Configure the NSFW checker at install time with default on (#1624)

* configure the NSFW checker at install time with default on

1. Changes the --safety_checker argument to --nsfw_checker and
--no-nsfw_checker. The original argument is recognized for backward
compatibility.

2. The configure script asks users whether to enable the checker
(default yes). Also offers users ability to select default sampler and
number of generation steps.

3.Enables the pasting of the caution icon on blurred images when
InvokeAI is installed into the package directory.

4. Adds documentation for the NSFW checker, including caveats about
accuracy, memory requirements, and intermediate image dispaly.

* use better fitting icon

* NSFW defaults false for testing

* set default back to nsfw active

Co-authored-by: Matthias Wild <40327258+mauwii@users.noreply.github.com>
Co-authored-by: mauwii <Mauwii@outlook.de>

.dev_scripts/diff_images.py

@@ -20,13 +20,13 @@ def calc_images_mean_L1(image1_path, image2_path):
 
 def parse_args():
     parser = argparse.ArgumentParser()
-    parser.add_argument("image1_path")
-    parser.add_argument("image2_path")
+    parser.add_argument('image1_path')
+    parser.add_argument('image2_path')
     args = parser.parse_args()
     return args
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     args = parse_args()
     mean_L1 = calc_images_mean_L1(args.image1_path, args.image2_path)
     print(mean_L1)

.dockerignore

@@ -1,9 +1,12 @@
 *
-!invokeai
-!pyproject.toml
-!docker/docker-entrypoint.sh
-!LICENSE
-
-**/node_modules
-**/__pycache__
-**/*.egg-info
+!backend
+!configs
+!environments-and-requirements
+!frontend
+!installer
+!ldm
+!main.py
+!scripts
+!server
+!static
+!setup.py

.git-blame-ignore-revs

@@ -1,2 +0,0 @@
-b3dccfaeb636599c02effc377cdd8a87d658256c
-218b6d0546b990fc449c876fb99f44b50c4daa35

.gitattributes

@@ -1,5 +1,4 @@
 # Auto normalizes line endings on commit so devs don't need to change local settings.
-# Only affects text files and ignores other file types.
+# Only affects text files and ignores other file types. 
 # For more info see: https://www.aleksandrhovhannisyan.com/blog/crlf-vs-lf-normalizing-line-endings-in-git/
 * text=auto
-docker/** text eol=lf

.github/CODEOWNERS

@@ -1,34 +1,7 @@
-# continuous integration
-/.github/workflows/  @lstein @blessedcoolant @hipsterusername
-
-# documentation
-/docs/ @lstein @blessedcoolant @hipsterusername @Millu
-/mkdocs.yml @lstein  @blessedcoolant @hipsterusername @Millu
-
-# nodes
-/invokeai/app/ @Kyle0654 @blessedcoolant @psychedelicious @brandonrising @hipsterusername
-
-# installation and configuration
-/pyproject.toml  @lstein @blessedcoolant @hipsterusername
-/docker/  @lstein @blessedcoolant @hipsterusername
-/scripts/ @ebr @lstein @hipsterusername
-/installer/ @lstein @ebr @hipsterusername
-/invokeai/assets @lstein @ebr @hipsterusername
-/invokeai/configs @lstein @hipsterusername
-/invokeai/version @lstein @blessedcoolant @hipsterusername
-
-# web ui
-/invokeai/frontend @blessedcoolant @psychedelicious @lstein @maryhipp @hipsterusername
-/invokeai/backend @blessedcoolant @psychedelicious @lstein @maryhipp @hipsterusername
-
-# generation, model management, postprocessing
-/invokeai/backend  @damian0815 @lstein @blessedcoolant @gregghelt2 @StAlKeR7779 @brandonrising @ryanjdick @hipsterusername
-
-# front ends
-/invokeai/frontend/CLI @lstein @hipsterusername
-/invokeai/frontend/install @lstein @ebr @hipsterusername 
-/invokeai/frontend/merge @lstein @blessedcoolant @hipsterusername
-/invokeai/frontend/training @lstein @blessedcoolant @hipsterusername
-/invokeai/frontend/web @psychedelicious @blessedcoolant @maryhipp @hipsterusername
-
-
+ldm/invoke/pngwriter.py @CapableWeb
+ldm/invoke/server_legacy.py @CapableWeb
+scripts/legacy_api.py @CapableWeb
+tests/legacy_tests.sh @CapableWeb
+installer/ @tildebyte
+.github/workflows/ @mauwii
+docker_build/ @mauwii

.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/ISSUE_TEMPLATE/FEATURE_REQUEST.yml

@@ -1,5 +1,5 @@
 name: Feature Request
-description: Contribute a idea or request a new feature
+description: Commit a idea or Request a new feature
 title: '[enhancement]: '
 labels: ['enhancement']
 # assignees:
@@ -9,14 +9,14 @@ body:
   - type: markdown
     attributes:
       value: |
-        Thanks for taking the time to fill out this feature request!
+        Thanks for taking the time to fill out this Feature request!
 
   - type: checkboxes
     attributes:
       label: Is there an existing issue for this?
       description: |
         Please make use of the [search function](https://github.com/invoke-ai/InvokeAI/labels/enhancement)
-        to see if a similar issue already exists for the feature you want to request
+        to see if a simmilar issue already exists for the feature you want to request
       options:
         - label: I have searched the existing issues
           required: true
@@ -34,9 +34,12 @@ body:
     id: whatisexpected
     attributes:
       label: What should this feature add?
-      description: Explain the functionality this feature should add. Feature requests should be for single features. Please create multiple requests if you want to request multiple features.
+      description: Please try to explain the functionality this feature should add
       placeholder: |
-        I'd like a button that creates an image of banana sushi every time I press it. Each image should be different. There should be a toggle next to the button that enables strawberry mode, in which the images are of strawberry sushi instead.
+        Instead of one huge textfield, it would be nice to have forms for bug-reports, feature-requests, ...
+        Great benefits with automatic labeling, assigning and other functionalitys not available in that form
+        via old-fashioned markdown-templates. I would also love to see the use of a moderator bot 🤖 like
+        https://github.com/marketplace/actions/issue-moderator-with-commands to auto close old issues and other things
     validations:
       required: true
 
@@ -48,6 +51,6 @@ body:
 
   - type: textarea
     attributes:
-      label: Additional Content
+      label: Aditional Content
       description: Add any other context or screenshots about the feature request here.
-      placeholder: This is a mockup of the design how I imagine it <screenshot>
+      placeholder: This is a Mockup of the design how I imagine it <screenshot>

.github/pull_request_template.md

@@ -1,51 +0,0 @@
-## What type of PR is this? (check all applicable)
-
-- [ ] Refactor
-- [ ] Feature
-- [ ] Bug Fix
-- [ ] Optimization
-- [ ] Documentation Update
-- [ ] Community Node Submission
-
-
-## Have you discussed this change with the InvokeAI team?
-- [ ] Yes
-- [ ] No, because:
-
-      
-## Have you updated all relevant documentation?
-- [ ] Yes
-- [ ] No
-
-
-## Description
-
-
-## Related Tickets & Documents
-
-<!--
-For pull requests that relate or close an issue, please include them
-below. 
-
-For example having the text: "closes #1234" would connect the current pull
-request to issue 1234.  And when we merge the pull request, Github will
-automatically close the issue.
--->
-
-- Related Issue #
-- Closes #
-
-## QA Instructions, Screenshots, Recordings
-
-<!-- 
-Please provide steps on how to test changes, any hardware or 
-software specifications as well as any other pertinent information. 
--->
-
-## Added/updated tests?
-
-- [ ] Yes
-- [ ] No : _please replace this line with details on why tests
-      have not been included_
-
-## [optional] Are there any post deployment tasks we need to perform?

.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

@@ -1,115 +1,43 @@
+# Building the Image without pushing to confirm it is still buildable
+# confirum functionality would unfortunately need way more resources
 name: build container image
 on:
   push:
     branches:
       - 'main'
-    paths:
-      - 'pyproject.toml'
-      - '.dockerignore'
-      - 'invokeai/**'
-      - 'docker/Dockerfile'
-      - 'docker/docker-entrypoint.sh'
-      - 'workflows/build-container.yml'
-    tags:
-      - 'v*'
-  workflow_dispatch:
-
-permissions:
-  contents: write
-  packages: write
+      - 'development'
+      - 'update-dockerfile'
 
 jobs:
   docker:
-    if: github.event.pull_request.draft == false
     strategy:
       fail-fast: false
       matrix:
-        gpu-driver:
-        - cuda
-        - cpu
-        - rocm
+        arch:
+          - x86_64
+          - aarch64
+        pip-requirements:
+          - requirements-lin-amd.txt
+          - requirements-lin-cuda.txt
     runs-on: ubuntu-latest
-    name: ${{ matrix.gpu-driver }}
-    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'
+    name: ${{ matrix.pip-requirements }} ${{ matrix.arch }}
     steps:
-      - name: Free up more disk space on the runner
-        # https://github.com/actions/runner-images/issues/2840#issuecomment-1284059930
-        run: |
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
-          sudo swapoff /mnt/swapfile
-          sudo rm -rf /mnt/swapfile
-
+      - name: prepare docker-tag
+        env:
+          repository: ${{ github.repository }}
+        run: echo "dockertag=${repository,,}" >> $GITHUB_ENV
       - name: Checkout
         uses: actions/checkout@v3
-
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v4
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          images: |
-            ghcr.io/${{ github.repository }}
-            ${{ env.DOCKERHUB_REPOSITORY }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=tag
-            type=pep440,pattern={{version}}
-            type=pep440,pattern={{major}}.{{minor}}
-            type=pep440,pattern={{major}}
-            type=sha,enable=true,prefix=sha-,format=short
-          flavor: |
-            latest=${{ matrix.gpu-driver == 'cuda' && github.ref == 'refs/heads/main' }}
-            suffix=-${{ matrix.gpu-driver }},onlatest=false
-
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v2
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v2
-        with:
-          platforms: ${{ env.PLATFORMS }}
-
-      - name: Login to GitHub Container Registry
-        if: github.event_name != 'pull_request'
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          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: Build container
-        id: docker_build
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v3
         with:
           context: .
-          file: docker/Dockerfile
-          platforms: ${{ env.PLATFORMS }}
-          push: ${{ github.ref == 'refs/heads/main' || github.ref_type == 'tag' }}
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
-          cache-from: |
-            type=gha,scope=${{ 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 }}
-
-      # - 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: ${{ github.event.repository.description }}
+          file: docker-build/Dockerfile
+          platforms: Linux/${{ matrix.arch }}
+          push: false
+          tags: ${{ env.dockertag }}:${{ matrix.pip-requirements }}-${{ matrix.arch }}
+          build-args: pip_requirements=${{ matrix.pip-requirements }}

.github/workflows/clean-caches.yml

@@ -1,34 +0,0 @@
-name: cleanup caches by a branch
-on:
-  pull_request:
-    types:
-      - closed
-  workflow_dispatch:
-
-jobs:
-  cleanup:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v3
-
-      - name: Cleanup
-        run: |
-          gh extension install actions/gh-actions-cache
-
-          REPO=${{ github.repository }}
-          BRANCH=${{ github.ref }}
-
-          echo "Fetching list of cache key"
-          cacheKeysForPR=$(gh actions-cache list -R $REPO -B $BRANCH | cut -f 1 )
-
-          ## Setting this to not fail the workflow while deleting cache keys.
-          set +e
-          echo "Deleting caches..."
-          for cacheKey in $cacheKeysForPR
-          do
-              gh actions-cache delete $cacheKey -R $REPO -B $BRANCH --confirm
-          done
-          echo "Done"
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

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

@@ -1,28 +0,0 @@
-name: Close inactive issues
-on:
-  schedule:
-    - cron: "00 4 * * *"
-
-env:
-  DAYS_BEFORE_ISSUE_STALE: 30
-  DAYS_BEFORE_ISSUE_CLOSE: 14
-
-jobs:
-  close-issues:
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-      pull-requests: write
-    steps:
-      - uses: actions/stale@v8
-        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
-          exempt-issue-labels: "Active Issue"
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-          operations-per-run: 500

.github/workflows/lint-frontend.yml

@@ -1,33 +0,0 @@
-name: Lint frontend
-
-on:
-  pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  push:
-    branches:
-      - 'main'
-  merge_group:
-  workflow_dispatch:
-
-defaults:
-  run:
-    working-directory: invokeai/frontend/web
-
-jobs:
-  lint-frontend:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-22.04
-    steps:
-      - name: Setup Node 18
-        uses: actions/setup-node@v3
-        with:
-          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'

.github/workflows/mkdocs-material.yml

@@ -2,19 +2,12 @@ name: mkdocs-material
 on:
   push:
     branches:
-      - 'refs/heads/main'
-
-permissions:
-    contents: write
+      - 'main'
+      - 'development'
 
 jobs:
   mkdocs-material:
-    if: github.event.pull_request.draft == false
     runs-on: ubuntu-latest
-    env:
-      REPO_URL: '${{ github.server_url }}/${{ github.repository }}'
-      REPO_NAME: '${{ github.repository }}'
-      SITE_URL: 'https://${{ github.repository_owner }}.github.io/InvokeAI'
     steps:
       - name: checkout sources
         uses: actions/checkout@v3
@@ -25,15 +18,11 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: '3.10'
-          cache: pip
-          cache-dependency-path: pyproject.toml
 
       - name: install requirements
-        env:
-          PIP_USE_PEP517: 1
         run: |
           python -m \
-            pip install ".[docs]"
+            pip install -r docs/requirements-mkdocs.txt
 
       - name: confirm buildability
         run: |

.github/workflows/pypi-release.yml

@@ -1,41 +0,0 @@
-name: PyPI Release
-
-on:
-  push:
-    paths:
-      - 'invokeai/version/invokeai_version.py'
-  workflow_dispatch:
-
-jobs:
-  release:
-    if: github.repository == 'invoke-ai/InvokeAI'
-    runs-on: ubuntu-22.04
-    env:
-      TWINE_USERNAME: __token__
-      TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
-      TWINE_NON_INTERACTIVE: 1
-    steps:
-      - name: checkout sources
-        uses: actions/checkout@v3
-
-      - name: install deps
-        run: pip install --upgrade build twine
-
-      - name: build package
-        run: python3 -m build
-
-      - name: check distribution
-        run: twine check dist/*
-
-      - name: check PyPI versions
-        if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
-        run: |
-          pip install --upgrade requests
-          python -c "\
-          import scripts.pypi_helper; \
-          EXISTS=scripts.pypi_helper.local_on_pypi(); \
-          print(f'PACKAGE_EXISTS={EXISTS}')" >> $GITHUB_ENV
-
-      - name: upload package
-        if: env.PACKAGE_EXISTS == 'False' && env.TWINE_PASSWORD != ''
-        run: twine upload dist/*

.github/workflows/style-checks.yml

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

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

@@ -0,0 +1,135 @@
+name: Test invoke.py
+on:
+  push:
+    branches:
+      - 'main'
+      - 'development'
+      - 'fix-gh-actions-fork'
+  pull_request:
+    branches:
+      - 'main'
+      - 'development'
+
+jobs:
+  matrix:
+    strategy:
+      matrix:
+        stable-diffusion-model:
+          - 'stable-diffusion-1.5'
+        environment-yaml:
+          - environment-lin-amd.yml
+          - environment-lin-cuda.yml
+          - environment-mac.yml
+        include:
+          - environment-yaml: environment-lin-amd.yml
+            os: ubuntu-latest
+            default-shell: bash -l {0}
+          - environment-yaml: environment-lin-cuda.yml
+            os: ubuntu-latest
+            default-shell: bash -l {0}
+          - environment-yaml: environment-mac.yml
+            os: macos-12
+            default-shell: bash -l {0}
+          - stable-diffusion-model: stable-diffusion-1.5
+            stable-diffusion-model-url: https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
+            stable-diffusion-model-dl-path: models/ldm/stable-diffusion-v1
+            stable-diffusion-model-dl-name: v1-5-pruned-emaonly.ckpt
+    name: ${{ matrix.environment-yaml }} on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    env:
+      CONDA_ENV_NAME: invokeai
+      INVOKEAI_ROOT: '${{ github.workspace }}/invokeai'
+    defaults:
+      run:
+        shell: ${{ matrix.default-shell }}
+    steps:
+      - name: Checkout sources
+        id: checkout-sources
+        uses: actions/checkout@v3
+
+      - name: create models.yaml from example
+        run: |
+          mkdir -p ${{ env.INVOKEAI_ROOT }}/configs
+          cp configs/models.yaml.example ${{ env.INVOKEAI_ROOT }}/configs/models.yaml
+
+      - name: create environment.yml
+        run: cp "environments-and-requirements/${{ matrix.environment-yaml }}" environment.yml
+
+      - name: Use cached conda packages
+        id: use-cached-conda-packages
+        uses: actions/cache@v3
+        with:
+          path: ~/conda_pkgs_dir
+          key: conda-pkgs-${{ runner.os }}-${{ runner.arch }}-${{ hashFiles(matrix.environment-yaml) }}
+
+      - name: Activate Conda Env
+        id: activate-conda-env
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          activate-environment: ${{ env.CONDA_ENV_NAME }}
+          environment-file: environment.yml
+          miniconda-version: latest
+
+      - name: set test prompt to main branch validation
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> $GITHUB_ENV
+
+      - name: set test prompt to development branch validation
+        if: ${{ github.ref == 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/dev_prompts.txt" >> $GITHUB_ENV
+
+      - name: set test prompt to Pull Request validation
+        if: ${{ github.ref != 'refs/heads/main' && github.ref != 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> $GITHUB_ENV
+
+      - name: Use Cached Stable Diffusion Model
+        id: cache-sd-model
+        uses: actions/cache@v3
+        env:
+          cache-name: cache-${{ matrix.stable-diffusion-model }}
+        with:
+          path: ${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}
+          key: ${{ env.cache-name }}
+
+      - name: Download ${{ matrix.stable-diffusion-model }}
+        id: download-stable-diffusion-model
+        if: ${{ steps.cache-sd-model.outputs.cache-hit != 'true' }}
+        run: |
+          mkdir -p "${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}"
+          curl \
+            -H "Authorization: Bearer ${{ secrets.HUGGINGFACE_TOKEN }}" \
+            -o "${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}/${{ matrix.stable-diffusion-model-dl-name }}" \
+            -L ${{ matrix.stable-diffusion-model-url }}
+
+      - name: run configure_invokeai.py
+        id: run-preload-models
+        run: |
+          python scripts/configure_invokeai.py --no-interactive --yes
+
+      - name: cat ~/.invokeai
+        id: cat-invokeai
+        run: cat ~/.invokeai
+
+      - name: Run the tests
+        id: run-tests
+        run: |
+          time python scripts/invoke.py \
+            --no-patchmatch \
+            --no-nsfw_checker \
+            --model ${{ matrix.stable-diffusion-model }} \
+            --from_file ${{ env.TEST_PROMPTS }} \
+            --root="${{ env.INVOKEAI_ROOT }}" \
+            --outdir="${{ env.INVOKEAI_ROOT }}/outputs"
+
+      - name: export conda env
+        id: export-conda-env
+        run: |
+          mkdir -p outputs/img-samples
+          conda env export --name ${{ env.CONDA_ENV_NAME }} > outputs/img-samples/environment-${{ runner.os }}-${{ runner.arch }}.yml
+
+      - name: Archive results
+        id: archive-results
+        uses: actions/upload-artifact@v3
+        with:
+          name: results_${{ matrix.requirements-file }}_${{ matrix.python-version }}
+          path: ${{ env.INVOKEAI_ROOT }}/outputs

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

@@ -3,127 +3,126 @@ on:
   push:
     branches:
       - 'main'
+      - 'development'
   pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  merge_group:
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
+    branches:
+      - 'main'
+      - 'development'
 
 jobs:
   matrix:
-    if: github.event.pull_request.draft == false
     strategy:
       matrix:
+        stable-diffusion-model:
+          - stable-diffusion-1.5
+        requirements-file:
+          - requirements-lin-cuda.txt
+          - requirements-lin-amd.txt
+          - requirements-mac-mps-cpu.txt
         python-version:
           # - '3.9'
           - '3.10'
-        pytorch:
-          - linux-cuda-11_7
-          - linux-rocm-5_2
-          - linux-cpu
-          - macos-default
-          - windows-cpu
         include:
-          - pytorch: linux-cuda-11_7
-            os: ubuntu-22.04
-            github-env: $GITHUB_ENV
-          - pytorch: linux-rocm-5_2
-            os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
-            github-env: $GITHUB_ENV
-          - pytorch: linux-cpu
-            os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/cpu'
-            github-env: $GITHUB_ENV
-          - pytorch: macos-default
+          - requirements-file: requirements-lin-cuda.txt
+            os: ubuntu-latest
+            default-shell: bash -l {0}
+          - requirements-file: requirements-lin-amd.txt
+            os: ubuntu-latest
+            default-shell: bash -l {0}
+          - requirements-file: requirements-mac-mps-cpu.txt
             os: macOS-12
-            github-env: $GITHUB_ENV
-          - pytorch: windows-cpu
-            os: windows-2022
-            github-env: $env:GITHUB_ENV
-    name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
+            default-shell: bash -l {0}
+          - stable-diffusion-model: stable-diffusion-1.5
+            stable-diffusion-model-url: https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
+            stable-diffusion-model-dl-path: models/ldm/stable-diffusion-v1
+            stable-diffusion-model-dl-name: v1-5-pruned-emaonly.ckpt
+    name: ${{ matrix.requirements-file }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: ${{ matrix.default-shell }}
     env:
-      PIP_USE_PEP517: '1'
+      INVOKEAI_ROOT: '${{ github.workspace }}/invokeai'
     steps:
       - name: Checkout sources
         id: checkout-sources
         uses: actions/checkout@v3
 
-      - name: Check for changed python files
-        id: changed-files
-        uses: tj-actions/changed-files@v37
-        with:
-          files_yaml: |
-            python:
-              - 'pyproject.toml'
-              - 'invokeai/**'
-              - '!invokeai/frontend/web/**'
-              - 'tests/**'
+      - name: create models.yaml from example
+        run: |
+          mkdir -p ${{ env.INVOKEAI_ROOT }}/configs
+          cp configs/models.yaml.example ${{ env.INVOKEAI_ROOT }}/configs/models.yaml
 
       - name: set test prompt to main branch validation
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> $GITHUB_ENV
+
+      - name: set test prompt to development branch validation
+        if: ${{ github.ref == 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/dev_prompts.txt" >> $GITHUB_ENV
+
+      - name: set test prompt to Pull Request validation
+        if: ${{ github.ref != 'refs/heads/main' && github.ref != 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> $GITHUB_ENV
+
+      - name: create requirements.txt
+        run: cp 'environments-and-requirements/${{ matrix.requirements-file }}' '${{ matrix.requirements-file }}'
 
       - name: setup python
-        if: steps.changed-files.outputs.python_any_changed == 'true'
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
-          cache: pip
-          cache-dependency-path: pyproject.toml
+          cache: 'pip'
+          cache-dependency-path: ${{ matrix.requirements-file }}
 
-      - name: install invokeai
-        if: steps.changed-files.outputs.python_any_changed == 'true'
+      # - name: install dependencies
+      #   run: ${{ env.pythonLocation }}/bin/pip install --upgrade pip setuptools wheel
+
+      - name: install requirements
+        run: ${{ env.pythonLocation }}/bin/pip install -r '${{ matrix.requirements-file }}'
+
+      - name: Use Cached Stable Diffusion Model
+        id: cache-sd-model
+        uses: actions/cache@v3
         env:
-          PIP_EXTRA_INDEX_URL: ${{ matrix.extra-index-url }}
-        run: >
-          pip3 install
-          --editable=".[test]"
+          cache-name: cache-${{ matrix.stable-diffusion-model }}
+        with:
+          path: ${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}
+          key: ${{ env.cache-name }}
 
-      - name: run pytest
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        id: run-pytest
-        run: pytest
+      - name: Download ${{ matrix.stable-diffusion-model }}
+        id: download-stable-diffusion-model
+        if: ${{ steps.cache-sd-model.outputs.cache-hit != 'true' }}
+        run: |
+          mkdir -p "${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}"
+          curl \
+            -H "Authorization: Bearer ${{ secrets.HUGGINGFACE_TOKEN }}" \
+            -o "${{ env.INVOKEAI_ROOT }}/${{ matrix.stable-diffusion-model-dl-path }}/${{ matrix.stable-diffusion-model-dl-name }}" \
+            -L ${{ matrix.stable-diffusion-model-url }}
 
-      # - name: run invokeai-configure
-      #   env:
-      #     HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
-      #   run: >
-      #     invokeai-configure
-      #     --yes
-      #     --default_only
-      #     --full-precision
-      #   # can't use fp16 weights without a GPU
+      - name: run configure_invokeai.py
+        id: run-preload-models
+        run: |
+          ${{ env.pythonLocation }}/bin/python scripts/configure_invokeai.py --no-interactive --yes
 
-      # - 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: cat ~/.invokeai
+        id: cat-invokeai
+        run: cat ~/.invokeai
 
-      # - name: Archive results
-      #   env:
-      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-      #   uses: actions/upload-artifact@v3
-      #   with:
-      #     name: results
-      #     path: ${{ env.INVOKEAI_OUTDIR }}
+      - name: Run the tests
+        id: run-tests
+        run: |
+          time ${{ env.pythonLocation }}/bin/python scripts/invoke.py \
+            --no-patchmatch \
+            --no-nsfw_checker \
+            --model ${{ matrix.stable-diffusion-model }} \
+            --from_file ${{ env.TEST_PROMPTS }} \
+            --root="${{ env.INVOKEAI_ROOT }}" \
+            --outdir="${{ env.INVOKEAI_ROOT }}/outputs"
+
+      - name: Archive results
+        id: archive-results
+        uses: actions/upload-artifact@v3
+        with:
+          name: results_${{ matrix.requirements-file }}_${{ matrix.python-version }}
+          path: ${{ env.INVOKEAI_ROOT }}/outputs

.gitignore

@@ -1,4 +1,17 @@
-.idea/
+# ignore default image save location and model symbolic link
+outputs/
+models/ldm/stable-diffusion-v1/model.ckpt
+**/restoration/codeformer/weights
+
+# ignore user models config
+configs/models.user.yaml
+config/models.user.yml
+
+# ignore the Anaconda/Miniconda installer used while building Docker image
+anaconda.sh
+
+# ignore a directory which serves as a place for initial images
+inputs/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -16,10 +29,11 @@ __pycache__/
 .Python
 build/
 develop-eggs/
-# dist/
+dist/
 downloads/
 eggs/
 .eggs/
+lib/
 lib64/
 parts/
 sdist/
@@ -46,21 +60,16 @@ pip-delete-this-directory.txt
 htmlcov/
 .tox/
 .nox/
-.coveragerc
 .coverage
 .coverage.*
 .cache
 nosetests.xml
 coverage.xml
-cov.xml
 *.cover
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.pytest.ini
 cover/
-junit/
-notes/
 
 # Translations
 *.mo
@@ -133,10 +142,12 @@ celerybeat.pid
 
 # Environments
 .env
-.venv*
+.venv
 env/
 venv/
 ENV/
+env.bak/
+venv.bak/
 
 # Spyder project settings
 .spyderproject
@@ -169,21 +180,57 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 
+src
 **/__pycache__/
+outputs
 
+# Logs and associated folders
+# created from generated embeddings.
+logs
+testtube
+checkpoints
 # If it's a Mac
 .DS_Store
 
 # Let the frontend manage its own gitignore
-!invokeai/frontend/web/*
+!frontend/*
 
 # Scratch folder
 .scratch/
 .vscode/
+gfpgan/
+models/ldm/stable-diffusion-v1/*.sha256
+
+
+# GFPGAN model files
+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
+
+# ignore environment.yml and requirements.txt
+# these are links to the real files in environments-and-requirements
+environment.yml
+requirements.txt
 
 # source installer files
-installer/*zip
-installer/install.bat
-installer/install.sh
-installer/update.bat
-installer/update.sh
+source_installer/*zip
+source_installer/invokeAI
+install.bat
+install.sh
+update.bat
+update.sh
+
+# this may be present if the user created a venv
+invokeai
+
+# no longer stored in source directory
+models

.pre-commit-config.yaml

@@ -1,24 +0,0 @@
-# See https://pre-commit.com/ for usage and config
-repos:
-- repo: local
-  hooks:
-  - id: black
-    name: black
-    stages: [commit]
-    language: system
-    entry: black
-    types: [python]
-
-  - id: flake8
-    name: flake8
-    stages: [commit]
-    language: system
-    entry: flake8
-    types: [python]
-
-  - id: isort
-    name: isort
-    stages: [commit]
-    language: system
-    entry: isort
-    types: [python]

InvokeAI_Statement_of_Values.md

@@ -1,4 +1,4 @@
-<img src="docs/assets/invoke_ai_banner.png" align="center">
+<img src="docs/assets/invoke_ai_banner.png" align="center">
 
 Invoke-AI is a community of software developers, researchers, and user
 interface experts who have come together on a voluntary basis to build
@@ -81,4 +81,5 @@ area. Disputes are resolved by open and honest communication.
 
 ## Signature
 
-This document has been collectively crafted and approved by the current InvokeAI team members, as of 28 Nov 2022: **lstein** (Lincoln Stein), **blessedcoolant**, **hipsterusername** (Kent Keirsey), **Kyle0654** (Kyle Schouviller), **damian0815**, **mauwii** (Matthias Wild), **Netsvetaev** (Artur Netsvetaev), **psychedelicious**, **tildebyte**, **keturn**, and **ebr** (Eugene Brodsky). Although individuals within the group may hold differing views on particular details and/or their implications, we are all in agreement about its fundamental statements, as well as their significance and importance to this project moving forward.
+This document has been collectively crafted and approved by the current InvokeAI team members, as of 28 Nov 2022: **lstein** (Lincoln Stein), **blessedcoolant**, **hipsterusername** (Kent Keirsey), **Kyle0654** (Kyle Schouviller), **damian0815**, **mauwii** (Matthias Wild), **Netsvetaev** (Artur Netsvetaev), **psychedelicious**, **tildebyte**, and **keturn**. Although individuals within the group may hold differing views on particular details and/or their implications, we are all in agreement about its fundamental statements, as well as their significance and importance to this project moving forward.  
+

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.

LICENSE-SDXL.txt

@@ -1,290 +0,0 @@
-Copyright (c) 2023 Stability AI
-CreativeML Open RAIL++-M License dated July 26, 2023
-
-Section I: PREAMBLE
-
-Multimodal generative models are being widely adopted and used, and
-have the potential to transform the way artists, among other
-individuals, conceive and benefit from AI or ML technologies as a tool
-for content creation.
-
-Notwithstanding the current and potential benefits that these
-artifacts can bring to society at large, there are also concerns about
-potential misuses of them, either due to their technical limitations
-or ethical considerations.
-
-In short, this license strives for both the open and responsible
-downstream use of the accompanying model. When it comes to the open
-character, we took inspiration from open source permissive licenses
-regarding the grant of IP rights. Referring to the downstream
-responsible use, we added use-based restrictions not permitting the
-use of the model in very specific scenarios, in order for the licensor
-to be able to enforce the license in case potential misuses of the
-Model may occur. At the same time, we strive to promote open and
-responsible research on generative models for art and content
-generation.
-
-Even though downstream derivative versions of the model could be
-released under different licensing terms, the latter will always have
-to include - at minimum - the same use-based restrictions as the ones
-in the original license (this license). We believe in the intersection
-between open and responsible AI development; thus, this agreement aims
-to strike a balance between both in order to enable responsible
-open-science in the field of AI.
-
-This CreativeML Open RAIL++-M License governs the use of the model
-(and its derivatives) and is informed by the model card associated
-with the model.
-
-NOW THEREFORE, You and Licensor agree as follows:
-
-Definitions
-
-"License" means the terms and conditions for use, reproduction, and
-Distribution as defined in this document.
-
-"Data" means a collection of information and/or content extracted from
-the dataset used with the Model, including to train, pretrain, or
-otherwise evaluate the Model. The Data is not licensed under this
-License.
-
-"Output" means the results of operating a Model as embodied in
-informational content resulting therefrom.
-
-"Model" means any accompanying machine-learning based assemblies
-(including checkpoints), consisting of learnt weights, parameters
-(including optimizer states), corresponding to the model architecture
-as embodied in the Complementary Material, that have been trained or
-tuned, in whole or in part on the Data, using the Complementary
-Material.
-
-"Derivatives of the Model" means all modifications to the Model, works
-based on the Model, or any other model which is created or initialized
-by transfer of patterns of the weights, parameters, activations or
-output of the Model, to the other model, in order to cause the other
-model to perform similarly to the Model, including - but not limited
-to - distillation methods entailing the use of intermediate data
-representations or methods based on the generation of synthetic data
-by the Model for training the other model.
-
-"Complementary Material" means the accompanying source code and
-scripts used to define, run, load, benchmark or evaluate the Model,
-and used to prepare data for training or evaluation, if any. This
-includes any accompanying documentation, tutorials, examples, etc, if
-any.
-
-"Distribution" means any transmission, reproduction, publication or
-other sharing of the Model or Derivatives of the Model to a third
-party, including providing the Model as a hosted service made
-available by electronic or other remote means - e.g. API-based or web
-access.
-
-"Licensor" means the copyright owner or entity authorized by the
-copyright owner that is granting the License, including the persons or
-entities that may have rights in the Model and/or distributing the
-Model.
-
-"You" (or "Your") means an individual or Legal Entity exercising
-permissions granted by this License and/or making use of the Model for
-whichever purpose and in any field of use, including usage of the
-Model in an end-use application - e.g. chatbot, translator, image
-generator.
-
-"Third Parties" means individuals or legal entities that are not under
-common control with Licensor or You.
-
-"Contribution" means any work of authorship, including the original
-version of the Model and any modifications or additions to that Model
-or Derivatives of the Model thereof, that is intentionally submitted
-to Licensor for inclusion in the Model 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
-Model, but excluding communication that is conspicuously marked or
-otherwise designated in writing by the copyright owner as "Not a
-Contribution."
-
-"Contributor" means Licensor and any individual or Legal Entity on
-behalf of whom a Contribution has been received by Licensor and
-subsequently incorporated within the Model.
-
-Section II: INTELLECTUAL PROPERTY RIGHTS
-
-Both copyright and patent grants apply to the Model, Derivatives of
-the Model and Complementary Material. The Model and Derivatives of the
-Model are subject to additional terms as described in
-
-Section III.
-
-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, publicly display, publicly
-perform, sublicense, and distribute the Complementary Material, the
-Model, and Derivatives of the Model.
-
-Grant of Patent License. Subject to the terms and conditions of this
-License and where and as applicable, each Contributor hereby grants to
-You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
-irrevocable (except as stated in this paragraph) patent license to
-make, have made, use, offer to sell, sell, import, and otherwise
-transfer the Model and the Complementary Material, 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 Model 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 Model and/or Complementary Material or a
-Contribution incorporated within the Model and/or Complementary
-Material constitutes direct or contributory patent infringement, then
-any patent licenses granted to You under this License for the Model
-and/or Work shall terminate as of the date such litigation is asserted
-or filed.
-
-Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
-
-Distribution and Redistribution. You may host for Third Party remote
-access purposes (e.g. software-as-a-service), reproduce and distribute
-copies of the Model or Derivatives of the Model thereof in any medium,
-with or without modifications, provided that You meet the following
-conditions: Use-based restrictions as referenced in paragraph 5 MUST
-be included as an enforceable provision by You in any type of legal
-agreement (e.g. a license) governing the use and/or distribution of
-the Model or Derivatives of the Model, and You shall give notice to
-subsequent users You Distribute to, that the Model or Derivatives of
-the Model are subject to paragraph 5. This provision does not apply to
-the use of Complementary Material. You must give any Third Party
-recipients of the Model or Derivatives of the Model a copy of this
-License; You must cause any modified files to carry prominent notices
-stating that You changed the files; You must retain all copyright,
-patent, trademark, and attribution notices excluding those notices
-that do not pertain to any part of the Model, Derivatives of the
-Model. You may add Your own copyright statement to Your modifications
-and may provide additional or different license terms and conditions -
-respecting paragraph 4.a. - for use, reproduction, or Distribution of
-Your modifications, or for any such Derivatives of the Model as a
-whole, provided Your use, reproduction, and Distribution of the Model
-otherwise complies with the conditions stated in this License.
-
-Use-based restrictions. The restrictions set forth in Attachment A are
-considered Use-based restrictions. Therefore You cannot use the Model
-and the Derivatives of the Model for the specified restricted
-uses. You may use the Model subject to this License, including only
-for lawful purposes and in accordance with the License. Use may
-include creating any content with, finetuning, updating, running,
-training, evaluating and/or reparametrizing the Model. You shall
-require all of Your users who use the Model or a Derivative of the
-Model to comply with the terms of this paragraph (paragraph 5).
-
-The Output You Generate.  Except as set forth herein, Licensor claims
-no rights in the Output You generate using the Model. You are
-accountable for the Output you generate and its subsequent uses. No
-use of the output can contravene any provision as stated in the
-License.
-
-Section IV: OTHER PROVISIONS
-
-Updates and Runtime Restrictions. To the maximum extent permitted by
-law, Licensor reserves the right to restrict (remotely or otherwise)
-usage of the Model in violation of this License.
-
-Trademarks and related. Nothing in this License permits You to make
-use of Licensors’ trademarks, trade names, logos or to otherwise
-suggest endorsement or misrepresent the relationship between the
-parties; and any rights not expressly granted herein are reserved by
-the Licensors.
-
-Disclaimer of Warranty. Unless required by applicable law or agreed to
-in writing, Licensor provides the Model and the Complementary Material
-(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 Model, Derivatives of
-the Model, and the Complementary Material and assume any risks
-associated with Your exercise of permissions under this License.
-
-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 Model and the
-Complementary Material (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.
-
-Accepting Warranty or Additional Liability. While redistributing the
-Model, Derivatives of the Model and the Complementary Material
-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.
-
-If any provision of this License is held to be invalid, illegal or
-unenforceable, the remaining provisions shall be unaffected thereby
-and remain valid as if such provision had not been set forth herein.
-
-
-END OF TERMS AND CONDITIONS
-
-Attachment A
-
-Use Restrictions
-
-You agree not to use the Model or Derivatives of the Model:
-
-* In any way that violates any applicable national, federal, state,
-local or international law or regulation;
-
-* For the purpose of exploiting, harming or attempting to exploit or
-harm minors in any way;
-
-* To generate or disseminate verifiably false information and/or
-  content with the purpose of harming others;
-
-* To generate or disseminate personal identifiable information that
-  can be used to harm an individual;
-
-* To defame, disparage or otherwise harass others;
-
-* For fully automated decision making that adversely impacts an
-  individual’s legal rights or otherwise creates or modifies a
-  binding, enforceable obligation;
-
-* For any use intended to or which has the effect of discriminating
-  against or harming individuals or groups based on online or offline
-  social behavior or known or predicted personal or personality
-  characteristics;
-
-* To exploit any of the vulnerabilities of a specific group of persons
-  based on their age, social, physical or mental characteristics, in
-  order to materially distort the behavior of a person pertaining to
-  that group in a manner that causes or is likely to cause that person
-  or another person physical or psychological harm;
-
-* For any use intended to or which has the effect of discriminating
-  against individuals or groups based on legally protected
-  characteristics or categories;
-
-* To provide medical advice and medical results interpretation;
-
-* To generate or disseminate information for the purpose to be used
-  for administration of justice, law enforcement, immigration or
-  asylum processes, such as predicting an individual will commit
-  fraud/crime commitment (e.g. by text profiling, drawing causal
-  relationships between assertions made in documents, indiscriminate
-  and arbitrarily-targeted use).
-

README.md

@@ -1,22 +1,23 @@
 <div align="center">
 
-![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/1a917d94-e099-4fa1-a70f-7dd8d0691018)
+# InvokeAI: A Stable Diffusion Toolkit
 
-# 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)
+_Formerly known as lstein/stable-diffusion_
 
+![project logo](docs/assets/logo.png)
 
 [![discord badge]][discord link]
 
 [![latest release badge]][latest release link] [![github stars badge]][github stars link] [![github forks badge]][github forks link]
 
-[![CI checks on main badge]][CI checks on main link] [![latest commit to main badge]][latest commit to main link]
+[![CI checks on main badge]][CI checks on main link] [![CI checks on dev badge]][CI checks on dev link] [![latest commit to dev badge]][latest commit to dev link]
 
-[![github open issues badge]][github open issues link] [![github open prs badge]][github open prs link] [![translation status badge]][translation status link]
+[![github open issues badge]][github open issues link] [![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
+[CI checks on dev link]: 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
-[CI checks on main link]:https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Amain
+[CI checks on main link]: 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
@@ -27,387 +28,159 @@
 [github open prs link]: 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
 [github stars link]: https://github.com/invoke-ai/InvokeAI/stargazers
-[latest commit to main badge]: https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/main?icon=github&color=yellow&label=last%20dev%20commit&cache=900
-[latest commit to main link]: https://github.com/invoke-ai/InvokeAI/commits/main
+[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
+[latest commit to dev link]: https://github.com/invoke-ai/InvokeAI/commits/development
 [latest release badge]: https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
-[translation status badge]: https://hosted.weblate.org/widgets/invokeai/-/svg-badge.svg
-[translation status link]: https://hosted.weblate.org/engage/invokeai/
-
 </div>
 
-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.
+This is a fork of
+[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion),
+the open source text-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, with
+GPU cards with as little as 4 GB of RAM. It provides both a polished
+Web interface (see below), and an easy-to-use command-line interface.
 
-**Quick links**: [[How to
-  Install](https://invoke-ai.github.io/InvokeAI/installation/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/issues">Bug Reports</a>]
-  [<a
-  href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion,
-  Ideas & Q&A</a>] 
-   [<a
-  href="https://invoke-ai.github.io/InvokeAI/contributing/CONTRIBUTING/">Contributing</a>] 
+**Quick links**: [<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>]
 
-<div align="center">
+<div align="center"><img src="docs/assets/invoke-web-server-1.png" width=640></div>
 
-![canvas preview](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/canvas_preview.png)
 
-</div>
+_Note: This fork 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 aid diagnose issues faster._
 
 ## Table of Contents
 
-Table of Contents 📝
+1. [Installation](#installation)
+2. [Hardware Requirements](#hardware-requirements)
+3. [Features](#features)
+4. [Latest Changes](#latest-changes)
+5. [Troubleshooting](#troubleshooting)
+6. [Contributing](#contributing)
+7. [Contributors](#contributors)
+8. [Support](#support)
+9. [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
-
-For full installation and upgrade instructions, please see:
-[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/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)
-
-2. Download the .zip file for your OS (Windows/macOS/Linux).
-
-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`.
-
-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
-location with at least 15 GB of free memory. More if you plan on
-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.
-
-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
-folder (if you didn't change it in step 5) is `~/invokeai` on
-Linux/Mac systems, and `C:\Users\YourName\invokeai` on Windows. This directory will contain launcher scripts named `invoke.sh` and `invoke.bat`.
-
-8. On Windows systems, double-click on the `invoke.bat` file. On
-macOS, open a Terminal window, drag `invoke.sh` from the folder into
-the Terminal, and press return. On Linux, run `invoke.sh`
-
-9. Press 2 to open the "browser-based UI", press enter/return, wait a
-minute or two for Stable Diffusion to start up, then open your browser
-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)
-
-You must have Python 3.10 through 3.11 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)
-
-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:
-
-    ```terminal
-    mkdir invokeai
-    ````
-
-3. Create a virtual environment named `.venv` inside this directory and activate it:
-
-    ```terminal
-    cd invokeai
-    python -m venv .venv --prompt InvokeAI
-    ```
-
-4. Activate the virtual environment (do it every time you run InvokeAI)
-
-    _For Linux/Mac users:_
-
-    ```sh
-    source .venv/bin/activate
-    ```
-
-    _For Windows users:_
-
-    ```ps
-    .venv\Scripts\activate
-    ```
-
-5. Install the InvokeAI module and its dependencies. Choose the command suited for your platform & GPU.
-
-    _For Windows/Linux with an NVIDIA GPU:_
-
-    ```terminal
-    pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-    ```
-
-    _For Linux with an AMD GPU:_
-
-    ```sh
-    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/M3:_
-
-    ```sh
-    pip install InvokeAI --use-pep517
-    ```
-
-6. Configure InvokeAI and install a starting set of image generation models (you only need to do this once):
-
-    ```terminal
-    invokeai-configure --root .
-    ```
-	Don't miss the dot at the end!
-
-7. Launch the web server (do it every time you run InvokeAI):
-
-    ```terminal
-    invokeai-web
-    ```
-
-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
+### Installation
 
 This fork is supported across Linux, Windows and Macintosh. Linux
 users can use either an Nvidia-based card (with CUDA support) or an
 AMD card (using the ROCm driver). For full installation and upgrade
 instructions, please see:
-[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_SOURCE/)
+[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
 
-<a name="migrating-to-3"></a>
-### Migrating a v2.3 InvokeAI root directory
+### Hardware Requirements
 
-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.
+#### System
 
-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.
+You wil need one of the following:
 
-#### Creating a new root directory and migrating old models
+- An NVIDIA-based graphics card with 4 GB or more VRAM memory.
+- An Apple computer with an M1 chip.
 
-This is the safer recipe because it leaves your old root directory in
-place to fall back on.
+#### Memory
 
-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"
+- At least 12 GB Main Memory RAM.
 
-2. When you are prompted to select models to install, select a minimal
-set of models, such as stable-diffusion-v1.5 only.
+#### Disk
 
-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.
+- At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
-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.
+**Note**
 
-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.
+If you have a Nvidia 10xx series card (e.g. the 1080ti), please
+run the dream script in full-precision mode as shown below.
 
- If you wish, you can pass the 2.3 root directory to both `--from` and
-`--to` in order to update in place. Warning: this directory will no
-longer be usable with InvokeAI 2.3.
+Similarly, specify full-precision mode on Apple M1 hardware.
 
-#### Migrating in place
-
-For the adventurous, you may do an in-place upgrade from 2.3 to 3.0
-without touching the command line. ***This recipe does not work on
-Windows platforms due to a bug in the Windows version of the 2.3
-upgrade script.** See the next section for a Windows recipe.
-
-##### For Mac and Linux Users:
-
-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.
-
-3. 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.
-
-##### For Windows Users:
-
-Windows Users can upgrade with the
-
-1. Enter the 2.3 root directory you wish to upgrade
-2. Launch `invoke.sh` or `invoke.bat`
-3. Select the "Developer's console" option [8]
-4. Type the following commands
-
-```
-pip install "invokeai @ https://github.com/invoke-ai/InvokeAI/archive/refs/tags/v3.0.0" --use-pep517 --upgrade
-invokeai-configure --root .
-```
-(Replace `v3.0.0` with the current release number if this document is out of date).
-
-The first command will install and upgrade new software to run
-InvokeAI. The second will prepare the 2.3 directory for use with 3.0.
-You may now launch the WebUI in the usual way, by selecting option [1]
-from the launcher script
-
-#### Migrating Images
-
-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. To do this, you 
-need to run an additional step:
-
-1. From a working InvokeAI 3.0 root directory, start the launcher and
-enter menu option [8] to open the "developer's console".
-
-2. At the developer's console command line, type the command:
+Precision is auto configured based on the device. If however you encounter
+errors like 'expected type Float but found Half' or 'not implemented for Half'
+you can try starting `invoke.py` with the `--precision=float32` flag:
 
 ```bash
-invokeai-import-images
+(invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32
 ```
 
-3. This will lead you through the process of confirming the desired
-   source and destination for the imported images. The images will
-   appear in the gallery board of your choice, and contain the
-   original prompt, model name, and other parameters used to generate
-   the image.
-   
-(Many kudos to **techjedi** for contributing this script.)
+### Features
 
-## Hardware Requirements
+#### Major Features
 
-InvokeAI is supported across Linux, Windows and macOS. Linux
-users can use either an Nvidia-based card (with CUDA support) or an
-AMD card (using the ROCm driver).
+- [Web Server](https://invoke-ai.github.io/InvokeAI/features/WEB/)
+- [Interactive Command Line Interface](https://invoke-ai.github.io/InvokeAI/features/CLI/)
+- [Image To Image](https://invoke-ai.github.io/InvokeAI/features/IMG2IMG/)
+- [Inpainting Support](https://invoke-ai.github.io/InvokeAI/features/INPAINTING/)
+- [Outpainting Support](https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/)
+- [Upscaling, face-restoration and outpainting](https://invoke-ai.github.io/InvokeAI/features/POSTPROCESS/)
+- [Reading Prompts From File](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#reading-prompts-from-a-file)
+- [Prompt Blending](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#prompt-blending)
+- [Thresholding and Perlin Noise Initialization Options](https://invoke-ai.github.io/InvokeAI/features/OTHER/#thresholding-and-perlin-noise-initialization-options)
+- [Negative/Unconditioned Prompts](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#negative-and-unconditioned-prompts)
+- [Variations](https://invoke-ai.github.io/InvokeAI/features/VARIATIONS/)
+- [Personalizing Text-to-Image Generation](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/)
+- [Simplified API for text to image generation](https://invoke-ai.github.io/InvokeAI/features/OTHER/#simplified-api)
 
-### System
-
-You will need one of the following:
-
-- An NVIDIA-based graphics card with 4 GB or more VRAM memory. 6-8 GB
-  of VRAM is highly recommended for rendering using the Stable
-  Diffusion XL models
-- An Apple computer with an M1 chip.
-- An AMD-based graphics card with 4GB or more VRAM memory (Linux
-  only), 6-8 GB for XL rendering.
-
-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.
-
-**Disk** - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
-
-## Features
-
-Feature documentation can be reviewed by navigating to [the InvokeAI Documentation page](https://invoke-ai.github.io/InvokeAI/features/)
-
-### *Web Server & UI*
-
-InvokeAI offers a locally hosted Web Server & React Frontend, with an industry leading user experience. The Web-based UI allows for simple and intuitive workflows, and is responsive for use on mobile devices and tablets accessing the web server.
-
-### *Unified Canvas*
-
-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.
-
-### *Workflows & Nodes*
-
-InvokeAI offers a fully featured workflow management solution, enabling users to combine the power of nodes based workflows with the easy of a UI. This allows for customizable generation pipelines to be developed and shared by users looking to create specific workflows to support their production use-cases.
-
-### *Board & Gallery Management*
-
-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. 
-
-### Other features
-
-- *Support for both ckpt and diffusers models*
-- *SD 2.0, 2.1, XL support*
-- *Upscaling Tools*
-- *Embedding Manager & Support*
-- *Model Manager & Support*
-- *Workflow creation & management*
-- *Node-Based Architecture*
+#### Other Features
 
+- [Google Colab](https://invoke-ai.github.io/InvokeAI/features/OTHER/#google-colab)
+- [Seamless Tiling](https://invoke-ai.github.io/InvokeAI/features/OTHER/#seamless-tiling)
+- [Shortcut: Reusing Seeds](https://invoke-ai.github.io/InvokeAI/features/OTHER/#shortcuts-reusing-seeds)
+- [Preload Models](https://invoke-ai.github.io/InvokeAI/features/OTHER/#preload-models)
 
 ### Latest Changes
 
-For our latest changes, view our [Release
-Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
-[CHANGELOG](docs/CHANGELOG.md).
+- v2.0.1 (13 October 2022)
+  - fix noisy images at high step count when using k* samplers
+  - dream.py script now calls invoke.py module directly rather than
+    via a new python process (which could break the environment)
+
+- v2.0.0 (9 October 2022)
+
+  - `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 <a href="https://invoke-ai.github.io/InvokeAI/features/INPAINTING/">inpainting</a> and <a href="https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/">outpainting</a>
+  - img2img runs on all k* samplers
+  - Support for <a href="https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#negative-and-unconditioned-prompts">negative prompts</a>
+  - Support for CodeFormer face reconstruction
+  - Support for Textual Inversion on Macintoshes
+  - Support in both WebGUI and CLI for <a href="https://invoke-ai.github.io/InvokeAI/features/POSTPROCESS/">post-processing of previously-generated images</a>
+    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 <a href="https://invoke-ai.github.io/InvokeAI/features/CLI/#txt2img">larger images to be created without duplicating elements</a>, at the cost of some performance.
+  - New `--perlin` and `--threshold` options allow you to add and control variation
+    during image generation (see <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options">Thresholding and Perlin Noise Initialization</a>
+  - Extensive metadata now written into PNG files, allowing reliable regeneration of images
+    and tweaking of previous settings.
+  - Command-line completion in `invoke.py` now works on Windows, Linux and Mac platforms.
+  - Improved <a href="https://invoke-ai.github.io/InvokeAI/features/CLI/">command-line completion behavior</a>.
+    New commands added:
+    - List command-line history with `!history`
+    - Search command-line history with `!search`
+    - Clear history with `!clear`
+  - Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
+    configure. To switch away from auto use the new flag like `--precision=float32`.
+
+For older changelogs, please visit the **[CHANGELOG](https://invoke-ai.github.io/InvokeAI/CHANGELOG#v114-11-september-2022)**.
 
 ### 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. For more help, please join our [Discord][discord link]
+problems and other issues.
 
-## Contributing
+# Contributing
 
 Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code
-cleanup, testing, or code reviews, is very much encouraged to do so.
-
-Get started with contributing by reading our [Contribution documentation](https://invoke-ai.github.io/InvokeAI/contributing/CONTRIBUTING/), joining the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) or the GitHub discussion board.
+cleanup, testing, or code reviews, is very much encouraged to do so. To join, just raise your hand on the InvokeAI
+Discord server or discussion board. 
 
 If you are unfamiliar with how
-to contribute to GitHub projects, we have a new contributor checklist you can follow to get started contributing: 
-[New Contributor Checklist](https://invoke-ai.github.io/InvokeAI/contributing/contribution_guides/newContributorChecklist/).
+to contribute to GitHub projects, here is a
+[Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github). A full set of contribution guidelines, along with templates, are in progress, but for now the most
+important thing is to **make your pull request against the "development" branch**, and not against
+"main". This will help keep public breakage to a minimum and will allow you to propose more radical
+changes.
 
 We hope you enjoy using our software as much as we enjoy creating it,
 and we hope that some of those of you who are reading this will elect
@@ -423,7 +196,13 @@ their time, hard work and effort.
 
 ### Support
 
-For support, please use this repository's GitHub Issues tracking service, or join the [Discord][discord link].
+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) 2023 by respective contributors.
+Original portions of the software are Copyright (c) 2020
+[Lincoln D. Stein](https://github.com/lstein)
 
+### Further Reading
+
+Please see the original README for more information on this software and underlying algorithm,
+located in the file [README-CompViz.md](https://invoke-ai.github.io/InvokeAI/other/README-CompViz/).

Stable_Diffusion_v1_Model_Card.md

@@ -21,7 +21,7 @@ This model card focuses on the model associated with the Stable Diffusion model,
 
 # Uses
 
-## Direct Use
+## Direct Use 
 The model is intended for research purposes only. Possible research areas and
 tasks include
 
@@ -68,11 +68,11 @@ Using the model to generate content that is cruel to individuals is a misuse of
   considerations.
 
 ### Bias
-While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
-Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
-which consists of images that are primarily limited to English descriptions.
-Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
-This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
+While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. 
+Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), 
+which consists of images that are primarily limited to English descriptions. 
+Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. 
+This affects the overall output of the model, as white and western cultures are often set as the default. Further, the 
 ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
 
 
@@ -84,7 +84,7 @@ The model developers used the following dataset for training the model:
 - LAION-2B (en) and subsets thereof (see next section)
 
 **Training Procedure**
-Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
+Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, 
 
 - Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
 - Text prompts are encoded through a ViT-L/14 text-encoder.
@@ -108,12 +108,12 @@ filtered to images with an original size `>= 512x512`, estimated aesthetics scor
 - **Batch:** 32 x 8 x 2 x 4 = 2048
 - **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant
 
-## Evaluation Results
+## Evaluation Results 
 Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
 5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling
 steps show the relative improvements of the checkpoints:
 
-![pareto](assets/v1-variants-scores.jpg)
+![pareto](assets/v1-variants-scores.jpg) 
 
 Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution.  Not optimized for FID scores.
 ## Environmental Impact

backend/modules/create_cmd_parser.py

@@ -0,0 +1,55 @@
+import argparse
+import os
+from ldm.invoke.args import PRECISION_CHOICES
+
+
+def create_cmd_parser():
+    parser = argparse.ArgumentParser(description="InvokeAI web UI")
+    parser.add_argument(
+        "--host",
+        type=str,
+        help="The host to serve on",
+        default="localhost",
+    )
+    parser.add_argument("--port", type=int, help="The port to serve on", default=9090)
+    parser.add_argument(
+        "--cors",
+        nargs="*",
+        type=str,
+        help="Additional allowed origins, comma-separated",
+    )
+    parser.add_argument(
+        "--embedding_path",
+        type=str,
+        help="Path to a pre-trained embedding manager checkpoint - can only be set on command line",
+    )
+    # TODO: Can't get flask to serve images from any dir (saving to the dir does work when specified)
+    # parser.add_argument(
+    #     "--output_dir",
+    #     default="outputs/",
+    #     type=str,
+    #     help="Directory for output images",
+    # )
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        help="Enables verbose logging",
+    )
+    parser.add_argument(
+        "--precision",
+        dest="precision",
+        type=str,
+        choices=PRECISION_CHOICES,
+        metavar="PRECISION",
+        help=f'Set model precision. Defaults to auto selected based on device. Options: {", ".join(PRECISION_CHOICES)}',
+        default="auto",
+    )
+    parser.add_argument(
+        '--free_gpu_mem',
+        dest='free_gpu_mem',
+        action='store_true',
+        help='Force free gpu memory before final decoding',
+    )
+
+    return parser

backend/modules/get_canvas_generation_mode.py

@@ -0,0 +1,117 @@
+from PIL import Image, ImageChops
+from PIL.Image import Image as ImageType
+from typing import Union, Literal
+
+# https://stackoverflow.com/questions/43864101/python-pil-check-if-image-is-transparent
+def check_for_any_transparency(img: Union[ImageType, str]) -> bool:
+    if type(img) is str:
+        img = Image.open(str)
+
+    if img.info.get("transparency", None) is not None:
+        return True
+    if img.mode == "P":
+        transparent = img.info.get("transparency", -1)
+        for _, index in img.getcolors():
+            if index == transparent:
+                return True
+    elif img.mode == "RGBA":
+        extrema = img.getextrema()
+        if extrema[3][0] < 255:
+            return True
+    return False
+
+
+def get_canvas_generation_mode(
+    init_img: Union[ImageType, str], init_mask: Union[ImageType, str]
+) -> Literal["txt2img", "outpainting", "inpainting", "img2img",]:
+    if type(init_img) is str:
+        init_img = Image.open(init_img)
+
+    if type(init_mask) is str:
+        init_mask = Image.open(init_mask)
+
+    init_img = init_img.convert("RGBA")
+
+    # Get alpha from init_img
+    init_img_alpha = init_img.split()[-1]
+    init_img_alpha_mask = init_img_alpha.convert("L")
+    init_img_has_transparency = check_for_any_transparency(init_img)
+
+    if init_img_has_transparency:
+        init_img_is_fully_transparent = (
+            True if init_img_alpha_mask.getbbox() is None else False
+        )
+
+    """
+    Mask images are white in areas where no change should be made, black where changes 
+    should be made.
+    """
+
+    # Fit the mask to init_img's size and convert it to greyscale
+    init_mask = init_mask.resize(init_img.size).convert("L")
+
+    """
+    PIL.Image.getbbox() returns the bounding box of non-zero areas of the image, so we first
+    invert the mask image so that masked areas are white and other areas black == zero.
+    getbbox() now tells us if the are any masked areas.
+    """
+    init_mask_bbox = ImageChops.invert(init_mask).getbbox()
+    init_mask_exists = False if init_mask_bbox is None else True
+
+    if init_img_has_transparency:
+        if init_img_is_fully_transparent:
+            return "txt2img"
+        else:
+            return "outpainting"
+    else:
+        if init_mask_exists:
+            return "inpainting"
+        else:
+            return "img2img"
+
+
+def main():
+    # Testing
+    init_img_opaque = "test_images/init-img_opaque.png"
+    init_img_partial_transparency = "test_images/init-img_partial_transparency.png"
+    init_img_full_transparency = "test_images/init-img_full_transparency.png"
+    init_mask_no_mask = "test_images/init-mask_no_mask.png"
+    init_mask_has_mask = "test_images/init-mask_has_mask.png"
+
+    print(
+        "OPAQUE IMAGE, NO MASK, expect img2img, got ",
+        get_canvas_generation_mode(init_img_opaque, init_mask_no_mask),
+    )
+
+    print(
+        "IMAGE WITH TRANSPARENCY, NO MASK, expect outpainting, got ",
+        get_canvas_generation_mode(
+            init_img_partial_transparency, init_mask_no_mask
+        ),
+    )
+
+    print(
+        "FULLY TRANSPARENT IMAGE NO MASK, expect txt2img, got ",
+        get_canvas_generation_mode(init_img_full_transparency, init_mask_no_mask),
+    )
+
+    print(
+        "OPAQUE IMAGE, WITH MASK, expect inpainting, got ",
+        get_canvas_generation_mode(init_img_opaque, init_mask_has_mask),
+    )
+
+    print(
+        "IMAGE WITH TRANSPARENCY, WITH MASK, expect outpainting, got ",
+        get_canvas_generation_mode(
+            init_img_partial_transparency, init_mask_has_mask
+        ),
+    )
+
+    print(
+        "FULLY TRANSPARENT IMAGE WITH MASK, expect txt2img, got ",
+        get_canvas_generation_mode(init_img_full_transparency, init_mask_has_mask),
+    )
+
+
+if __name__ == "__main__":
+    main()

backend/modules/parameters.py

@@ -0,0 +1,71 @@
+from backend.modules.parse_seed_weights import parse_seed_weights
+import argparse
+
+SAMPLER_CHOICES = [
+    "ddim",
+    "k_dpm_2_a",
+    "k_dpm_2",
+    "k_dpmpp_2_a",
+    "k_dpmpp_2",
+    "k_euler_a",
+    "k_euler",
+    "k_heun",
+    "k_lms",
+    "plms",
+]
+
+
+def parameters_to_command(params):
+    """
+    Converts dict of parameters into a `invoke.py` REPL command.
+    """
+
+    switches = list()
+
+    if "prompt" in params:
+        switches.append(f'"{params["prompt"]}"')
+    if "steps" in params:
+        switches.append(f'-s {params["steps"]}')
+    if "seed" in params:
+        switches.append(f'-S {params["seed"]}')
+    if "width" in params:
+        switches.append(f'-W {params["width"]}')
+    if "height" in params:
+        switches.append(f'-H {params["height"]}')
+    if "cfg_scale" in params:
+        switches.append(f'-C {params["cfg_scale"]}')
+    if "sampler_name" in params:
+        switches.append(f'-A {params["sampler_name"]}')
+    if "seamless" in params and params["seamless"] == True:
+        switches.append(f"--seamless")
+    if "hires_fix" in params and params["hires_fix"] == True:
+        switches.append(f"--hires")
+    if "init_img" in params and len(params["init_img"]) > 0:
+        switches.append(f'-I {params["init_img"]}')
+    if "init_mask" in params and len(params["init_mask"]) > 0:
+        switches.append(f'-M {params["init_mask"]}')
+    if "init_color" in params and len(params["init_color"]) > 0:
+        switches.append(f'--init_color {params["init_color"]}')
+    if "strength" in params and "init_img" in params:
+        switches.append(f'-f {params["strength"]}')
+        if "fit" in params and params["fit"] == True:
+            switches.append(f"--fit")
+    if "facetool" in params:
+        switches.append(f'-ft {params["facetool"]}')
+    if "facetool_strength" in params and params["facetool_strength"]:
+        switches.append(f'-G {params["facetool_strength"]}')
+    elif "gfpgan_strength" in params and params["gfpgan_strength"]:
+        switches.append(f'-G {params["gfpgan_strength"]}')
+    if "codeformer_fidelity" in params:
+        switches.append(f'-cf {params["codeformer_fidelity"]}')
+    if "upscale" in params and params["upscale"]:
+        switches.append(f'-U {params["upscale"][0]} {params["upscale"][1]}')
+    if "variation_amount" in params and params["variation_amount"] > 0:
+        switches.append(f'-v {params["variation_amount"]}')
+        if "with_variations" in params:
+            seed_weight_pairs = ",".join(
+                f"{seed}:{weight}" for seed, weight in params["with_variations"]
+            )
+            switches.append(f"-V {seed_weight_pairs}")
+
+    return " ".join(switches)

backend/modules/parse_seed_weights.py

@@ -0,0 +1,47 @@
+def parse_seed_weights(seed_weights):
+    """
+    Accepts seed weights as string in "12345:0.1,23456:0.2,3456:0.3" format
+    Validates them
+    If valid: returns as [[12345, 0.1], [23456, 0.2], [3456, 0.3]]
+    If invalid: returns False
+    """
+
+    # Must be a string
+    if not isinstance(seed_weights, str):
+        return False
+    # String must not be empty
+    if len(seed_weights) == 0:
+        return False
+
+    pairs = []
+
+    for pair in seed_weights.split(","):
+        split_values = pair.split(":")
+
+        # Seed and weight are required
+        if len(split_values) != 2:
+            return False
+
+        if len(split_values[0]) == 0 or len(split_values[1]) == 1:
+            return False
+
+        # Try casting the seed to int and weight to float
+        try:
+            seed = int(split_values[0])
+            weight = float(split_values[1])
+        except ValueError:
+            return False
+
+        # Seed must be 0 or above
+        if not seed >= 0:
+            return False
+
+        # Weight must be between 0 and 1
+        if not (weight >= 0 and weight <= 1):
+            return False
+
+        # This pair is valid
+        pairs.append([seed, weight])
+
+    # All pairs are valid
+    return pairs

configs/INITIAL_MODELS.yaml

@@ -0,0 +1,80 @@
+stable-diffusion-1.5:
+   description: The newest Stable Diffusion version 1.5 weight file (4.27 GB)
+   repo_id: runwayml/stable-diffusion-v1-5
+   config: v1-inference.yaml
+   file: v1-5-pruned-emaonly.ckpt
+   recommended: true
+   width: 512
+   height: 512
+inpainting-1.5:
+   description: RunwayML SD 1.5 model optimized for inpainting (4.27 GB)
+   repo_id: runwayml/stable-diffusion-inpainting
+   config: v1-inpainting-inference.yaml
+   file: sd-v1-5-inpainting.ckpt
+   recommended: True
+   width: 512
+   height: 512
+ft-mse-improved-autoencoder-840000:
+   description: StabilityAI improved autoencoder fine-tuned for human faces (recommended; 335 MB)
+   repo_id: stabilityai/sd-vae-ft-mse-original
+   config: VAE/default
+   file: vae-ft-mse-840000-ema-pruned.ckpt
+   recommended: True
+   width: 512
+   height: 512
+stable-diffusion-1.4:
+   description: The original Stable Diffusion version 1.4 weight file (4.27 GB)
+   repo_id: CompVis/stable-diffusion-v-1-4-original
+   config: v1-inference.yaml
+   file: sd-v1-4.ckpt
+   recommended: False
+   width: 512
+   height: 512
+waifu-diffusion-1.3:
+   description: Stable Diffusion 1.4 fine tuned on anime-styled images (4.27)
+   repo_id: hakurei/waifu-diffusion-v1-3
+   config: v1-inference.yaml
+   file: model-epoch09-float32.ckpt
+   recommended: False
+   width: 512
+   height: 512
+trinart-2.0:
+   description: An SD model finetuned with ~40,000 assorted high resolution manga/anime-style pictures (2.13 GB)
+   repo_id: naclbit/trinart_stable_diffusion_v2
+   config: v1-inference.yaml
+   file: trinart2_step95000.ckpt
+   recommended: False
+   width: 512
+   height: 512
+trinart_characters-1.0:
+   description: An SD model finetuned with 19.2M anime/manga style images (2.13 GB)
+   repo_id: naclbit/trinart_characters_19.2m_stable_diffusion_v1
+   config: v1-inference.yaml
+   file: trinart_characters_it4_v1.ckpt
+   recommended: False
+   width: 512
+   height: 512
+trinart_vae:
+   description: Custom autoencoder for trinart_characters
+   repo_id: naclbit/trinart_characters_19.2m_stable_diffusion_v1
+   config: VAE/trinart
+   file: autoencoder_fix_kl-f8-trinart_characters.ckpt
+   recommended: False
+   width: 512
+   height: 512
+papercut-1.0:
+   description: SD 1.5 fine-tuned for papercut art (use "PaperCut" in your prompts) (2.13 GB)
+   repo_id: Fictiverse/Stable_Diffusion_PaperCut_Model
+   config: v1-inference.yaml
+   file: PaperCut_v1.ckpt
+   recommended: False
+   width: 512
+   height: 512
+voxel_art-1.0:
+   description: Stable Diffusion trained on voxel art (use "VoxelArt" in your prompts) (4.27 GB)
+   repo_id: Fictiverse/Stable_Diffusion_VoxelArt_Model
+   config: v1-inference.yaml
+   file: VoxelArt_v1.ckpt
+   recommended: False
+   width: 512
+   height: 512

configs/models.yaml.example

@@ -0,0 +1,27 @@
+# This file describes the alternative machine learning models
+# available to InvokeAI script.
+#
+# To add a new model, follow the examples below. Each
+# model requires a model config file, a weights file,
+# and the width and height of the images it
+# was trained on.
+stable-diffusion-1.5:
+  description: The newest Stable Diffusion version 1.5 weight file (4.27 GB)
+  weights: models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt
+  config: configs/stable-diffusion/v1-inference.yaml
+  width: 512
+  height: 512
+  vae: ./models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  default: true
+stable-diffusion-1.4:
+  description: Stable Diffusion inference model version 1.4
+  config: configs/stable-diffusion/v1-inference.yaml
+  weights: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  width: 512
+  height: 512
+inpainting-1.5:
+  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+  config: configs/stable-diffusion/v1-inpainting-inference.yaml
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  description: RunwayML SD 1.5 model optimized for inpainting

configs/sd-concepts.txt

@@ -0,0 +1,803 @@
+sd-concepts-library/001glitch-core
+sd-concepts-library/2814-roth
+sd-concepts-library/3d-female-cyborgs
+sd-concepts-library/4tnght
+sd-concepts-library/80s-anime-ai
+sd-concepts-library/80s-anime-ai-being
+sd-concepts-library/852style-girl
+sd-concepts-library/8bit
+sd-concepts-library/8sconception
+sd-concepts-library/Aflac-duck
+sd-concepts-library/Akitsuki
+sd-concepts-library/Atako
+sd-concepts-library/Exodus-Styling
+sd-concepts-library/RINGAO
+sd-concepts-library/a-female-hero-from-the-legend-of-mir
+sd-concepts-library/a-hat-kid
+sd-concepts-library/a-tale-of-two-empires
+sd-concepts-library/aadhav-face
+sd-concepts-library/aavegotchi
+sd-concepts-library/abby-face
+sd-concepts-library/abstract-concepts
+sd-concepts-library/accurate-angel
+sd-concepts-library/agm-style-nao
+sd-concepts-library/aj-fosik
+sd-concepts-library/alberto-mielgo
+sd-concepts-library/alex-portugal
+sd-concepts-library/alex-thumbnail-object-2000-steps
+sd-concepts-library/aleyna-tilki
+sd-concepts-library/alf
+sd-concepts-library/alicebeta
+sd-concepts-library/alien-avatar
+sd-concepts-library/alisa
+sd-concepts-library/all-rings-albuns
+sd-concepts-library/altvent
+sd-concepts-library/altyn-helmet
+sd-concepts-library/amine
+sd-concepts-library/amogus
+sd-concepts-library/anders-zorn
+sd-concepts-library/angus-mcbride-style
+sd-concepts-library/animalve3-1500seq
+sd-concepts-library/anime-background-style
+sd-concepts-library/anime-background-style-v2
+sd-concepts-library/anime-boy
+sd-concepts-library/anime-girl
+sd-concepts-library/anyXtronXredshift
+sd-concepts-library/anya-forger
+sd-concepts-library/apex-wingman
+sd-concepts-library/apulian-rooster-v0-1
+sd-concepts-library/arcane-face
+sd-concepts-library/arcane-style-jv
+sd-concepts-library/arcimboldo-style
+sd-concepts-library/armando-reveron-style
+sd-concepts-library/armor-concept
+sd-concepts-library/arq-render
+sd-concepts-library/art-brut
+sd-concepts-library/arthur1
+sd-concepts-library/artist-yukiko-kanagai
+sd-concepts-library/arwijn
+sd-concepts-library/ashiok
+sd-concepts-library/at-wolf-boy-object
+sd-concepts-library/atm-ant
+sd-concepts-library/atm-ant-2
+sd-concepts-library/axe-tattoo
+sd-concepts-library/ayush-spider-spr
+sd-concepts-library/azura-from-vibrant-venture
+sd-concepts-library/ba-shiroko
+sd-concepts-library/babau
+sd-concepts-library/babs-bunny
+sd-concepts-library/babushork
+sd-concepts-library/backrooms
+sd-concepts-library/bad_Hub_Hugh
+sd-concepts-library/bada-club
+sd-concepts-library/baldi
+sd-concepts-library/baluchitherian
+sd-concepts-library/bamse
+sd-concepts-library/bamse-og-kylling
+sd-concepts-library/bee
+sd-concepts-library/beholder
+sd-concepts-library/beldam
+sd-concepts-library/belen
+sd-concepts-library/bella-goth
+sd-concepts-library/belle-delphine
+sd-concepts-library/bert-muppet
+sd-concepts-library/better-collage3
+sd-concepts-library/between2-mt-fade
+sd-concepts-library/birb-style
+sd-concepts-library/black-and-white-design
+sd-concepts-library/black-waifu
+sd-concepts-library/bloo
+sd-concepts-library/blue-haired-boy
+sd-concepts-library/blue-zombie
+sd-concepts-library/blue-zombiee
+sd-concepts-library/bluebey
+sd-concepts-library/bluebey-2
+sd-concepts-library/bobs-burgers
+sd-concepts-library/boissonnard
+sd-concepts-library/bonzi-monkey
+sd-concepts-library/borderlands
+sd-concepts-library/bored-ape-textual-inversion
+sd-concepts-library/boris-anderson
+sd-concepts-library/bozo-22
+sd-concepts-library/breakcore
+sd-concepts-library/brittney-williams-art
+sd-concepts-library/bruma
+sd-concepts-library/brunnya
+sd-concepts-library/buddha-statue
+sd-concepts-library/bullvbear
+sd-concepts-library/button-eyes
+sd-concepts-library/canadian-goose
+sd-concepts-library/canary-cap
+sd-concepts-library/cancer_style
+sd-concepts-library/captain-haddock
+sd-concepts-library/captainkirb
+sd-concepts-library/car-toy-rk
+sd-concepts-library/carasibana
+sd-concepts-library/carlitos-el-mago
+sd-concepts-library/carrascharacter
+sd-concepts-library/cartoona-animals
+sd-concepts-library/cat-toy
+sd-concepts-library/centaur
+sd-concepts-library/cgdonny1
+sd-concepts-library/cham
+sd-concepts-library/chandra-nalaar
+sd-concepts-library/char-con
+sd-concepts-library/character-pingu
+sd-concepts-library/cheburashka
+sd-concepts-library/chen-1
+sd-concepts-library/child-zombie
+sd-concepts-library/chillpill
+sd-concepts-library/chonkfrog
+sd-concepts-library/chop
+sd-concepts-library/christo-person
+sd-concepts-library/chuck-walton
+sd-concepts-library/chucky
+sd-concepts-library/chungus-poodl-pet
+sd-concepts-library/cindlop
+sd-concepts-library/collage-cutouts
+sd-concepts-library/collage14
+sd-concepts-library/collage3
+sd-concepts-library/collage3-hubcity
+sd-concepts-library/cologne
+sd-concepts-library/color-page
+sd-concepts-library/colossus
+sd-concepts-library/command-and-conquer-remastered-cameos
+sd-concepts-library/concept-art
+sd-concepts-library/conner-fawcett-style
+sd-concepts-library/conway-pirate
+sd-concepts-library/coop-himmelblau
+sd-concepts-library/coraline
+sd-concepts-library/cornell-box
+sd-concepts-library/cortana
+sd-concepts-library/covid-19-rapid-test
+sd-concepts-library/cow-uwu
+sd-concepts-library/cowboy
+sd-concepts-library/crazy-1
+sd-concepts-library/crazy-2
+sd-concepts-library/crb-portraits
+sd-concepts-library/crb-surrealz
+sd-concepts-library/crbart
+sd-concepts-library/crested-gecko
+sd-concepts-library/crinos-form-garou
+sd-concepts-library/cry-baby-style
+sd-concepts-library/crybaby-style-2-0
+sd-concepts-library/csgo-awp-object
+sd-concepts-library/csgo-awp-texture-map
+sd-concepts-library/cubex
+sd-concepts-library/cumbia-peruana
+sd-concepts-library/cute-bear
+sd-concepts-library/cute-cat
+sd-concepts-library/cute-game-style
+sd-concepts-library/cyberpunk-lucy
+sd-concepts-library/dabotap
+sd-concepts-library/dan-mumford
+sd-concepts-library/dan-seagrave-art-style
+sd-concepts-library/dark-penguin-pinguinanimations
+sd-concepts-library/darkpenguinanimatronic
+sd-concepts-library/darkplane
+sd-concepts-library/david-firth-artstyle
+sd-concepts-library/david-martinez-cyberpunk
+sd-concepts-library/david-martinez-edgerunners
+sd-concepts-library/david-moreno-architecture
+sd-concepts-library/daycare-attendant-sun-fnaf
+sd-concepts-library/ddattender
+sd-concepts-library/degods
+sd-concepts-library/degodsheavy
+sd-concepts-library/depthmap
+sd-concepts-library/depthmap-style
+sd-concepts-library/design
+sd-concepts-library/detectivedinosaur1
+sd-concepts-library/diaosu-toy
+sd-concepts-library/dicoo
+sd-concepts-library/dicoo2
+sd-concepts-library/dishonored-portrait-styles
+sd-concepts-library/disquieting-muses
+sd-concepts-library/ditko
+sd-concepts-library/dlooak
+sd-concepts-library/doc
+sd-concepts-library/doener-red-line-art
+sd-concepts-library/dog
+sd-concepts-library/dog-django
+sd-concepts-library/doge-pound
+sd-concepts-library/dong-ho
+sd-concepts-library/dong-ho2
+sd-concepts-library/doose-s-realistic-art-style
+sd-concepts-library/dq10-anrushia
+sd-concepts-library/dr-livesey
+sd-concepts-library/dr-strange
+sd-concepts-library/dragonborn
+sd-concepts-library/dreamcore
+sd-concepts-library/dreamy-painting
+sd-concepts-library/drive-scorpion-jacket
+sd-concepts-library/dsmuses
+sd-concepts-library/dtv-pkmn
+sd-concepts-library/dullboy-caricature
+sd-concepts-library/duranduran
+sd-concepts-library/durer-style
+sd-concepts-library/dyoudim-style
+sd-concepts-library/early-mishima-kurone
+sd-concepts-library/eastward
+sd-concepts-library/eddie
+sd-concepts-library/edgerunners-style
+sd-concepts-library/edgerunners-style-v2
+sd-concepts-library/el-salvador-style-style
+sd-concepts-library/elegant-flower
+sd-concepts-library/elspeth-tirel
+sd-concepts-library/eru-chitanda-casual
+sd-concepts-library/erwin-olaf-style
+sd-concepts-library/ettblackteapot
+sd-concepts-library/explosions-cat
+sd-concepts-library/eye-of-agamotto
+sd-concepts-library/f-22
+sd-concepts-library/facadeplace
+sd-concepts-library/fairy-tale-painting-style
+sd-concepts-library/fairytale
+sd-concepts-library/fang-yuan-001
+sd-concepts-library/faraon-love-shady
+sd-concepts-library/fasina
+sd-concepts-library/felps
+sd-concepts-library/female-kpop-singer
+sd-concepts-library/fergal-cat
+sd-concepts-library/filename-2
+sd-concepts-library/fileteado-porteno
+sd-concepts-library/final-fantasy-logo
+sd-concepts-library/fireworks-over-water
+sd-concepts-library/fish
+sd-concepts-library/flag-ussr
+sd-concepts-library/flatic
+sd-concepts-library/floral
+sd-concepts-library/fluid-acrylic-jellyfish-creatures-style-of-carl-ingram-art
+sd-concepts-library/fnf-boyfriend
+sd-concepts-library/fold-structure
+sd-concepts-library/fox-purple
+sd-concepts-library/fractal
+sd-concepts-library/fractal-flame
+sd-concepts-library/fractal-temple-style
+sd-concepts-library/frank-frazetta
+sd-concepts-library/franz-unterberger
+sd-concepts-library/freddy-fazbear
+sd-concepts-library/freefonix-style
+sd-concepts-library/furrpopasthetic
+sd-concepts-library/fursona
+sd-concepts-library/fzk
+sd-concepts-library/galaxy-explorer
+sd-concepts-library/ganyu-genshin-impact
+sd-concepts-library/garcon-the-cat
+sd-concepts-library/garfield-pizza-plush
+sd-concepts-library/garfield-pizza-plush-v2
+sd-concepts-library/gba-fe-class-cards
+sd-concepts-library/gba-pokemon-sprites
+sd-concepts-library/geggin
+sd-concepts-library/ggplot2
+sd-concepts-library/ghost-style
+sd-concepts-library/ghostproject-men
+sd-concepts-library/gibasachan-v0
+sd-concepts-library/gim
+sd-concepts-library/gio
+sd-concepts-library/giygas
+sd-concepts-library/glass-pipe
+sd-concepts-library/glass-prism-cube
+sd-concepts-library/glow-forest
+sd-concepts-library/goku
+sd-concepts-library/gram-tops
+sd-concepts-library/green-blue-shanshui
+sd-concepts-library/green-tent
+sd-concepts-library/grifter
+sd-concepts-library/grisstyle
+sd-concepts-library/grit-toy
+sd-concepts-library/gt-color-paint-2
+sd-concepts-library/gta5-artwork
+sd-concepts-library/guttestreker
+sd-concepts-library/gymnastics-leotard-v2
+sd-concepts-library/half-life-2-dog
+sd-concepts-library/handstand
+sd-concepts-library/hanfu-anime-style
+sd-concepts-library/happy-chaos
+sd-concepts-library/happy-person12345
+sd-concepts-library/happy-person12345-assets
+sd-concepts-library/harley-quinn
+sd-concepts-library/harmless-ai-1
+sd-concepts-library/harmless-ai-house-style-1
+sd-concepts-library/hd-emoji
+sd-concepts-library/heather
+sd-concepts-library/henjo-techno-show
+sd-concepts-library/herge-style
+sd-concepts-library/hiten-style-nao
+sd-concepts-library/hitokomoru-style-nao
+sd-concepts-library/hiyuki-chan
+sd-concepts-library/hk-bamboo
+sd-concepts-library/hk-betweenislands
+sd-concepts-library/hk-bicycle
+sd-concepts-library/hk-blackandwhite
+sd-concepts-library/hk-breakfast
+sd-concepts-library/hk-buses
+sd-concepts-library/hk-clouds
+sd-concepts-library/hk-goldbuddha
+sd-concepts-library/hk-goldenlantern
+sd-concepts-library/hk-hkisland
+sd-concepts-library/hk-leaves
+sd-concepts-library/hk-market
+sd-concepts-library/hk-oldcamera
+sd-concepts-library/hk-opencamera
+sd-concepts-library/hk-peach
+sd-concepts-library/hk-phonevax
+sd-concepts-library/hk-streetpeople
+sd-concepts-library/hk-vintage
+sd-concepts-library/hoi4
+sd-concepts-library/hoi4-leaders
+sd-concepts-library/homestuck-sprite
+sd-concepts-library/homestuck-troll
+sd-concepts-library/hours-sentry-fade
+sd-concepts-library/hours-style
+sd-concepts-library/hrgiger-drmacabre
+sd-concepts-library/huang-guang-jian
+sd-concepts-library/huatli
+sd-concepts-library/huayecai820-greyscale
+sd-concepts-library/hub-city
+sd-concepts-library/hubris-oshri
+sd-concepts-library/huckleberry
+sd-concepts-library/hydrasuit
+sd-concepts-library/i-love-chaos
+sd-concepts-library/ibere-thenorio
+sd-concepts-library/ic0n
+sd-concepts-library/ie-gravestone
+sd-concepts-library/ikea-fabler
+sd-concepts-library/illustration-style
+sd-concepts-library/ilo-kunst
+sd-concepts-library/ilya-shkipin
+sd-concepts-library/im-poppy
+sd-concepts-library/ina-art
+sd-concepts-library/indian-watercolor-portraits
+sd-concepts-library/indiana
+sd-concepts-library/ingmar-bergman
+sd-concepts-library/insidewhale
+sd-concepts-library/interchanges
+sd-concepts-library/inuyama-muneto-style-nao
+sd-concepts-library/irasutoya
+sd-concepts-library/iridescent-illustration-style
+sd-concepts-library/iridescent-photo-style
+sd-concepts-library/isabell-schulte-pv-pvii-3000steps
+sd-concepts-library/isabell-schulte-pviii-1-image-style
+sd-concepts-library/isabell-schulte-pviii-1024px-1500-steps-style
+sd-concepts-library/isabell-schulte-pviii-12tiles-3000steps-style
+sd-concepts-library/isabell-schulte-pviii-4-tiles-1-lr-3000-steps-style
+sd-concepts-library/isabell-schulte-pviii-4-tiles-3-lr-5000-steps-style
+sd-concepts-library/isabell-schulte-pviii-4tiles-500steps
+sd-concepts-library/isabell-schulte-pviii-4tiles-6000steps
+sd-concepts-library/isabell-schulte-pviii-style
+sd-concepts-library/isometric-tile-test
+sd-concepts-library/jacqueline-the-unicorn
+sd-concepts-library/james-web-space-telescope
+sd-concepts-library/jamie-hewlett-style
+sd-concepts-library/jamiels
+sd-concepts-library/jang-sung-rak-style
+sd-concepts-library/jetsetdreamcastcovers
+sd-concepts-library/jin-kisaragi
+sd-concepts-library/jinjoon-lee-they
+sd-concepts-library/jm-bergling-monogram
+sd-concepts-library/joe-mad
+sd-concepts-library/joe-whiteford-art-style
+sd-concepts-library/joemad
+sd-concepts-library/john-blanche
+sd-concepts-library/johnny-silverhand
+sd-concepts-library/jojo-bizzare-adventure-manga-lineart
+sd-concepts-library/jos-de-kat
+sd-concepts-library/junji-ito-artstyle
+sd-concepts-library/kaleido
+sd-concepts-library/kaneoya-sachiko
+sd-concepts-library/kanovt
+sd-concepts-library/kanv1
+sd-concepts-library/karan-gloomy
+sd-concepts-library/karl-s-lzx-1
+sd-concepts-library/kasumin
+sd-concepts-library/kawaii-colors
+sd-concepts-library/kawaii-girl-plus-object
+sd-concepts-library/kawaii-girl-plus-style
+sd-concepts-library/kawaii-girl-plus-style-v1-1
+sd-concepts-library/kay
+sd-concepts-library/kaya-ghost-assasin
+sd-concepts-library/ki
+sd-concepts-library/kinda-sus
+sd-concepts-library/kings-quest-agd
+sd-concepts-library/kiora
+sd-concepts-library/kira-sensei
+sd-concepts-library/kirby
+sd-concepts-library/klance
+sd-concepts-library/kodakvision500t
+sd-concepts-library/kogatan-shiny
+sd-concepts-library/kogecha
+sd-concepts-library/kojima-ayami
+sd-concepts-library/koko-dog
+sd-concepts-library/kuvshinov
+sd-concepts-library/kysa-v-style
+sd-concepts-library/laala-character
+sd-concepts-library/larrette
+sd-concepts-library/lavko
+sd-concepts-library/lazytown-stephanie
+sd-concepts-library/ldr
+sd-concepts-library/ldrs
+sd-concepts-library/led-toy
+sd-concepts-library/lego-astronaut
+sd-concepts-library/leica
+sd-concepts-library/leif-jones
+sd-concepts-library/lex
+sd-concepts-library/liliana
+sd-concepts-library/liliana-vess
+sd-concepts-library/liminal-spaces-2-0
+sd-concepts-library/liminalspaces
+sd-concepts-library/line-art
+sd-concepts-library/line-style
+sd-concepts-library/linnopoke
+sd-concepts-library/liquid-light
+sd-concepts-library/liqwid-aquafarmer
+sd-concepts-library/lizardman
+sd-concepts-library/loab-character
+sd-concepts-library/loab-style
+sd-concepts-library/lofa
+sd-concepts-library/logo-with-face-on-shield
+sd-concepts-library/lolo
+sd-concepts-library/looney-anime
+sd-concepts-library/lost-rapper
+sd-concepts-library/lphr-style
+sd-concepts-library/lucario
+sd-concepts-library/lucky-luke
+sd-concepts-library/lugal-ki-en
+sd-concepts-library/luinv2
+sd-concepts-library/lula-13
+sd-concepts-library/lumio
+sd-concepts-library/lxj-o4
+sd-concepts-library/m-geo
+sd-concepts-library/m-geoo
+sd-concepts-library/madhubani-art
+sd-concepts-library/mafalda-character
+sd-concepts-library/magic-pengel
+sd-concepts-library/malika-favre-art-style
+sd-concepts-library/manga-style
+sd-concepts-library/marbling-art
+sd-concepts-library/margo
+sd-concepts-library/marty
+sd-concepts-library/marty6
+sd-concepts-library/mass
+sd-concepts-library/masyanya
+sd-concepts-library/masyunya
+sd-concepts-library/mate
+sd-concepts-library/matthew-stone
+sd-concepts-library/mattvidpro
+sd-concepts-library/maurice-quentin-de-la-tour-style
+sd-concepts-library/maus
+sd-concepts-library/max-foley
+sd-concepts-library/mayor-richard-irvin
+sd-concepts-library/mechasoulall
+sd-concepts-library/medazzaland
+sd-concepts-library/memnarch-mtg
+sd-concepts-library/metagabe
+sd-concepts-library/meyoco
+sd-concepts-library/meze-audio-elite-headphones
+sd-concepts-library/midjourney-style
+sd-concepts-library/mikako-method
+sd-concepts-library/mikako-methodi2i
+sd-concepts-library/miko-3-robot
+sd-concepts-library/milady
+sd-concepts-library/mildemelwe-style
+sd-concepts-library/million-live-akane-15k
+sd-concepts-library/million-live-akane-3k
+sd-concepts-library/million-live-akane-shifuku-3k
+sd-concepts-library/million-live-spade-q-object-3k
+sd-concepts-library/million-live-spade-q-style-3k
+sd-concepts-library/minecraft-concept-art
+sd-concepts-library/mishima-kurone
+sd-concepts-library/mizkif
+sd-concepts-library/moeb-style
+sd-concepts-library/moebius
+sd-concepts-library/mokoko
+sd-concepts-library/mokoko-seed
+sd-concepts-library/monster-girl
+sd-concepts-library/monster-toy
+sd-concepts-library/monte-novo
+sd-concepts-library/moo-moo
+sd-concepts-library/morino-hon-style
+sd-concepts-library/moxxi
+sd-concepts-library/msg
+sd-concepts-library/mtg-card
+sd-concepts-library/mtl-longsky
+sd-concepts-library/mu-sadr
+sd-concepts-library/munch-leaks-style
+sd-concepts-library/museum-by-coop-himmelblau
+sd-concepts-library/muxoyara
+sd-concepts-library/my-hero-academia-style
+sd-concepts-library/my-mug
+sd-concepts-library/mycat
+sd-concepts-library/mystical-nature
+sd-concepts-library/naf
+sd-concepts-library/nahiri
+sd-concepts-library/namine-ritsu
+sd-concepts-library/naoki-saito
+sd-concepts-library/nard-style
+sd-concepts-library/naruto
+sd-concepts-library/natasha-johnston
+sd-concepts-library/nathan-wyatt
+sd-concepts-library/naval-portrait
+sd-concepts-library/nazuna
+sd-concepts-library/nebula
+sd-concepts-library/ned-flanders
+sd-concepts-library/neon-pastel
+sd-concepts-library/new-priests
+sd-concepts-library/nic-papercuts
+sd-concepts-library/nikodim
+sd-concepts-library/nissa-revane
+sd-concepts-library/nixeu
+sd-concepts-library/noggles
+sd-concepts-library/nomad
+sd-concepts-library/nouns-glasses
+sd-concepts-library/obama-based-on-xi
+sd-concepts-library/obama-self-2
+sd-concepts-library/og-mox-style
+sd-concepts-library/ohisashiburi-style
+sd-concepts-library/oleg-kuvaev
+sd-concepts-library/olli-olli
+sd-concepts-library/on-kawara
+sd-concepts-library/one-line-drawing
+sd-concepts-library/onepunchman
+sd-concepts-library/onzpo
+sd-concepts-library/orangejacket
+sd-concepts-library/ori
+sd-concepts-library/ori-toor
+sd-concepts-library/orientalist-art
+sd-concepts-library/osaka-jyo
+sd-concepts-library/osaka-jyo2
+sd-concepts-library/osrsmini2
+sd-concepts-library/osrstiny
+sd-concepts-library/other-mother
+sd-concepts-library/ouroboros
+sd-concepts-library/outfit-items
+sd-concepts-library/overprettified
+sd-concepts-library/owl-house
+sd-concepts-library/painted-by-silver-of-999
+sd-concepts-library/painted-by-silver-of-999-2
+sd-concepts-library/painted-student
+sd-concepts-library/painting
+sd-concepts-library/pantone-milk
+sd-concepts-library/paolo-bonolis
+sd-concepts-library/party-girl
+sd-concepts-library/pascalsibertin
+sd-concepts-library/pastelartstyle
+sd-concepts-library/paul-noir
+sd-concepts-library/pen-ink-portraits-bennorthen
+sd-concepts-library/phan
+sd-concepts-library/phan-s-collage
+sd-concepts-library/phc
+sd-concepts-library/phoenix-01
+sd-concepts-library/pineda-david
+sd-concepts-library/pink-beast-pastelae-style
+sd-concepts-library/pintu
+sd-concepts-library/pion-by-august-semionov
+sd-concepts-library/piotr-jablonski
+sd-concepts-library/pixel-mania
+sd-concepts-library/pixel-toy
+sd-concepts-library/pjablonski-style
+sd-concepts-library/plant-style
+sd-concepts-library/plen-ki-mun
+sd-concepts-library/pokemon-conquest-sprites
+sd-concepts-library/pool-test
+sd-concepts-library/poolrooms
+sd-concepts-library/poring-ragnarok-online
+sd-concepts-library/poutine-dish
+sd-concepts-library/princess-knight-art
+sd-concepts-library/progress-chip
+sd-concepts-library/puerquis-toy
+sd-concepts-library/purplefishli
+sd-concepts-library/pyramidheadcosplay
+sd-concepts-library/qpt-atrium
+sd-concepts-library/quiesel
+sd-concepts-library/r-crumb-style
+sd-concepts-library/rahkshi-bionicle
+sd-concepts-library/raichu
+sd-concepts-library/rail-scene
+sd-concepts-library/rail-scene-style
+sd-concepts-library/ralph-mcquarrie
+sd-concepts-library/ransom
+sd-concepts-library/rayne-weynolds
+sd-concepts-library/rcrumb-portraits-style
+sd-concepts-library/rd-chaos
+sd-concepts-library/rd-paintings
+sd-concepts-library/red-glasses
+sd-concepts-library/reeducation-camp
+sd-concepts-library/reksio-dog
+sd-concepts-library/rektguy
+sd-concepts-library/remert
+sd-concepts-library/renalla
+sd-concepts-library/repeat
+sd-concepts-library/retro-girl
+sd-concepts-library/retro-mecha-rangers
+sd-concepts-library/retropixelart-pinguin
+sd-concepts-library/rex-deno
+sd-concepts-library/rhizomuse-machine-bionic-sculpture
+sd-concepts-library/ricar
+sd-concepts-library/rickyart
+sd-concepts-library/rico-face
+sd-concepts-library/riker-doll
+sd-concepts-library/rikiart
+sd-concepts-library/rikiboy-art
+sd-concepts-library/rilakkuma
+sd-concepts-library/rishusei-style
+sd-concepts-library/rj-palmer
+sd-concepts-library/rl-pkmn-test
+sd-concepts-library/road-to-ruin
+sd-concepts-library/robertnava
+sd-concepts-library/roblox-avatar
+sd-concepts-library/roy-lichtenstein
+sd-concepts-library/ruan-jia
+sd-concepts-library/russian
+sd-concepts-library/s1m-naoto-ohshima
+sd-concepts-library/saheeli-rai
+sd-concepts-library/sakimi-style
+sd-concepts-library/salmonid
+sd-concepts-library/sam-yang
+sd-concepts-library/sanguo-guanyu
+sd-concepts-library/sas-style
+sd-concepts-library/scarlet-witch
+sd-concepts-library/schloss-mosigkau
+sd-concepts-library/scrap-style
+sd-concepts-library/scratch-project
+sd-concepts-library/sculptural-style
+sd-concepts-library/sd-concepts-library-uma-meme
+sd-concepts-library/seamless-ground
+sd-concepts-library/selezneva-alisa
+sd-concepts-library/sem-mac2n
+sd-concepts-library/senneca
+sd-concepts-library/seraphimmoonshadow-art
+sd-concepts-library/sewerslvt
+sd-concepts-library/she-hulk-law-art
+sd-concepts-library/she-mask
+sd-concepts-library/sherhook-painting
+sd-concepts-library/sherhook-painting-v2
+sd-concepts-library/shev-linocut
+sd-concepts-library/shigure-ui-style
+sd-concepts-library/shiny-polyman
+sd-concepts-library/shrunken-head
+sd-concepts-library/shu-doll
+sd-concepts-library/shvoren-style
+sd-concepts-library/sims-2-portrait
+sd-concepts-library/singsing
+sd-concepts-library/singsing-doll
+sd-concepts-library/sintez-ico
+sd-concepts-library/skyfalls
+sd-concepts-library/slm
+sd-concepts-library/smarties
+sd-concepts-library/smiling-friend-style
+sd-concepts-library/smooth-pencils
+sd-concepts-library/smurf-style
+sd-concepts-library/smw-map
+sd-concepts-library/society-finch
+sd-concepts-library/sorami-style
+sd-concepts-library/spider-gwen
+sd-concepts-library/spritual-monsters
+sd-concepts-library/stable-diffusion-conceptualizer
+sd-concepts-library/star-tours-posters
+sd-concepts-library/stardew-valley-pixel-art
+sd-concepts-library/starhavenmachinegods
+sd-concepts-library/sterling-archer
+sd-concepts-library/stretch-re1-robot
+sd-concepts-library/stuffed-penguin-toy
+sd-concepts-library/style-of-marc-allante
+sd-concepts-library/summie-style
+sd-concepts-library/sunfish
+sd-concepts-library/super-nintendo-cartridge
+sd-concepts-library/supitcha-mask
+sd-concepts-library/sushi-pixel
+sd-concepts-library/swamp-choe-2
+sd-concepts-library/t-skrang
+sd-concepts-library/takuji-kawano
+sd-concepts-library/tamiyo
+sd-concepts-library/tangles
+sd-concepts-library/tb303
+sd-concepts-library/tcirle
+sd-concepts-library/teelip-ir-landscape
+sd-concepts-library/teferi
+sd-concepts-library/tela-lenca
+sd-concepts-library/tela-lenca2
+sd-concepts-library/terraria-style
+sd-concepts-library/tesla-bot
+sd-concepts-library/test
+sd-concepts-library/test-epson
+sd-concepts-library/test2
+sd-concepts-library/testing
+sd-concepts-library/thalasin
+sd-concepts-library/thegeneral
+sd-concepts-library/thorneworks
+sd-concepts-library/threestooges
+sd-concepts-library/thunderdome-cover
+sd-concepts-library/thunderdome-covers
+sd-concepts-library/ti-junglepunk-v0
+sd-concepts-library/tili-concept
+sd-concepts-library/titan-robot
+sd-concepts-library/tnj
+sd-concepts-library/toho-pixel
+sd-concepts-library/tomcat
+sd-concepts-library/tonal1
+sd-concepts-library/tony-diterlizzi-s-planescape-art
+sd-concepts-library/towerplace
+sd-concepts-library/toy
+sd-concepts-library/toy-bonnie-plush
+sd-concepts-library/toyota-sera
+sd-concepts-library/transmutation-circles
+sd-concepts-library/trash-polka-artstyle
+sd-concepts-library/travis-bedel
+sd-concepts-library/trigger-studio
+sd-concepts-library/trust-support
+sd-concepts-library/trypophobia
+sd-concepts-library/ttte
+sd-concepts-library/tubby
+sd-concepts-library/tubby-cats
+sd-concepts-library/tudisco
+sd-concepts-library/turtlepics
+sd-concepts-library/type
+sd-concepts-library/ugly-sonic
+sd-concepts-library/uliana-kudinova
+sd-concepts-library/uma
+sd-concepts-library/uma-clean-object
+sd-concepts-library/uma-meme
+sd-concepts-library/uma-meme-style
+sd-concepts-library/uma-style-classic
+sd-concepts-library/unfinished-building
+sd-concepts-library/urivoldemort
+sd-concepts-library/uzumaki
+sd-concepts-library/valorantstyle
+sd-concepts-library/vb-mox
+sd-concepts-library/vcr-classique
+sd-concepts-library/venice
+sd-concepts-library/vespertine
+sd-concepts-library/victor-narm
+sd-concepts-library/vietstoneking
+sd-concepts-library/vivien-reid
+sd-concepts-library/vkuoo1
+sd-concepts-library/vraska
+sd-concepts-library/w3u
+sd-concepts-library/walter-wick-photography
+sd-concepts-library/warhammer-40k-drawing-style
+sd-concepts-library/waterfallshadow
+sd-concepts-library/wayne-reynolds-character
+sd-concepts-library/wedding
+sd-concepts-library/wedding-HandPainted
+sd-concepts-library/werebloops
+sd-concepts-library/wheatland
+sd-concepts-library/wheatland-arknight
+sd-concepts-library/wheelchair
+sd-concepts-library/wildkat
+sd-concepts-library/willy-hd
+sd-concepts-library/wire-angels
+sd-concepts-library/wish-artist-stile
+sd-concepts-library/wlop-style
+sd-concepts-library/wojak
+sd-concepts-library/wojaks-now
+sd-concepts-library/wojaks-now-now-now
+sd-concepts-library/xatu
+sd-concepts-library/xatu2
+sd-concepts-library/xbh
+sd-concepts-library/xi
+sd-concepts-library/xidiversity
+sd-concepts-library/xioboma
+sd-concepts-library/xuna
+sd-concepts-library/xyz
+sd-concepts-library/yb-anime
+sd-concepts-library/yerba-mate
+sd-concepts-library/yesdelete
+sd-concepts-library/yf21
+sd-concepts-library/yilanov2
+sd-concepts-library/yinit
+sd-concepts-library/yoji-shinkawa-style
+sd-concepts-library/yolandi-visser
+sd-concepts-library/yoshi
+sd-concepts-library/youpi2
+sd-concepts-library/youtooz-candy
+sd-concepts-library/yuji-himukai-style
+sd-concepts-library/zaney
+sd-concepts-library/zaneypixelz
+sd-concepts-library/zdenek-art
+sd-concepts-library/zero
+sd-concepts-library/zero-bottle
+sd-concepts-library/zero-suit-samus
+sd-concepts-library/zillertal-can
+sd-concepts-library/zizigooloo
+sd-concepts-library/zk
+sd-concepts-library/zoroark

configs/stable-diffusion/v1-finetune.yaml

@@ -0,0 +1,110 @@
+model:
+  base_learning_rate: 5.0e-03
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["sculpture"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 1
+    num_workers: 2
+    wrap: false
+    train:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 500
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True
+    max_steps: 4000000
+#    max_steps: 4000
+    

configs/stable-diffusion/v1-finetune_style.yaml

@@ -0,0 +1,103 @@
+model:
+  base_learning_rate: 5.0e-03
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["painting"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 16
+    wrap: false
+    train:
+      target: ldm.data.personalized_style.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized_style.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True

configs/stable-diffusion/v1-inference.yaml

@@ -0,0 +1,79 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['sculpture']
+        per_image_tokens: false
+        num_vectors_per_token: 8
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.WeightedFrozenCLIPEmbedder

configs/stable-diffusion/v1-inpainting-inference.yaml

@@ -0,0 +1,79 @@
+model:
+  base_learning_rate: 7.5e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: hybrid   # important
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    finetune_keys: null
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['sculpture']
+        per_image_tokens: false
+        num_vectors_per_token: 8
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 9  # 4 data + 4 downscaled image + 1 mask
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.WeightedFrozenCLIPEmbedder

configs/stable-diffusion/v1-m1-finetune.yaml

@@ -0,0 +1,110 @@
+model:
+  base_learning_rate: 5.0e-03
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['sculpture']
+        per_image_tokens: false
+        num_vectors_per_token: 6
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 1
+    num_workers: 2
+    wrap: false
+    train:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 500
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 5
+        increase_log_steps: False
+
+  trainer:
+    benchmark: False
+    max_steps: 6200
+#    max_steps: 4000
+    

coverage/.gitignore

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

docker-build/Dockerfile

@@ -0,0 +1,34 @@
+FROM ubuntu:22.10
+
+# use bash
+SHELL [ "/bin/bash", "-c" ]
+
+# Install necesarry packages
+RUN apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    build-essential \
+    gcc \
+    git \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    pip \
+    python3 \
+    python3-dev \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
+
+# set workdir and copy sources
+WORKDIR /invokeai
+ARG PIP_REQUIREMENTS=requirements-lin-cuda.txt
+COPY . ./environments-and-requirements/${PIP_REQUIREMENTS} ./
+
+# install requirements and link outputs folder
+RUN pip install \
+  --no-cache-dir \
+  -r ${PIP_REQUIREMENTS}
+
+# set Environment, Entrypoint and default CMD
+ENV INVOKEAI_ROOT /data
+ENTRYPOINT [ "python3", "scripts/invoke.py", "--outdir=/data/outputs" ]
+CMD [ "--web", "--host=0.0.0.0" ]

docker-build/build.sh

@@ -0,0 +1,49 @@
+#!/usr/bin/env bash
+set -e
+
+# IMPORTANT: You need to have a token on huggingface.co to be able to download the checkpoints!!!
+# configure values by using env when executing build.sh f.e. `env ARCH=aarch64 ./build.sh`
+
+source ./docker-build/env.sh \
+  || echo "please execute docker-build/build.sh from repository root" \
+  || exit 1
+
+pip_requirements=${PIP_REQUIREMENTS:-requirements-lin-cuda.txt}
+dockerfile=${INVOKE_DOCKERFILE:-docker-build/Dockerfile}
+
+# print the settings
+echo "You are using these values:"
+echo -e "Dockerfile:\t\t ${dockerfile}"
+echo -e "requirements:\t\t ${pip_requirements}"
+echo -e "volumename:\t\t ${volumename}"
+echo -e "arch:\t\t\t ${arch}"
+echo -e "platform:\t\t ${platform}"
+echo -e "invokeai_tag:\t\t ${invokeai_tag}\n"
+
+if [[ -n "$(docker volume ls -f name="${volumename}" -q)" ]]; then
+  echo "Volume already exists"
+  echo
+else
+  echo -n "createing docker volume "
+  docker volume create "${volumename}"
+fi
+
+# Build Container
+docker build \
+  --platform="${platform}" \
+  --tag="${invokeai_tag}" \
+  --build-arg="PIP_REQUIREMENTS=${pip_requirements}" \
+  --file="${dockerfile}" \
+  .
+
+docker run \
+  --rm \
+  --platform="$platform" \
+  --name="$project_name" \
+  --hostname="$project_name" \
+  --mount="source=$volumename,target=/data" \
+  --mount="type=bind,source=$HOME/.huggingface,target=/root/.huggingface" \
+  --env="HUGGINGFACE_TOKEN=${HUGGINGFACE_TOKEN}" \
+  --entrypoint="python3" \
+  "${invokeai_tag}" \
+  scripts/configure_invokeai.py --yes

docker-build/env.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+project_name=${PROJECT_NAME:-invokeai}
+volumename=${VOLUMENAME:-${project_name}_data}
+arch=${ARCH:-x86_64}
+platform=${PLATFORM:-Linux/${arch}}
+invokeai_tag=${INVOKEAI_TAG:-${project_name}:${arch}}
+
+export project_name
+export volumename
+export arch
+export platform
+export invokeai_tag

docker-build/run.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+set -e
+
+source ./docker-build/env.sh || echo "please run from repository root" || exit 1
+
+docker run \
+  --interactive \
+  --tty \
+  --rm \
+  --platform="$platform" \
+  --name="$project_name" \
+  --hostname="$project_name" \
+  --mount="source=$volumename,target=/data" \
+  --publish=9090:9090 \
+  "$invokeai_tag" ${1:+$@}

docker/.env.sample

@@ -1,15 +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,
-## in addition to the examples below.
-
-# 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=
-
-# Get this value from your HuggingFace account settings page.
-# HUGGING_FACE_HUB_TOKEN=
-
-## optional variables specific to the docker setup.
-# GPU_DRIVER=cuda # or rocm
-# CONTAINER_UID=1000

docker/Dockerfile

@@ -1,124 +0,0 @@
-# syntax=docker/dockerfile:1.4
-
-## Builder stage
-
-FROM library/ubuntu:23.04 AS builder
-
-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-venv \
-        python3-pip \
-        build-essential
-
-ENV INVOKEAI_SRC=/opt/invokeai
-ENV VIRTUAL_ENV=/opt/venv/invokeai
-
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-ARG TORCH_VERSION=2.1.0
-ARG TORCHVISION_VERSION=0.16
-ARG GPU_DRIVER=cuda
-ARG TARGETPLATFORM="linux/amd64"
-# unused but available
-ARG BUILDPLATFORM
-
-WORKDIR ${INVOKEAI_SRC}
-
-# 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="--index-url https://download.pytorch.org/whl/rocm5.6"; \
-    else \
-        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
-    fi &&\
-    pip install $extra_index_url_arg \
-        torch==$TORCH_VERSION \
-        torchvision==$TORCHVISION_VERSION
-
-# Install the local package.
-# Editable mode helps use the same image for development:
-# the local working copy can be bind-mounted into the image
-# at path defined by ${INVOKEAI_SRC}
-COPY invokeai ./invokeai
-COPY pyproject.toml ./
-RUN --mount=type=cache,target=/root/.cache/pip \
-    # xformers + triton fails to install on arm64
-    if [ "$GPU_DRIVER" = "cuda" ] && [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
-        pip install -e ".[xformers]"; \
-    else \
-        pip install -e "."; \
-    fi
-
-# #### Build the Web UI ------------------------------------
-
-FROM node:18 AS web-builder
-WORKDIR /build
-COPY invokeai/frontend/web/ ./
-RUN --mount=type=cache,target=/usr/lib/node_modules \
-    npm install --include dev
-RUN --mount=type=cache,target=/usr/lib/node_modules \
-    yarn vite build
-
-
-#### Runtime stage ---------------------------------------
-
-FROM library/ubuntu:23.04 AS runtime
-
-ARG DEBIAN_FRONTEND=noninteractive
-ENV PYTHONUNBUFFERED=1
-ENV PYTHONDONTWRITEBYTECODE=1
-
-RUN apt update && apt install -y --no-install-recommends \
-        git \
-        curl \
-        vim \
-        tmux \
-        ncdu \
-        iotop \
-        bzip2 \
-        gosu \
-        magic-wormhole \
-        libglib2.0-0 \
-        libgl1-mesa-glx \
-        python3-venv \
-        python3-pip \
-        build-essential \
-        libopencv-dev \
-        libstdc++-10-dev &&\
-    apt-get clean && apt-get autoclean
-
-
-ENV INVOKEAI_SRC=/opt/invokeai
-ENV VIRTUAL_ENV=/opt/venv/invokeai
-ENV INVOKEAI_ROOT=/invokeai
-ENV PATH="$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 ${INVOKEAI_SRC}
-
-# build patchmatch
-RUN cd /usr/lib/$(uname -p)-linux-gnu/pkgconfig/ && ln -sf opencv4.pc opencv.pc
-RUN python3 -c "from patchmatch import patch_match"
-
-RUN mkdir -p ${INVOKEAI_ROOT} && chown -R 1000:1000 ${INVOKEAI_ROOT}
-
-COPY docker/docker-entrypoint.sh ./
-ENTRYPOINT ["/opt/invokeai/docker-entrypoint.sh"]
-CMD ["invokeai-web", "--host", "0.0.0.0"]

docker/README.md

@@ -1,78 +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://docs.docker.com/compose/install/linux/#install-using-the-repository).
-    - 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 (values are optional, but setting `INVOKEAI_ROOT` is highly recommended):
-
-```bash
-INVOKEAI_ROOT=/Volumes/WorkDrive/invokeai
-HUGGINGFACE_TOKEN=the_actual_token
-CONTAINER_UID=1000
-GPU_DRIVER=cuda
-```
-
-Any environment variables supported by InvokeAI can be set here - please see the [Configuration docs](https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/) for further detail.
-
-## Even Moar Customizing!
-
-See the `docker-compose.yml` 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
-
-```yaml
-command:
-  - invokeai-configure
-  - --yes
-```
-
-Or install models:
-
-```yaml
-command:
-  - invokeai-model-install
-```