noise predictor examines noise A, and the words tokenized by CLIP from your prompt (conditioning). It generates its own noise tensor to predict what the final image might look like in latent space. We’ll call this noise B.
-1. Noise B is subtracted from noise A in an attempt to create a final latent image indicative of the inputs. This step is repeated for the number of sampler steps chosen.
-1. The VAE decodes the final latent image from latent space into image space.
-
-image-to-image is a similar process, with only step 1 being different:
-1. The input image is decoded from image space into latent space by the VAE. Noise is then added to the input latent image. Denoising Strength dictates how much noise is added, 0 being none, and 1 being all-encompassing. We’ll call this noise A. The process is then the same as steps 2-4 in the text-to-image explanation above. 
-
-Furthermore, a model provides the CLIP prompt tokenizer, the VAE, and a U-Net (where noise prediction occurs given a prompt and initial noise tensor).
-
-A noise scheduler (eg. DPM++ 2M Karras) schedules the subtraction of noise from the latent image across the sampler steps chosen (step 3 above). Less noise is usually subtracted at higher sampler steps. 
-
-## Node Types (Base Nodes)
-
-| Node <img width=160 align="right"> | Function                                                                              |
-| ---------------------------------- | --------------------------------------------------------------------------------------|
-| Add                                | Adds two numbers |
-| CannyImageProcessor                | Canny edge detection for ControlNet |
-| ClipSkip                           | Skip layers in clip text_encoder model |
-| Collect                            | Collects values into a collection |
-| Prompt (Compel)                    | Parse prompt using compel package to conditioning |
-| ContentShuffleImageProcessor       | Applies content shuffle processing to image |
-| ControlNet                         | Collects ControlNet info to pass to other nodes |
-| CvInpaint                          | Simple inpaint using opencv |
-| Divide                             | Divides two numbers |
-| DynamicPrompt                      | Parses a prompt using adieyal/dynamic prompt's random or combinatorial generator |
-| FloatLinearRange                   | Creates a range |
-| HedImageProcessor                  | Applies HED edge detection to image |
-| ImageBlur                          | Blurs an image |
-| ImageChannel                       | Gets a channel from an image |
-| ImageCollection                    | Load a collection of images and provide it as output |
-| ImageConvert                       | Converts an image to a different mode |
-| ImageCrop                          | Crops an image to a specified box. The box can be outside of the image. |
-| ImageInverseLerp                   | Inverse linear interpolation of all pixels of an image |
-| ImageLerp                          | Linear interpolation of all pixels of an image |
-| ImageMultiply                      | Multiplies two images together using `PIL.ImageChops.Multiply()` |
-| ImagePaste                         | Pastes an image into another image |
-| ImageProcessor                     | Base class for invocations that reprocess images for ControlNet |
-| ImageResize                        | Resizes an image to specific dimensions |
-| ImageScale                         | Scales an image by a factor |
-| ImageToLatents                     | Scales latents by a given factor |
-| InfillColor                        | Infills transparent areas of an image with a solid color |
-| InfillPatchMatch                   | Infills transparent areas of an image using the PatchMatch algorithm |
-| InfillTile                         | Infills transparent areas of an image with tiles of the image |
-| Inpaint                            | Generates an image using inpaint |
-| Iterate                            | Iterates over a list of items |
-| LatentsToImage                     | Generates an image from latents |
-| LatentsToLatents                   | Generates latents using latents as base image |
-| LeresImageProcessor                | Applies leres processing to image |
-| LineartAnimeImageProcessor         | Applies line art anime processing to image |
-| LineartImageProcessor              | Applies line art processing to image |
-| LoadImage                          | Load an image and provide it as output |
-| Lora Loader                        | Apply selected lora to unet and text_encoder |
-| Model Loader                       | Loads a main model, outputting its submodels |
-| MaskFromAlpha                      | Extracts the alpha channel of an image as a mask |
-| MediapipeFaceProcessor             | Applies mediapipe face processing to image |
-| MidasDepthImageProcessor           | Applies Midas depth processing to image |
-| MlsdImageProcessor                 | Applied MLSD processing to image |
-| Multiply                           | Multiplies two numbers |
-| Noise                              | Generates latent noise |
-| NormalbaeImageProcessor            | Applies NormalBAE processing to image |
-| OpenposeImageProcessor             | Applies Openpose processing to image |
-| ParamFloat                         | A float parameter |
-| ParamInt                           | An integer parameter |
-| PidiImageProcessor                 | Applies PIDI processing to an image |
-| Progress Image                     | Displays the progress image in the Node Editor |
-| RandomInit                         | Outputs a single random integer |
-| RandomRange                        | Creates a collection of random numbers |
-| Range                              | Creates a range of numbers from start to stop with step |
-| RangeOfSize                        | Creates a range from start to start + size with step |
-| ResizeLatents                      | Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8. |
-| RestoreFace                        | Restores faces in the image |
-| ScaleLatents                       | Scales latents by a given factor |
-| SegmentAnythingProcessor           | Applies segment anything processing to image |
-| ShowImage                          | Displays a provided image, and passes it forward in the pipeline |
-| StepParamEasing                    | Experimental per-step parameter for easing for denoising steps |
-| Subtract                           | Subtracts two numbers |
-| TextToLatents                      | Generates latents from conditionings |
-| TileResampleProcessor              | Bass class for invocations that preprocess images for ControlNet |
-| Upscale                            | Upscales an image |
-| VAE Loader                         | Loads a VAE model, outputting a VaeLoaderOutput |
-| ZoeDepthImageProcessor             | Applies Zoe depth processing to image |
-
-## Node Grouping Concepts
-
-There are several node grouping concepts that can be examined with a narrow focus. These (and other) groupings can be pieced together to make up functional graph setups, and are important to understanding how groups of nodes work together as part of a whole. Note that the screenshots below aren't examples of complete functioning node graphs (see Examples).
-
-### Noise
-
-As described, an initial noise tensor is necessary for the latent diffusion process. As a result, all non-image *ToLatents nodes require a noise node input.  
-
-<img width="654" alt="groupsnoise" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/2e8d297e-ad55-4d27-bc93-c119dad2a2c5">
-
-### Conditioning
-
-As described, conditioning is necessary for the latent diffusion process, whether empty or not. As a result, all non-image *ToLatents nodes require positive and negative conditioning inputs. Conditioning is reliant on a CLIP tokenizer provided by the Model Loader node.
-
-<img width="1024" alt="groupsconditioning" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/f8f7ad8a-8d9c-418e-b5ad-1437b774b27e">
-
-### Image Space & VAE
-
-The ImageToLatents node doesn't require a noise node input, but requires a VAE input to convert the image from image space into latent space. In reverse, the LatentsToImage node requires a VAE input to convert from latent space back into image space.
-
-<img width="637" alt="groupsimgvae" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/dd99969c-e0a8-4f78-9b17-3ffe179cef9a">
-
-### Defined & Random Seeds
-
-It is common to want to use both the same seed (for continuity) and random seeds (for variance). To define a seed, simply enter it into the 'Seed' field on a noise node. Conversely, the RandomInt node generates a random integer between 'Low' and 'High', and can be used as input to the 'Seed' edge point on a noise node to randomize your seed.
-
-<img width="922" alt="groupsrandseed" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/af55bc20-60f6-438e-aba5-3ec871443710">
-
-### Control
-
-Control means to guide the diffusion process to adhere to a defined input or structure. Control can be provided as input to non-image *ToLatents nodes from ControlNet nodes. ControlNet nodes usually require an image processor which converts an input image for use with ControlNet.
-
-<img width="805" alt="groupscontrol" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/cc9c5de7-23a7-46c8-bbad-1f3609d999a6">
-
-### LoRA
-
-The Lora Loader node lets you load a LoRA (say that ten times fast) and pass it as output to both the Prompt (Compel) and non-image *ToLatents nodes. A model's CLIP tokenizer is passed through the LoRA into Prompt (Compel), where it affects conditioning. A model's U-Net is also passed through the LoRA into a non-image *ToLatents node, where it affects noise prediction.
-
-<img width="993" alt="groupslora" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/630962b0-d914-4505-b3ea-ccae9b0269da">
-
-### Scaling
-
-Use the ImageScale, ScaleLatents, and Upscale nodes to upscale images and/or latent images. The chosen method differs across contexts. However, be aware that latents are already noisy and compressed at their original resolution; scaling an image could produce more detailed results.
-
-<img width="644" alt="groupsallscale" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/99314f05-dd9f-4b6d-b378-31de55346a13">
-
-### Iteration + Multiple Images as Input
-
-Iteration is a common concept in any processing, and means to repeat a process with given input. In nodes, you're able to use the Iterate node to iterate through collections usually gathered by the Collect node. The Iterate node has many potential uses, from processing a collection of images one after another, to varying seeds across multiple image generations and more. This screenshot demonstrates how to collect several images and pass them out one at a time.
-
-<img width="788" alt="groupsiterate" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/4af5ca27-82c9-4018-8c5b-024d3ee0a121">
-
-### Multiple Image Generation + Random Seeds
-
-Multiple image generation in the node editor is done using the RandomRange node. In this case, the 'Size' field represents the number of images to generate. As RandomRange produces a collection of integers, we need to add the Iterate node to iterate through the collection. 
-
-To control seeds across generations takes some care. The first row in the screenshot will generate multiple images with different seeds, but using the same RandomRange parameters across invocations will result in the same group of random seeds being used across the images, producing repeatable results. In the second row, adding the RandomInt node as input to RandomRange's 'Seed' edge point will ensure that seeds are varied across all images across invocations, producing varied results.
-
-<img width="1027" alt="groupsmultigenseeding" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/518d1b2b-fed1-416b-a052-ab06552521b3">
-
-## Examples
-
-With our knowledge of node grouping and the diffusion process, let’s break down some basic graphs in the nodes editor. Note that a node's options can be overridden by inputs from other nodes. These examples aren't strict rules to follow and only demonstrate some basic configurations.
-
-### Basic text-to-image Node Graph
-
-<img width="875" alt="nodest2i" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/17c67720-c376-4db8-94f0-5e00381a61ee">
-
-- Model Loader: A necessity to generating images (as we’ve read above). We choose our model from the dropdown. It outputs a U-Net, CLIP tokenizer, and VAE.
-- Prompt (Compel): Another necessity. Two prompt nodes are created. One will output positive conditioning (what you want, ‘dog’), one will output negative (what you don’t want, ‘cat’). They both input the CLIP tokenizer that the Model Loader node outputs.
-- Noise: Consider this noise A from step one of the text-to-image explanation above. Choose a seed number, width, and height.
-- TextToLatents: This node takes many inputs for converting and processing text & noise from image space into latent space, hence the name TextTo**Latents**. In this setup, it inputs positive and negative conditioning from the prompt nodes for processing (step 2 above). It inputs noise from the noise node for processing (steps 2 & 3 above). Lastly, it inputs a U-Net from the Model Loader node for processing (step 2 above). It outputs latents for use in the next LatentsToImage node. Choose number of sampler steps, CFG scale, and scheduler.
-- LatentsToImage: This node takes in processed latents from the TextToLatents node, and the model’s VAE from the Model Loader node which is responsible for decoding latents back into the image space, hence the name LatentsTo**Image**. This node is the last stop, and once the image is decoded, it is saved to the gallery.
-
-### Basic image-to-image Node Graph
-
-<img width="998" alt="nodesi2i" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/3f2c95d5-cee7-4415-9b79-b46ee60a92fe">
-
-- Model Loader: Choose a model from the dropdown.
-- Prompt (Compel): Two prompt nodes. One positive (dog), one negative (dog). Same CLIP inputs from the Model Loader node as before.
-- ImageToLatents: Upload a source image directly in the node window, via drag'n'drop from the gallery, or passed in as input. The ImageToLatents node inputs the VAE from the Model Loader node to decode the chosen image from image space into latent space, hence the name ImageTo**Latents**. It outputs latents for use in the next LatentsToLatents node. It also outputs the source image's width and height for use in the next Noise node if the final image is to be the same dimensions as the source image.
-- Noise: A noise tensor is created with the width and height of the source image, and connected to the next LatentsToLatents node. Notice the width and height fields are overridden by the input from the ImageToLatents width and height outputs.
-- LatentsToLatents: The inputs and options are nearly identical to TextToLatents, except that LatentsToLatents also takes latents as an input. Considering our source image is already converted to latents in the last ImageToLatents node, and text + noise are no longer the only inputs to process, we use the LatentsToLatents node. 
-- LatentsToImage: Like previously, the LatentsToImage node will use the VAE from the Model Loader as input to decode the latents from LatentsToLatents into image space, and save it to the gallery.
-
-### Basic ControlNet Node Graph
-
-<img width="703" alt="nodescontrol" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/b02ded86-ceb4-44a2-9910-e19ad184d471">
-
-- Model Loader
-- Prompt (Compel)
-- Noise: Width and height of the CannyImageProcessor ControlNet image is passed in to set the dimensions of the noise passed to TextToLatents.
-- CannyImageProcessor: The CannyImageProcessor node is used to process the source image being used as a ControlNet. Each ControlNet processor node applies control in different ways, and has some different options to configure. Width and height are passed to noise, as mentioned. The processed ControlNet image is output to the ControlNet node.
-- ControlNet: Select the type of control model. In this case, canny is chosen as the CannyImageProcessor was used to generate the ControlNet image. Configure the control node options, and pass the control output to TextToLatents.
-- TextToLatents: Similar to the basic text-to-image example, except ControlNet is passed to the control input edge point.
-- LatentsToImage

docs/features/NSFW.md

@@ -31,22 +31,10 @@ turned on and off on the command line using `--nsfw_checker` and
 
 At installation time, InvokeAI will ask whether the checker should be
 activated by default (neither argument given on the command line). The
-response is stored in the InvokeAI initialization file
-(`invokeai.yaml` in the InvokeAI root directory).  You can change the
-default at any time by opening this file in a text editor and
-changing the line `nsfw_checker:` from true to false or vice-versa:
-
-
-```
-...
-  Features:
-    esrgan: true
-    internet_available: true
-    log_tokenization: false
-    nsfw_checker: true
-    patchmatch: true
-    restore: true
-```
+response is stored in the InvokeAI initialization file (usually
+`.invokeai` in your home directory). You can change the default at any
+time by opening this file in a text editor and commenting or
+uncommenting the line `--nsfw_checker`.
 
 ## Caveats
 
@@ -91,3 +79,11 @@ generates. However, it does write metadata into the PNG data area,
 including the prompt used to generate the image and relevant parameter
 settings. These fields can be examined using the `sd-metadata.py`
 script that comes with the InvokeAI package.
+
+Note that several other Stable Diffusion distributions offer
+wavelet-based "invisible" watermarking. We have experimented with the
+library used to generate these watermarks and have reached the
+conclusion that while the watermarking library may be adding
+watermarks to PNG images, the currently available version is unable to
+retrieve them successfully. If and when a functioning version of the
+library becomes available, we will offer this feature as well.

docs/features/OTHER.md

@@ -18,16 +18,43 @@ Output Example:
 
 ## **Seamless Tiling**
 
-The seamless tiling mode causes generated images to seamlessly tile
-with itself creating repetitive wallpaper-like patterns. To use it,
-activate the Seamless Tiling option in the Web GUI and then select
-whether to tile on the X (horizontal) and/or Y (vertical) axes. Tiling
-will then be active for the next set of generations.
-
-A nice prompt to test seamless tiling with is:
+The seamless tiling mode causes generated images to seamlessly tile with itself. To use it, add the
+`--seamless` option when starting the script which will result in all generated images to tile, or
+for each `invoke>` prompt as shown here:
 
+```python
+invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
 ```
-pond garden with lotus by claude monet"
+
+By default this will tile on both the X and Y axes. However, you can also specify specific axes to tile on with `--seamless_axes`.
+Possible values are `x`, `y`, and `x,y`:
+```python
+invoke> "pond garden with lotus by claude monet" --seamless --seamless_axes=x -s100 -n4
+```
+
+---
+
+## **Shortcuts: Reusing Seeds**
+
+Since it is so common to reuse seeds while refining a prompt, there is now a shortcut as of version
+1.11. Provide a `-S` (or `--seed`) switch of `-1` to use the seed of the most recent image
+generated. If you produced multiple images with the `-n` switch, then you can go back further
+using `-2`, `-3`, etc. up to the first image generated by the previous command. Sorry, but you can't go
+back further than one command.
+
+Here's an example of using this to do a quick refinement. It also illustrates using the new `-G`
+switch to turn on upscaling and face enhancement (see previous section):
+
+```bash
+invoke> a cute child playing hopscotch -G0.5
+[...]
+outputs/img-samples/000039.3498014304.png: "a cute child playing hopscotch" -s50 -W512 -H512 -C7.5 -mk_lms -S3498014304
+
+# I wonder what it will look like if I bump up the steps and set facial enhancement to full strength?
+invoke> a cute child playing hopscotch -G1.0 -s100 -S -1
+reusing previous seed 3498014304
+[...]
+outputs/img-samples/000040.3498014304.png: "a cute child playing hopscotch" -G1.0 -s100 -W512 -H512 -C7.5 -mk_lms -S3498014304
 ```
 
 ---
@@ -46,27 +73,66 @@ This will tell the sampler to invest 25% of its effort on the tabby cat aspect o
 on the white duck aspect (surprisingly, this example actually works). The prompt weights can use any
 combination of integers and floating point numbers, and they do not need to add up to 1.
 
+---
+
+## **Filename Format**
+
+The argument `--fnformat` allows to specify the filename of the
+ image. Supported wildcards are all arguments what can be set such as
+ `perlin`, `seed`, `threshold`, `height`, `width`, `gfpgan_strength`,
+ `sampler_name`, `steps`, `model`, `upscale`, `prompt`, `cfg_scale`,
+ `prefix`.
+
+The following prompt
+```bash
+dream> a red car --steps 25 -C 9.8 --perlin 0.1 --fnformat {prompt}_steps.{steps}_cfg.{cfg_scale}_perlin.{perlin}.png
+```
+
+generates a file with the name: `outputs/img-samples/a red car_steps.25_cfg.9.8_perlin.0.1.png`
+
+---
+
 ## **Thresholding and Perlin Noise Initialization Options**
 
-Under the Noise section of the Web UI, you will find two options named
-Perlin Noise and Noise Threshold. [Perlin
-noise](https://en.wikipedia.org/wiki/Perlin_noise) is a type of
-structured noise used to simulate terrain and other natural
-textures. The slider controls the percentage of perlin noise that will
-be mixed into the image at the beginning of generation. Adding a little
-perlin noise to a generation will alter the image substantially.
-
-The noise threshold limits the range of the latent values during
-sampling and helps combat the oversharpening seem with higher CFG
-scale values.
+Two new options are the thresholding (`--threshold`) and the perlin noise initialization (`--perlin`) options. Thresholding limits the range of the latent values during optimization, which helps combat oversaturation with higher CFG scale values. Perlin noise initialization starts with a percentage (a value ranging from 0 to 1) of perlin noise mixed into the initial noise. Both features allow for more variations and options in the course of generating images.
 
 For better intuition into what these options do in practice:
 
 ![here is a graphic demonstrating them both](../assets/truncation_comparison.jpg)
 
-In generating this graphic, perlin noise at initialization was
-programmatically varied going across on the diagram by values 0.0,
-0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied
-going down from 0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are
-fixed using the prompt "a portrait of a beautiful young lady" a CFG of
-20, 100 steps, and a seed of 1950357039.
+In generating this graphic, perlin noise at initialization was programmatically varied going across on the diagram by values 0.0, 0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied going down from
+0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are fixed, so the initial prompt is as follows (no thresholding or perlin noise):
+
+```bash
+invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 0 --perlin 0
+```
+
+Here's an example of another prompt used when setting the threshold to 5 and perlin noise to 0.2:
+
+```bash
+invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 5 --perlin 0.2
+```
+
+!!! note
+
+    currently the thresholding feature is only implemented for the k-diffusion style samplers, and empirically appears to work best with `k_euler_a` and `k_dpm_2_a`. Using 0 disables thresholding. Using 0 for perlin noise disables using perlin noise for initialization. Finally, using 1 for perlin noise uses only perlin noise for initialization.
+
+---
+
+## **Simplified API**
+
+For programmers who wish to incorporate stable-diffusion into other products, this repository
+includes a simplified API for text to image generation, which lets you create images from a prompt
+in just three lines of code:
+
+```bash
+from ldm.generate import Generate
+g       = Generate()
+outputs = g.txt2img("a unicorn in manhattan")
+```
+
+Outputs is a list of lists in the format [filename1,seed1],[filename2,seed2]...].
+
+Please see the documentation in ldm/generate.py for more information.
+
+---

docs/features/POSTPROCESS.md

@@ -8,6 +8,12 @@ title: Postprocessing
 
 This extension provides the ability to restore faces and upscale images.
 
+Face restoration and upscaling can be applied at the time you generate the
+images, or at any later time against a previously-generated PNG file, using the
+[!fix](#fixing-previously-generated-images) command.
+[Outpainting and outcropping](OUTPAINTING.md) can only be applied after the
+fact.
+
 ## Face Fixing
 
 The default face restoration module is GFPGAN. The default upscale is
@@ -17,7 +23,8 @@ Real-ESRGAN. For an alternative face restoration module, see
 As of version 1.14, environment.yaml will install the Real-ESRGAN package into
 the standard install location for python packages, and will put GFPGAN into a
 subdirectory of "src" in the InvokeAI directory. Upscaling with Real-ESRGAN
-should "just work" without further intervention. Simply indicate the desired scale on
+should "just work" without further intervention. Simply pass the `--upscale`
+(`-U`) option on the `invoke>` command line, or indicate the desired scale on
 the popup in the Web GUI.
 
 **GFPGAN** requires a series of downloadable model files to work. These are
@@ -34,75 +41,48 @@ reconstruction.
 
 ### Upscaling
 
-Open the upscaling dialog by clicking on the "expand" icon located
-above the image display area in the Web UI:
+`-U : <upscaling_factor> <upscaling_strength>`
 
-<figure markdown>
-![upscale1](../assets/features/upscale-dialog.png)
-</figure>
+The upscaling prompt argument takes two values. The first value is a scaling
+factor and should be set to either `2` or `4` only. This will either scale the
+image 2x or 4x respectively using different models.
 
-There are three different upscaling parameters that you can
-adjust. The first is the scale itself, either 2x or 4x.
+You can set the scaling stength between `0` and `1.0` to control intensity of
+the of the scaling. This is handy because AI upscalers generally tend to smooth
+out texture details. If you wish to retain some of those for natural looking
+results, we recommend using values between `0.5 to 0.8`.
 
-The second is the "Denoising Strength." Higher values will smooth out
-the image and remove digital chatter, but may lose fine detail at
-higher values.
-
-Third, "Upscale Strength" allows you to adjust how the You can set the
-scaling stength between `0` and `1.0` to control the intensity of the
-scaling. AI upscalers generally tend to smooth out texture details. If
-you wish to retain some of those for natural looking results, we
-recommend using values between `0.5 to 0.8`.
-
-[This figure](../assets/features/upscaling-montage.png) illustrates
-the effects of denoising and strength. The original image was 512x512,
-4x scaled to 2048x2048. The "original" version on the upper left was
-scaled using simple pixel averaging. The remainder use the ESRGAN
-upscaling algorithm at different levels of denoising and strength.
-
-<figure markdown>
-![upscaling](../assets/features/upscaling-montage.png){ width=720 }
-</figure>
-
-Both denoising and strength default to 0.75.
+If you do not explicitly specify an upscaling_strength, it will default to 0.75.
 
 ### Face Restoration
 
-InvokeAI offers alternative two face restoration algorithms,
-[GFPGAN](https://github.com/TencentARC/GFPGAN) and
-[CodeFormer](https://huggingface.co/spaces/sczhou/CodeFormer). These
-algorithms improve the appearance of faces, particularly eyes and
-mouths. Issues with faces are less common with the latest set of
-Stable Diffusion models than with the original 1.4 release, but the
-restoration algorithms can still make a noticeable improvement in
-certain cases. You can also apply restoration to old photographs you
-upload.
+`-G : <facetool_strength>`
 
-To access face restoration, click the "smiley face" icon in the
-toolbar above the InvokeAI image panel. You will be presented with a
-dialog that offers a choice between the two algorithm and sliders that
-allow you to adjust their parameters. Alternatively, you may open the
-left-hand accordion panel labeled "Face Restoration" and have the
-restoration algorithm of your choice applied to generated images
-automatically.
+This prompt argument controls the strength of the face restoration that is being
+applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.
 
+You can use either one or both without any conflicts. In cases where you use
+both, the image will be first upscaled and then the face restoration process
+will be executed to ensure you get the highest quality facial features.
 
-Like upscaling, there are a number of parameters that adjust the face
-restoration output. GFPGAN has a single parameter, `strength`, which
-controls how much the algorithm is allowed to adjust the
-image. CodeFormer has two parameters, `strength`, and `fidelity`,
-which together control the quality of the output image as described in
-the [CodeFormer project
-page](https://shangchenzhou.com/projects/CodeFormer/). Default values
-are 0.75 for both parameters, which achieves a reasonable balance
-between changing the image too much and not enough.
+`--save_orig`
 
-[This figure](../assets/features/restoration-montage.png) illustrates
-the effects of adjusting GFPGAN and CodeFormer parameters.
+When you use either `-U` or `-G`, the final result you get is upscaled or face
+modified. If you want to save the original Stable Diffusion generation, you can
+use the `-save_orig` prompt argument to save the original unaffected version
+too.
 
-<figure markdown>
-![upscaling](../assets/features/restoration-montage.png){ width=720 }
-</figure>
+### Example Usage
+
+```bash
+invoke> "superman dancing with a panda bear" -U 2 0.6 -G 0.4
+```
+
+This also works with img2img:
+
+```bash
+invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
+```
 
 !!! note
 
@@ -115,8 +95,69 @@ the effects of adjusting GFPGAN and CodeFormer parameters.
     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.
+
+## CodeFormer Support
+
+This repo also allows you to perform face restoration using
+[CodeFormer](https://github.com/sczhou/CodeFormer).
+
+In order to setup CodeFormer to work, you need to download the models like with
+GFPGAN. You can do this either by running `invokeai-configure` or by manually
+downloading the
+[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
+and saving it to `ldm/invoke/restoration/codeformer/weights` folder.
+
+You can use `-ft` prompt argument to swap between CodeFormer and the default
+GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
+strength of the restoration effect.
+
+### CodeFormer Usage
+
+The following command will perform face restoration with CodeFormer instead of
+the default gfpgan.
+
+`<prompt> -G 0.8 -ft codeformer`
+
+### Other Options
+
+- `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces
+  high quality results but low accuracy and 1 produces lower quality results but
+  higher accuacy to your original face.
+
+The following command will perform face restoration with CodeFormer. CodeFormer
+will output a result that is closely matching to the input face.
+
+`<prompt> -G 1.0 -ft codeformer -cf 0.9`
+
+The following command will perform face restoration with CodeFormer. CodeFormer
+will output a result that is the best restoration possible. This may deviate
+slightly from the original face. This is an excellent option to use in
+situations when there is very little facial data to work with.
+
+`<prompt> -G 1.0 -ft codeformer -cf 0.1`
+
+## Fixing Previously-Generated Images
+
+It is easy to apply face restoration and/or upscaling to any
+previously-generated file. Just use the syntax
+`!fix path/to/file.png <options>`. For example, to apply GFPGAN at strength 0.8
+and upscale 2X for a file named `./outputs/img-samples/000044.2945021133.png`,
+just run:
+
+```bash
+invoke> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
+```
+
+A new file named `000044.2945021133.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.
+
 ## How to disable
 
 If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
 you can disable them on the invoke.py command line with the `--no_restore` and
-`--no_esrgan` options, respectively.
+`--no_upscale` options, respectively.

docs/features/PROMPTS.md

@@ -4,12 +4,77 @@ title: Prompting-Features
 
 # :octicons-command-palette-24: Prompting-Features
 
+## **Reading Prompts from a File**
+
+You can automate `invoke.py` by providing a text file with the prompts you want
+to run, one line per prompt. The text file must be composed with a text editor
+(e.g. Notepad) and not a word processor. Each line should look like what you
+would type at the invoke> prompt:
+
+```bash
+"a beautiful sunny day in the park, children playing" -n4 -C10
+"stormy weather on a mountain top, goats grazing" -s100
+"innovative packaging for a squid's dinner" -S137038382
+```
+
+Then pass this file's name to `invoke.py` when you invoke it:
+
+```bash
+python scripts/invoke.py --from_file "/path/to/prompts.txt"
+```
+
+You may also read a series of prompts from standard input by providing
+a filename of `-`. For example, here is a python script that creates a
+matrix of prompts, each one varying slightly:
+
+```bash
+#!/usr/bin/env python
+
+adjectives = ['sunny','rainy','overcast']
+samplers = ['k_lms','k_euler_a','k_heun']
+cfg = [7.5, 9, 11]
+
+for adj in adjectives:
+    for samp in samplers:
+        for cg in cfg:
+            print(f'a {adj} day -A{samp} -C{cg}')
+```
+
+Its output looks like this (abbreviated):
+
+```bash
+a sunny day -Aklms -C7.5
+a sunny day -Aklms -C9
+a sunny day -Aklms -C11
+a sunny day -Ak_euler_a -C7.5
+a sunny day -Ak_euler_a -C9
+...
+a overcast day -Ak_heun -C9
+a overcast day -Ak_heun -C11
+```
+
+To feed it to invoke.py, pass the filename of "-"
+
+```bash
+python matrix.py | python scripts/invoke.py --from_file -
+```
+
+When the script is finished, each of the 27 combinations
+of adjective, sampler and CFG will be executed.
+
+The command-line interface provides `!fetch` and `!replay` commands
+which allow you to read the prompts from a single previously-generated
+image or a whole directory of them, write the prompts to a file, and
+then replay them. Or you can create your own file of prompts and feed
+them to the command-line client from within an interactive session.
+See [Command-Line Interface](CLI.md) for details.
+
+---
+
 ## **Negative and Unconditioned Prompts**
 
-Any words between a pair of square brackets will instruct Stable
-Diffusion to attempt to ban the concept from the generated image. The
-same effect is achieved by placing words in the "Negative Prompts"
-textbox in the Web UI.
+Any words between a pair of square brackets will instruct Stable Diffusion to
+attempt to ban the concept from the generated image.
 
 ```text
 this is a test prompt [not really] to make you understand [cool] how this works.
@@ -22,9 +87,7 @@ Here's a prompt that depicts what it does.
 
 original prompt:
 
-`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve"`
-
-`#!bash parameters: steps=20, dimensions=512x768, CFG=7.5, Scheduler=k_euler_a, seed=1654590180`
+`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
 
@@ -36,8 +99,7 @@ That image has a woman, so if we want the horse without a rider, we can
 influence the image not to have a woman by putting [woman] in the prompt, like
 this:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]"`
-(same parameters as above)
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
 
@@ -48,8 +110,7 @@ this:
 That's nice - but say we also don't want the image to be quite so blue. We can
 add "blue" to the list of negative prompts, so it's now [woman blue]:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]"`
-(same parameters as above)
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
 
@@ -60,8 +121,7 @@ add "blue" to the list of negative prompts, so it's now [woman blue]:
 Getting close - but there's no sense in having a saddle when our horse doesn't
 have a rider, so we'll add one more negative prompt: [woman blue saddle].
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]"`
-(same parameters as above)
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
 
@@ -201,6 +261,19 @@ Prompt2prompt `.swap()` is not compatible with xformers, which will be temporari
 The `prompt2prompt` code is based off
 [bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
 
+Note that `prompt2prompt` is not currently working with the runwayML inpainting
+model, and may never work due to the way this model is set up. If you attempt to
+use `prompt2prompt` you will get the original image back. However, since this
+model is so good at inpainting, a good substitute is to use the `clipseg` text
+masking option:
+
+```bash
+invoke> a fluffy cat eating a hotdot
+Outputs:
+[1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
+invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat
+```
+
 ### Escaping parantheses () and speech marks ""
 
 If the model you are using has parentheses () or speech marks "" as part of its
@@ -301,48 +374,6 @@ summoning up the concept of some sort of scifi creature? Let's find out.
 Indeed, removing the word "hybrid" produces an image that is more like what we'd
 expect.
 
-## Dynamic Prompts
-
-Dynamic Prompts are a powerful feature designed to produce a variety of prompts based on user-defined options. Using a special syntax, you can construct a prompt with multiple possibilities, and the system will automatically generate a series of permutations based on your settings. This is extremely beneficial for ideation, exploring various scenarios, or testing different concepts swiftly and efficiently.
-
-### Structure of a Dynamic Prompt
-
-A Dynamic Prompt comprises of regular text, supplemented with alternatives enclosed within curly braces {} and separated by a vertical bar |. For example: {option1|option2|option3}. The system will then select one of the options to include in the final prompt. This flexible system allows for options to be placed throughout the text as needed.
-
-Furthermore, Dynamic Prompts can designate multiple selections from a single group of options. This feature is triggered by prefixing the options with a numerical value followed by $$. For example, in {2$$option1|option2|option3}, the system will select two distinct options from the set.
-### Creating Dynamic Prompts
-
-To create a Dynamic Prompt, follow these steps:
-
-    Draft your sentence or phrase, identifying words or phrases with multiple possible options.
-    Encapsulate the different options within curly braces {}.
-    Within the braces, separate each option using a vertical bar |.
-    If you want to include multiple options from a single group, prefix with the desired number and $$.
-
-For instance: A {house|apartment|lodge|cottage} in {summer|winter|autumn|spring} designed in {2$$style1|style2|style3}.
-### How Dynamic Prompts Work
-
-Once a Dynamic Prompt is configured, the system generates an array of combinations using the options provided. Each group of options in curly braces is treated independently, with the system selecting one option from each group. For a prefixed set (e.g., 2$$), the system will select two distinct options.
-
-For example, the following prompts could be generated from the above Dynamic Prompt:
-
-    A house in summer designed in style1, style2
-    A lodge in autumn designed in style3, style1
-    A cottage in winter designed in style2, style3
-    And many more!
-
-When the `Combinatorial` setting is on, Invoke will disable the "Images" selection, and generate every combination up until the setting for Max Prompts is reached.
-When the `Combinatorial` setting is off, Invoke will randomly generate combinations up until the setting for Images has been reached.
-
-
-
-### Tips and Tricks for Using Dynamic Prompts
-
-Below are some useful strategies for creating Dynamic Prompts:
-
-    Utilize Dynamic Prompts to generate a wide spectrum of prompts, perfect for brainstorming and exploring diverse ideas.
-    Ensure that the options within a group are contextually relevant to the part of the sentence where they are used. For instance, group building types together, and seasons together.
-    Apply the 2$$ prefix when you want to incorporate more than one option from a single group. This becomes quite handy when mixing and matching different elements.
-    Experiment with different quantities for the prefix. For example, 3$$ will select three distinct options.
-    Be aware of coherence in your prompts. Although the system can generate all possible combinations, not all may semantically make sense. Therefore, carefully choose the options for each group.
-    Always review and fine-tune the generated prompts as needed. While Dynamic Prompts can help you generate a multitude of combinations, the final polishing and refining remain in your hands.
+In conclusion, prompt blending is great for exploring creative space, but can be
+difficult to direct. A forthcoming release of InvokeAI will feature more
+deterministic prompt weighting.

docs/features/TEXTUAL_INVERSION.md

@@ -0,0 +1,335 @@
+---
+title: Textual-Inversion
+---
+
+# :material-file-document: Textual Inversion
+
+## **Personalizing Text-to-Image Generation**
+
+You may personalize the generated images to provide your own styles or objects
+by training a new LDM checkpoint and introducing a new vocabulary to the fixed
+model as a (.pt) embeddings file. Alternatively, you may use or train
+HuggingFace Concepts embeddings files (.bin) from
+<https://huggingface.co/sd-concepts-library> and its associated
+notebooks.
+
+## **Hardware and Software Requirements**
+
+You will need a GPU to perform training in a reasonable length of
+time, and at least 12 GB of VRAM. We recommend using the [`xformers`
+library](../installation/070_INSTALL_XFORMERS) to accelerate the
+training process further. During training, about ~8 GB is temporarily
+needed in order to store intermediate models, checkpoints and logs.
+
+## **Preparing for Training**
+
+To train, prepare a folder that contains 3-5 images that illustrate
+the object or concept. It is good to provide a variety of examples or
+poses to avoid overtraining the system. Format these images as PNG
+(preferred) or JPG. You do not need to resize or crop the images in
+advance, but for more control you may wish to do so.
+
+Place the training images in a directory on the machine InvokeAI runs
+on. We recommend placing them in a subdirectory of the
+`text-inversion-training-data` folder located in the InvokeAI root
+directory, ordinarily `~/invokeai` (Linux/Mac), or
+`C:\Users\your_name\invokeai` (Windows). For example, to create an
+embedding for the "psychedelic" style, you'd place the training images
+into the directory
+`~invokeai/text-inversion-training-data/psychedelic`.
+
+## **Launching Training Using the Console Front End**
+
+InvokeAI 2.3 and higher comes with a text console-based training front
+end. From within the `invoke.sh`/`invoke.bat` Invoke launcher script,
+start the front end by selecting choice (3):
+
+```sh
+Do you want to generate images using the
+1. command-line
+2. browser-based UI
+3. textual inversion training
+4. open the developer console
+Please enter 1, 2, 3, or 4: [1] 3
+```
+
+From the command line, with the InvokeAI virtual environment active,
+you can launch the front end with the command `invokeai-ti --gui`.
+
+This will launch a text-based front end that will look like this:
+
+<figure markdown>
+![ti-frontend](../assets/textual-inversion/ti-frontend.png)
+</figure>
+
+The interface is keyboard-based. Move from field to field using
+control-N (^N) to move to the next field and control-P (^P) to the
+previous one. <Tab> and <shift-TAB> work as well. Once a field is
+active, use the cursor keys. In a checkbox group, use the up and down
+cursor keys to move from choice to choice, and <space> to select a
+choice. In a scrollbar, use the left and right cursor keys to increase
+and decrease the value of the scroll. In textfields, type the desired
+values.
+
+The number of parameters may look intimidating, but in most cases the
+predefined defaults work fine. The red circled fields in the above
+illustration are the ones you will adjust most frequently.
+
+### Model Name
+
+This will list all the diffusers models that are currently
+installed. Select the one you wish to use as the basis for your
+embedding. Be aware that if you use a SD-1.X-based model for your
+training, you will only be able to use this embedding with other
+SD-1.X-based models. Similarly, if you train on SD-2.X, you will only
+be able to use the embeddings with models based on SD-2.X.
+
+### Trigger Term
+
+This is the prompt term you will use to trigger the embedding. Type a
+single word or phrase you wish to use as the trigger, example
+"psychedelic" (without angle brackets). Within InvokeAI, you will then
+be able to activate the trigger using the syntax `<psychedelic>`.
+
+### Initializer
+
+This is a single character that is used internally during the training
+process as a placeholder for the trigger term. It defaults to "*" and
+can usually be left alone.
+
+### Resume from last saved checkpoint
+
+As training proceeds, textual inversion will write a series of
+intermediate files that can be used to resume training from where it
+was left off in the case of an interruption. This checkbox will be
+automatically selected if you provide a previously used trigger term
+and at least one checkpoint file is found on disk.
+
+Note that as of 20 January 2023, resume does not seem to be working
+properly due to an issue with the upstream code.
+
+### Data Training Directory
+
+This is the location of the images to be used for training. When you
+select a trigger term like "my-trigger", the frontend will prepopulate
+this field with `~/invokeai/text-inversion-training-data/my-trigger`,
+but you can change the path to wherever you want.
+
+### Output Destination Directory
+
+This is the location of the logs, checkpoint files, and embedding
+files created during training. When you select a trigger term like
+"my-trigger", the frontend will prepopulate this field with
+`~/invokeai/text-inversion-output/my-trigger`, but you can change the
+path to wherever you want.
+
+### Image resolution
+
+The images in the training directory will be automatically scaled to
+the value you use here. For best results, you will want to use the
+same default resolution of the underlying model (512 pixels for
+SD-1.5, 768 for the larger version of SD-2.1).
+
+### Center crop images
+
+If this is selected, your images will be center cropped to make them
+square before resizing them to the desired resolution. Center cropping
+can indiscriminately cut off the top of subjects' heads for portrait
+aspect images, so if you have images like this, you may wish to use a
+photoeditor to manually crop them to a square aspect ratio.
+
+### Mixed precision
+
+Select the floating point precision for the embedding. "no" will
+result in a full 32-bit precision, "fp16" will provide 16-bit
+precision, and "bf16" will provide mixed precision (only available
+when XFormers is used).
+
+### Max training steps
+
+How many steps the training will take before the model converges. Most
+training sets will converge with 2000-3000 steps.
+
+### Batch size
+
+This adjusts how many training images are processed simultaneously in
+each step. Higher values will cause the training process to run more
+quickly, but use more memory. The default size is selected based on
+whether you have the `xformers` memory-efficient attention library
+installed. If `xformers` is available, the batch size will be 8,
+otherwise 3.  These values were chosen to allow training to run with
+GPUs with as little as 12 GB VRAM.
+
+### Learning rate
+
+The rate at which the system adjusts its internal weights during
+training. Higher values risk overtraining (getting the same image each
+time), and lower values will take more steps to train a good
+model. The default of 0.0005 is conservative; you may wish to increase
+it to 0.005 to speed up training.
+
+### Scale learning rate by number of GPUs, steps and batch size
+
+If this is selected (the default) the system will adjust the provided
+learning rate to improve performance.
+
+### Use xformers acceleration
+
+This will activate XFormers memory-efficient attention, which will
+reduce memory requirements by half or more and allow you to select a
+higher batch size. You need to have XFormers installed for this to
+have an effect.
+
+### Learning rate scheduler
+
+This adjusts how the learning rate changes over the course of
+training. The default "constant" means to use a constant learning rate
+for the entire training session. The other values scale the learning
+rate according to various formulas.
+
+Only "constant" is supported by the XFormers library.
+
+### Gradient accumulation steps
+
+This is a parameter that allows you to use bigger batch sizes than
+your GPU's VRAM would ordinarily accommodate, at the cost of some
+performance.
+
+### Warmup steps
+
+If "constant_with_warmup" is selected in the learning rate scheduler,
+then this provides the number of warmup steps. Warmup steps have a
+very low learning rate, and are one way of preventing early
+overtraining.
+
+## The training run
+
+Start the training run by advancing to the OK button (bottom right)
+and pressing <enter>. A series of progress messages will be displayed
+as the training process proceeds. This may take an hour or two,
+depending on settings and the speed of your system. Various log and
+checkpoint files will be written into the output directory (ordinarily
+`~/invokeai/text-inversion-output/my-model/`)
+
+At the end of successful training, the system will copy the file
+`learned_embeds.bin` into the InvokeAI root directory's `embeddings`
+directory, using a subdirectory named after the trigger token. For
+example, if the trigger token was `psychedelic`, then look for the
+embeddings file in
+`~/invokeai/embeddings/psychedelic/learned_embeds.bin`
+
+You may now launch InvokeAI and try out a prompt that uses the trigger
+term. For example `a plate of banana sushi in <psychedelic> style`.
+
+## **Training with the Command-Line Script**
+
+Training can also be done using a traditional command-line script. It
+can be launched from within the "developer's console", or from the
+command line after activating InvokeAI's virtual environment.
+
+It accepts a large number of arguments, which can be summarized by
+passing the `--help` argument:
+
+```sh
+invokeai-ti --help
+```
+
+Typical usage is shown here:
+```sh
+invokeai-ti \
+       --model=stable-diffusion-1.5 \
+       --resolution=512 \
+       --learnable_property=style \
+       --initializer_token='*' \
+       --placeholder_token='<psychedelic>' \
+       --train_data_dir=/home/lstein/invokeai/training-data/psychedelic \
+       --output_dir=/home/lstein/invokeai/text-inversion-training/psychedelic \
+       --scale_lr \
+       --train_batch_size=8 \
+       --gradient_accumulation_steps=4 \
+       --max_train_steps=3000 \
+       --learning_rate=0.0005 \
+       --resume_from_checkpoint=latest \
+       --lr_scheduler=constant \
+       --mixed_precision=fp16 \
+       --only_save_embeds
+```
+
+## Using Distributed Training
+
+If you have multiple GPUs on one machine, or a cluster of GPU-enabled
+machines, you can activate distributed training. See the [HuggingFace
+Accelerate pages](https://huggingface.co/docs/accelerate/index) for
+full information, but the basic recipe is:
+
+1. Enter the InvokeAI developer's console command line by selecting
+option [8] from the `invoke.sh`/`invoke.bat` script.
+
+2. Configurate Accelerate using `accelerate config`:
+```sh
+accelerate config
+```
+This will guide you through the configuration process, including
+specifying how many machines you will run training on and the number
+of GPUs pe rmachine.
+
+You only need to do this once.
+
+3. Launch training from the command line using `accelerate launch`. Be sure
+that your current working directory is the InvokeAI root directory (usually
+named `invokeai` in your home directory):
+
+```sh
+accelerate launch .venv/bin/invokeai-ti \
+       --model=stable-diffusion-1.5 \
+       --resolution=512 \
+       --learnable_property=object \
+       --initializer_token='*' \
+       --placeholder_token='<shraddha>' \
+       --train_data_dir=/home/lstein/invokeai/text-inversion-training-data/shraddha \
+       --output_dir=/home/lstein/invokeai/text-inversion-training/shraddha \
+       --scale_lr \
+       --train_batch_size=10 \
+       --gradient_accumulation_steps=4 \
+       --max_train_steps=2000 \
+       --learning_rate=0.0005 \
+       --lr_scheduler=constant \
+       --mixed_precision=fp16 \
+       --only_save_embeds
+```
+
+## Using Embeddings
+
+After training completes, the resultant embeddings will be saved into your `$INVOKEAI_ROOT/embeddings/<trigger word>/learned_embeds.bin`.
+
+These will be automatically loaded when you start InvokeAI.
+
+Add the trigger word, surrounded by angle brackets, to use that embedding. For example, if your trigger word was `terence`, use `<terence>` in prompts. This is the same syntax used by the HuggingFace concepts library.
+
+**Note:** `.pt` embeddings do not require the angle brackets.
+
+## Troubleshooting
+
+### `Cannot load embedding for <trigger>. It was trained on a model with token dimension 1024, but the current model has token dimension 768`
+
+Messages like this indicate you trained the embedding on a different base model than the currently selected one.
+
+For example, in the error above, the training was done on SD2.1 (768x768) but it was used on SD1.5 (512x512).
+
+## Reading
+
+For more information on textual inversion, please see the following
+resources:
+
+* The [textual inversion repository](https://github.com/rinongal/textual_inversion) and
+  associated paper for details and limitations.
+* [HuggingFace's textual inversion training
+  page](https://huggingface.co/docs/diffusers/training/text_inversion)
+* [HuggingFace example script
+  documentation](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion)
+  (Note that this script is similar to, but not identical, to
+  `textual_inversion`, but produces embed files that are completely compatible.
+
+---
+
+copyright (c) 2023, Lincoln Stein and the InvokeAI Development Team

docs/features/TRAINING.md

@@ -1,286 +0,0 @@
----
-title: Training
----
-
-# :material-file-document: Training
-
-# Textual Inversion Training
-## **Personalizing Text-to-Image Generation**
-
-You may personalize the generated images to provide your own styles or objects
-by training a new LDM checkpoint and introducing a new vocabulary to the fixed
-model as a (.pt) embeddings file. Alternatively, you may use or train
-HuggingFace Concepts embeddings files (.bin) from
-<https://huggingface.co/sd-concepts-library> and its associated
-notebooks.
-
-## **Hardware and Software Requirements**
-
-You will need a GPU to perform training in a reasonable length of
-time, and at least 12 GB of VRAM. We recommend using the [`xformers`
-library](../installation/070_INSTALL_XFORMERS.md) to accelerate the
-training process further. During training, about ~8 GB is temporarily
-needed in order to store intermediate models, checkpoints and logs.
-
-## **Preparing for Training**
-
-To train, prepare a folder that contains 3-5 images that illustrate
-the object or concept. It is good to provide a variety of examples or
-poses to avoid overtraining the system. Format these images as PNG
-(preferred) or JPG. You do not need to resize or crop the images in
-advance, but for more control you may wish to do so.
-
-Place the training images in a directory on the machine InvokeAI runs
-on. We recommend placing them in a subdirectory of the
-`text-inversion-training-data` folder located in the InvokeAI root
-directory, ordinarily `~/invokeai` (Linux/Mac), or
-`C:\Users\your_name\invokeai` (Windows). For example, to create an
-embedding for the "psychedelic" style, you'd place the training images
-into the directory
-`~invokeai/text-inversion-training-data/psychedelic`.
-
-## **Launching Training Using the Console Front End**
-
-InvokeAI 2.3 and higher comes with a text console-based training front
-end. From within the `invoke.sh`/`invoke.bat` Invoke launcher script,
-start the front end by selecting choice (3):
-
-```sh
-Do you want to generate images using the
-1: Browser-based UI
-2: Command-line interface
-3: Run textual inversion training
-4: Merge models (diffusers type only)
-5: Download and install models
-6: Change InvokeAI startup options
-7: Re-run the configure script to fix a broken install
-8: Open the developer console
-9: Update InvokeAI
-10: Command-line help
-Q: Quit
-
-Please enter 1-10, Q: [1] 
-```
-
-From the command line, with the InvokeAI virtual environment active,
-you can launch the front end with the command `invokeai-ti --gui`.
-
-This will launch a text-based front end that will look like this:
-
-<figure markdown>
-![ti-frontend](../assets/textual-inversion/ti-frontend.png)
-</figure>
-
-The interface is keyboard-based. Move from field to field using
-control-N (^N) to move to the next field and control-P (^P) to the
-previous one. <Tab> and <shift-TAB> work as well. Once a field is
-active, use the cursor keys. In a checkbox group, use the up and down
-cursor keys to move from choice to choice, and <space> to select a
-choice. In a scrollbar, use the left and right cursor keys to increase
-and decrease the value of the scroll. In textfields, type the desired
-values.
-
-The number of parameters may look intimidating, but in most cases the
-predefined defaults work fine. The red circled fields in the above
-illustration are the ones you will adjust most frequently.
-
-### Model Name
-
-This will list all the diffusers models that are currently
-installed. Select the one you wish to use as the basis for your
-embedding. Be aware that if you use a SD-1.X-based model for your
-training, you will only be able to use this embedding with other
-SD-1.X-based models. Similarly, if you train on SD-2.X, you will only
-be able to use the embeddings with models based on SD-2.X.
-
-### Trigger Term
-
-This is the prompt term you will use to trigger the embedding. Type a
-single word or phrase you wish to use as the trigger, example
-"psychedelic" (without angle brackets). Within InvokeAI, you will then
-be able to activate the trigger using the syntax `<psychedelic>`.
-
-### Initializer
-
-This is a single character that is used internally during the training
-process as a placeholder for the trigger term. It defaults to "*" and
-can usually be left alone.
-
-### Resume from last saved checkpoint
-
-As training proceeds, textual inversion will write a series of
-intermediate files that can be used to resume training from where it
-was left off in the case of an interruption. This checkbox will be
-automatically selected if you provide a previously used trigger term
-and at least one checkpoint file is found on disk.
-
-Note that as of 20 January 2023, resume does not seem to be working
-properly due to an issue with the upstream code.
-
-### Data Training Directory
-
-This is the location of the images to be used for training. When you
-select a trigger term like "my-trigger", the frontend will prepopulate
-this field with `~/invokeai/text-inversion-training-data/my-trigger`,
-but you can change the path to wherever you want.
-
-### Output Destination Directory
-
-This is the location of the logs, checkpoint files, and embedding
-files created during training. When you select a trigger term like
-"my-trigger", the frontend will prepopulate this field with
-`~/invokeai/text-inversion-output/my-trigger`, but you can change the
-path to wherever you want.
-
-### Image resolution
-
-The images in the training directory will be automatically scaled to
-the value you use here. For best results, you will want to use the
-same default resolution of the underlying model (512 pixels for
-SD-1.5, 768 for the larger version of SD-2.1).
-
-### Center crop images
-
-If this is selected, your images will be center cropped to make them
-square before resizing them to the desired resolution. Center cropping
-can indiscriminately cut off the top of subjects' heads for portrait
-aspect images, so if you have images like this, you may wish to use a
-photoeditor to manually crop them to a square aspect ratio.
-
-### Mixed precision
-
-Select the floating point precision for the embedding. "no" will
-result in a full 32-bit precision, "fp16" will provide 16-bit
-precision, and "bf16" will provide mixed precision (only available
-when XFormers is used).
-
-### Max training steps
-
-How many steps the training will take before the model converges. Most
-training sets will converge with 2000-3000 steps.
-
-### Batch size
-
-This adjusts how many training images are processed simultaneously in
-each step. Higher values will cause the training process to run more
-quickly, but use more memory. The default size will run with GPUs with
-as little as 12 GB.
-
-### Learning rate
-
-The rate at which the system adjusts its internal weights during
-training. Higher values risk overtraining (getting the same image each
-time), and lower values will take more steps to train a good
-model. The default of 0.0005 is conservative; you may wish to increase
-it to 0.005 to speed up training.
-
-### Scale learning rate by number of GPUs, steps and batch size
-
-If this is selected (the default) the system will adjust the provided
-learning rate to improve performance.
-
-### Use xformers acceleration
-
-This will activate XFormers memory-efficient attention. You need to
-have XFormers installed for this to have an effect.
-
-### Learning rate scheduler
-
-This adjusts how the learning rate changes over the course of
-training. The default "constant" means to use a constant learning rate
-for the entire training session. The other values scale the learning
-rate according to various formulas.
-
-Only "constant" is supported by the XFormers library.
-
-### Gradient accumulation steps
-
-This is a parameter that allows you to use bigger batch sizes than
-your GPU's VRAM would ordinarily accommodate, at the cost of some
-performance.
-
-### Warmup steps
-
-If "constant_with_warmup" is selected in the learning rate scheduler,
-then this provides the number of warmup steps. Warmup steps have a
-very low learning rate, and are one way of preventing early
-overtraining.
-
-## The training run
-
-Start the training run by advancing to the OK button (bottom right)
-and pressing <enter>. A series of progress messages will be displayed
-as the training process proceeds. This may take an hour or two,
-depending on settings and the speed of your system. Various log and
-checkpoint files will be written into the output directory (ordinarily
-`~/invokeai/text-inversion-output/my-model/`)
-
-At the end of successful training, the system will copy the file
-`learned_embeds.bin` into the InvokeAI root directory's `embeddings`
-directory, using a subdirectory named after the trigger token. For
-example, if the trigger token was `psychedelic`, then look for the
-embeddings file in
-`~/invokeai/embeddings/psychedelic/learned_embeds.bin`
-
-You may now launch InvokeAI and try out a prompt that uses the trigger
-term. For example `a plate of banana sushi in <psychedelic> style`.
-
-## **Training with the Command-Line Script**
-
-Training can also be done using a traditional command-line script. It
-can be launched from within the "developer's console", or from the
-command line after activating InvokeAI's virtual environment.
-
-It accepts a large number of arguments, which can be summarized by
-passing the `--help` argument:
-
-```sh
-invokeai-ti --help
-```
-
-Typical usage is shown here:
-```sh
-invokeai-ti \
-       --model=stable-diffusion-1.5 \
-       --resolution=512 \
-       --learnable_property=style \
-       --initializer_token='*' \
-       --placeholder_token='<psychedelic>' \
-       --train_data_dir=/home/lstein/invokeai/training-data/psychedelic \
-       --output_dir=/home/lstein/invokeai/text-inversion-training/psychedelic \
-       --scale_lr \
-       --train_batch_size=8 \
-       --gradient_accumulation_steps=4 \
-       --max_train_steps=3000 \
-       --learning_rate=0.0005 \
-       --resume_from_checkpoint=latest \
-       --lr_scheduler=constant \
-       --mixed_precision=fp16 \
-       --only_save_embeds
-```
-
-## Troubleshooting
-
-### `Cannot load embedding for <trigger>. It was trained on a model with token dimension 1024, but the current model has token dimension 768`
-
-Messages like this indicate you trained the embedding on a different base model than the currently selected one.
-
-For example, in the error above, the training was done on SD2.1 (768x768) but it was used on SD1.5 (512x512).
-
-## Reading
-
-For more information on textual inversion, please see the following
-resources:
-
-* The [textual inversion repository](https://github.com/rinongal/textual_inversion) and
-  associated paper for details and limitations.
-* [HuggingFace's textual inversion training
-  page](https://huggingface.co/docs/diffusers/training/text_inversion)
-* [HuggingFace example script
-  documentation](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion)
-  (Note that this script is similar to, but not identical, to
-  `textual_inversion`, but produces embed files that are completely compatible.
-
----
-
-copyright (c) 2023, Lincoln Stein and the InvokeAI Development Team

docs/features/VARIATIONS.md

@@ -6,7 +6,9 @@ title: Variations
 
 ## Intro
 
-InvokeAI's support for variations enables you to do the following:
+Release 1.13 of SD-Dream adds support for image variations.
+
+You are able 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.
@@ -28,7 +30,19 @@ The prompt we will use throughout is:
 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.
+requesting six iterations:
+
+```bash
+invoke> lucy lawless as xena, warrior princess, character portrait, high resolution -n6
+...
+Outputs:
+./outputs/Xena/000001.1579445059.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1579445059
+./outputs/Xena/000001.1880768722.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1880768722
+./outputs/Xena/000001.332057179.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S332057179
+./outputs/Xena/000001.2224800325.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S2224800325
+./outputs/Xena/000001.465250761.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S465250761
+./outputs/Xena/000001.3357757885.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S3357757885
+```
 
 <figure markdown>
 ![var1](../assets/variation_walkthru/000001.3357757885.png)
@@ -39,16 +53,22 @@ requesting six iterations.
 
 ## 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.
+Let's try to generate some variations. Using the same seed, we pass the argument
+`-v0.1` (or --variant_amount), which generates a series of variations each
+differing by a variation amount of 0.2. This number ranges from `0` to `1.0`,
+with higher numbers being larger amounts of variation.
 
-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.
+```bash
+invoke> "prompt" -n6 -S3357757885 -v0.2
+...
+Outputs:
+./outputs/Xena/000002.784039624.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 784039624:0.2 -S3357757885
+./outputs/Xena/000002.3647897225.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.2 -S3357757885
+./outputs/Xena/000002.917731034.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 917731034:0.2 -S3357757885
+./outputs/Xena/000002.4116285959.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 4116285959:0.2 -S3357757885
+./outputs/Xena/000002.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1614299449:0.2 -S3357757885
+./outputs/Xena/000002.1335553075.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1335553075:0.2 -S3357757885
+```
 
 ### **Variation Sub Seeding**
 

docs/features/WEB.md

@@ -299,6 +299,14 @@ initial image" icons are located.
 
 See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
 
+## Parting remarks
+
+This concludes the walkthrough, but there are several more features that you can
+explore. Please check out the [Command Line Interface](CLI.md) documentation for
+further explanation of the advanced features that were not covered here.
+
+The WebUI is only rapid development. Check back regularly for updates!
+
 ## Reference
 
 ### Additional Options
@@ -341,9 +349,11 @@ the settings configured in the toolbar.
 
 See below for additional documentation related to each feature:
 
+- [Core Prompt Settings](./CLI.md)
 - [Variations](./VARIATIONS.md)
 - [Upscaling](./POSTPROCESS.md#upscaling)
 - [Image to Image](./IMG2IMG.md)
+- [Inpainting](./INPAINTING.md)
 - [Other](./OTHER.md)
 
 #### Invocation Gallery

docs/features/index.md

@@ -2,53 +2,84 @@
 title: Overview
 ---
 
-Here you can find the documentation for InvokeAI's various features.
+-   The Basics
 
-## The Basics
-### * The [Web User Interface](WEB.md)
-Guide to the Web interface. Also see the [WebUI Hotkeys Reference Guide](WEBUIHOTKEYS.md)
+    -   The [Web User Interface](WEB.md)
 
-### * The [Unified Canvas](UNIFIED_CANVAS.md)
-Build complex scenes by combine and modifying multiple images in a stepwise
-fashion. This feature combines img2img, inpainting and outpainting in
-a single convenient digital artist-optimized user interface.
+        Guide to the Web interface. Also see the
+        [WebUI Hotkeys Reference Guide](WEBUIHOTKEYS.md)
 
-## Image Generation
-### * [Prompt Engineering](PROMPTS.md)
-Get the images you want with the InvokeAI  prompt engineering language.
+    -   The [Unified Canvas](UNIFIED_CANVAS.md)
 
-## * The [Concepts Library](CONCEPTS.md)
-Add custom subjects and styles using HuggingFace's repository of embeddings.
+        Build complex scenes by combine and modifying multiple images in a
+        stepwise fashion. This feature combines img2img, inpainting and
+        outpainting in a single convenient digital artist-optimized user
+        interface.
 
-### * [Image-to-Image Guide](IMG2IMG.md)
-Use a seed image to build new creations in the CLI.
+    -   The [Command Line Interface (CLI)](CLI.md)
 
-### * [Generating Variations](VARIATIONS.md)
-Have an image you like and want to generate many more like it? Variations
-are the ticket.
+        Scriptable access to InvokeAI's features.
 
-## Model Management
+    -   [Visual Manual for InvokeAI](https://docs.google.com/presentation/d/e/2PACX-1vSE90aC7bVVg0d9KXVMhy-Wve-wModgPFp7AGVTOCgf4xE03SnV24mjdwldolfCr59D_35oheHe4Cow/pub?start=false&loop=true&delayms=60000) (contributed by Statcomm)
 
-## * [Model Installation](../installation/050_INSTALLING_MODELS.md)
-Learn how to import third-party models and switch among them. This
-guide also covers optimizing models to load quickly.
+-   Image Generation
 
-## * [Merging Models](MODEL_MERGING.md)
-Teach an old model new tricks. Merge 2-3 models together to create a
-new model that combines characteristics of the originals.
+    -   [Prompt Engineering](PROMPTS.md)
 
-## * [Textual Inversion](TEXTUAL_INVERSION.md)
-Personalize models by adding your own style or subjects.
+        Get the images you want with the InvokeAI prompt engineering language.
 
-# Other Features
+    -   [Post-Processing](POSTPROCESS.md)
 
-## * [The NSFW Checker](NSFW.md)
-Prevent InvokeAI from displaying unwanted racy images.
+        Restore mangled faces and make images larger with upscaling. Also see
+        the [Embiggen Upscaling Guide](EMBIGGEN.md).
 
-## * [Controlling Logging](LOGGING.md)
-Control how InvokeAI logs status messages.
+    -   The [Concepts Library](CONCEPTS.md)
 
-## * [Miscellaneous](OTHER.md)
-Run InvokeAI on Google Colab, generate images with repeating patterns,
-batch process a file of prompts, increase the "creativity" of image
-generation by adding initial noise, and more!
+        Add custom subjects and styles using HuggingFace's repository of
+        embeddings.
+
+    -   [Image-to-Image Guide for the CLI](IMG2IMG.md)
+
+        Use a seed image to build new creations in the CLI.
+
+    -   [Inpainting Guide for the CLI](INPAINTING.md)
+
+        Selectively erase and replace portions of an existing image in the CLI.
+
+    -   [Outpainting Guide for the CLI](OUTPAINTING.md)
+
+        Extend the borders of the image with an "outcrop" function within the
+        CLI.
+
+    -   [Generating Variations](VARIATIONS.md)
+
+        Have an image you like and want to generate many more like it?
+        Variations are the ticket.
+
+-   Model Management
+
+    -   [Model Installation](../installation/050_INSTALLING_MODELS.md)
+
+        Learn how to import third-party models and switch among them. This guide
+        also covers optimizing models to load quickly.
+
+    -   [Merging Models](MODEL_MERGING.md)
+
+        Teach an old model new tricks. Merge 2-3 models together to create a new
+        model that combines characteristics of the originals.
+
+    -   [Textual Inversion](TEXTUAL_INVERSION.md)
+
+        Personalize models by adding your own style or subjects.
+
+-   Other Features
+
+    -   [The NSFW Checker](NSFW.md)
+
+        Prevent InvokeAI from displaying unwanted racy images.
+
+    -   [Miscellaneous](OTHER.md)
+
+        Run InvokeAI on Google Colab, generate images with repeating patterns,
+        batch process a file of prompts, increase the "creativity" of image
+        generation by adding initial noise, and more!

docs/help/IDE-Settings/index.md

@@ -0,0 +1,4 @@
+# :octicons-file-code-16: IDE-Settings
+
+Here we will share settings for IDEs used by our developers, maybe you can find
+something interestening which will help to boost your development efficency 🔥

docs/help/IDE-Settings/vs-code.md

@@ -0,0 +1,250 @@
+---
+title: Visual Studio Code
+---
+
+# :material-microsoft-visual-studio-code:Visual Studio Code
+
+The Workspace Settings are stored in the project (repository) root and get
+higher priorized than your user settings.
+
+This helps to have different settings for different projects, while the user
+settings get used as a default value if no workspace settings are provided.
+
+## tasks.json
+
+First we will create a task configuration which will create a virtual
+environment and update the deps (pip, setuptools and wheel).
+
+Into this venv we will then install the pyproject.toml in editable mode with
+dev, docs and test dependencies.
+
+```json title=".vscode/tasks.json"
+{
+    // See https://go.microsoft.com/fwlink/?LinkId=733558
+    // for the documentation about the tasks.json format
+    "version": "2.0.0",
+    "tasks": [
+        {
+            "label": "Create virtual environment",
+            "detail": "Create .venv and upgrade pip, setuptools and wheel",
+            "command": "python3",
+            "args": [
+                "-m",
+                "venv",
+                ".venv",
+                "--prompt",
+                "InvokeAI",
+                "--upgrade-deps"
+            ],
+            "runOptions": {
+                "instanceLimit": 1,
+                "reevaluateOnRerun": true
+            },
+            "group": {
+                "kind": "build"
+            },
+            "presentation": {
+                "echo": true,
+                "reveal": "always",
+                "focus": false,
+                "panel": "shared",
+                "showReuseMessage": true,
+                "clear": false
+            }
+        },
+        {
+            "label": "build InvokeAI",
+            "detail": "Build pyproject.toml with extras dev, docs and test",
+            "command": "${workspaceFolder}/.venv/bin/python3",
+            "args": [
+                "-m",
+                "pip",
+                "install",
+                "--use-pep517",
+                "--editable",
+                ".[dev,docs,test]"
+            ],
+            "dependsOn": "Create virtual environment",
+            "dependsOrder": "sequence",
+            "group": {
+                "kind": "build",
+                "isDefault": true
+            },
+            "presentation": {
+                "echo": true,
+                "reveal": "always",
+                "focus": false,
+                "panel": "shared",
+                "showReuseMessage": true,
+                "clear": false
+            }
+        }
+    ]
+}
+```
+
+The fastest way to build InvokeAI now is ++cmd+shift+b++
+
+## launch.json
+
+This file is used to define debugger configurations, so that you can one-click
+launch and monitor the application, set halt points to inspect specific states,
+...
+
+```json title=".vscode/launch.json"
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "invokeai web",
+            "type": "python",
+            "request": "launch",
+            "program": ".venv/bin/invokeai",
+            "justMyCode": true
+        },
+        {
+            "name": "invokeai cli",
+            "type": "python",
+            "request": "launch",
+            "program": ".venv/bin/invokeai",
+            "justMyCode": true
+        },
+        {
+            "name": "mkdocs serve",
+            "type": "python",
+            "request": "launch",
+            "program": ".venv/bin/mkdocs",
+            "args": ["serve"],
+            "justMyCode": true
+        }
+    ]
+}
+```
+
+Then you only need to hit ++f5++ and the fun begins :nerd: (It is asumed that
+you have created a virtual environment via the [tasks](#tasksjson) from the
+previous step.)
+
+## extensions.json
+
+A list of recommended vscode-extensions to make your life easier:
+
+```json title=".vscode/extensions.json"
+{
+    "recommendations": [
+        "editorconfig.editorconfig",
+        "github.vscode-pull-request-github",
+        "ms-python.black-formatter",
+        "ms-python.flake8",
+        "ms-python.isort",
+        "ms-python.python",
+        "ms-python.vscode-pylance",
+        "redhat.vscode-yaml",
+        "tamasfe.even-better-toml",
+        "eamodio.gitlens",
+        "foxundermoon.shell-format",
+        "timonwong.shellcheck",
+        "esbenp.prettier-vscode",
+        "davidanson.vscode-markdownlint",
+        "yzhang.markdown-all-in-one",
+        "bierner.github-markdown-preview",
+        "ms-azuretools.vscode-docker",
+        "mads-hartmann.bash-ide-vscode"
+    ]
+}
+```
+
+## settings.json
+
+With bellow settings your files already get formated when you save them (only
+your modifications if available), which will help you to not run into trouble
+with the pre-commit hooks. If the hooks fail, they will prevent you from
+commiting, but most hooks directly add a fixed version, so that you just need to
+stage and commit them:
+
+```json title=".vscode/settings.json"
+{
+    "[json]": {
+        "editor.defaultFormatter": "esbenp.prettier-vscode",
+        "editor.quickSuggestions": {
+            "comments": false,
+            "strings": true,
+            "other": true
+        },
+        "editor.suggest.insertMode": "replace",
+        "gitlens.codeLens.scopes": ["document"]
+    },
+    "[jsonc]": {
+        "editor.defaultFormatter": "esbenp.prettier-vscode",
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "modificationsIfAvailable"
+    },
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "file"
+    },
+    "[toml]": {
+        "editor.defaultFormatter": "tamasfe.even-better-toml",
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "modificationsIfAvailable"
+    },
+    "[yaml]": {
+        "editor.defaultFormatter": "esbenp.prettier-vscode",
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "modificationsIfAvailable"
+    },
+    "[markdown]": {
+        "editor.defaultFormatter": "esbenp.prettier-vscode",
+        "editor.rulers": [80],
+        "editor.unicodeHighlight.ambiguousCharacters": false,
+        "editor.unicodeHighlight.invisibleCharacters": false,
+        "diffEditor.ignoreTrimWhitespace": false,
+        "editor.wordWrap": "on",
+        "editor.quickSuggestions": {
+            "comments": "off",
+            "strings": "off",
+            "other": "off"
+        },
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "modificationsIfAvailable"
+    },
+    "[shellscript]": {
+        "editor.defaultFormatter": "foxundermoon.shell-format"
+    },
+    "[ignore]": {
+        "editor.defaultFormatter": "foxundermoon.shell-format"
+    },
+    "editor.rulers": [88],
+    "evenBetterToml.formatter.alignEntries": false,
+    "evenBetterToml.formatter.allowedBlankLines": 1,
+    "evenBetterToml.formatter.arrayAutoExpand": true,
+    "evenBetterToml.formatter.arrayTrailingComma": true,
+    "evenBetterToml.formatter.arrayAutoCollapse": true,
+    "evenBetterToml.formatter.columnWidth": 88,
+    "evenBetterToml.formatter.compactArrays": true,
+    "evenBetterToml.formatter.compactInlineTables": true,
+    "evenBetterToml.formatter.indentEntries": false,
+    "evenBetterToml.formatter.inlineTableExpand": true,
+    "evenBetterToml.formatter.reorderArrays": true,
+    "evenBetterToml.formatter.reorderKeys": true,
+    "evenBetterToml.formatter.compactEntries": false,
+    "evenBetterToml.schema.enabled": true,
+    "python.analysis.typeCheckingMode": "basic",
+    "python.formatting.provider": "black",
+    "python.languageServer": "Pylance",
+    "python.linting.enabled": true,
+    "python.linting.flake8Enabled": true,
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "python.testing.pytestArgs": [
+        "tests",
+        "--cov=ldm",
+        "--cov-branch",
+        "--cov-report=term:skip-covered"
+    ],
+    "yaml.schemas": {
+        "https://json.schemastore.org/prettierrc.json": "${workspaceFolder}/.prettierrc.yaml"
+    }
+}
+```

docs/help/contributing/010_PULL_REQUEST.md

@@ -0,0 +1,135 @@
+---
+title: Pull-Request
+---
+
+# :octicons-git-pull-request-16: Pull-Request
+
+## pre-requirements
+
+To follow the steps in this tutorial you will need:
+
+-   [GitHub](https://github.com) account
+-   [git](https://git-scm.com/downloads) source controll
+-   Text / Code Editor (personally I preffer
+    [Visual Studio Code](https://code.visualstudio.com/Download))
+-   Terminal:
+    -   If you are on Linux/MacOS you can use bash or zsh
+    -   for Windows Users the commands are written for PowerShell
+
+## Fork Repository
+
+The first step to be done if you want to contribute to InvokeAI, is to fork the
+rpeository.
+
+Since you are already reading this doc, the easiest way to do so is by clicking
+[here](https://github.com/invoke-ai/InvokeAI/fork). You could also open
+[InvokeAI](https://github.com/invoke-ai/InvoekAI) and click on the "Fork" Button
+in the top right.
+
+## Clone your fork
+
+After you forked the Repository, you should clone it to your dev machine:
+
+=== ":fontawesome-brands-linux:Linux / :simple-apple:macOS"
+
+    ``` sh
+    git clone https://github.com/<github username>/InvokeAI \
+    && cd InvokeAI
+    ```
+
+=== ":fontawesome-brands-windows:Windows"
+
+    ``` powershell
+    git clone https://github.com/<github username>/InvokeAI `
+    && cd InvokeAI
+    ```
+
+## Install in Editable Mode
+
+To install InvokeAI in editable mode, (as always) we recommend to create and
+activate a venv first. Afterwards you can install the InvokeAI Package,
+including dev and docs extras in editable mode, follwed by the installation of
+the pre-commit hook:
+
+=== ":fontawesome-brands-linux:Linux / :simple-apple:macOS"
+
+    ``` sh
+    python -m venv .venv \
+      --prompt InvokeAI \
+      --upgrade-deps \
+    && source .venv/bin/activate \
+    && pip install \
+      --upgrade-deps \
+      --use-pep517 \
+      --editable=".[dev,docs]" \
+    && pre-commit install
+    ```
+
+=== ":fontawesome-brands-windows:Windows"
+
+    ``` powershell
+    python -m venv .venv `
+      --prompt InvokeAI `
+      --upgrade-deps `
+    && .venv/scripts/activate.ps1 `
+    && pip install `
+      --upgrade `
+      --use-pep517 `
+      --editable=".[dev,docs]" `
+    && pre-commit install
+    ```
+
+## Create a branch
+
+Make sure you are on main branch, from there create your feature branch:
+
+=== ":fontawesome-brands-linux:Linux / :simple-apple:macOS"
+
+    ``` sh
+    git checkout main \
+    && git pull \
+    && git checkout -B <branch name>
+    ```
+
+=== ":fontawesome-brands-windows:Windows"
+
+    ``` powershell
+    git checkout main `
+    && git pull `
+    && git checkout -B <branch name>
+    ```
+
+## Commit your changes
+
+When you are done with adding / updating content, you need to commit those
+changes to your repository before you can actually open an PR:
+
+```{ .sh .annotate }
+git add <files you have changed> # (1)!
+git commit -m "A commit message which describes your change"
+git push
+```
+
+1. Replace this with a space seperated list of the files you changed, like:
+   `README.md foo.sh bar.json baz`
+
+## Create a Pull Request
+
+After pushing your changes, you are ready to create a Pull Request. just head
+over to your fork on [GitHub](https://github.com), which should already show you
+a message that there have been recent changes on your feature branch and a green
+button which you could use to create the PR.
+
+The default target for your PRs would be the main branch of
+[invoke-ai/InvokeAI](https://github.com/invoke-ai/InvokeAI)
+
+Another way would be to create it in VS-Code or via the GitHub CLI (or even via
+the GitHub CLI in a VS-Code Terminal Window 🤭):
+
+```sh
+gh pr create
+```
+
+The CLI will inform you if there are still unpushed commits on your branch. It
+will also prompt you for things like the the Title and the Body (Description) if
+you did not already pass them as arguments.

docs/help/contributing/020_ISSUES.md

@@ -0,0 +1,26 @@
+---
+title: Issues
+---
+
+# :octicons-issue-opened-16: Issues
+
+## :fontawesome-solid-bug: Report a bug
+
+If you stumbled over a bug while using InvokeAI, we would apreciate it a lot if
+you
+[open a issue](https://github.com/invoke-ai/InvokeAI/issues/new?assignees=&labels=bug&template=BUG_REPORT.yml&title=%5Bbug%5D%3A+)
+to inform us about the details so that our developers can look into it.
+
+If you also know how to fix the bug, take a look [here](010_PULL_REQUEST.md) to
+find out how to create a Pull Request.
+
+## Request a feature
+
+If you have a idea for a new feature on your mind which you would like to see in
+InvokeAI, there is a
+[feature request](https://github.com/invoke-ai/InvokeAI/issues/new?assignees=&labels=bug&template=BUG_REPORT.yml&title=%5Bbug%5D%3A+)
+available in the issues section of the repository.
+
+If you are just curious which features already got requested you can find the
+overview of open requests
+[here](https://github.com/invoke-ai/InvokeAI/labels/enhancement)

docs/help/contributing/030_DOCS.md

@@ -0,0 +1,32 @@
+---
+title: docs
+---
+
+# :simple-readthedocs: MkDocs-Material
+
+If you want to contribute to the docs, there is a easy way to verify the results
+of your changes before commiting them.
+
+Just follow the steps in the [Pull-Requests](010_PULL_REQUEST.md) docs, there we
+already
+[create a venv and install the docs extras](010_PULL_REQUEST.md#install-in-editable-mode).
+When installed it's as simple as:
+
+```sh
+mkdocs serve
+```
+
+This will build the docs locally and serve them on your local host, even
+auto-refresh is included, so you can just update a doc, save it and tab to the
+browser, without the needs of restarting the `mkdocs serve`.
+
+More information about the "mkdocs flavored markdown syntax" can be found
+[here](https://squidfunk.github.io/mkdocs-material/reference/).
+
+## :material-microsoft-visual-studio-code:VS-Code
+
+We also provide a
+[launch configuration for VS-Code](../IDE-Settings/vs-code.md#launchjson) which
+includes a `mkdocs serve` entrypoint as well. You also don't have to worry about
+the formatting since this is automated via prettier, but this is of course not
+limited to VS-Code.

docs/help/contributing/090_NODE_TRANSFORMATION.md

@@ -0,0 +1,76 @@
+# Tranformation to nodes
+
+## Current state
+
+```mermaid
+flowchart TD
+    web[WebUI];
+    cli[CLI];
+    web --> |img2img| generate(generate);
+    web --> |txt2img| generate(generate);
+    cli --> |txt2img| generate(generate);
+    cli --> |img2img| generate(generate);
+    generate --> model_manager;
+    generate --> generators;
+    generate --> ti_manager[TI Manager];
+    generate --> etc;
+```
+
+## Transitional Architecture
+
+### first step
+
+```mermaid
+flowchart TD
+    web[WebUI];
+    cli[CLI];
+    web --> |img2img| img2img_node(Img2img node);
+    web --> |txt2img| generate(generate);
+    img2img_node --> model_manager;
+    img2img_node --> generators;
+    cli --> |txt2img| generate;
+    cli --> |img2img| generate;
+    generate --> model_manager;
+    generate --> generators;
+    generate --> ti_manager[TI Manager];
+    generate --> etc;
+```
+
+### second step
+
+```mermaid
+flowchart TD
+    web[WebUI];
+    cli[CLI];
+    web --> |img2img| img2img_node(img2img node);
+    img2img_node --> model_manager;
+    img2img_node --> generators;
+    web --> |txt2img| txt2img_node(txt2img node);
+    cli --> |txt2img| txt2img_node;
+    cli --> |img2img| generate(generate);
+    generate --> model_manager;
+    generate --> generators;
+    generate --> ti_manager[TI Manager];
+    generate --> etc;
+    txt2img_node --> model_manager;
+    txt2img_node --> generators;
+    txt2img_node --> ti_manager[TI Manager];
+```
+
+## Final Architecture
+
+```mermaid
+flowchart TD
+    web[WebUI];
+    cli[CLI];
+    web --> |img2img|img2img_node(img2img node);
+    cli --> |img2img|img2img_node;
+    web --> |txt2img|txt2img_node(txt2img node);
+    cli --> |txt2img|txt2img_node;
+    img2img_node --> model_manager;
+    txt2img_node --> model_manager;
+    img2img_node --> generators;
+    txt2img_node --> generators;
+    img2img_node --> ti_manager[TI Manager];
+    txt2img_node --> ti_manager[TI Manager];
+```

docs/help/contributing/index.md

@@ -0,0 +1,16 @@
+---
+title: Contributing
+---
+
+# :fontawesome-solid-code-commit: Contributing
+
+There are different ways how you can contribute to
+[InvokeAI](https://github.com/invoke-ai/InvokeAI), like Translations, opening
+Issues for Bugs or ideas how to improve.
+
+This Section of the docs will explain some of the different ways of how you can
+contribute to make it easier for newcommers as well as advanced users :nerd:
+
+If you want to contribute code, but you do not have an exact idea yet, take a
+look at the currently open
+[:fontawesome-solid-bug: Bug Reports](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)

docs/help/index.md

@@ -0,0 +1,12 @@
+# :material-help:Help
+
+If you are looking for help with the installation of InvokeAI, please take a
+look into the [Installation](../installation/index.md) section of the docs.
+
+Here you will find help to topics like
+
+-   how to contribute
+-   configuration recommendation for IDEs
+
+If you have an Idea about what's missing and aren't scared from contributing,
+just take a look at [DOCS](./contributing/030_DOCS.md) to find out how to do so.

docs/index.md

@@ -2,6 +2,8 @@
 title: Home
 ---
 
+# :octicons-home-16: Home
+
 <!--
   The Docs you find here (/docs/*) are built and deployed via mkdocs. If you want to run a local version to verify your changes, it's as simple as::
 
@@ -13,7 +15,6 @@ title: Home
 
 <div align="center" markdown>
 
-
 [![project logo](assets/invoke_ai_banner.png)](https://github.com/invoke-ai/InvokeAI)
 
 [![discord badge]][discord link]
@@ -30,36 +31,36 @@ title: Home
 [![github open prs badge]][github open prs link]
 
 [ci checks on dev badge]:
-  https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
+    https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
 [ci checks on dev link]:
-  https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
+    https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
 [ci checks on main badge]:
-  https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
+    https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
 [ci checks on main link]:
-  https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
+    https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
 [discord badge]: https://flat.badgen.net/discord/members/ZmtBAhwWhy?icon=discord
 [discord link]: https://discord.gg/ZmtBAhwWhy
 [github forks badge]:
-  https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
+    https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
 [github forks link]:
-  https://useful-forks.github.io/?repo=lstein%2Fstable-diffusion
+    https://useful-forks.github.io/?repo=lstein%2Fstable-diffusion
 [github open issues badge]:
-  https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
+    https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
 [github open issues link]:
-  https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
+    https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
 [github open prs badge]:
-  https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
+    https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
 [github open prs link]:
-  https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
+    https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
 [github stars badge]:
-  https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
+    https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
 [github stars link]: https://github.com/invoke-ai/InvokeAI/stargazers
 [latest commit to dev badge]:
-  https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
+    https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
 [latest commit to dev link]:
-  https://github.com/invoke-ai/InvokeAI/commits/development
+    https://github.com/invoke-ai/InvokeAI/commits/development
 [latest release badge]:
-  https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
+    https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
 
 </div>
@@ -68,7 +69,7 @@ title: Home
 implementation of Stable Diffusion, the open source text-to-image and
 image-to-image generator. It provides a streamlined process with various new
 features and options to aid the image generation process. It runs on Windows,
-Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
+Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM.
 
 **Quick links**: [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>]
 [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a
@@ -88,24 +89,24 @@ Q&A</a>]
 
 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.
+-   :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.
 
 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
+-   NVIDIA 10xx series cards such as the 1080ti
+-   GTX 1650 series cards
+-   GTX 1660 series cards
 
 ### :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.
+-   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.
 
 ## :octicons-package-dependencies-24: Installation
 
@@ -114,109 +115,407 @@ either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
 driver).
 
 ### [Installation Getting Started Guide](installation)
+
 #### [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
+
 This method is recommended for 1st time users
+
 #### [Manual Installation](installation/020_INSTALL_MANUAL.md)
+
 This method is recommended for experienced users and developers
+
 #### [Docker Installation](installation/040_INSTALL_DOCKER.md)
+
 This method is recommended for those familiar with running Docker containers
+
 ### Other Installation Guides
-  - [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
-  - [XFormers](installation/070_INSTALL_XFORMERS.md)
-  - [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
-  - [Installing New Models](installation/050_INSTALLING_MODELS.md)
+
+-   [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
+-   [XFormers](installation/070_INSTALL_XFORMERS.md)
+-   [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
+-   [Installing New Models](installation/050_INSTALLING_MODELS.md)
 
 ## :octicons-gift-24: InvokeAI Features
 
 ### The InvokeAI Web Interface
-- [WebUI overview](features/WEB.md)
-- [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
-- [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
 
+-   [WebUI overview](features/WEB.md)
+-   [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
+-   [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
+-   [Visual Manual for InvokeAI v2.3.1](https://docs.google.com/presentation/d/e/2PACX-1vSE90aC7bVVg0d9KXVMhy-Wve-wModgPFp7AGVTOCgf4xE03SnV24mjdwldolfCr59D_35oheHe4Cow/pub?start=false&loop=true&delayms=60000) (contributed by Statcomm)
+
+<!-- separator -->
+
+<!-- separator -->
+
+### The InvokeAI Command Line Interface
+
+-   [Command Line Interace Reference Guide](features/CLI.md)
 <!-- separator -->
 
 ### Image Management
-- [Image2Image](features/IMG2IMG.md)
-- [Adding custom styles and subjects](features/CONCEPTS.md)
-- [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
-- [Other Features](features/OTHER.md)
+
+-   [Image2Image](features/IMG2IMG.md)
+-   [Inpainting](features/INPAINTING.md)
+-   [Outpainting](features/OUTPAINTING.md)
+-   [Adding custom styles and subjects](features/CONCEPTS.md)
+-   [Using LoRA models](features/LORAS.md)
+-   [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
+-   [Embiggen upscaling](features/EMBIGGEN.md)
+-   [Other Features](features/OTHER.md)
 
 <!-- separator -->
+
 ### Model Management
-- [Installing](installation/050_INSTALLING_MODELS.md)
-- [Model Merging](features/MODEL_MERGING.md)
-- [Style/Subject Concepts and Embeddings](features/CONCEPTS.md)
-- [Textual Inversion](features/TEXTUAL_INVERSION.md)
-- [Not Safe for Work (NSFW) Checker](features/NSFW.md)
+
+-   [Installing](installation/050_INSTALLING_MODELS.md)
+-   [Model Merging](features/MODEL_MERGING.md)
+-   [Adding custom styles and subjects via embeddings](features/CONCEPTS.md)
+-   [Textual Inversion](features/TEXTUAL_INVERSION.md)
+-   [Not Safe for Work (NSFW) Checker](features/NSFW.md)
 <!-- seperator -->
+
 ### Prompt Engineering
-- [Prompt Syntax](features/PROMPTS.md)
-- [Generating Variations](features/VARIATIONS.md)
 
-### InvokeAI Configuration
-- [Guide to InvokeAI Runtime Settings](features/CONFIGURATION.md)
+-   [Prompt Syntax](features/PROMPTS.md)
+-   [Generating Variations](features/VARIATIONS.md)
 
-## :octicons-log-16: Important Changes Since Version 2.3
+## :octicons-log-16: Latest Changes
 
-### Nodes
+### v2.3.3 <small>(29 March 2023)</small>
 
-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.
+#### Bug Fixes
+1. When using legacy checkpoints with an external VAE, the VAE file is now scanned for malware prior to loading. Previously only the main model weights file was scanned.
+2. Textual inversion will select an appropriate batchsize based on whether `xformers` is active, and will default to `xformers` enabled if the library is detected.
+3. The batch script log file names have been fixed to be compatible with Windows.
+4. Occasional corruption of the `.next_prefix` file (which stores the next output file name in sequence) on Windows systems is now detected and corrected.
+5. An infinite loop when opening the developer's console from within the `invoke.sh` script has been corrected.
 
-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.
+#### Enhancements
+1. It is now possible to load and run several community-contributed SD-2.0 based models, including the infamous "Illuminati" model.
+2. The "NegativePrompts" embedding file, and others like it, can now be loaded by placing it in the InvokeAI `embeddings` directory.
+3. If no `--model` is specified at launch time, InvokeAI will remember the last model used and restore it the next time it is launched.
+4. On Linux systems, the `invoke.sh` launcher now uses a prettier console-based interface. To take advantage of it, install the `dialog` package using your package manager (e.g. `sudo apt install dialog`).
+5. When loading legacy models (safetensors/ckpt) you can specify a custom config file and/or a VAE by placing like-named files in the same directory as the model following this example:
+```
+my-favorite-model.ckpt
+my-favorite-model.yaml
+my-favorite-model.vae.pt      # or my-favorite-model.vae.safetensors
+```
 
-### Command-Line Interface Retired
+### v2.3.2 <small>(13 March 2023)</small>
 
-The original "invokeai" command-line interface has been retired. The
-`invokeai` command will now launch a new command-line client that can
-be used by developers to create and test nodes. It is not intended to
-be used for routine image generation or manipulation.
+#### Bugfixes
 
-To launch the Web GUI from the command-line, use the command
-`invokeai-web` rather than the traditional `invokeai --web`.
+Since version 2.3.1 the following bugs have been fixed:
 
-### ControlNet
+1. Black images appearing for potential NSFW images when generating with legacy checkpoint models and both `--no-nsfw_checker` and `--ckpt_convert` turned on.
+2. Black images appearing when generating from models fine-tuned on Stable-Diffusion-2-1-base. When importing V2-derived models, you may be asked to select whether the model was derived from a "base" model (512 pixels) or the 768-pixel SD-2.1 model.
+3. The "Use All" button was not restoring the Hi-Res Fix setting on the WebUI
+4. When using the model installer console app, models failed to import correctly when importing from directories with spaces in their names. A similar issue with the output directory was also fixed.
+5. Crashes that occurred during model merging.
+6. Restore previous naming of Stable Diffusion base and 768 models.
+7. Upgraded to latest versions of `diffusers`, `transformers`, `safetensors` and `accelerate` libraries upstream. We hope that this will fix the `assertion NDArray > 2**32` issue that MacOS users have had when generating images larger than 768x768 pixels. Please report back.
 
-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)
+As part of the upgrade to `diffusers`, the location of the diffusers-based models has changed from `models/diffusers` to `models/hub`. When you launch InvokeAI for the first time, it will prompt you to OK a one-time move. This should be quick and harmless, but if you have modified your `models/diffusers` directory in some way, for example using symlinks, you may wish to cancel the migration and make appropriate adjustments.
 
-### New Schedulers
+#### New "Invokeai-batch" script
 
-The list of schedulers has been completely revamped and brought up to date:
+2.3.2 introduces a new command-line only script called
+`invokeai-batch` that can be used to generate hundreds of images from
+prompts and settings that vary systematically. This can be used to try
+the same prompt across multiple combinations of models, steps, CFG
+settings and so forth. It also allows you to template prompts and
+generate a combinatorial list like: ``` a shack in the mountains,
+photograph a shack in the mountains, watercolor a shack in the
+mountains, oil painting a chalet in the mountains, photograph a chalet
+in the mountains, watercolor a chalet in the mountains, oil painting a
+shack in the desert, photograph ...  ```
 
-| **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                    |
+If you have a system with multiple GPUs, or a single GPU with lots of
+VRAM, you can parallelize generation across the combinatorial set,
+reducing wait times and using your system's resources efficiently
+(make sure you have good GPU cooling).
 
-Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details.
+To try `invokeai-batch` out. Launch the "developer's console" using
+the `invoke` launcher script, or activate the invokeai virtual
+environment manually. From the console, give the command
+`invokeai-batch --help` in order to learn how the script works and
+create your first template file for dynamic prompt generation.
+
+### v2.3.1 <small>(26 February 2023)</small>
+
+This is primarily a bugfix release, but it does provide several new features that will improve the user experience. 
+
+#### Enhanced support for model management
+
+InvokeAI now makes it convenient to add, remove and modify models. You can individually import models that are stored on your local system, scan an entire folder and its subfolders for models and import them automatically, and even directly import models from the internet by providing their download URLs. You also have the option of designating a local folder to scan for new models each time InvokeAI is restarted.
+
+There are three ways of accessing the model management features:
+
+1. ***From the WebUI***, click on the cube to the right of the model selection menu. This will bring up a form that allows you to import models individually from your local disk or scan a directory for models to import.
+
+![image](https://user-images.githubusercontent.com/111189/220638091-918492cc-0719-4194-b033-3741e8289b30.png)
+
+2. **Using the Model Installer App**
+
+Choose option (5) _download and install models_ from the `invoke` launcher script to start a new console-based application for model management. You can use this to select from a curated set of starter models, or import checkpoint, safetensors, and diffusers models from a local disk or the internet. The example below shows importing two checkpoint URLs from popular SD sites and a HuggingFace diffusers model using its Repository ID. It also shows how to designate a folder to be scanned at startup time for new models to import.
+
+Command-line users can start this app using the command `invokeai-model-install`.
+
+![image](https://user-images.githubusercontent.com/111189/220660363-22ff3a2e-8082-410e-a818-d2b3a0529bac.png)
+
+3. **Using the Command Line Client (CLI)**
+
+The `!install_model` and `!convert_model` commands have been enhanced to allow entering of URLs and local directories to scan and import. The first command installs .ckpt and .safetensors files as-is. The second one converts them into the faster diffusers format before installation.
+
+Internally InvokeAI is able to probe the contents of a .ckpt or .safetensors file to distinguish among v1.x, v2.x and inpainting models. This means that you do **not** need to include "inpaint" in your model names to use an inpainting model. Note that Stable Diffusion v2.x models will be autoconverted into a diffusers model the first time you use it.
+
+Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management.
+
+#### An Improved Installer Experience
+
+The installer now launches a console-based UI for setting and changing commonly-used startup options:
+
+![image](https://user-images.githubusercontent.com/111189/220644777-3d3a90ca-f9e2-4e6d-93da-cbdd66bf12f3.png)
+
+After selecting the desired options, the installer installs several support models needed by InvokeAI's face reconstruction and upscaling features and then launches the interface for selecting and installing models shown earlier. At any time,  you can edit the startup options by launching `invoke.sh`/`invoke.bat` and entering option (6) _change InvokeAI startup options_
+
+Command-line users can launch the new configure app using `invokeai-configure`.
+
+This release also comes with a renewed updater. To do an update without going through a whole reinstallation, launch `invoke.sh` or `invoke.bat` and choose option (9) _update InvokeAI_ . This will bring you to a screen that prompts you to update to the latest released version, to the most current development version, or any released or unreleased version you choose by selecting the tag or branch of the desired version.
+
+![image](https://user-images.githubusercontent.com/111189/220650124-30a77137-d9cd-406e-a87d-d8283f99a4b3.png)
+
+Command-line users can run this interface by typing `invokeai-configure`
+
+#### Image Symmetry Options
+
+There are now features to generate horizontal and vertical symmetry during generation. The way these work is to wait until a selected step in the generation process and then to turn on a mirror image effect. In addition to generating some cool images, you can also use this to make side-by-side comparisons of how an image will look with more or fewer steps. Access this option from the WebUI by selecting _Symmetry_ from the image generation settings, or within the CLI by using the options `--h_symmetry_time_pct` and `--v_symmetry_time_pct` (these can be abbreviated to `--h_sym` and `--v_sym` like all other options).
+
+![image](https://user-images.githubusercontent.com/111189/220658687-47fd0f2c-7069-4d95-aec9-7196fceb360d.png)
+
+#### A New Unified Canvas Look
+
+This release introduces a beta version of the WebUI Unified Canvas. To try it out, open up the settings dialogue in the WebUI (gear icon) and select _Use Canvas Beta Layout_:
+
+![image](https://user-images.githubusercontent.com/111189/220646958-b7eca95e-dc39-4cd2-b277-63eac98ed446.png)
+
+Refresh the screen and go to to Unified Canvas (left side of screen, third icon from the top). The new layout is designed to provide more space to work in and to keep the image controls close to the image itself:
+
+![image](https://user-images.githubusercontent.com/111189/220647560-4a9265a1-6926-44f9-9d08-e1ef2ce61ff8.png)
+
+#### Model conversion and merging within the WebUI
+
+The WebUI now has an intuitive interface for model merging, as well as for permanent conversion of models from legacy .ckpt/.safetensors formats into diffusers format. These options are also available directly from the `invoke.sh`/`invoke.bat` scripts.
+
+#### An easier way to contribute translations to the WebUI
+
+We have migrated our translation efforts to [Weblate](https://hosted.weblate.org/engage/invokeai/), a FOSS translation product. Maintaining the growing project's translations is now far simpler for the maintainers and community. Please review our brief [translation guide](https://github.com/invoke-ai/InvokeAI/blob/v2.3.1/docs/other/TRANSLATION.md) for more information on how to contribute.
+
+#### Numerous internal bugfixes and performance issues
+
+This releases quashes multiple bugs that were reported in 2.3.0. Major internal changes include upgrading to `diffusers 0.13.0`, and using the `compel` library for prompt parsing. See [Detailed Change Log](#full-change-log) for a detailed list of bugs caught and squished.
+
+#### Summary of InvokeAI command line scripts (all accessible via the launcher menu)
+
+| Command                  | Description                                                         |
+|--------------------------|---------------------------------------------------------------------|
+| `invokeai`               | Command line interface                                              |
+| `invokeai --web`         | Web interface                                                       |
+| `invokeai-model-install` | Model installer with console forms-based front end                  |
+| `invokeai-ti --gui`      | Textual inversion, with a console forms-based front end             |
+| `invokeai-merge --gui`   | Model merging, with a console forms-based front end                 |
+| `invokeai-configure`     | Startup configuration; can also be used to reinstall support models |
+| `invokeai-update`        | InvokeAI software updater                                           |
+
+
+### v2.3.0 <small>(9 February 2023)</small>
+
+#### Migration to Stable Diffusion `diffusers` models
+
+Previous versions of InvokeAI supported the original model file format
+introduced with Stable Diffusion 1.4. In the original format, known variously as
+"checkpoint", or "legacy" format, there is a single large weights file ending
+with `.ckpt` or `.safetensors`. Though this format has served the community
+well, it has a number of disadvantages, including file size, slow loading times,
+and a variety of non-standard variants that require special-case code to handle.
+In addition, because checkpoint files are actually a bundle of multiple machine
+learning sub-models, it is hard to swap different sub-models in and out, or to
+share common sub-models. A new format, introduced by the StabilityAI company in
+collaboration with HuggingFace, is called `diffusers` and consists of a
+directory of individual models. The most immediate benefit of `diffusers` is
+that they load from disk very quickly. A longer term benefit is that in the near
+future `diffusers` models will be able to share common sub-models, dramatically
+reducing disk space when you have multiple fine-tune models derived from the
+same base.
+
+When you perform a new install of version 2.3.0, you will be offered the option
+to install the `diffusers` versions of a number of popular SD models, including
+Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of
+2.1). These will act and work just like the checkpoint versions. Do not be
+concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk!
+InvokeAI 2.3.0 can still load these and generate images from them without any
+extra intervention on your part.
+
+To take advantage of the optimized loading times of `diffusers` models, InvokeAI
+offers options to convert legacy checkpoint models into optimized `diffusers`
+models. If you use the `invokeai` command line interface, the relevant commands
+are:
+
+-   `!convert_model` -- Take the path to a local checkpoint file or a URL that
+    is pointing to one, convert it into a `diffusers` model, and import it into
+    InvokeAI's models registry file.
+-   `!optimize_model` -- If you already have a checkpoint model in your InvokeAI
+    models file, this command will accept its short name and convert it into a
+    like-named `diffusers` model, optionally deleting the original checkpoint
+    file.
+-   `!import_model` -- Take the local path of either a checkpoint file or a
+    `diffusers` model directory and import it into InvokeAI's registry file. You
+    may also provide the ID of any diffusers model that has been published on
+    the
+    [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads)
+    and it will be downloaded and installed automatically.
+
+The WebGUI offers similar functionality for model management.
+
+For advanced users, new command-line options provide additional functionality.
+Launching `invokeai` with the argument `--autoconvert <path to directory>` takes
+the path to a directory of checkpoint files, automatically converts them into
+`diffusers` models and imports them. Each time the script is launched, the
+directory will be scanned for new checkpoint files to be loaded. Alternatively,
+the `--ckpt_convert` argument will cause any checkpoint or safetensors model
+that is already registered with InvokeAI to be converted into a `diffusers`
+model on the fly, allowing you to take advantage of future diffusers-only
+features without explicitly converting the model and saving it to disk.
+
+Please see
+[INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/)
+for more information on model management in both the command-line and Web
+interfaces.
+
+#### Support for the `XFormers` Memory-Efficient Crossattention Package
+
+On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once
+installed, the`xformers` package dramatically reduces the memory footprint of
+loaded Stable Diffusion models files and modestly increases image generation
+speed. `xformers` will be installed and activated automatically if you specify a
+CUDA system at install time.
+
+The caveat with using `xformers` is that it introduces slightly
+non-deterministic behavior, and images generated using the same seed and other
+settings will be subtly different between invocations. Generally the changes are
+unnoticeable unless you rapidly shift back and forth between images, but to
+disable `xformers` and restore fully deterministic behavior, you may launch
+InvokeAI using the `--no-xformers` option. This is most conveniently done by
+opening the file `invokeai/invokeai.init` with a text editor, and adding the
+line `--no-xformers` at the bottom.
+
+#### A Negative Prompt Box in the WebUI
+
+There is now a separate text input box for negative prompts in the WebUI. This
+is convenient for stashing frequently-used negative prompts ("mangled limbs, bad
+anatomy"). The `[negative prompt]` syntax continues to work in the main prompt
+box as well.
+
+To see exactly how your prompts are being parsed, launch `invokeai` with the
+`--log_tokenization` option. The console window will then display the
+tokenization process for both positive and negative prompts.
+
+#### Model Merging
+
+Version 2.3.0 offers an intuitive user interface for merging up to three Stable
+Diffusion models using an intuitive user interface. Model merging allows you to
+mix the behavior of models to achieve very interesting effects. To use this,
+each of the models must already be imported into InvokeAI and saved in
+`diffusers` format, then launch the merger using a new menu item in the InvokeAI
+launcher script (`invoke.sh`, `invoke.bat`) or directly from the command line
+with `invokeai-merge --gui`. You will be prompted to select the models to merge,
+the proportions in which to mix them, and the mixing algorithm. The script will
+create a new merged `diffusers` model and import it into InvokeAI for your use.
+
+See
+[MODEL MERGING](https://invoke-ai.github.io/InvokeAI/features/MODEL_MERGING/)
+for more details.
+
+#### Textual Inversion Training
+
+Textual Inversion (TI) is a technique for training a Stable Diffusion model to
+emit a particular subject or style when triggered by a keyword phrase. You can
+perform TI training by placing a small number of images of the subject or style
+in a directory, and choosing a distinctive trigger phrase, such as
+"pointillist-style". After successful training, The subject or style will be
+activated by including `<pointillist-style>` in your prompt.
+
+Previous versions of InvokeAI were able to perform TI, but it required using a
+command-line script with dozens of obscure command-line arguments. Version 2.3.0
+features an intuitive TI frontend that will build a TI model on top of any
+`diffusers` model. To access training you can launch from a new item in the
+launcher script or from the command line using `invokeai-ti --gui`.
+
+See
+[TEXTUAL INVERSION](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/)
+for further details.
+
+#### A New Installer Experience
+
+The InvokeAI installer has been upgraded in order to provide a smoother and
+hopefully more glitch-free experience. In addition, InvokeAI is now packaged as
+a PyPi project, allowing developers and power-users to install InvokeAI with the
+command `pip install InvokeAI  --use-pep517`. Please see
+[Installation](#installation) for details.
+
+Developers should be aware that the `pip` installation procedure has been
+simplified and that the `conda` method is no longer supported at all.
+Accordingly, the `environments_and_requirements` directory has been deleted from
+the repository.
+
+#### Command-line name changes
+
+All of InvokeAI's functionality, including the WebUI, command-line interface,
+textual inversion training and model merging, can all be accessed from the
+`invoke.sh` and `invoke.bat` launcher scripts. The menu of options has been
+expanded to add the new functionality. For the convenience of developers and
+power users, we have normalized the names of the InvokeAI command-line scripts:
+
+-   `invokeai` -- Command-line client
+-   `invokeai --web` -- Web GUI
+-   `invokeai-merge --gui` -- Model merging script with graphical front end
+-   `invokeai-ti --gui` -- Textual inversion script with graphical front end
+-   `invokeai-configure` -- Configuration tool for initializing the `invokeai`
+    directory and selecting popular starter models.
+
+For backward compatibility, the old command names are also recognized, including
+`invoke.py` and `configure-invokeai.py`. However, these are deprecated and will
+eventually be removed.
+
+Developers should be aware that the locations of the script's source code has
+been moved. The new locations are:
+
+-   `invokeai` => `ldm/invoke/CLI.py`
+-   `invokeai-configure` => `ldm/invoke/config/configure_invokeai.py`
+-   `invokeai-ti`=> `ldm/invoke/training/textual_inversion.py`
+-   `invokeai-merge` => `ldm/invoke/merge_diffusers`
+
+Developers are strongly encouraged to perform an "editable" install of InvokeAI
+using `pip install -e .  --use-pep517` in the Git repository, and then to call
+the scripts using their 2.3.0 names, rather than executing the scripts directly.
+Developers should also be aware that the several important data files have been
+relocated into a new directory named `invokeai`. This includes the WebGUI's
+`frontend` and `backend` directories, and the `INITIAL_MODELS.yaml` files used
+by the installer to select starter models. Eventually all InvokeAI modules will
+be in subdirectories of `invokeai`.
+
+Please see
+[2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0)
+for further details. For older changelogs, please visit the
+**[CHANGELOG](CHANGELOG/#v223-2-december-2022)**.
 
 ## :material-target: Troubleshooting
 
-Please check out our **[:material-frequently-asked-questions:
-Troubleshooting
-Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)** to
-get solutions for common installation problems and other issues.
+Please check out our
+**[:material-frequently-asked-questions: Troubleshooting Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)**
+to get solutions for common installation problems and other issues.
 
 ## :octicons-repo-push-24: Contributing
 
@@ -242,6 +541,11 @@ thank them for their time, hard work and effort.
 For support, please use this repository's GitHub Issues tracking service. Feel
 free to send me an email if you use and like the script.
 
-Original portions of the software are Copyright (c) 2022-23
-by [The InvokeAI Team](https://github.com/invoke-ai).
+Original portions of the software are Copyright (c) 2022-23 by
+[The InvokeAI Team](https://github.com/invoke-ai).
 
+## :octicons-book-24: Further Reading
+
+Please see the original README for more information on this software and
+underlying algorithm, located in the file
+[README-CompViz.md](other/README-CompViz.md).

docs/installation/010_INSTALL_AUTOMATED.md

@@ -89,7 +89,7 @@ experimental versions later.
          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 apt install python3.10 python3-pip python3.10-venv
          sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
          ```
 

docs/installation/020_INSTALL_MANUAL.md

@@ -148,13 +148,13 @@ manager, please follow these steps:
     === "CUDA (NVidia)"
 
         ```bash
-        pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+        pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
         ```
 
     === "ROCm (AMD)"
 
         ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -216,7 +216,7 @@ manager, please follow these steps:
 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
+    (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:
@@ -315,7 +315,7 @@ installation protocol (important!)
 
     === "ROCm (AMD)"
         ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -77,7 +77,7 @@ machine. To test, open up a terminal window and issue the following
 command:
 
 ```
-rocm-smi
+rocminfo
 ```
 
 If you get a table labeled "ROCm System Management Interface" the
@@ -95,9 +95,17 @@ 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
+After installation, please run `rocminfo` 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.
+do a reboot in order to load the driver. In addition, if you see
+errors relating to your username not being a member of the `render`
+group, you may fix this by adding yourself to this group with the command:
+
+```
+sudo usermod -a -G render myUserName
+```
+
+(Thanks to @EgoringKosmos for the usermod recipe.)
 
 ### Linux Install with a ROCm-docker Container
 

docs/installation/050_INSTALLING_MODELS.md

@@ -11,7 +11,7 @@ The model checkpoint files ('\*.ckpt') are the Stable Diffusion
 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
+which many people named `model.ckpt`. Now there are hundreds
 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
@@ -29,9 +29,10 @@ 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.
 
-While InvokeAI will continue to support `.ckpt` and `.safetensors`
+While InvokeAI will continue to support legacy `.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.
+be withdrawn in version 3.0, after which all legacy models will be
+converted into diffusers at the time they are loaded.
 
 This manual will guide you through installing and configuring model
 weight files and converting legacy `.ckpt` and `.safetensors` files
@@ -50,7 +51,7 @@ subset that are currently installed are found in
 |stable-diffusion-1.5|runwayml/stable-diffusion-v1-5|Stable Diffusion version 1.5 diffusers model (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-v1-5 |
 |sd-inpainting-1.5|runwayml/stable-diffusion-inpainting|RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-inpainting |
 |stable-diffusion-2.1|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
-|sd-inpainting-2.0|stabilityai/stable-diffusion-2-inpainting|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-inpainting |
+|sd-inpainting-2.0|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
 |analog-diffusion-1.0|wavymulder/Analog-Diffusion|An SD-1.5 model trained on diverse analog photographs (2.13 GB)|https://huggingface.co/wavymulder/Analog-Diffusion |
 |deliberate-1.0|XpucT/Deliberate|Versatile model that produces detailed images up to 768px (4.27 GB)|https://huggingface.co/XpucT/Deliberate |
 |d&d-diffusion-1.0|0xJustin/Dungeons-and-Diffusion|Dungeons & Dragons characters (2.13 GB)|https://huggingface.co/0xJustin/Dungeons-and-Diffusion |
@@ -89,15 +90,18 @@ aware that CIVITAI hosts many models that generate NSFW content.
 !!! note
 
     InvokeAI 2.3.x does not support directly importing and
-    running Stable Diffusion version 2 checkpoint models. You may instead
-    convert them into `diffusers` models using the conversion methods
-    described below.
+    running Stable Diffusion version 2 checkpoint models. If you
+    try to import them, they will be automatically
+    converted into `diffusers` models on the fly. This adds about 20s
+    to loading time. To avoid this overhead, you are encouraged to
+    use one of the conversion methods described below to convert them
+    permanently.
 
 ## Installation
 
 There are multiple ways to install and manage models:
 
-1. The `invokeai-configure` script which will download and install them for you.
+1. The `invokeai-model-install` script which will download and install them for you.
 
 2. The command-line tool (CLI) has commands that allows you to import, configure and modify
    models files.
@@ -105,14 +109,41 @@ There are multiple ways to install and manage models:
 3. The web interface (WebUI) has a GUI for importing and managing
    models.
 
-### Installation via `invokeai-configure`
+### Installation via `invokeai-model-install`
 
-From the `invoke` launcher, choose option (6) "re-run the configure
-script to download new 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.
+From the `invoke` launcher, choose option (5) "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.
+
+This script allows you to load 3d party models. Look for a large text
+entry box labeled "IMPORT LOCAL AND REMOTE MODELS." In this box, you
+can cut and paste one or more of any of the following:
+
+1. A URL that points to a downloadable .ckpt or .safetensors file.
+2. A file path pointing to a .ckpt or .safetensors  file.
+3. A diffusers model repo_id (from HuggingFace) in the format
+   "owner/repo_name".
+4. A directory path pointing to a diffusers model directory.
+5. A directory path pointing to a directory containing a bunch of
+   .ckpt and .safetensors files. All will be imported.
+
+You can enter multiple items into the textbox, each one on a separate
+line. You can paste into the textbox using ctrl-shift-V or by dragging
+and dropping a file/directory from the desktop into the box.
+
+The script also lets you designate a directory that will be scanned
+for new model files each time InvokeAI starts up. These models will be
+added automatically.
+
+Lastly, the script gives you a checkbox option to convert legacy models
+into diffusers, or to run the legacy model directly. If you choose to
+convert, the original .ckpt/.safetensors file will **not** be deleted,
+but a new diffusers directory will be created, using twice your disk
+space. However, the diffusers version will load faster, and will be
+compatible with InvokeAI 3.0.
 
 ### Installation via the CLI
 
@@ -144,19 +175,15 @@ invoke> !import_model https://example.org/sd_models/martians.safetensors
 For this to work, the URL must not be password-protected. Otherwise
 you will receive a 404 error.
 
-When you import a legacy model, the CLI will first ask you what type
-of model this is. You can indicate whether it is a model based on
-Stable Diffusion 1.x (1.4 or 1.5), one based on Stable Diffusion 2.x,
-or a 1.x inpainting model. Be careful to indicate the correct model
-type, or it will not load correctly. You can correct the model type
-after the fact using the `!edit_model` command.
-
-The system will then ask you a few other questions about the model,
-including what size image it was trained on (usually 512x512), what
-name and description you wish to use for it, and whether you would
-like to install a custom VAE (variable autoencoder) file for the
-model. For recent models, the answer to the VAE question is usually
-"no," but it won't hurt to answer "yes".
+When you import a legacy model, the CLI will try to figure out what
+type of model it is and select the correct load configuration file.
+However, one thing it can't do is to distinguish between Stable
+Diffusion 2.x models trained on 512x512 vs 768x768 images. In this
+case, the CLI will pop up a menu of choices, asking you to select
+which type of model it is. Please consult the model documentation to
+identify the correct answer, as loading with the wrong configuration
+will lead to black images. You can correct the model type after the
+fact using the `!edit_model` command.
 
 After importing, the model will load. If this is successful, you will
 be asked if you want to keep the model loaded in memory to start
@@ -211,109 +238,6 @@ description for the model, whether to make this the default model that
 is loaded at InvokeAI startup time, and whether to replace its
 VAE. Generally the answer to the latter question is "no".
 
-### Converting legacy models into `diffusers`
-
-The CLI `!convert_model` will convert a `.safetensors` or `.ckpt`
-models file into `diffusers` and install it.This will enable the model
-to load and run faster without loss of image quality.
-
-The usage is identical to `!import_model`. You may point the command
-to either a downloaded model file on disk, or to a (non-password
-protected) URL:
-
-```bash
-invoke> !convert_model C:/Users/fred/Downloads/martians.safetensors
-```
-
-After a successful conversion, the CLI will offer you the option of
-deleting the original `.ckpt` or `.safetensors` file.
-
-### Optimizing a previously-installed model
-
-Lastly, if you have previously installed a `.ckpt` or `.safetensors`
-file and wish to convert it into a `diffusers` model, you can do this
-without re-downloading and converting the original file using the
-`!optimize_model` command. Simply pass the short name of an existing
-installed model:
-
-```bash
-invoke> !optimize_model martians-v1.0
-```
-
-The model will be converted into `diffusers` format and replace the
-previously installed version. You will again be offered the
-opportunity to delete the original `.ckpt` or `.safetensors` file.
-
-### Related CLI Commands
-
-There are a whole series of additional model management commands in
-the CLI that you can read about in [Command-Line
-Interface](../features/CLI.md). These include:
-
-* `!models` - List all installed models
-* `!switch <model name>` - Switch to the indicated model
-* `!edit_model <model name>` - Edit the indicated model to change its name, description or other properties
-* `!del_model <model name>` - Delete the indicated model
-
-### Manually editing `configs/models.yaml`
-
-
-If you are comfortable with a text editor then you may simply edit `models.yaml`
-directly.
-
-You will need to download the desired `.ckpt/.safetensors` file and
-place it somewhere on your machine's filesystem. Alternatively, for a
-`diffusers` model, record the repo_id or download the whole model
-directory. Then using a **text** editor (e.g. the Windows Notepad
-application), open the file `configs/models.yaml`, and add a new
-stanza that follows this model:
-
-#### A legacy model
-
-A legacy `.ckpt` or `.safetensors` entry will look like this:
-
-```yaml
-arabian-nights-1.0:
-  description: A great fine-tune in Arabian Nights style
-  weights: ./path/to/arabian-nights-1.0.ckpt
-  config: ./configs/stable-diffusion/v1-inference.yaml
-  format: ckpt
-  width: 512
-  height: 512
-  default: false
-```
-
-Note that `format` is `ckpt` for both `.ckpt` and `.safetensors` files.
-
-#### A diffusers model
-
-A stanza for a `diffusers` model will look like this for a HuggingFace
-model with a repository ID:
-
-```yaml
-arabian-nights-1.1:
-  description: An even better fine-tune of the Arabian Nights
-  repo_id: captahab/arabian-nights-1.1
-  format: diffusers
-  default: true
-```
-
-And for a downloaded directory:
-
-```yaml
-arabian-nights-1.1:
-  description: An even better fine-tune of the Arabian Nights
-  path: /path/to/captahab-arabian-nights-1.1
-  format: diffusers
-  default: true
-```
-
-There is additional syntax for indicating an external VAE to use with
-this model. See `INITIAL_MODELS.yaml` and `models.yaml` for examples.
-
-After you save the modified `models.yaml` file relaunch
-`invokeai`. The new model will now be available for your use.
-
 ### Installation via the WebUI
 
 To access the WebUI Model Manager, click on the button that looks like
@@ -393,3 +317,143 @@ And here is what the same argument looks like in `invokeai.init`:
 --no-nsfw_checker
 --autoconvert /home/fred/stable-diffusion-checkpoints
 ```
+
+### Specifying a configuration file for legacy checkpoints
+
+Some checkpoint files come with instructions to use a specific .yaml
+configuration file. For InvokeAI load this file correctly, please put
+the config file in the same directory as the corresponding `.ckpt` or
+`.safetensors` file and make sure the file has the same basename as
+the model file. Here is an example:
+
+```bash
+wonderful-model-v2.ckpt
+wonderful-model-v2.yaml
+```
+
+This is not needed for `diffusers` models, which come with their own
+pre-packaged configuration.
+
+### Specifying a custom VAE file for legacy checkpoints
+
+To associate a custom VAE with a legacy file, place the VAE file in
+the same directory as the corresponding `.ckpt` or
+`.safetensors` file and make sure the file has the same basename as
+the model file. Use the suffix `.vae.pt` for VAE checkpoint files, and
+`.vae.safetensors` for VAE safetensors files. There is no requirement
+that both the model and the VAE follow the same format.
+
+Example:
+
+```bash
+wonderful-model-v2.pt
+wonderful-model-v2.vae.safetensors
+```
+
+### Converting legacy models into `diffusers`
+
+The CLI `!convert_model` will convert a `.safetensors` or `.ckpt`
+models file into `diffusers` and install it.This will enable the model
+to load and run faster without loss of image quality.
+
+The usage is identical to `!import_model`. You may point the command
+to either a downloaded model file on disk, or to a (non-password
+protected) URL:
+
+```bash
+invoke> !convert_model C:/Users/fred/Downloads/martians.safetensors
+```
+
+After a successful conversion, the CLI will offer you the option of
+deleting the original `.ckpt` or `.safetensors` file.
+
+### Optimizing a previously-installed model
+
+Lastly, if you have previously installed a `.ckpt` or `.safetensors`
+file and wish to convert it into a `diffusers` model, you can do this
+without re-downloading and converting the original file using the
+`!optimize_model` command. Simply pass the short name of an existing
+installed model:
+
+```bash
+invoke> !optimize_model martians-v1.0
+```
+
+The model will be converted into `diffusers` format and replace the
+previously installed version. You will again be offered the
+opportunity to delete the original `.ckpt` or `.safetensors` file.
+
+Alternatively you can use the WebUI's model manager to handle diffusers
+optimization. Select the legacy model you wish to convert, and then
+look for a button labeled "Convert to Diffusers" in the upper right of
+the window.
+
+### Related CLI Commands
+
+There are a whole series of additional model management commands in
+the CLI that you can read about in [Command-Line
+Interface](../features/CLI.md). These include:
+
+* `!models` - List all installed models
+* `!switch <model name>` - Switch to the indicated model
+* `!edit_model <model name>` - Edit the indicated model to change its name, description or other properties
+* `!del_model <model name>` - Delete the indicated model
+
+### Manually editing `configs/models.yaml`
+
+If you are comfortable with a text editor then you may simply edit `models.yaml`
+directly.
+
+You will need to download the desired `.ckpt/.safetensors` file and
+place it somewhere on your machine's filesystem. Alternatively, for a
+`diffusers` model, record the repo_id or download the whole model
+directory. Then using a **text** editor (e.g. the Windows Notepad
+application), open the file `configs/models.yaml`, and add a new
+stanza that follows this model:
+
+#### A legacy model
+
+A legacy `.ckpt` or `.safetensors` entry will look like this:
+
+```yaml
+arabian-nights-1.0:
+  description: A great fine-tune in Arabian Nights style
+  weights: ./path/to/arabian-nights-1.0.ckpt
+  config: ./configs/stable-diffusion/v1-inference.yaml
+  format: ckpt
+  width: 512
+  height: 512
+  default: false
+```
+
+Note that `format` is `ckpt` for both `.ckpt` and `.safetensors` files.
+
+#### A diffusers model
+
+A stanza for a `diffusers` model will look like this for a HuggingFace
+model with a repository ID:
+
+```yaml
+arabian-nights-1.1:
+  description: An even better fine-tune of the Arabian Nights
+  repo_id: captahab/arabian-nights-1.1
+  format: diffusers
+  default: true
+```
+
+And for a downloaded directory:
+
+```yaml
+arabian-nights-1.1:
+  description: An even better fine-tune of the Arabian Nights
+  path: /path/to/captahab-arabian-nights-1.1
+  format: diffusers
+  default: true
+```
+
+There is additional syntax for indicating an external VAE to use with
+this model. See `INITIAL_MODELS.yaml` and `models.yaml` for examples.
+
+After you save the modified `models.yaml` file relaunch
+`invokeai`. The new model will now be available for your use.
+

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -24,7 +24,7 @@ You need to have opencv installed so that pypatchmatch can be built:
 brew install opencv
 ```
 
-The next time you start `invoke`, after successfully installing opencv, pypatchmatch will be built.
+The next time you start `invoke`, after sucesfully installing opencv, pypatchmatch will be built.
 
 ## Linux
 
@@ -56,7 +56,7 @@ Prior to installing PyPatchMatch, you need to take the following steps:
 
 5. Confirm that pypatchmatch is installed. At the command-line prompt enter
    `python`, and then at the `>>>` line type
-   `from patchmatch import patch_match`: It should look like the following:
+   `from patchmatch import patch_match`: It should look like the follwing:
 
     ```py
     Python 3.9.5 (default, Nov 23 2021, 15:27:38)
@@ -87,18 +87,18 @@ Prior to installing PyPatchMatch, you need to take the following steps:
     sudo pacman -S --needed base-devel
     ```
 
-2. Install `opencv` and `blas`:
+2. Install `opencv`:
 
     ```sh
-    sudo pacman -S opencv blas
+    sudo pacman -S opencv
     ```
 
     or for CUDA support
 
     ```sh
-    sudo pacman -S opencv-cuda blas
+    sudo pacman -S opencv-cuda
     ```
-    
+
 3. Fix the naming of the `opencv` package configuration file:
 
     ```sh
@@ -108,4 +108,4 @@ Prior to installing PyPatchMatch, you need to take the following steps:
 
 [**Next, Follow Steps 4-6 from the Debian Section above**](#linux)
 
-If you see no errors you're ready to go!
+If you see no errors, then you're ready to go!

docs/other/CONTRIBUTORS.md

@@ -23,14 +23,16 @@ We thank them for all of their time and hard work.
 * @damian0815 - Attention Systems and Gameplay Engineer
 * @mauwii (Matthias Wild) - Continuous integration and product maintenance engineer
 * @Netsvetaev (Artur Netsvetaev) - UI/UX Developer
-* @tildebyte - General gadfly and resident (self-appointed) know-it-all
 * @keturn - Lead for Diffusers port
 * @ebr (Eugene Brodsky) - Cloud/DevOps/Sofware engineer; your friendly neighbourhood cluster-autoscaler
 * @jpphoto (Jonathan Pollack) - Inference and rendering engine optimization
 * @genomancer (Gregg Helt) - Model training and merging
+* @gogurtenjoyer - User support and testing
+* @whosawwhatsis - User support and testing
 
 ## **Contributions by**
 
+- [tildebyte](https://github.com/tildebyte)
 - [Sean McLellan](https://github.com/Oceanswave)
 - [Kevin Gibbons](https://github.com/bakkot)
 - [Tesseract Cat](https://github.com/TesseractCat)
@@ -78,6 +80,7 @@ We thank them for all of their time and hard work.
 - [psychedelicious](https://github.com/psychedelicious)
 - [damian0815](https://github.com/damian0815)
 - [Eugene Brodsky](https://github.com/ebr)
+- [Statcomm](https://github.com/statcomm)
 
 ## **Original CompVis Authors**
 

docs/requirements-mkdocs.txt

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

installer/create_installer.sh

@@ -11,10 +11,10 @@ if [[ -v "VIRTUAL_ENV" ]]; then
     exit -1
 fi
 
-VERSION=$(cd ..; python -c "from invokeai.version import __version__ as version; print(version)")
+VERSION=$(cd ..; python -c "from ldm.invoke import __version__ as version; print(version)")
 PATCH=""
 VERSION="v${VERSION}${PATCH}"
-LATEST_TAG="v3.0-latest"
+LATEST_TAG="v2.3-latest"
 
 echo Building installer for version $VERSION
 echo "Be certain that you're in the 'installer' directory before continuing."

installer/install.bat.in

@@ -38,7 +38,6 @@ echo    https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist
 echo.
 echo See %INSTRUCTIONS% for more details.
 echo.
-echo "For the best user experience we suggest enlarging or maximizing this window now."
 pause
 
 @rem ---------------------------- check Python version ---------------

installer/install.sh.in

@@ -25,8 +25,7 @@ done
 
 if [ -z "$PYTHON" ]; then
     echo "A suitable Python interpreter could not be found"
-    echo "Please install Python $MINIMUM_PYTHON_VERSION or higher (maximum $MAXIMUM_PYTHON_VERSION) before running this script. See instructions at $INSTRUCTIONS for help."
-    echo "For the best user experience we suggest enlarging or maximizing this window now."
+    echo "Please install Python 3.9 or higher before running this script. See instructions at $INSTRUCTIONS for help."
     read -p "Press any key to exit"
     exit -1
 fi

installer/lib/installer.py

@@ -144,12 +144,12 @@ class Installer:
 
             from plumbum import FG, local
 
-            pip = local[get_pip_from_venv(venv_dir)]
-            pip[ "install", "--upgrade", "pip"] & FG
+            python = local[get_python_from_venv(venv_dir)]
+            python[ "-m", "pip", "install", "--upgrade", "pip"] & FG
 
         return venv_dir
 
-    def install(self, root: str = "~/invokeai-3", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
+    def install(self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
         """
         Install the InvokeAI application into the given runtime path
 
@@ -241,15 +241,18 @@ class InvokeAiInstance:
 
         from plumbum import FG, local
 
+        # Note that we're installing pinned versions of torch and
+        # torchvision here, which *should* correspond to what is
+        # in pyproject.toml. This is to prevent torch 2.0 from
+        # being installed and immediately uninstalled and replaced with 1.13
         pip = local[self.pip]
 
         (
             pip[
                 "install",
                 "--require-virtualenv",
-                "torch~=2.0.0",
-                "torchmetrics==0.11.4",
-                "torchvision>=0.14.1",
+                "torch~=1.13.1",
+                "torchvision~=0.14.1",
                 "--force-reinstall",
                 "--find-links" if find_links is not None else None,
                 find_links,
@@ -292,7 +295,7 @@ class InvokeAiInstance:
                     src = Path(__file__).parents[1].expanduser().resolve()
                     # if the above directory contains one of these files, we'll do a source install
                     next(src.glob("pyproject.toml"))
-                    next(src.glob("invokeai"))
+                    next(src.glob("ldm"))
                 except StopIteration:
                     print("Unable to find a wheel or perform a source install. Giving up.")
 
@@ -343,14 +346,14 @@ class InvokeAiInstance:
 
         introduction()
 
-        from invokeai.frontend.install import invokeai_configure
+        from ldm.invoke.config 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()
+            invokeai_configure.main()
             succeeded = True
         except requests.exceptions.ConnectionError as e:
             print(f'\nA network error was encountered during configuration and download: {str(e)}')
@@ -380,6 +383,9 @@ class InvokeAiInstance:
             shutil.copy(src, dest)
             os.chmod(dest, 0o0755)
 
+        if OS == "Linux":
+            shutil.copy(Path(__file__).parents[1] / "templates" / "dialogrc", self.runtime / '.dialogrc')
+
     def update(self):
         pass
 
@@ -406,6 +412,22 @@ def get_pip_from_venv(venv_path: Path) -> str:
     return str(venv_path.expanduser().resolve() / pip)
 
 
+def get_python_from_venv(venv_path: Path) -> str:
+    """
+    Given a path to a virtual environment, get the absolute path to the `python` executable
+    in a cross-platform fashion. Does not validate that the python executable
+    actually exists in the virtualenv.
+
+    :param venv_path: Path to the virtual environment
+    :type venv_path: Path
+    :return: Absolute path to the python executable
+    :rtype: str
+    """
+
+    python = "Scripts\python.exe" if OS == "Windows" else "bin/python"
+    return str(venv_path.expanduser().resolve() / python)
+
+
 def set_sys_path(venv_path: Path) -> None:
     """
     Given a path to a virtual environment, set the sys.path, in a cross-platform fashion,
@@ -457,7 +479,7 @@ def get_torch_source() -> (Union[str, None],str):
     optional_modules = None
     if OS == "Linux":
         if device == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.4.2"
+            url = "https://download.pytorch.org/whl/rocm5.2"
         elif device == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 

installer/lib/messages.py

@@ -293,8 +293,6 @@ def introduction() -> None:
                 "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",
             ),
         )
     )

installer/templates/dialogrc

@@ -0,0 +1,27 @@
+# Screen 
+use_shadow = OFF
+use_colors = ON
+screen_color = (BLACK, BLACK, ON)
+
+# Box 
+dialog_color = (YELLOW, BLACK , ON) 
+title_color = (YELLOW, BLACK, ON) 
+border_color = (YELLOW, BLACK, OFF) 
+border2_color = (YELLOW, BLACK, OFF) 
+
+# Button 
+button_active_color = (RED, BLACK, OFF) 
+button_inactive_color = (YELLOW, BLACK, OFF) 
+button_label_active_color = (YELLOW,BLACK,ON) 
+button_label_inactive_color = (YELLOW,BLACK,ON)
+ 
+# Menu box 
+menubox_color = (BLACK, BLACK, ON) 
+menubox_border_color = (YELLOW, BLACK, OFF) 
+menubox_border2_color = (YELLOW, BLACK, OFF) 
+
+# Menu window 
+item_color = (YELLOW, BLACK, OFF) 
+item_selected_color = (BLACK, YELLOW, OFF) 
+tag_key_color = (YELLOW, BLACK, OFF) 
+tag_key_selected_color = (BLACK, YELLOW, OFF)

installer/templates/invoke.bat.in

@@ -7,42 +7,42 @@ call .venv\Scripts\activate.bat
 set INVOKEAI_ROOT=.
 
 :start
-echo Desired action:
-echo 1. Generate images with the browser-based interface
-echo 2. Explore InvokeAI nodes using a command-line interface
-echo 3. Run textual inversion training
-echo 4. Merge models (diffusers type only)
-echo 5. Download and install models
-echo 6. Change InvokeAI startup options
-echo 7. Re-run the configure script to fix a broken install or to complete a major upgrade
-echo 8. Open the developer console
-echo 9. Update InvokeAI
-echo 10. Command-line help
-echo Q - Quit
-set /P choice="Please enter 1-10, Q: [2] "
-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 Do you want to generate images using the
+echo 1. command-line interface
+echo 2. browser-based UI
+echo 3. run textual inversion training
+echo 4. merge models (diffusers type only)
+echo 5. download and install models
+echo 6. change InvokeAI startup options
+echo 7. re-run the configure script to fix a broken install
+echo 8. open the developer console
+echo 9. update InvokeAI
+echo 10. command-line help
+echo Q - quit
+set /P restore="Please enter 1-10, Q: [2] "
+if not defined restore set restore=2
+IF /I "%restore%" == "1" (
     echo Starting the InvokeAI command-line..
     python .venv\Scripts\invokeai.exe %*
-) ELSE IF /I "%choice%" == "3" (
+) ELSE IF /I "%restore%" == "2" (
+    echo Starting the InvokeAI browser-based UI..
+    python .venv\Scripts\invokeai.exe --web %*
+) ELSE IF /I "%restore%" == "3" (
     echo Starting textual inversion training..
     python .venv\Scripts\invokeai-ti.exe --gui
-) ELSE IF /I "%choice%" == "4" (
+) ELSE IF /I "%restore%" == "4" (
     echo Starting model merging script..
     python .venv\Scripts\invokeai-merge.exe --gui
-) ELSE IF /I "%choice%" == "5" (
+) ELSE IF /I "%restore%" == "5" (
     echo Running invokeai-model-install...
     python .venv\Scripts\invokeai-model-install.exe
-) ELSE IF /I "%choice%" == "6" (
+) ELSE IF /I "%restore%" == "6" (
     echo Running invokeai-configure...
     python .venv\Scripts\invokeai-configure.exe --skip-sd-weight --skip-support-models
-) ELSE IF /I "%choice%" == "7" (
+) ELSE IF /I "%restore%" == "7" (
     echo Running invokeai-configure...
     python .venv\Scripts\invokeai-configure.exe --yes --default_only
-) ELSE IF /I "%choice%" == "8" (
+) ELSE IF /I "%restore%" == "8" (
     echo Developer Console
     echo Python command is:
     where python
@@ -54,15 +54,15 @@ 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%" == "9" (
+) ELSE IF /I "%restore%" == "9" (
    echo Running invokeai-update...
-   python -m invokeai.frontend.install.invokeai_update
-) ELSE IF /I "%choice%" == "10" (
+   python .venv\Scripts\invokeai-update.exe %*
+) ELSE IF /I "%restore%" == "10" (
     echo Displaying command line help...
     python .venv\Scripts\invokeai.exe --help %*
     pause
     exit /b
-) ELSE IF /I "%choice%" == "q" (
+) ELSE IF /I "%restore%" == "q" (
     echo Goodbye!
     goto ending
 ) ELSE (

installer/templates/invoke.sh.in

@@ -52,11 +52,11 @@ do_choice() {
     1)
         clear
         printf "Generate images with a browser-based interface\n"
-        invokeai-web $PARAMS
+        invokeai --web $PARAMS
         ;;
     2)
         clear
-        printf "Explore InvokeAI nodes using a command-line interface\n"
+        printf "Generate images using a command-line interface\n"
         invokeai $PARAMS
         ;;
     3)
@@ -81,7 +81,7 @@ do_choice() {
         ;;
     7)
         clear
-        printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
+        printf "Re-run the configure script to fix a broken install\n"
         invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
         ;;
     8)
@@ -93,7 +93,7 @@ do_choice() {
     9)
         clear
         printf "Update InvokeAI\n"
-        python -m invokeai.frontend.install.invokeai_update
+        invokeai-update
         ;;
     10)
         clear
@@ -118,19 +118,19 @@ do_choice() {
 do_dialog() {
     options=(
         1 "Generate images with a browser-based interface"
-        2 "Explore InvokeAI nodes using a command-line interface"
+        2 "Generate images using a command-line interface"
         3 "Textual inversion training"
         4 "Merge models (diffusers type only)"
         5 "Download and install models"
         6 "Change InvokeAI startup options"
-        7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
+        7 "Re-run the configure script to fix a broken install"
         8 "Open the developer console"
         9 "Update InvokeAI")
 
     choice=$(dialog --clear \
         --backtitle "\Zb\Zu\Z3InvokeAI" \
         --colors \
-        --title "What would you like to do?" \
+        --title "What would you like to run?" \
         --ok-label "Run" \
         --cancel-label "Exit" \
         --help-button \
@@ -147,9 +147,9 @@ do_dialog() {
 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: Explore InvokeAI nodes using the command-line interface\n"
+    printf "Do you want to generate images using the\n"
+    printf "1: Browser-based UI\n"
+    printf "2: Command-line interface\n"
     printf "3: Run textual inversion training\n"
     printf "4: Merge models (diffusers type only)\n"
     printf "5: Download and install models\n"

invokeai/README

@@ -1,11 +1,3 @@
-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
-	
+After version 2.3 is released, the ldm/invoke modules will be migrated to this location
+so that we have a proper invokeai distribution. Currently it is only being used for
+data files.

invokeai/app/api/dependencies.py

@@ -1,143 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
-from logging import Logger
-import os
-from invokeai.app.services.board_image_record_storage import (
-    SqliteBoardImageRecordStorage,
-)
-from invokeai.app.services.board_images import (
-    BoardImagesService,
-    BoardImagesServiceDependencies,
-)
-from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
-from invokeai.app.services.boards import BoardService, BoardServiceDependencies
-from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-from invokeai.app.services.images import ImageService, ImageServiceDependencies
-from invokeai.app.services.resource_name import SimpleNameService
-from invokeai.app.services.urls import LocalUrlService
-from invokeai.backend.util.logging import InvokeAILogger
-from invokeai.version.invokeai_version import __version__
-
-from ..services.default_graphs import create_system_graphs
-from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-from ..services.graph import GraphExecutionState, LibraryGraph
-from ..services.image_file_storage import DiskImageFileStorage
-from ..services.invocation_queue import MemoryInvocationQueue
-from ..services.invocation_services import InvocationServices
-from ..services.invoker import Invoker
-from ..services.processor import DefaultInvocationProcessor
-from ..services.sqlite import SqliteItemStorage
-from ..services.model_manager_service import ModelManagerService
-from .events import FastAPIEventService
-
-
-# TODO: is there a better way to achieve this?
-def check_internet() -> bool:
-    """
-    Return true if the internet is reachable.
-    It does this by pinging huggingface.co.
-    """
-    import urllib.request
-
-    host = "http://huggingface.co"
-    try:
-        urllib.request.urlopen(host, timeout=1)
-        return True
-    except:
-        return False
-
-
-logger = InvokeAILogger.getLogger()
-
-
-class ApiDependencies:
-    """Contains and initializes all dependencies for the API"""
-
-    invoker: Invoker = None
-
-    @staticmethod
-    def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger):
-        logger.debug(f"InvokeAI version {__version__}")
-        logger.debug(f"Internet connectivity is {config.internet_available}")
-
-        events = FastAPIEventService(event_handler_id)
-
-        output_folder = config.output_path
-
-        # TODO: build a file/path manager?
-        db_location = config.db_path
-        db_location.parent.mkdir(parents=True, exist_ok=True)
-
-        graph_execution_manager = SqliteItemStorage[GraphExecutionState](
-            filename=db_location, table_name="graph_executions"
-        )
-
-        urls = LocalUrlService()
-        image_record_storage = SqliteImageRecordStorage(db_location)
-        image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
-        names = SimpleNameService()
-        latents = ForwardCacheLatentsStorage(
-            DiskLatentsStorage(f"{output_folder}/latents")
-        )
-
-        board_record_storage = SqliteBoardRecordStorage(db_location)
-        board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
-
-        boards = BoardService(
-            services=BoardServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                board_record_storage=board_record_storage,
-                image_record_storage=image_record_storage,
-                url=urls,
-                logger=logger,
-            )
-        )
-
-        board_images = BoardImagesService(
-            services=BoardImagesServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                board_record_storage=board_record_storage,
-                image_record_storage=image_record_storage,
-                url=urls,
-                logger=logger,
-            )
-        )
-
-        images = ImageService(
-            services=ImageServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                image_record_storage=image_record_storage,
-                image_file_storage=image_file_storage,
-                url=urls,
-                logger=logger,
-                names=names,
-                graph_execution_manager=graph_execution_manager,
-            )
-        )
-
-        services = InvocationServices(
-            model_manager=ModelManagerService(config, logger),
-            events=events,
-            latents=latents,
-            images=images,
-            boards=boards,
-            board_images=board_images,
-            queue=MemoryInvocationQueue(),
-            graph_library=SqliteItemStorage[LibraryGraph](
-                filename=db_location, table_name="graphs"
-            ),
-            graph_execution_manager=graph_execution_manager,
-            processor=DefaultInvocationProcessor(),
-            configuration=config,
-            logger=logger,
-        )
-
-        create_system_graphs(services.graph_library)
-
-        ApiDependencies.invoker = Invoker(services)
-
-    @staticmethod
-    def shutdown():
-        if ApiDependencies.invoker:
-            ApiDependencies.invoker.stop()

invokeai/app/api/events.py

@@ -1,52 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
-import asyncio
-import threading
-from queue import Empty, Queue
-from typing import Any
-
-from fastapi_events.dispatcher import dispatch
-
-from ..services.events import EventServiceBase
-
-
-class FastAPIEventService(EventServiceBase):
-    event_handler_id: int
-    __queue: Queue
-    __stop_event: threading.Event
-
-    def __init__(self, event_handler_id: int) -> None:
-        self.event_handler_id = event_handler_id
-        self.__queue = Queue()
-        self.__stop_event = threading.Event()
-        asyncio.create_task(self.__dispatch_from_queue(stop_event=self.__stop_event))
-
-        super().__init__()
-
-    def stop(self, *args, **kwargs):
-        self.__stop_event.set()
-        self.__queue.put(None)
-
-    def dispatch(self, event_name: str, payload: Any) -> None:
-        self.__queue.put(dict(event_name=event_name, payload=payload))
-
-    async def __dispatch_from_queue(self, stop_event: threading.Event):
-        """Get events on from the queue and dispatch them, from the correct thread"""
-        while not stop_event.is_set():
-            try:
-                event = self.__queue.get(block=False)
-                if not event:  # Probably stopping
-                    continue
-
-                dispatch(
-                    event.get("event_name"),
-                    payload=event.get("payload"),
-                    middleware_id=self.event_handler_id,
-                )
-
-            except Empty:
-                await asyncio.sleep(0.1)
-                pass
-
-            except asyncio.CancelledError as e:
-                raise e  # Raise a proper error

invokeai/app/api/routers/app_info.py

@@ -1,36 +0,0 @@
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, Field
-
-from invokeai.backend.image_util.patchmatch import PatchMatch
-from invokeai.version import __version__
-
-app_router = APIRouter(prefix="/v1/app", tags=["app"])
-
-
-class AppVersion(BaseModel):
-    """App Version Response"""
-
-    version: str = Field(description="App version")
-
-
-class AppConfig(BaseModel):
-    """App Config Response"""
-
-    infill_methods: list[str] = Field(description="List of available infill methods")
-
-
-@app_router.get(
-    "/version", operation_id="app_version", status_code=200, response_model=AppVersion
-)
-async def get_version() -> AppVersion:
-    return AppVersion(version=__version__)
-
-
-@app_router.get(
-    "/config", operation_id="get_config", status_code=200, response_model=AppConfig
-)
-async def get_config() -> AppConfig:
-    infill_methods = ['tile']
-    if PatchMatch.patchmatch_available():
-        infill_methods.append('patchmatch')
-    return AppConfig(infill_methods=infill_methods)

invokeai/app/api/routers/board_images.py

@@ -1,69 +0,0 @@
-from fastapi import Body, HTTPException, Path, Query
-from fastapi.routing import APIRouter
-from invokeai.app.services.board_record_storage import BoardRecord, BoardChanges
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.board_record import BoardDTO
-from invokeai.app.services.models.image_record import ImageDTO
-
-from ..dependencies import ApiDependencies
-
-board_images_router = APIRouter(prefix="/v1/board_images", tags=["boards"])
-
-
-@board_images_router.post(
-    "/",
-    operation_id="create_board_image",
-    responses={
-        201: {"description": "The image was added to a board successfully"},
-    },
-    status_code=201,
-)
-async def create_board_image(
-    board_id: str = Body(description="The id of the board to add to"),
-    image_name: str = Body(description="The name of the image to add"),
-):
-    """Creates a board_image"""
-    try:
-        result = ApiDependencies.invoker.services.board_images.add_image_to_board(board_id=board_id, image_name=image_name)
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to add to board")
-    
-@board_images_router.delete(
-    "/",
-    operation_id="remove_board_image",
-    responses={
-        201: {"description": "The image was removed from the board successfully"},
-    },
-    status_code=201,
-)
-async def remove_board_image(
-    board_id: str = Body(description="The id of the board"),
-    image_name: str = Body(description="The name of the image to remove"),
-):
-    """Deletes a board_image"""
-    try:
-        result = ApiDependencies.invoker.services.board_images.remove_image_from_board(board_id=board_id, image_name=image_name)
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to update board")
-
-
-
-@board_images_router.get(
-    "/{board_id}",
-    operation_id="list_board_images",
-    response_model=OffsetPaginatedResults[ImageDTO],
-)
-async def list_board_images(
-    board_id: str = Path(description="The id of the board"),
-    offset: int = Query(default=0, description="The page offset"),
-    limit: int = Query(default=10, description="The number of boards per page"),
-) -> OffsetPaginatedResults[ImageDTO]:
-    """Gets a list of images for a board"""
-
-    results = ApiDependencies.invoker.services.board_images.get_images_for_board(
-        board_id,
-    )
-    return results
-

invokeai/app/api/routers/boards.py

@@ -1,117 +0,0 @@
-from typing import Optional, Union
-from fastapi import Body, HTTPException, Path, Query
-from fastapi.routing import APIRouter
-from invokeai.app.services.board_record_storage import BoardChanges
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.board_record import BoardDTO
-
-
-from ..dependencies import ApiDependencies
-
-boards_router = APIRouter(prefix="/v1/boards", tags=["boards"])
-
-
-@boards_router.post(
-    "/",
-    operation_id="create_board",
-    responses={
-        201: {"description": "The board was created successfully"},
-    },
-    status_code=201,
-    response_model=BoardDTO,
-)
-async def create_board(
-    board_name: str = Query(description="The name of the board to create"),
-) -> BoardDTO:
-    """Creates a board"""
-    try:
-        result = ApiDependencies.invoker.services.boards.create(board_name=board_name)
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to create board")
-
-
-@boards_router.get("/{board_id}", operation_id="get_board", response_model=BoardDTO)
-async def get_board(
-    board_id: str = Path(description="The id of board to get"),
-) -> BoardDTO:
-    """Gets a board"""
-
-    try:
-        result = ApiDependencies.invoker.services.boards.get_dto(board_id=board_id)
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=404, detail="Board not found")
-
-
-@boards_router.patch(
-    "/{board_id}",
-    operation_id="update_board",
-    responses={
-        201: {
-            "description": "The board was updated successfully",
-        },
-    },
-    status_code=201,
-    response_model=BoardDTO,
-)
-async def update_board(
-    board_id: str = Path(description="The id of board to update"),
-    changes: BoardChanges = Body(description="The changes to apply to the board"),
-) -> BoardDTO:
-    """Updates a board"""
-    try:
-        result = ApiDependencies.invoker.services.boards.update(
-            board_id=board_id, changes=changes
-        )
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to update board")
-
-
-@boards_router.delete("/{board_id}", operation_id="delete_board")
-async def delete_board(
-    board_id: str = Path(description="The id of board to delete"),
-    include_images: Optional[bool] = Query(
-        description="Permanently delete all images on the board", default=False
-    ),
-) -> None:
-    """Deletes a board"""
-    try:
-        if include_images is True:
-            ApiDependencies.invoker.services.images.delete_images_on_board(
-                board_id=board_id
-            )
-            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
-        else:
-            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
-    except Exception as e:
-        # TODO: Does this need any exception handling at all?
-        pass
-
-
-@boards_router.get(
-    "/",
-    operation_id="list_boards",
-    response_model=Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]],
-)
-async def list_boards(
-    all: Optional[bool] = Query(default=None, description="Whether to list all boards"),
-    offset: Optional[int] = Query(default=None, description="The page offset"),
-    limit: Optional[int] = Query(
-        default=None, description="The number of boards per page"
-    ),
-) -> Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]]:
-    """Gets a list of boards"""
-    if all:
-        return ApiDependencies.invoker.services.boards.get_all()
-    elif offset is not None and limit is not None:
-        return ApiDependencies.invoker.services.boards.get_many(
-            offset,
-            limit,
-        )
-    else:
-        raise HTTPException(
-            status_code=400,
-            detail="Invalid request: Must provide either 'all' or both 'offset' and 'limit'",
-        )

invokeai/app/api/routers/images.py

@@ -1,262 +0,0 @@
-import io
-from typing import Optional
-
-from fastapi import (Body, HTTPException, Path, Query, Request, Response,
-                     UploadFile)
-from fastapi.responses import FileResponse
-from fastapi.routing import APIRouter
-from PIL import Image
-
-from invokeai.app.invocations.metadata import ImageMetadata
-from invokeai.app.models.image import ImageCategory, ResourceOrigin
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.item_storage import PaginatedResults
-from invokeai.app.services.models.image_record import (ImageDTO,
-                                                       ImageRecordChanges,
-                                                       ImageUrlsDTO)
-
-from ..dependencies import ApiDependencies
-
-images_router = APIRouter(prefix="/v1/images", tags=["images"])
-
-# images are immutable; set a high max-age
-IMAGE_MAX_AGE = 31536000
-
-
-@images_router.post(
-    "/",
-    operation_id="upload_image",
-    responses={
-        201: {"description": "The image was uploaded successfully"},
-        415: {"description": "Image upload failed"},
-    },
-    status_code=201,
-    response_model=ImageDTO,
-)
-async def upload_image(
-    file: UploadFile,
-    request: Request,
-    response: Response,
-    image_category: ImageCategory = Query(description="The category of the image"),
-    is_intermediate: bool = Query(description="Whether this is an intermediate image"),
-    session_id: Optional[str] = Query(
-        default=None, description="The session ID associated with this upload, if any"
-    ),
-) -> ImageDTO:
-    """Uploads an image"""
-    if not file.content_type.startswith("image"):
-        raise HTTPException(status_code=415, detail="Not an image")
-
-    contents = await file.read()
-
-    try:
-        pil_image = Image.open(io.BytesIO(contents))
-    except:
-        # Error opening the image
-        raise HTTPException(status_code=415, detail="Failed to read image")
-
-    try:
-        image_dto = ApiDependencies.invoker.services.images.create(
-            image=pil_image,
-            image_origin=ResourceOrigin.EXTERNAL,
-            image_category=image_category,
-            session_id=session_id,
-            is_intermediate=is_intermediate,
-        )
-
-        response.status_code = 201
-        response.headers["Location"] = image_dto.image_url
-
-        return image_dto
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to create image")
-
-
-@images_router.delete("/{image_name}", operation_id="delete_image")
-async def delete_image(
-    image_name: str = Path(description="The name of the image to delete"),
-) -> None:
-    """Deletes an image"""
-
-    try:
-        ApiDependencies.invoker.services.images.delete(image_name)
-    except Exception as e:
-        # TODO: Does this need any exception handling at all?
-        pass
-
-
-@images_router.patch(
-    "/{image_name}",
-    operation_id="update_image",
-    response_model=ImageDTO,
-)
-async def update_image(
-    image_name: str = Path(description="The name of the image to update"),
-    image_changes: ImageRecordChanges = Body(
-        description="The changes to apply to the image"
-    ),
-) -> ImageDTO:
-    """Updates an image"""
-
-    try:
-        return ApiDependencies.invoker.services.images.update(image_name, image_changes)
-    except Exception as e:
-        raise HTTPException(status_code=400, detail="Failed to update image")
-
-
-@images_router.get(
-    "/{image_name}",
-    operation_id="get_image_dto",
-    response_model=ImageDTO,
-)
-async def get_image_dto(
-    image_name: str = Path(description="The name of image to get"),
-) -> ImageDTO:
-    """Gets an image's DTO"""
-
-    try:
-        return ApiDependencies.invoker.services.images.get_dto(image_name)
-    except Exception as e:
-        raise HTTPException(status_code=404)
-
-@images_router.get(
-    "/{image_name}/metadata",
-    operation_id="get_image_metadata",
-    response_model=ImageMetadata,
-)
-async def get_image_metadata(
-    image_name: str = Path(description="The name of image to get"),
-) -> ImageMetadata:
-    """Gets an image's metadata"""
-
-    try:
-        return ApiDependencies.invoker.services.images.get_metadata(image_name)
-    except Exception as e:
-        raise HTTPException(status_code=404)
-
-
-@images_router.get(
-    "/{image_name}/full",
-    operation_id="get_image_full",
-    response_class=Response,
-    responses={
-        200: {
-            "description": "Return the full-resolution image",
-            "content": {"image/png": {}},
-        },
-        404: {"description": "Image not found"},
-    },
-)
-async def get_image_full(
-    image_name: str = Path(description="The name of full-resolution image file to get"),
-) -> FileResponse:
-    """Gets a full-resolution image file"""
-
-    try:
-        path = ApiDependencies.invoker.services.images.get_path(image_name)
-
-        if not ApiDependencies.invoker.services.images.validate_path(path):
-            raise HTTPException(status_code=404)
-
-        response = FileResponse(
-            path,
-            media_type="image/png",
-            filename=image_name,
-            content_disposition_type="inline",
-        )
-        response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
-        return response
-    except Exception as e:
-        raise HTTPException(status_code=404)
-
-
-@images_router.get(
-    "/{image_name}/thumbnail",
-    operation_id="get_image_thumbnail",
-    response_class=Response,
-    responses={
-        200: {
-            "description": "Return the image thumbnail",
-            "content": {"image/webp": {}},
-        },
-        404: {"description": "Image not found"},
-    },
-)
-async def get_image_thumbnail(
-    image_name: str = Path(description="The name of thumbnail image file to get"),
-) -> FileResponse:
-    """Gets a thumbnail image file"""
-
-    try:
-        path = ApiDependencies.invoker.services.images.get_path(
-            image_name, thumbnail=True
-        )
-        if not ApiDependencies.invoker.services.images.validate_path(path):
-            raise HTTPException(status_code=404)
-
-        response = FileResponse(
-            path, media_type="image/webp", content_disposition_type="inline"
-        )
-        response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
-        return response
-    except Exception as e:
-        raise HTTPException(status_code=404)
-
-
-@images_router.get(
-    "/{image_name}/urls",
-    operation_id="get_image_urls",
-    response_model=ImageUrlsDTO,
-)
-async def get_image_urls(
-    image_name: str = Path(description="The name of the image whose URL to get"),
-) -> ImageUrlsDTO:
-    """Gets an image and thumbnail URL"""
-
-    try:
-        image_url = ApiDependencies.invoker.services.images.get_url(image_name)
-        thumbnail_url = ApiDependencies.invoker.services.images.get_url(
-            image_name, thumbnail=True
-        )
-        return ImageUrlsDTO(
-            image_name=image_name,
-            image_url=image_url,
-            thumbnail_url=thumbnail_url,
-        )
-    except Exception as e:
-        raise HTTPException(status_code=404)
-
-
-@images_router.get(
-    "/",
-    operation_id="list_image_dtos",
-    response_model=OffsetPaginatedResults[ImageDTO],
-)
-async def list_image_dtos(
-    image_origin: Optional[ResourceOrigin] = Query(
-        default=None, description="The origin of images to list"
-    ),
-    categories: Optional[list[ImageCategory]] = Query(
-        default=None, description="The categories of image to include"
-    ),
-    is_intermediate: Optional[bool] = Query(
-        default=None, description="Whether to list intermediate images"
-    ),
-    board_id: Optional[str] = Query(
-        default=None, description="The board id to filter by"
-    ),
-    offset: int = Query(default=0, description="The page offset"),
-    limit: int = Query(default=10, description="The number of images per page"),
-) -> OffsetPaginatedResults[ImageDTO]:
-    """Gets a list of image DTOs"""
-
-    image_dtos = ApiDependencies.invoker.services.images.get_many(
-        offset,
-        limit,
-        image_origin,
-        categories,
-        is_intermediate,
-        board_id,
-    )
-
-    return image_dtos

invokeai/app/api/routers/models.py

@@ -1,397 +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 Literal, List, Optional, Union
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, parse_obj_as
-from starlette.exceptions import HTTPException
-
-from invokeai.backend import BaseModelType, ModelType
-from invokeai.backend.model_management.models import (
-    OPENAPI_MODEL_CONFIGS,
-    SchedulerPredictionType,
-    ModelNotFoundException,
-)
-from invokeai.backend.model_management import MergeInterpolationMethod
-
-from ..dependencies import ApiDependencies
-
-models_router = APIRouter(prefix="/v1/models", tags=["models"])
-
-UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-
-class ModelsList(BaseModel):
-    models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
-
-@models_router.get(
-    "/",
-    operation_id="list_models",
-    responses={200: {"model": ModelsList }},
-)
-async def list_models(
-    base_model: Optional[BaseModelType] = Query(default=None, description="Base model"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-) -> ModelsList:
-    """Gets a list of models"""
-    models_raw = ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type)
-    models = parse_obj_as(ModelsList, { "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:
-        # rename operation requested
-        if info.model_name != model_name or info.base_model != base_model:
-            result = 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.debug(f'renaming result = {result}')
-            logger.info(f'Successfully renamed {base_model}/{model_name}=>{info.base_model}/{info.model_name}')
-            model_name = info.model_name
-            base_model = info.base_model
-            
-        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 = parse_obj_as(UpdateModelResponse, 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"},
-        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 checkpoint files', default="v_prediction"),
-) -> ImportModelResponse:
-    """ Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically """
-    
-    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=424)
-        
-        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 parse_obj_as(ImportModelResponse, 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.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.dict()
-        )
-        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 parse_obj_as(ImportModelResponse, 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 = parse_obj_as(ConvertModelResponse, 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.get(
-    "/sync",
-    operation_id="sync_to_config",
-    responses={
-        201: { "description": "synchronization successful" },
-    },
-    status_code = 201,
-    response_model = None
-)
-async def sync_to_config(
-)->None:
-    """Call after making changes to models.yaml, autoimport directories or models directory to synchronize
-    in-memory data structures with disk data structures."""
-    return ApiDependencies.invoker.services.model_manager.sync_to_config()
-        
-@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(
-        base_model: BaseModelType                  = Path(description="Base model"),
-        model_names: List[str]                     = Body(description="model name", min_items=2, max_items=3),
-        merged_model_name: Optional[str]           = Body(description="Name of destination model"),
-        alpha: Optional[float]                     = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
-        interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method"),
-        force: Optional[bool]                      = Body(description="Force merging of models created with different versions of diffusers", default=False),
-        merge_dest_directory: Optional[str]       = Body(description="Save the merged model to the designated directory (with 'merged_model_name' appended)", default=None)
-) -> MergeModelResponse:
-    """Convert a checkpoint model into a diffusers model"""
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(f"Merging models: {model_names} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
-        dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
-        result = ApiDependencies.invoker.services.model_manager.merge_models(model_names,
-                                                                             base_model,
-                                                                             merged_model_name=merged_model_name or "+".join(model_names),
-                                                                             alpha=alpha,
-                                                                             interp=interp,
-                                                                             force=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 = parse_obj_as(ConvertModelResponse, model_raw)
-    except ModelNotFoundException:
-        raise HTTPException(status_code=404, detail=f"One or more of the models '{model_names}' not found")
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response
-
-# The rename operation is now supported by update_model and no longer needs to be
-# a standalone route.
-# @models_router.post(
-#     "/rename/{base_model}/{model_type}/{model_name}",
-#     operation_id="rename_model",
-#     responses= {
-#         201: {"description" : "The model was renamed successfully"},
-#         404: {"description" : "The model could not be found"},
-#         409: {"description" : "There is already a model corresponding to the new name"},
-#     },
-#     status_code=201,
-#     response_model=ImportModelResponse
-# )
-# async def rename_model(
-#         base_model: BaseModelType = Path(description="Base model"),
-#         model_type: ModelType = Path(description="The type of model"),
-#         model_name: str = Path(description="current model name"),
-#         new_name: Optional[str] = Query(description="new model name", default=None),
-#         new_base: Optional[BaseModelType] = Query(description="new model base", default=None),
-# ) -> ImportModelResponse:
-#     """ Rename a model"""
-    
-#     logger = ApiDependencies.invoker.services.logger
-
-#     try:
-#         result = ApiDependencies.invoker.services.model_manager.rename_model(
-#             base_model = base_model,
-#             model_type = model_type,
-#             model_name = model_name,
-#             new_name = new_name,
-#             new_base = new_base,
-#         )
-#         logger.debug(result)
-#         logger.info(f'Successfully renamed {model_name}=>{new_name}')
-#         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-#             model_name=new_name or model_name,
-#             base_model=new_base or base_model,
-#             model_type=model_type
-#         )
-#         return parse_obj_as(ImportModelResponse, 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))

invokeai/app/api/routers/sessions.py

@@ -1,286 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
-from typing import Annotated, List, Optional, Union
-
-from fastapi import Body, HTTPException, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic.fields import Field
-
-from ...invocations import *
-from ...invocations.baseinvocation import BaseInvocation
-from ...services.graph import (
-    Edge,
-    EdgeConnection,
-    Graph,
-    GraphExecutionState,
-    NodeAlreadyExecutedError,
-)
-from ...services.item_storage import PaginatedResults
-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"},
-    },
-)
-async def create_session(
-    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(graph)
-    return session
-
-
-@session_router.get(
-    "/",
-    operation_id="list_sessions",
-    responses={200: {"model": PaginatedResults[GraphExecutionState]}},
-)
-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"},
-    },
-)
-async def add_node(
-    session_id: str = Path(description="The id of the session"),
-    node: Annotated[
-        Union[BaseInvocation.get_invocations()], Field(discriminator="type") # type: ignore
-    ] = Body(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"},
-    },
-)
-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") # type: ignore
-    ] = Body(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"},
-    },
-)
-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"},
-    },
-)
-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"},
-    },
-)
-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"},
-    },
-)
-async def invoke_session(
-    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(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"}
-    },
-)
-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)