update version number (#2199)

* installer tweaks in preparation for v2.2.5

- pin numpy to 1.23.* to avoid requirements conflict with numba
- update.sh and update.bat now accept a tag or branch string, not a URL
- update scripts download latest requirements-base before updating.

* update.bat.in debugged and working

* update pulls from "latest" now

* bump version number

* fix permissions on create_installer.sh

* give Linux user option of installing ROCm or CUDA

* rc2.2.5 (install.sh) relative path fixes (#2155)

* (installer) fix bug in resolution of relative paths in linux install script

point installer at 2.2.5-rc1

selecting ~/Data/myapps/ as location  would create a ./~/Data/myapps
instead of expanding the ~/ to the value of ${HOME}

also, squash the trailing slash in path, if it was entered by the user

* (installer) add option to automatically start the app after install

also: when exiting, print the command to get back into the app

* remove extraneous whitespace

* model_cache applies rootdir to config path

* bring installers up to date with 2.2.5-rc2

* bump rc version

* create_installer now adds version number

* rebuild frontend

* bump rc#

* add locales to frontend dist package

- bump to patchlevel 6

* bump patchlevel

* use invoke-ai version of GFPGAN

- This version is very slightly modified to allow weights files
  to be pre-downloaded by the configure script.

* fix formatting error during startup

* bump patch level

* workaround #2 for GFPGAN facexlib() weights downloading

* bump patch

* ready for merge and release

* remove extraneous comment

* set PYTORCH_ENABLE_MPS_FALLBACK directly in invoke.py

Co-authored-by: Eugene Brodsky <ebr@users.noreply.github.com>

.dockerignore

@@ -0,0 +1,19 @@
+*
+!backend
+!environments-and-requirements
+!frontend
+!ldm
+!main.py
+!scripts
+!server
+!static
+!setup.py
+
+# Guard against pulling in any models that might exist in the directory tree
+**/*.pt*
+
+# unignore configs, but only ignore the custom models.yaml, in case it exists
+!configs
+configs/models.yaml
+
+**/__pycache__

.editorconfig

@@ -0,0 +1,12 @@
+# All files
+[*]
+charset = utf-8
+end_of_line = lf
+indent_size = 2
+indent_style = space
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+# Python
+[*.py]
+indent_size = 4

.gitattributes

@@ -1,4 +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

.github/CODEOWNERS

@@ -0,0 +1,7 @@
+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

@@ -0,0 +1,102 @@
+name: 🐞 Bug Report
+
+description: File a bug report
+
+title: '[bug]: '
+
+labels: ['bug']
+
+# assignees:
+#   - moderator_bot
+#   - lstein
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this Bug Report!
+
+  - type: checkboxes
+    attributes:
+      label: Is there an existing issue for this?
+      description: |
+        Please use the [search function](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
+        irst to see if an issue already exists for the bug you encountered.
+      options:
+        - label: I have searched the existing issues
+          required: true
+
+  - type: markdown
+    attributes:
+      value: __Describe your environment__
+
+  - type: dropdown
+    id: os_dropdown
+    attributes:
+      label: OS
+      description: Which operating System did you use when the bug occured
+      multiple: false
+      options:
+        - 'Linux'
+        - 'Windows'
+        - 'macOS'
+    validations:
+      required: true
+
+  - type: dropdown
+    id: gpu_dropdown
+    attributes:
+      label: GPU
+      description: Which kind of Graphic-Adapter is your System using
+      multiple: false
+      options:
+        - 'cuda'
+        - 'amd'
+        - 'mps'
+        - 'cpu'
+    validations:
+      required: true
+
+  - type: input
+    id: vram
+    attributes:
+      label: VRAM
+      description: Size of the VRAM if known
+      placeholder: 8GB
+    validations:
+      required: false
+
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What happened?
+      description: |
+        Briefly describe what happened, what you expected to happen and how to reproduce this bug.
+      placeholder: When using the webinterface and right-clicking on button X instead of the popup-menu there error Y appears
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Screenshots
+      description: If applicable, add screenshots to help explain your problem
+      placeholder: this is what the result looked like <screenshot>
+    validations:
+      required: false
+
+  - type: textarea
+    attributes:
+      label: Additional context
+      description: Add any other context about the problem here
+      placeholder: Only happens when there is full moon and Friday the 13th on Christmas Eve 🎅🏻
+    validations:
+      required: false
+
+  - type: input
+    id: contact
+    attributes:
+      label: Contact Details
+      description: __OPTIONAL__ How can we get in touch with you if we need more info (besides this issue)?
+      placeholder: ex. email@example.com, discordname, twitter, ...
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/FEATURE_REQUEST.yml

@@ -0,0 +1,56 @@
+name: Feature Request
+description: Commit a idea or Request a new feature
+title: '[enhancement]: '
+labels: ['enhancement']
+# assignees:
+#   - lstein
+#   - tildebyte
+body:
+  - type: markdown
+    attributes:
+      value: |
+        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 simmilar issue already exists for the feature you want to request
+      options:
+        - label: I have searched the existing issues
+          required: true
+
+  - type: input
+    id: contact
+    attributes:
+      label: Contact Details
+      description: __OPTIONAL__ How could we get in touch with you if we need more info (besides this issue)?
+      placeholder: ex. email@example.com, discordname, twitter, ...
+    validations:
+      required: false
+
+  - type: textarea
+    id: whatisexpected
+    attributes:
+      label: What should this feature add?
+      description: Please try to explain the functionality this feature should add
+      placeholder: |
+        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
+
+  - type: textarea
+    attributes:
+      label: Alternatives
+      description: Describe alternatives you've considered
+      placeholder: A clear and concise description of any alternative solutions or features you've considered.
+
+  - type: textarea
+    attributes:
+      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>

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,36 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Describe your environment**
-- GPU: [cuda/amd/mps/cpu]
-- VRAM: [if known]
-- CPU arch: [x86/arm]
-- OS: [Linux/Windows/macOS]
-- Python: [Anaconda/miniconda/miniforge/pyenv/other (explain)]
-- Branch: [if `git status` says anything other than "On branch main" paste it here]
-- Commit: [run `git show` and paste the line that starts with "Merge" here]
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Additional context**
-Add any other context about the problem here.

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,14 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Project-Documentation
+    url: https://invoke-ai.github.io/InvokeAI/
+    about: Should be your first place to go when looking for manuals/FAQs regarding our InvokeAI Toolkit
+  - name: Discord
+    url: https://discord.gg/ZmtBAhwWhy
+    about: Our Discord Community could maybe help you out via live-chat
+  - name: GitHub Community Support
+    url: https://github.com/orgs/community/discussions
+    about: Please ask and answer questions regarding the GitHub Platform here.
+  - name: GitHub Security Bug Bounty
+    url: https://bounty.github.com/
+    about: Please report security vulnerabilities of the GitHub Platform here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,20 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/workflows/build-cloud-img.yml

@@ -0,0 +1,87 @@
+name: Build and push cloud image
+on:
+  workflow_dispatch:
+  # push:
+  #   branches:
+  #   - main
+  #   tags:
+  #     - v*
+  # # we will NOT push the image on pull requests, only test buildability.
+  # pull_request:
+  #   branches:
+  #   - main
+
+permissions:
+  contents: read
+  packages: write
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  docker:
+    strategy:
+      fail-fast: false
+      matrix:
+        arch:
+        - x86_64
+        # requires resolving a patchmatch issue
+        # - aarch64
+    runs-on: ubuntu-latest
+    name: ${{ matrix.arch }}
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v3
+
+    - name: Set up QEMU
+      uses: docker/setup-qemu-action@v2
+      if: matrix.arch == 'aarch64'
+
+    - name: Docker meta
+      id: meta
+      uses: docker/metadata-action@v4
+      with:
+        images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+        # see https://github.com/docker/metadata-action
+        # will push the following tags:
+        # :edge
+        # :main (+ any other branches enabled in the workflow)
+        # :<tag>
+        # :1.2.3 (for semver tags)
+        # :1.2 (for semver tags)
+        # :<sha>
+        tags: |
+          type=edge,branch=main
+          type=ref,event=branch
+          type=ref,event=tag
+          type=semver,pattern={{version}}
+          type=semver,pattern={{major}}.{{minor}}
+          type=sha
+        # suffix image tags with architecture
+        flavor: |
+          latest=auto
+          suffix=-${{ matrix.arch }},latest=true
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2
+
+    # do not login to container registry on PRs
+    - if: github.event_name != 'pull_request'
+      name: Docker login
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Build and push cloud image
+      uses: docker/build-push-action@v3
+      with:
+        context: .
+        file: docker-build/Dockerfile.cloud
+        platforms: Linux/${{ matrix.arch }}
+        # do not push the image on PRs
+        push: false
+        tags: ${{ steps.meta.outputs.tags }}
+        labels: ${{ steps.meta.outputs.labels }}

.github/workflows/build-container.yml

@@ -0,0 +1,74 @@
+name: build container image
+on:
+  push:
+    branches:
+      - 'main'
+
+jobs:
+  docker:
+    strategy:
+      fail-fast: false
+      matrix:
+        registry:
+          - ghcr.io
+        flavor:
+          - amd
+          - cuda
+          # - cloud
+        include:
+          - flavor: amd
+            pip-requirements: requirements-lin-amd.txt
+            dockerfile: docker-build/Dockerfile
+            platforms: linux/amd64,linux/arm64
+          - flavor: cuda
+            pip-requirements: requirements-lin-cuda.txt
+            dockerfile: docker-build/Dockerfile
+            platforms: linux/amd64,linux/arm64
+          # - flavor: cloud
+          #   pip-requirements: requirements-lin-cuda.txt
+          #   dockerfile: docker-build/Dockerfile.cloud
+          #   platforms: linux/amd64
+    runs-on: ubuntu-latest
+    name: ${{ matrix.flavor }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: ${{ matrix.registry }}/${{ github.repository }}-${{ matrix.flavor }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=sha
+          flavor: |
+            latest=true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - if: github.event_name != 'pull_request'
+        name: Docker login
+        uses: docker/login-action@v2
+        with:
+          registry: ${{ matrix.registry }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build container
+        uses: docker/build-push-action@v3
+        with:
+          context: .
+          file: ${{ matrix.dockerfile }}
+          platforms: ${{ matrix.platforms }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          build-args: pip_requirements=${{ matrix.pip-requirements }}

.github/workflows/create-caches.yml

@@ -1,70 +0,0 @@
-name: Create Caches
-on:
-  workflow_dispatch
-jobs:
-  build:
-    strategy:
-      matrix:
-        os: [ ubuntu-latest, macos-12 ]
-    name: Create Caches on ${{ matrix.os }} conda
-    runs-on: ${{ matrix.os }}
-    steps:
-      - name: Set platform variables
-        id: vars
-        run: |
-            if [ "$RUNNER_OS" = "macOS" ]; then
-                echo "::set-output name=ENV_FILE::environment-mac.yml"
-                echo "::set-output name=PYTHON_BIN::/usr/local/miniconda/envs/ldm/bin/python"
-            elif [ "$RUNNER_OS" = "Linux" ]; then
-                echo "::set-output name=ENV_FILE::environment.yml"
-                echo "::set-output name=PYTHON_BIN::/usr/share/miniconda/envs/ldm/bin/python"
-            fi
-      - name: Checkout sources
-        uses: actions/checkout@v3
-      - name: Use Cached Stable Diffusion v1.4 Model
-        id: cache-sd-v1-4
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-sd-v1-4
-        with:
-          path: models/ldm/stable-diffusion-v1/model.ckpt
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}
-      - name: Download Stable Diffusion v1.4 Model
-        if: ${{ steps.cache-sd-v1-4.outputs.cache-hit != 'true' }}
-        run: |
-          if [ ! -e models/ldm/stable-diffusion-v1 ]; then
-              mkdir -p models/ldm/stable-diffusion-v1
-          fi
-          if [ ! -e models/ldm/stable-diffusion-v1/model.ckpt ]; then
-            curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
-          fi
-      - name: Use Cached Dependencies
-        id: cache-conda-env-ldm
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-conda-env-ldm
-        with:
-          path: ~/.conda/envs/ldm
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(steps.vars.outputs.ENV_FILE) }}
-      - name: Install Dependencies
-        if: ${{ steps.cache-conda-env-ldm.outputs.cache-hit != 'true' }}
-        run: |
-          conda env create -f ${{ steps.vars.outputs.ENV_FILE }}
-      - name: Use Cached Huggingface and Torch models
-        id: cache-huggingface-torch
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-huggingface-torch
-        with:
-          path: ~/.cache
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ hashFiles('scripts/preload_models.py') }}
-      - name: Download Huggingface and Torch models
-        if: ${{ steps.cache-huggingface-torch.outputs.cache-hit != 'true' }}
-        run: |
-          ${{ steps.vars.outputs.PYTHON_BIN }} scripts/preload_models.py

.github/workflows/lint-frontend.yml

@@ -0,0 +1,28 @@
+name: Lint frontend
+
+on:
+  pull_request:
+    paths:
+      - 'frontend/**'
+  push:
+    paths:
+      - 'frontend/**'
+
+defaults:
+  run:
+    working-directory: frontend
+
+jobs:
+  lint-frontend:
+    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 tsc'
+      - run: 'yarn run madge'
+      - run: 'yarn run lint --max-warnings=0'
+      - run: 'yarn run prettier --check'

.github/workflows/mkdocs-flow.yml

@@ -1,28 +0,0 @@
-name: Deploy
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-    branches:
-      - main
-jobs:
-  build:
-    name: Deploy docs to GitHub Pages
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-      - name: Build
-        uses: Tiryoh/actions-mkdocs@v0
-        with:
-          mkdocs_version: 'latest' # option
-          requirements: '/requirements-mkdocs.txt' # option
-          configfile: '/mkdocs.yml' # option
-      - name: Deploy
-        uses: peaceiris/actions-gh-pages@v3
-        with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          publish_dir: ./site

.github/workflows/mkdocs-material.yml

@@ -0,0 +1,40 @@
+name: mkdocs-material
+on:
+  push:
+    branches:
+      - 'main'
+      - 'development'
+
+jobs:
+  mkdocs-material:
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout sources
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: setup python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: install requirements
+        run: |
+          python -m \
+            pip install -r docs/requirements-mkdocs.txt
+
+      - name: confirm buildability
+        run: |
+          python -m \
+            mkdocs build \
+            --clean \
+            --verbose
+
+      - name: deploy to gh-pages
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: |
+          python -m \
+            mkdocs gh-deploy \
+            --clean \
+            --force

.github/workflows/pyflakes.yml

@@ -0,0 +1,19 @@
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+      - development
+      - 'release-candidate-*'
+
+jobs:
+  pyflakes:
+    name: runner / pyflakes
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: pyflakes
+        uses: reviewdog/action-pyflakes@v1
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          reporter: github-pr-review

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

@@ -1,97 +0,0 @@
-name: Test Dream with Conda
-on:
-  push:
-    branches:
-      - 'main'
-      - 'development'
-jobs:
-  os_matrix:
-    strategy:
-      matrix:
-        os: [ ubuntu-latest, macos-12 ]
-    name: Test dream.py on ${{ matrix.os }} with conda
-    runs-on: ${{ matrix.os }}
-    steps:
-      - run: |
-          echo The PR was merged
-      - name: Set platform variables
-        id: vars
-        run: |
-          # Note, can't "activate" via github action; specifying the env's python has the same effect
-          if [ "$RUNNER_OS" = "macOS" ]; then
-              echo "::set-output name=ENV_FILE::environment-mac.yml"
-              echo "::set-output name=PYTHON_BIN::/usr/local/miniconda/envs/ldm/bin/python"
-          elif [ "$RUNNER_OS" = "Linux" ]; then
-              echo "::set-output name=ENV_FILE::environment.yml"
-              echo "::set-output name=PYTHON_BIN::/usr/share/miniconda/envs/ldm/bin/python"
-          fi
-      - name: Checkout sources
-        uses: actions/checkout@v3
-      - name: Use Cached Stable Diffusion v1.4 Model
-        id: cache-sd-v1-4
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-sd-v1-4
-        with:
-          path: models/ldm/stable-diffusion-v1/model.ckpt
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}
-      - name: Download Stable Diffusion v1.4 Model
-        if: ${{ steps.cache-sd-v1-4.outputs.cache-hit != 'true' }}
-        run: |
-          if [ ! -e models/ldm/stable-diffusion-v1 ]; then
-              mkdir -p models/ldm/stable-diffusion-v1
-          fi
-          if [ ! -e models/ldm/stable-diffusion-v1/model.ckpt ]; then
-            curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
-          fi
-      - name: Use Cached Dependencies
-        id: cache-conda-env-ldm
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-conda-env-ldm
-        with:
-          path: ~/.conda/envs/ldm
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(steps.vars.outputs.ENV_FILE) }}
-      - name: Install Dependencies
-        if: ${{ steps.cache-conda-env-ldm.outputs.cache-hit != 'true' }}
-        run: |
-          conda env create -f ${{ steps.vars.outputs.ENV_FILE }}
-      - name: Use Cached Huggingface and Torch models
-        id: cache-hugginface-torch
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-hugginface-torch
-        with:
-          path: ~/.cache
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ hashFiles('scripts/preload_models.py') }}
-      - name: Download Huggingface and Torch models
-        if: ${{ steps.cache-hugginface-torch.outputs.cache-hit != 'true' }}
-        run: |
-          ${{ steps.vars.outputs.PYTHON_BIN }} scripts/preload_models.py
-#       - name: Run tmate
-#         uses: mxschmitt/action-tmate@v3
-#         timeout-minutes: 30
-      - name: Run the tests
-        run: |
-          # Note, can't "activate" via github action; specifying the env's python has the same effect
-          if [ $(uname) = "Darwin" ]; then
-              export PYTORCH_ENABLE_MPS_FALLBACK=1
-          fi
-          # Utterly hacky, but I don't know how else to do this
-          if [[ ${{ github.ref }} == 'refs/heads/master' ]]; then
-            time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/dream.py --from_file tests/preflight_prompts.txt
-          elif [[ ${{ github.ref }} == 'refs/heads/development' ]]; then
-            time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/dream.py --from_file tests/dev_prompts.txt
-          fi
-          mkdir -p outputs/img-samples
-      - name: Archive results
-        uses: actions/upload-artifact@v3
-        with:
-          name: results
-          path: outputs/img-samples

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

@@ -0,0 +1,161 @@
+name: Test invoke.py
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    branches:
+      - 'main'
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+      - 'converted_to_draft'
+
+concurrency:
+   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+   cancel-in-progress: true
+
+jobs:
+  fail_if_pull_request_is_draft:
+    if: github.event.pull_request.draft == true
+    runs-on: ubuntu-22.04
+    steps:
+    - name: Fails in order to indicate that pull request needs to be marked as ready to review and unit tests workflow needs to pass.
+      run: exit 1
+
+  matrix:
+    if: github.event.pull_request.draft == false
+    strategy:
+      matrix:
+        stable-diffusion-model:
+          - 'stable-diffusion-1.5'
+        environment-yaml:
+          - environment-lin-amd.yml
+          - environment-lin-cuda.yml
+          - environment-mac.yml
+          - environment-win-cuda.yml
+        include:
+          - environment-yaml: environment-lin-amd.yml
+            os: ubuntu-22.04
+            curl-command: curl
+            github-env: $GITHUB_ENV
+            default-shell: bash -l {0}
+          - environment-yaml: environment-lin-cuda.yml
+            os: ubuntu-22.04
+            curl-command: curl
+            github-env: $GITHUB_ENV
+            default-shell: bash -l {0}
+          - environment-yaml: environment-mac.yml
+            os: macos-12
+            curl-command: curl
+            github-env: $GITHUB_ENV
+            default-shell: bash -l {0}
+          - environment-yaml: environment-win-cuda.yml
+            os: windows-2022
+            curl-command: curl.exe
+            github-env: $env:GITHUB_ENV
+            default-shell: pwsh
+          - 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" >> ${{ matrix.github-env }}
+
+      - name: set test prompt to development branch validation
+        if: ${{ github.ref == 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/dev_prompts.txt" >> ${{ matrix.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" >> ${{ matrix.github-env }}
+
+      - name: Use Cached Stable Diffusion Model
+        id: cache-sd-model
+        uses: actions/cache@v3
+        env:
+          cache-name: cache-${{ 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 }}"
+          ${{ matrix.curl-command }} -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 --skip-sd-weights --yes
+
+      - name: cat invokeai.init
+        id: cat-invokeai
+        run: cat ${{ env.INVOKEAI_ROOT }}/invokeai.init
+
+      - name: Run the tests
+        id: run-tests
+        if: matrix.os != 'windows-2022'
+        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
+        if: matrix.os != 'windows-2022'
+        run: |
+          mkdir -p outputs/img-samples
+          conda env export --name ${{ env.CONDA_ENV_NAME }} > ${{ env.INVOKEAI_ROOT }}/outputs/environment-${{ runner.os }}-${{ runner.arch }}.yml
+
+      - name: Archive results
+        if: matrix.os != 'windows-2022'
+        id: archive-results
+        uses: actions/upload-artifact@v3
+        with:
+          name: results_${{ matrix.requirements-file }}_${{ matrix.python-version }}
+          path: ${{ env.INVOKEAI_ROOT }}/outputs

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

@@ -0,0 +1,144 @@
+name: Test invoke.py pip
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    branches:
+      - 'main'
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+      - 'converted_to_draft'
+
+concurrency:
+   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+   cancel-in-progress: true
+
+jobs:
+  fail_if_pull_request_is_draft:
+    if: github.event.pull_request.draft == true
+    runs-on: ubuntu-18.04
+    steps:
+    - name: Fails in order to indicate that pull request needs to be marked as ready to review and unit tests workflow needs to pass.
+      run: exit 1
+  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
+          - requirements-win-colab-cuda.txt
+        python-version:
+          # - '3.9'
+          - '3.10'
+        include:
+          - requirements-file: requirements-lin-cuda.txt
+            os: ubuntu-22.04
+            curl-command: curl
+            github-env: $GITHUB_ENV
+          - requirements-file: requirements-lin-amd.txt
+            os: ubuntu-22.04
+            curl-command: curl
+            github-env: $GITHUB_ENV
+          - requirements-file: requirements-mac-mps-cpu.txt
+            os: macOS-12
+            curl-command: curl
+            github-env: $GITHUB_ENV
+          - requirements-file: requirements-win-colab-cuda.txt
+            os: windows-2022
+            curl-command: curl.exe
+            github-env: $env:GITHUB_ENV
+          - 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: ${{ matrix.os }}
+    steps:
+      - name: Checkout sources
+        id: checkout-sources
+        uses: actions/checkout@v3
+
+      - name: set INVOKEAI_ROOT Windows
+        if: matrix.os == 'windows-2022'
+        run: |
+          echo "INVOKEAI_ROOT=${{ github.workspace }}\invokeai" >> ${{ matrix.github-env }}
+          echo "INVOKEAI_OUTDIR=${{ github.workspace }}\invokeai\outputs" >> ${{ matrix.github-env }}
+
+      - name: set INVOKEAI_ROOT others
+        if: matrix.os != 'windows-2022'
+        run: |
+          echo "INVOKEAI_ROOT=${{ github.workspace }}/invokeai" >> ${{ matrix.github-env }}
+          echo "INVOKEAI_OUTDIR=${{ github.workspace }}/invokeai/outputs" >> ${{ matrix.github-env }}
+
+      - 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: ${{ github.ref == 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> ${{ matrix.github-env }}
+
+      - name: set test prompt to development branch validation
+        if: ${{ github.ref == 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/dev_prompts.txt" >> ${{ matrix.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" >> ${{ matrix.github-env }}
+
+      - name: create requirements.txt
+        run: cp 'environments-and-requirements/${{ matrix.requirements-file }}' '${{ matrix.requirements-file }}'
+
+      - name: setup python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          # cache: 'pip'
+          # cache-dependency-path: ${{ matrix.requirements-file }}
+
+      - name: install dependencies
+        run: pip3 install --upgrade pip setuptools wheel
+
+      - name: install requirements
+        run: pip3 install -r '${{ matrix.requirements-file }}'
+
+      - 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 }}"
+          ${{ matrix.curl-command }} -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: python3 scripts/configure_invokeai.py --skip-sd-weights --yes
+
+      - name: Run the tests
+        id: run-tests
+        if: matrix.os != 'windows-2022'
+        run: python3 scripts/invoke.py --no-patchmatch --no-nsfw_checker --model ${{ matrix.stable-diffusion-model }} --from_file ${{ env.TEST_PROMPTS }} --root="${{ env.INVOKEAI_ROOT }}" --outdir="${{ env.INVOKEAI_OUTDIR }}"
+
+      - name: Archive results
+        id: archive-results
+        if: matrix.os != 'windows-2022'
+        uses: actions/upload-artifact@v3
+        with:
+          name: results_${{ matrix.requirements-file }}_${{ matrix.python-version }}
+          path: ${{ env.INVOKEAI_ROOT }}/outputs

.gitignore

@@ -1,7 +1,12 @@
 # ignore default image save location and model symbolic link
 outputs/
 models/ldm/stable-diffusion-v1/model.ckpt
-ldm/dream/restoration/codeformer/weights
+**/restoration/codeformer/weights
+
+# ignore user models config
+configs/models.user.yaml
+config/models.user.yml
+invokeai.init
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -180,7 +185,7 @@ src
 **/__pycache__/
 outputs
 
-# Logs and associated folders 
+# Logs and associated folders
 # created from generated embeddings.
 logs
 testtube
@@ -195,7 +200,37 @@ checkpoints
 .scratch/
 .vscode/
 gfpgan/
-models/ldm/stable-diffusion-v1/model.sha256
+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
+
+# this may be present if the user created a venv
+invokeai
+
+# no longer stored in source directory
+models

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior
+may be reported to the community leaders responsible for enforcement
+at https://github.com/invoke-ai/InvokeAI/issues.  All complaints will
+be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

InvokeAI_Statement_of_Values.md

@@ -0,0 +1,84 @@
+<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
+software tools which support cutting edge AI text-to-image
+applications. This community is open to anyone who wishes to
+contribute to the effort and has the skill and time to do so.
+
+# Our Values
+
+The InvokeAI team is a diverse community which includes individuals
+from various parts of the world and many walks of life. Despite our
+differences, we share a number of core values which we ask prospective
+contributors to understand and respect. We believe:
+
+1. That Open Source Software is a positive force in the world. We
+create software that can be used, reused, and redistributed, without
+restrictions, under a straightforward Open Source license (MIT). We
+believe that Open Source benefits society as a whole by increasing the
+availability of high quality software to all.
+
+2. That those who create software should receive proper attribution
+for their creative work. While we support the exchange and reuse of
+Open Source Software, we feel strongly that the original authors of a
+piece of code should receive credit for their contribution, and we
+endeavor to do so whenever possible.
+
+3. That there is moral ambiguity surrounding AI-assisted art. We are
+aware of the moral and ethical issues surrounding the release of the
+Stable Diffusion model and similar products. We are aware that, due to
+the composition of their training sets, current AI-generated image
+models are biased against certain ethnic groups, cultural concepts of
+beauty, ethnic stereotypes, and gender roles.
+
+      1. We recognize the potential for harm to these groups that these biases
+       represent and trust that future AI models will take steps towards
+       reducing or eliminating the biases noted above, respect and give due
+       credit to the artists whose work is sourced, and call on developers
+       and users to favor these models over the older ones as they become
+       available.
+
+4. We are deeply committed to ensuring that this technology benefits
+everyone, including artists. We see AI art not as a replacement for
+the artist, but rather as a tool to empower them. With that
+in mind, we are constantly debating how to build systems that put
+artists’ needs first: tools which can be readily integrated into an
+artist’s existing workflows and practices, enhancing their work and
+helping them to push it further. Every decision we take as a team,
+which includes several artists, aims to build towards that goal.
+
+5. That artificial intelligence can be a force for good in the world,
+but must be used responsibly. Artificial intelligence technologies
+have the potential to improve society, in everything from cancer care,
+to customer service, to creative writing.
+
+     1. While we do not believe that software should arbitrarily limit what
+     users can do with it, we recognize that when used irresponsibly, AI
+     has the potential to do much harm. Our Discord server is actively
+     moderated in order to minimize the potential of harm from
+     user-contributed images. In addition, we ask users of our software to
+     refrain from using it in any way that would cause mental, emotional or
+     physical harm to individuals and vulnerable populations including (but
+     not limited to) women; minors; ethnic minorities; religious groups;
+     members of LGBTQIA communities; and people with disabilities or
+     impairments.
+
+     2. Note that some of the image generation AI models which the Invoke-AI
+     toolkit supports carry licensing agreements which impose restrictions
+     on how the model is used. We ask that our users read and agree to
+     these terms if they wish to make use of these models. These agreements
+     are distinct from the MIT license which applies to the InvokeAI
+     software and source code.
+
+6. That mutual respect is key to a healthy software development
+community. Members of the InvokeAI community are expected to treat
+each other with respect, beneficence, and empathy. Each of us has a
+different background and a unique set of skills. We strive to help
+each other grow and gain new skills, and we apportion expectations in
+a way that balances the members' time, skillset, and interest
+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.

LICENSE

@@ -1,17 +1,6 @@
 MIT License
 
-Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
-
-This software is derived from a fork of the source code available from
-https://github.com/pesser/stable-diffusion and
-https://github.com/CompViz/stable-diffusion. They carry the following
-copyrights:
-
-Copyright (c) 2022 Machine Vision and Learning Group, LMU Munich
-Copyright (c) 2022 Robin Rombach and Patrick Esser and contributors
-
-Please see individual source code files for copyright and authorship
-attributions.
+Copyright (c) 2022 InvokeAI Team
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,18 +1,9 @@
 <div align="center">
 
+![project logo](docs/assets/invoke_ai_banner.png)
+
 # InvokeAI: A Stable Diffusion Toolkit
 
-_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._
-
-_This repository was formally known as lstein/stable-diffusion_
-
-# **Table of Contents**
-
-![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]
@@ -24,7 +15,7 @@ _This repository was formally known as lstein/stable-diffusion_
 [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/workflows/test-dream-conda.yml
+[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
@@ -41,14 +32,37 @@ _This repository was formally known as lstein/stable-diffusion_
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
 </div>
 
-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, and runs on
-GPU cards with as little as 4 GB or RAM.
+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, macOS 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.
 
-_Note: This fork is rapidly evolving. Please use the
+**Quick links**: [[How to Install](#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
+
+_Note: InvokeAI is rapidly evolving. Please use the
 [Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
-requests. Be sure to use the provided templates. They will help aid diagnose issues faster._
+requests. Be sure to use the provided templates. They will help us diagnose issues faster._
+
+# Getting Started with InvokeAI
+
+For full installation and upgrade instructions, please see:
+[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
+
+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. If you are on Windows, double-click on the `install.bat` script. On macOS, open a Terminal window, drag the file `install.sh` from Finder into the Terminal, and press return. On Linux, run `install.sh`.
+5. Wait a while, until it is done.
+6. The folder where you ran the installer from will now be filled with lots of files. If you are on Windows, 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`
+7. 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.
+8. Type `banana sushi` in the box on the top left and click `Invoke`:
+
+<div align="center"><img src="docs/assets/invoke-web-server-1.png" width=640></div>
+
+
 
 ## Table of Contents
 
@@ -64,17 +78,17 @@ requests. Be sure to use the provided templates. They will help aid diagnose iss
 
 ### Installation
 
-This fork is supported across multiple platforms. You can find individual installation instructions
-below.
-
-- #### [Linux](docs/installation/INSTALL_LINUX.md)
-
-- #### [Windows](docs/installation/INSTALL_WINDOWS.md)
-
-- #### [Macintosh](docs/installation/INSTALL_MAC.md)
+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/)
 
 ### Hardware Requirements
 
+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).
 #### System
 
 You wil need one of the following:
@@ -82,108 +96,89 @@ You wil need one of the following:
 - An NVIDIA-based graphics card with 4 GB or more VRAM memory.
 - An Apple computer with an M1 chip.
 
+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 6 GB of free disk space for the machine learning model, Python, and all its dependencies.
+- At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
-#### Note
+**Note**
+
+If you have a Nvidia 10xx series card (e.g. the 1080ti), please
+run the dream script in full-precision mode as shown below.
+
+Similarly, specify full-precision mode on Apple M1 hardware.
 
 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 `dream.py` with the `--precision=float32` flag:
+you can try starting `invoke.py` with the `--precision=float32` flag to your initialization command
 
 ```bash
-(ldm) ~/stable-diffusion$ python scripts/dream.py --precision=float32
+(invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32
 ```
+Or by updating your InvokeAI configuration file with this argument.
 
 ### Features
 
 #### Major Features
 
-- [Interactive Command Line Interface](docs/features/CLI.md)
-- [Image To Image](docs/features/IMG2IMG.md)
-- [Inpainting Support](docs/features/INPAINTING.md)
-- [Outpainting Support](docs/features/OUTPAINTING.md)
-- [Upscaling, face-restoration and outpainting](docs/features/POSTPROCESS.md)
-- [Seamless Tiling](docs/features/OTHER.md#seamless-tiling)
-- [Google Colab](docs/features/OTHER.md#google-colab)
-- [Web Server](docs/features/WEB.md)
-- [Reading Prompts From File](docs/features/PROMPTS.md#reading-prompts-from-a-file)
-- [Shortcut: Reusing Seeds](docs/features/OTHER.md#shortcuts-reusing-seeds)
-- [Prompt Blending](docs/features/PROMPTS.md#prompt-blending)
-- [Thresholding and Perlin Noise Initialization Options](/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options)
-- [Negative/Unconditioned Prompts](docs/features/PROMPTS.md#negative-and-unconditioned-prompts)
-- [Variations](docs/features/VARIATIONS.md)
-- [Personalizing Text-to-Image Generation](docs/features/TEXTUAL_INVERSION.md)
-- [Simplified API for text to image generation](docs/features/OTHER.md#simplified-api)
+- [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)
 
 #### Other Features
 
-- [Creating Transparent Regions for Inpainting](docs/features/INPAINTING.md#creating-transparent-regions-for-inpainting)
-- [Preload Models](docs/features/OTHER.md#preload-models)
+- [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
 
-- vNEXT (TODO 2022)
-
-  - Deprecated `--full_precision` / `-F`. Simply omit it and `dream.py` will auto
-    configure. To switch away from auto use the new flag like `--precision=float32`.
-
-- v1.14 (11 September 2022)
-
-  - Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
-  - Full support for Apple hardware with M1 or M2 chips.
-  - Add "seamless mode" for circular tiling of image. Generates beautiful effects.
-    ([prixt](https://github.com/prixt)).
-  - Inpainting support.
-  - Improved web server GUI.
-  - Lots of code and documentation cleanups.
-
-- v1.13 (3 September 2022
-
-  - Support image variations (see [VARIATIONS](docs/features/VARIATIONS.md)
-    ([Kevin Gibbons](https://github.com/bakkot) and many contributors and reviewers)
-  - Supports a Google Colab notebook for a standalone server running on Google hardware
-    [Arturo Mendivil](https://github.com/artmen1516)
-  - WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling
-    [Kevin Gibbons](https://github.com/bakkot)
-  - WebUI supports incremental display of in-progress images during generation
-    [Kevin Gibbons](https://github.com/bakkot)
-  - A new configuration file scheme that allows new models (including upcoming
-    stable-diffusion-v1.5) to be added without altering the code.
-    ([David Wager](https://github.com/maddavid12))
-  - Can specify --grid on dream.py command line as the default.
-  - Miscellaneous internal bug and stability fixes.
-  - Works on M1 Apple hardware.
-  - Multiple bug fixes.
-
-For older changelogs, please visit the **[CHANGELOG](docs/features/CHANGELOG.md)**.
+For our latest changes, view our [Release Notes](https://github.com/invoke-ai/InvokeAI/releases)
 
 ### Troubleshooting
 
-Please check out our **[Q&A](docs/help/TROUBLESHOOT.md)** to get solutions for common installation
+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.
 
 # 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. If you are unfamiliar with how
-to contribute to GitHub projects, here is a
-[Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github).
+cleanup, testing, or code reviews, is very much encouraged to do so.
 
-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.
+To join, just raise your hand on the InvokeAI Discord server (#dev-chat) or the GitHub discussion board.
+
+If you are unfamiliar with how
+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. You can **make your pull request against the "main" branch**. 
+
+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
+to become part of our community.
+
+Welcome to InvokeAI!
 
 ### Contributors
 
 This fork is a combined effort of various people from across the world.
-[Check out the list of all these amazing people](docs/other/CONTRIBUTORS.md). We thank them for
+[Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
 their time, hard work and effort.
 
 ### Support
@@ -191,10 +186,10 @@ their time, hard work and effort.
 For support, please use this repository's GitHub Issues tracking service. Feel free to send me an
 email if you use and like the script.
 
-Original portions of the software are Copyright (c) 2020
+Original portions of the software are Copyright (c) 2022
 [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](docs/other/README-CompViz.md).
+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

@@ -1,6 +1,6 @@
 import argparse
 import os
-from ldm.dream.args import PRECISION_CHOICES
+from ldm.invoke.args import PRECISION_CHOICES
 
 
 def create_cmd_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

@@ -5,6 +5,8 @@ SAMPLER_CHOICES = [
     "ddim",
     "k_dpm_2_a",
     "k_dpm_2",
+    "k_dpmpp_2_a",
+    "k_dpmpp_2",
     "k_euler_a",
     "k_euler",
     "k_heun",
@@ -15,7 +17,7 @@ SAMPLER_CHOICES = [
 
 def parameters_to_command(params):
     """
-    Converts dict of parameters into a `dream.py` REPL command.
+    Converts dict of parameters into a `invoke.py` REPL command.
     """
 
     switches = list()
@@ -36,6 +38,8 @@ def parameters_to_command(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:
@@ -46,8 +50,14 @@ def parameters_to_command(params):
         switches.append(f'-f {params["strength"]}')
         if "fit" in params and params["fit"] == True:
             switches.append(f"--fit")
-    if "gfpgan_strength" in params and params["gfpgan_strength"]:
+    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:

backend/server.py

@@ -1,821 +0,0 @@
-import mimetypes
-import transformers
-import json
-import os
-import traceback
-import eventlet
-import glob
-import shlex
-import math
-import shutil
-import sys
-
-sys.path.append(".")
-
-from argparse import ArgumentTypeError
-from modules.create_cmd_parser import create_cmd_parser
-
-parser = create_cmd_parser()
-opt = parser.parse_args()
-
-
-from flask_socketio import SocketIO
-from flask import Flask, send_from_directory, url_for, jsonify
-from pathlib import Path
-from PIL import Image
-from pytorch_lightning import logging
-from threading import Event
-from uuid import uuid4
-from send2trash import send2trash
-
-
-from ldm.generate import Generate
-from ldm.dream.restoration import Restoration
-from ldm.dream.pngwriter import PngWriter, retrieve_metadata
-from ldm.dream.args import APP_ID, APP_VERSION, calculate_init_img_hash
-from ldm.dream.conditioning import split_weighted_subprompts
-
-from modules.parameters import parameters_to_command
-
-
-"""
-USER CONFIG
-"""
-if opt.cors and "*" in opt.cors:
-    raise ArgumentTypeError('"*" is not an allowed CORS origin')
-
-
-output_dir = "outputs/"  # Base output directory for images
-host = opt.host  # Web & socket.io host
-port = opt.port  # Web & socket.io port
-verbose = opt.verbose  # enables copious socket.io logging
-precision = opt.precision
-free_gpu_mem = opt.free_gpu_mem
-embedding_path = opt.embedding_path
-additional_allowed_origins = (
-    opt.cors if opt.cors else []
-)  # additional CORS allowed origins
-model = "stable-diffusion-1.4"
-
-"""
-END USER CONFIG
-"""
-
-
-print("* Initializing, be patient...\n")
-
-
-"""
-SERVER SETUP
-"""
-
-
-# fix missing mimetypes on windows due to registry wonkiness
-mimetypes.add_type("application/javascript", ".js")
-mimetypes.add_type("text/css", ".css")
-
-app = Flask(__name__, static_url_path="", static_folder="../frontend/dist/")
-
-
-app.config["OUTPUTS_FOLDER"] = "../outputs"
-
-
-@app.route("/outputs/<path:filename>")
-def outputs(filename):
-    return send_from_directory(app.config["OUTPUTS_FOLDER"], filename)
-
-
-@app.route("/", defaults={"path": ""})
-def serve(path):
-    return send_from_directory(app.static_folder, "index.html")
-
-
-logger = True if verbose else False
-engineio_logger = True if verbose else False
-
-# default 1,000,000, needs to be higher for socketio to accept larger images
-max_http_buffer_size = 10000000
-
-cors_allowed_origins = [f"http://{host}:{port}"] + additional_allowed_origins
-
-socketio = SocketIO(
-    app,
-    logger=logger,
-    engineio_logger=engineio_logger,
-    max_http_buffer_size=max_http_buffer_size,
-    cors_allowed_origins=cors_allowed_origins,
-    ping_interval=(50, 50),
-    ping_timeout=60,
-)
-
-
-"""
-END SERVER SETUP
-"""
-
-
-"""
-APP SETUP
-"""
-
-
-class CanceledException(Exception):
-    pass
-
-
-try:
-    gfpgan, codeformer, esrgan = None, None, None
-    from ldm.dream.restoration.base import Restoration
-
-    restoration = Restoration()
-    gfpgan, codeformer = restoration.load_face_restore_models()
-    esrgan = restoration.load_esrgan()
-
-    # coreformer.process(self, image, strength, device, seed=None, fidelity=0.75)
-
-except (ModuleNotFoundError, ImportError):
-    print(traceback.format_exc(), file=sys.stderr)
-    print(">> You may need to install the ESRGAN and/or GFPGAN modules")
-
-canceled = Event()
-
-# reduce logging outputs to error
-transformers.logging.set_verbosity_error()
-logging.getLogger("pytorch_lightning").setLevel(logging.ERROR)
-
-# Initialize and load model
-generate = Generate(
-    model,
-    precision=precision,
-    embedding_path=embedding_path,
-)
-generate.free_gpu_mem = free_gpu_mem
-generate.load_model()
-
-
-# location for "finished" images
-result_path = os.path.join(output_dir, "img-samples/")
-
-# temporary path for intermediates
-intermediate_path = os.path.join(result_path, "intermediates/")
-
-# path for user-uploaded init images and masks
-init_image_path = os.path.join(result_path, "init-images/")
-mask_image_path = os.path.join(result_path, "mask-images/")
-
-# txt log
-log_path = os.path.join(result_path, "dream_log.txt")
-
-# make all output paths
-[
-    os.makedirs(path, exist_ok=True)
-    for path in [result_path, intermediate_path, init_image_path, mask_image_path]
-]
-
-
-"""
-END APP SETUP
-"""
-
-
-"""
-SOCKET.IO LISTENERS
-"""
-
-
-@socketio.on("requestSystemConfig")
-def handle_request_capabilities():
-    print(f">> System config requested")
-    config = get_system_config()
-    socketio.emit("systemConfig", config)
-
-
-@socketio.on("requestImages")
-def handle_request_images(page=1, offset=0, last_mtime=None):
-    chunk_size = 50
-
-    if last_mtime:
-        print(f">> Latest images requested")
-    else:
-        print(
-            f">> Page {page} of images requested (page size {chunk_size} offset {offset})"
-        )
-
-    paths = glob.glob(os.path.join(result_path, "*.png"))
-    sorted_paths = sorted(paths, key=lambda x: os.path.getmtime(x), reverse=True)
-
-    if last_mtime:
-        image_paths = filter(lambda x: os.path.getmtime(x) > last_mtime, sorted_paths)
-    else:
-
-        image_paths = sorted_paths[
-            slice(chunk_size * (page - 1) + offset, chunk_size * page + offset)
-        ]
-        page = page + 1
-
-    image_array = []
-
-    for path in image_paths:
-        metadata = retrieve_metadata(path)
-        image_array.append(
-            {
-                "url": path,
-                "mtime": os.path.getmtime(path),
-                "metadata": metadata["sd-metadata"],
-            }
-        )
-
-    socketio.emit(
-        "galleryImages",
-        {
-            "images": image_array,
-            "nextPage": page,
-            "offset": offset,
-            "onlyNewImages": True if last_mtime else False,
-        },
-    )
-
-
-@socketio.on("generateImage")
-def handle_generate_image_event(
-    generation_parameters, esrgan_parameters, gfpgan_parameters
-):
-    print(
-        f">> Image generation requested: {generation_parameters}\nESRGAN parameters: {esrgan_parameters}\nGFPGAN parameters: {gfpgan_parameters}"
-    )
-    generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters)
-
-
-@socketio.on("runESRGAN")
-def handle_run_esrgan_event(original_image, esrgan_parameters):
-    print(
-        f'>> ESRGAN upscale requested for "{original_image["url"]}": {esrgan_parameters}'
-    )
-    progress = {
-        "currentStep": 1,
-        "totalSteps": 1,
-        "currentIteration": 1,
-        "totalIterations": 1,
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = Image.open(original_image["url"])
-
-    seed = (
-        original_image["metadata"]["seed"]
-        if "seed" in original_image["metadata"]
-        else "unknown_seed"
-    )
-
-    progress["currentStatus"] = "Upscaling"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = esrgan.process(
-        image=image,
-        upsampler_scale=esrgan_parameters["upscale"][0],
-        strength=esrgan_parameters["upscale"][1],
-        seed=seed,
-    )
-
-    progress["currentStatus"] = "Saving image"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    esrgan_parameters["seed"] = seed
-    metadata = parameters_to_post_processed_image_metadata(
-        parameters=esrgan_parameters,
-        original_image_path=original_image["url"],
-        type="esrgan",
-    )
-    command = parameters_to_command(esrgan_parameters)
-
-    path = save_image(image, command, metadata, result_path, postprocessing="esrgan")
-
-    write_log_message(f'[Upscaled] "{original_image["url"]}" > "{path}": {command}')
-
-    progress["currentStatus"] = "Finished"
-    progress["currentStep"] = 0
-    progress["totalSteps"] = 0
-    progress["currentIteration"] = 0
-    progress["totalIterations"] = 0
-    progress["isProcessing"] = False
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    socketio.emit(
-        "esrganResult",
-        {
-            "url": os.path.relpath(path),
-            "mtime": os.path.getmtime(path),
-            "metadata": metadata,
-        },
-    )
-
-
-@socketio.on("runGFPGAN")
-def handle_run_gfpgan_event(original_image, gfpgan_parameters):
-    print(
-        f'>> GFPGAN face fix requested for "{original_image["url"]}": {gfpgan_parameters}'
-    )
-    progress = {
-        "currentStep": 1,
-        "totalSteps": 1,
-        "currentIteration": 1,
-        "totalIterations": 1,
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = Image.open(original_image["url"])
-
-    seed = (
-        original_image["metadata"]["seed"]
-        if "seed" in original_image["metadata"]
-        else "unknown_seed"
-    )
-
-    progress["currentStatus"] = "Fixing faces"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = gfpgan.process(
-        image=image, strength=gfpgan_parameters["gfpgan_strength"], seed=seed
-    )
-
-    progress["currentStatus"] = "Saving image"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    gfpgan_parameters["seed"] = seed
-    metadata = parameters_to_post_processed_image_metadata(
-        parameters=gfpgan_parameters,
-        original_image_path=original_image["url"],
-        type="gfpgan",
-    )
-    command = parameters_to_command(gfpgan_parameters)
-
-    path = save_image(image, command, metadata, result_path, postprocessing="gfpgan")
-
-    write_log_message(f'[Fixed faces] "{original_image["url"]}" > "{path}": {command}')
-
-    progress["currentStatus"] = "Finished"
-    progress["currentStep"] = 0
-    progress["totalSteps"] = 0
-    progress["currentIteration"] = 0
-    progress["totalIterations"] = 0
-    progress["isProcessing"] = False
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    socketio.emit(
-        "gfpganResult",
-        {
-            "url": os.path.relpath(path),
-            "mtime": os.path.mtime(path),
-            "metadata": metadata,
-        },
-    )
-
-
-@socketio.on("cancel")
-def handle_cancel():
-    print(f">> Cancel processing requested")
-    canceled.set()
-    socketio.emit("processingCanceled")
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("deleteImage")
-def handle_delete_image(path, uuid):
-    print(f'>> Delete requested "{path}"')
-    send2trash(path)
-    socketio.emit("imageDeleted", {"url": path, "uuid": uuid})
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("uploadInitialImage")
-def handle_upload_initial_image(bytes, name):
-    print(f'>> Init image upload requested "{name}"')
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    file_path = os.path.join(init_image_path, name)
-    os.makedirs(os.path.dirname(file_path), exist_ok=True)
-    newFile = open(file_path, "wb")
-    newFile.write(bytes)
-    socketio.emit("initialImageUploaded", {"url": file_path, "uuid": ""})
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("uploadMaskImage")
-def handle_upload_mask_image(bytes, name):
-    print(f'>> Mask image upload requested "{name}"')
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    file_path = os.path.join(mask_image_path, name)
-    os.makedirs(os.path.dirname(file_path), exist_ok=True)
-    newFile = open(file_path, "wb")
-    newFile.write(bytes)
-    socketio.emit("maskImageUploaded", {"url": file_path, "uuid": ""})
-
-
-"""
-END SOCKET.IO LISTENERS
-"""
-
-
-"""
-ADDITIONAL FUNCTIONS
-"""
-
-
-def get_system_config():
-    return {
-        "model": "stable diffusion",
-        "model_id": model,
-        "model_hash": generate.model_hash,
-        "app_id": APP_ID,
-        "app_version": APP_VERSION,
-    }
-
-
-def parameters_to_post_processed_image_metadata(parameters, original_image_path, type):
-    # top-level metadata minus `image` or `images`
-    metadata = get_system_config()
-
-    orig_hash = calculate_init_img_hash(original_image_path)
-
-    image = {"orig_path": original_image_path, "orig_hash": orig_hash}
-
-    if type == "esrgan":
-        image["type"] = "esrgan"
-        image["scale"] = parameters["upscale"][0]
-        image["strength"] = parameters["upscale"][1]
-    elif type == "gfpgan":
-        image["type"] = "gfpgan"
-        image["strength"] = parameters["gfpgan_strength"]
-    else:
-        raise TypeError(f"Invalid type: {type}")
-
-    metadata["image"] = image
-    return metadata
-
-
-def parameters_to_generated_image_metadata(parameters):
-    # top-level metadata minus `image` or `images`
-
-    metadata = get_system_config()
-    # remove any image keys not mentioned in RFC #266
-    rfc266_img_fields = [
-        "type",
-        "postprocessing",
-        "sampler",
-        "prompt",
-        "seed",
-        "variations",
-        "steps",
-        "cfg_scale",
-        "threshold",
-        "perlin",
-        "step_number",
-        "width",
-        "height",
-        "extra",
-        "seamless",
-    ]
-
-    rfc_dict = {}
-
-    for item in parameters.items():
-        key, value = item
-        if key in rfc266_img_fields:
-            rfc_dict[key] = value
-
-    postprocessing = []
-
-    # 'postprocessing' is either null or an
-    if "gfpgan_strength" in parameters:
-
-        postprocessing.append(
-            {"type": "gfpgan", "strength": float(parameters["gfpgan_strength"])}
-        )
-
-    if "upscale" in parameters:
-        postprocessing.append(
-            {
-                "type": "esrgan",
-                "scale": int(parameters["upscale"][0]),
-                "strength": float(parameters["upscale"][1]),
-            }
-        )
-
-    rfc_dict["postprocessing"] = postprocessing if len(postprocessing) > 0 else None
-
-    # semantic drift
-    rfc_dict["sampler"] = parameters["sampler_name"]
-
-    # display weighted subprompts (liable to change)
-    subprompts = split_weighted_subprompts(parameters["prompt"])
-    subprompts = [{"prompt": x[0], "weight": x[1]} for x in subprompts]
-    rfc_dict["prompt"] = subprompts
-
-    # 'variations' should always exist and be an array, empty or consisting of {'seed': seed, 'weight': weight} pairs
-    variations = []
-
-    if "with_variations" in parameters:
-        variations = [
-            {"seed": x[0], "weight": x[1]} for x in parameters["with_variations"]
-        ]
-
-    rfc_dict["variations"] = variations
-
-    if "init_img" in parameters:
-        rfc_dict["type"] = "img2img"
-        rfc_dict["strength"] = parameters["strength"]
-        rfc_dict["fit"] = parameters["fit"]  # TODO: Noncompliant
-        rfc_dict["orig_hash"] = calculate_init_img_hash(parameters["init_img"])
-        rfc_dict["init_image_path"] = parameters["init_img"]  # TODO: Noncompliant
-        rfc_dict["sampler"] = "ddim"  # TODO: FIX ME WHEN IMG2IMG SUPPORTS ALL SAMPLERS
-        if "init_mask" in parameters:
-            rfc_dict["mask_hash"] = calculate_init_img_hash(
-                parameters["init_mask"]
-            )  # TODO: Noncompliant
-            rfc_dict["mask_image_path"] = parameters["init_mask"]  # TODO: Noncompliant
-    else:
-        rfc_dict["type"] = "txt2img"
-
-    metadata["image"] = rfc_dict
-
-    return metadata
-
-
-def make_unique_init_image_filename(name):
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    return name
-
-
-def write_log_message(message, log_path=log_path):
-    """Logs the filename and parameters used to generate or process that image to log file"""
-    message = f"{message}\n"
-    with open(log_path, "a", encoding="utf-8") as file:
-        file.writelines(message)
-
-
-def save_image(
-    image, command, metadata, output_dir, step_index=None, postprocessing=False
-):
-    pngwriter = PngWriter(output_dir)
-    prefix = pngwriter.unique_prefix()
-
-    seed = "unknown_seed"
-
-    if "image" in metadata:
-        if "seed" in metadata["image"]:
-            seed = metadata["image"]["seed"]
-
-    filename = f"{prefix}.{seed}"
-
-    if step_index:
-        filename += f".{step_index}"
-    if postprocessing:
-        filename += f".postprocessed"
-
-    filename += ".png"
-
-    path = pngwriter.save_image_and_prompt_to_png(
-        image=image, dream_prompt=command, metadata=metadata, name=filename
-    )
-
-    return path
-
-
-def calculate_real_steps(steps, strength, has_init_image):
-    return math.floor(strength * steps) if has_init_image else steps
-
-
-def generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters):
-    canceled.clear()
-
-    step_index = 1
-    prior_variations = (
-        generation_parameters["with_variations"]
-        if "with_variations" in generation_parameters
-        else []
-    )
-    """
-    If a result image is used as an init image, and then deleted, we will want to be
-    able to use it as an init image in the future. Need to copy it.
-
-    If the init/mask image doesn't exist in the init_image_path/mask_image_path,
-    make a unique filename for it and copy it there.
-    """
-    if "init_img" in generation_parameters:
-        filename = os.path.basename(generation_parameters["init_img"])
-        if not os.path.exists(os.path.join(init_image_path, filename)):
-            unique_filename = make_unique_init_image_filename(filename)
-            new_path = os.path.join(init_image_path, unique_filename)
-            shutil.copy(generation_parameters["init_img"], new_path)
-            generation_parameters["init_img"] = new_path
-        if "init_mask" in generation_parameters:
-            filename = os.path.basename(generation_parameters["init_mask"])
-            if not os.path.exists(os.path.join(mask_image_path, filename)):
-                unique_filename = make_unique_init_image_filename(filename)
-                new_path = os.path.join(init_image_path, unique_filename)
-                shutil.copy(generation_parameters["init_img"], new_path)
-                generation_parameters["init_mask"] = new_path
-
-    totalSteps = calculate_real_steps(
-        steps=generation_parameters["steps"],
-        strength=generation_parameters["strength"]
-        if "strength" in generation_parameters
-        else None,
-        has_init_image="init_img" in generation_parameters,
-    )
-
-    progress = {
-        "currentStep": 1,
-        "totalSteps": totalSteps,
-        "currentIteration": 1,
-        "totalIterations": generation_parameters["iterations"],
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    def image_progress(sample, step):
-        if canceled.is_set():
-            raise CanceledException
-
-        nonlocal step_index
-        nonlocal generation_parameters
-        nonlocal progress
-
-        progress["currentStep"] = step + 1
-        progress["currentStatus"] = "Generating"
-        progress["currentStatusHasSteps"] = True
-
-        if (
-            generation_parameters["progress_images"]
-            and step % 5 == 0
-            and step < generation_parameters["steps"] - 1
-        ):
-            image = generate.sample_to_image(sample)
-
-            metadata = parameters_to_generated_image_metadata(generation_parameters)
-            command = parameters_to_command(generation_parameters)
-            path = save_image(image, command, metadata, intermediate_path, step_index=step_index, postprocessing=False)
-
-            step_index += 1
-            socketio.emit(
-                "intermediateResult",
-                {
-                    "url": os.path.relpath(path),
-                    "mtime": os.path.getmtime(path),
-                    "metadata": metadata,
-                },
-            )
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-    def image_done(image, seed, first_seed):
-        nonlocal generation_parameters
-        nonlocal esrgan_parameters
-        nonlocal gfpgan_parameters
-        nonlocal progress
-
-        step_index = 1
-        nonlocal prior_variations
-
-        progress["currentStatus"] = "Generation complete"
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        all_parameters = generation_parameters
-        postprocessing = False
-
-        if (
-            "variation_amount" in all_parameters
-            and all_parameters["variation_amount"] > 0
-        ):
-            first_seed = first_seed or seed
-            this_variation = [[seed, all_parameters["variation_amount"]]]
-            all_parameters["with_variations"] = prior_variations + this_variation
-            all_parameters["seed"] = first_seed
-        elif ("with_variations" in all_parameters):
-            all_parameters["seed"] = first_seed
-        else:
-            all_parameters["seed"] = seed
-
-        if esrgan_parameters:
-            progress["currentStatus"] = "Upscaling"
-            progress["currentStatusHasSteps"] = False
-            socketio.emit("progressUpdate", progress)
-            eventlet.sleep(0)
-
-            image = esrgan.process(
-                image=image,
-                upsampler_scale=esrgan_parameters["level"],
-                strength=esrgan_parameters["strength"],
-                seed=seed,
-            )
-
-            postprocessing = True
-            all_parameters["upscale"] = [
-                esrgan_parameters["level"],
-                esrgan_parameters["strength"],
-            ]
-
-        if gfpgan_parameters:
-            progress["currentStatus"] = "Fixing faces"
-            progress["currentStatusHasSteps"] = False
-            socketio.emit("progressUpdate", progress)
-            eventlet.sleep(0)
-
-            image = gfpgan.process(
-                image=image, strength=gfpgan_parameters["strength"], seed=seed
-            )
-            postprocessing = True
-            all_parameters["gfpgan_strength"] = gfpgan_parameters["strength"]
-
-        progress["currentStatus"] = "Saving image"
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        metadata = parameters_to_generated_image_metadata(all_parameters)
-        command = parameters_to_command(all_parameters)
-
-        path = save_image(
-            image, command, metadata, result_path, postprocessing=postprocessing
-        )
-
-        print(f'>> Image generated: "{path}"')
-        write_log_message(f'[Generated] "{path}": {command}')
-
-        if progress["totalIterations"] > progress["currentIteration"]:
-            progress["currentStep"] = 1
-            progress["currentIteration"] += 1
-            progress["currentStatus"] = "Iteration finished"
-            progress["currentStatusHasSteps"] = False
-        else:
-            progress["currentStep"] = 0
-            progress["totalSteps"] = 0
-            progress["currentIteration"] = 0
-            progress["totalIterations"] = 0
-            progress["currentStatus"] = "Finished"
-            progress["isProcessing"] = False
-
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        socketio.emit(
-            "generationResult",
-            {
-                "url": os.path.relpath(path),
-                "mtime": os.path.getmtime(path),
-                "metadata": metadata,
-            },
-        )
-        eventlet.sleep(0)
-
-    try:
-        generate.prompt2image(
-            **generation_parameters,
-            step_callback=image_progress,
-            image_callback=image_done,
-        )
-
-    except KeyboardInterrupt:
-        raise
-    except CanceledException:
-        pass
-    except Exception as e:
-        socketio.emit("error", {"message": (str(e))})
-        print("\n")
-        traceback.print_exc()
-        print("\n")
-
-
-"""
-END ADDITIONAL FUNCTIONS
-"""
-
-
-if __name__ == "__main__":
-    print(f">> Starting server at http://{host}:{port}")
-    socketio.run(app, host=host, port=port)

binary_installer/install.bat.in

@@ -0,0 +1,164 @@
+@echo off
+
+@rem This script will install git (if not found on the PATH variable)
+@rem  using micromamba (an 8mb static-linked single-file binary, conda replacement).
+@rem For users who already have git, this step will be skipped.
+
+@rem Next, it'll download the project's source code.
+@rem Then it will download a self-contained, standalone Python and unpack it.
+@rem Finally, it'll create the Python virtual environment and preload the models.
+
+@rem This enables a user to install this project without manually installing git or Python
+
+@rem change to the script's directory
+PUSHD "%~dp0"
+
+set "no_cache_dir=--no-cache-dir"
+if "%1" == "use-cache" (
+    set "no_cache_dir="
+)
+
+echo ***** Installing InvokeAI.. *****
+@rem Config
+set INSTALL_ENV_DIR=%cd%\installer_files\env
+@rem https://mamba.readthedocs.io/en/latest/installation.html
+set MICROMAMBA_DOWNLOAD_URL=https://github.com/cmdr2/stable-diffusion-ui/releases/download/v1.1/micromamba.exe
+set RELEASE_URL=https://github.com/invoke-ai/InvokeAI
+set RELEASE_SOURCEBALL=/archive/refs/heads/main.tar.gz
+set PYTHON_BUILD_STANDALONE_URL=https://github.com/indygreg/python-build-standalone/releases/download
+set PYTHON_BUILD_STANDALONE=20221002/cpython-3.10.7+20221002-x86_64-pc-windows-msvc-shared-install_only.tar.gz
+
+set PACKAGES_TO_INSTALL=
+
+call git --version >.tmp1 2>.tmp2
+if "%ERRORLEVEL%" NEQ "0" set PACKAGES_TO_INSTALL=%PACKAGES_TO_INSTALL% git
+
+@rem Cleanup
+del /q .tmp1 .tmp2
+
+@rem (if necessary) install git into a contained environment
+if "%PACKAGES_TO_INSTALL%" NEQ "" (
+    @rem download micromamba
+    echo ***** Downloading micromamba from %MICROMAMBA_DOWNLOAD_URL% to micromamba.exe *****
+
+    call curl -L "%MICROMAMBA_DOWNLOAD_URL%" > micromamba.exe
+
+    @rem test the mamba binary
+    echo ***** Micromamba version:  *****
+    call micromamba.exe --version
+
+    @rem create the installer env
+    if not exist "%INSTALL_ENV_DIR%" (
+        call micromamba.exe create -y --prefix "%INSTALL_ENV_DIR%"
+    )
+
+    echo ***** Packages to install:%PACKAGES_TO_INSTALL% *****
+
+    call micromamba.exe install -y --prefix "%INSTALL_ENV_DIR%" -c conda-forge %PACKAGES_TO_INSTALL%
+
+    if not exist "%INSTALL_ENV_DIR%" (
+        echo ----- There was a problem while installing "%PACKAGES_TO_INSTALL%" using micromamba. Cannot continue. -----
+        pause
+        exit /b
+    )
+)
+
+del /q micromamba.exe
+
+@rem For 'git' only
+set PATH=%INSTALL_ENV_DIR%\Library\bin;%PATH%
+
+@rem Download/unpack/clean up InvokeAI release sourceball
+set err_msg=----- InvokeAI source download failed -----
+echo Trying to download "%RELEASE_URL%%RELEASE_SOURCEBALL%"
+curl -L %RELEASE_URL%%RELEASE_SOURCEBALL% --output InvokeAI.tgz
+if %errorlevel% neq 0 goto err_exit
+
+set err_msg=----- InvokeAI source unpack failed -----
+tar -zxf InvokeAI.tgz
+if %errorlevel% neq 0 goto err_exit
+
+del /q InvokeAI.tgz
+
+set err_msg=----- InvokeAI source copy failed -----
+cd InvokeAI-*
+xcopy . .. /e /h
+if %errorlevel% neq 0 goto err_exit
+cd ..
+
+@rem cleanup
+for /f %%i in ('dir /b InvokeAI-*') do rd /s /q %%i
+rd /s /q .dev_scripts .github docker-build tests
+del /q requirements.in requirements-mkdocs.txt shell.nix
+
+echo ***** Unpacked InvokeAI source *****
+
+@rem Download/unpack/clean up python-build-standalone
+set err_msg=----- Python download failed -----
+curl -L %PYTHON_BUILD_STANDALONE_URL%/%PYTHON_BUILD_STANDALONE% --output python.tgz
+if %errorlevel% neq 0 goto err_exit
+
+set err_msg=----- Python unpack failed -----
+tar -zxf python.tgz
+if %errorlevel% neq 0 goto err_exit
+
+del /q python.tgz
+
+echo ***** Unpacked python-build-standalone *****
+
+@rem create venv
+set err_msg=----- problem creating venv -----
+.\python\python -E -s -m venv .venv
+if %errorlevel% neq 0 goto err_exit
+call .venv\Scripts\activate.bat
+
+echo ***** Created Python virtual environment *****
+
+@rem Print venv's Python version
+set err_msg=----- problem calling venv's python -----
+echo We're running under
+.venv\Scripts\python --version
+if %errorlevel% neq 0 goto err_exit
+
+set err_msg=----- pip update failed -----
+.venv\Scripts\python -m pip install %no_cache_dir% --no-warn-script-location --upgrade pip wheel
+if %errorlevel% neq 0 goto err_exit
+
+echo ***** Updated pip and wheel *****
+
+set err_msg=----- requirements file copy failed -----
+copy binary_installer\py3.10-windows-x86_64-cuda-reqs.txt requirements.txt
+if %errorlevel% neq 0 goto err_exit
+
+set err_msg=----- main pip install failed -----
+.venv\Scripts\python -m pip install %no_cache_dir% --no-warn-script-location -r requirements.txt
+if %errorlevel% neq 0 goto err_exit
+
+echo ***** Installed Python dependencies *****
+
+set err_msg=----- InvokeAI setup failed -----
+.venv\Scripts\python -m pip install %no_cache_dir% --no-warn-script-location -e .
+if %errorlevel% neq 0 goto err_exit
+
+copy binary_installer\invoke.bat.in .\invoke.bat
+echo ***** Installed invoke launcher script ******
+
+@rem more cleanup
+rd /s /q binary_installer installer_files
+
+@rem preload the models
+call .venv\Scripts\python scripts\configure_invokeai.py
+set err_msg=----- model download clone failed -----
+if %errorlevel% neq 0 goto err_exit
+deactivate
+
+echo ***** Finished downloading models *****
+
+echo All done! Execute the file invoke.bat in this directory to start InvokeAI
+pause
+exit
+
+:err_exit
+    echo %err_msg%
+    pause
+    exit

binary_installer/install.sh.in

@@ -0,0 +1,235 @@
+#!/usr/bin/env bash
+
+# ensure we're in the correct folder in case user's CWD is somewhere else
+scriptdir=$(dirname "$0")
+cd "$scriptdir"
+
+set -euo pipefail
+IFS=$'\n\t'
+
+function _err_exit {
+    if test "$1" -ne 0
+    then
+        echo -e "Error code $1; Error caught was '$2'"
+        read -p "Press any key to exit..."
+        exit
+    fi
+}
+
+# This script will install git (if not found on the PATH variable)
+#  using micromamba (an 8mb static-linked single-file binary, conda replacement).
+# For users who already have git, this step will be skipped.
+
+# Next, it'll download the project's source code.
+# Then it will download a self-contained, standalone Python and unpack it.
+# Finally, it'll create the Python virtual environment and preload the models.
+
+# This enables a user to install this project without manually installing git or Python
+
+echo -e "\n***** Installing InvokeAI into $(pwd)... *****\n"
+
+export no_cache_dir="--no-cache-dir"
+if [ $# -ge 1 ]; then
+    if [ "$1" = "use-cache" ]; then
+        export no_cache_dir=""
+    fi
+fi
+
+
+OS_NAME=$(uname -s)
+case "${OS_NAME}" in
+    Linux*)     OS_NAME="linux";;
+    Darwin*)    OS_NAME="darwin";;
+    *)          echo -e "\n----- Unknown OS: $OS_NAME! This script runs only on Linux or macOS -----\n" && exit
+esac
+
+OS_ARCH=$(uname -m)
+case "${OS_ARCH}" in
+    x86_64*)    ;;
+    arm64*)     ;;
+    *)          echo -e "\n----- Unknown system architecture: $OS_ARCH! This script runs only on x86_64 or arm64 -----\n" && exit
+esac
+
+# https://mamba.readthedocs.io/en/latest/installation.html
+MAMBA_OS_NAME=$OS_NAME
+MAMBA_ARCH=$OS_ARCH
+if [ "$OS_NAME" == "darwin" ]; then
+    MAMBA_OS_NAME="osx"
+fi
+
+if [ "$OS_ARCH" == "linux" ]; then
+    MAMBA_ARCH="aarch64"
+fi
+
+if [ "$OS_ARCH" == "x86_64" ]; then
+    MAMBA_ARCH="64"
+fi
+
+PY_ARCH=$OS_ARCH
+if [ "$OS_ARCH" == "arm64" ]; then
+    PY_ARCH="aarch64"
+fi
+
+# Compute device ('cd' segment of reqs files) detect goes here
+# This needs a ton of work
+# Suggestions:
+#   - lspci
+#   - check $PATH for nvidia-smi, gtt CUDA/GPU version from output
+#   - Surely there's a similar utility for AMD?
+CD="cuda"
+if [ "$OS_NAME" == "darwin" ] && [ "$OS_ARCH" == "arm64" ]; then
+    CD="mps"
+fi
+
+# config
+INSTALL_ENV_DIR="$(pwd)/installer_files/env"
+MICROMAMBA_DOWNLOAD_URL="https://micro.mamba.pm/api/micromamba/${MAMBA_OS_NAME}-${MAMBA_ARCH}/latest"
+RELEASE_URL=https://github.com/invoke-ai/InvokeAI
+RELEASE_SOURCEBALL=/archive/refs/heads/main.tar.gz
+PYTHON_BUILD_STANDALONE_URL=https://github.com/indygreg/python-build-standalone/releases/download
+if [ "$OS_NAME" == "darwin" ]; then
+    PYTHON_BUILD_STANDALONE=20221002/cpython-3.10.7+20221002-${PY_ARCH}-apple-darwin-install_only.tar.gz
+elif [ "$OS_NAME" == "linux" ]; then
+    PYTHON_BUILD_STANDALONE=20221002/cpython-3.10.7+20221002-${PY_ARCH}-unknown-linux-gnu-install_only.tar.gz
+fi
+echo "INSTALLING $RELEASE_SOURCEBALL FROM $RELEASE_URL"
+
+PACKAGES_TO_INSTALL=""
+
+if ! hash "git" &>/dev/null; then PACKAGES_TO_INSTALL="$PACKAGES_TO_INSTALL git"; fi
+
+# (if necessary) install git and conda into a contained environment
+if [ "$PACKAGES_TO_INSTALL" != "" ]; then
+    # download micromamba
+    echo -e "\n***** Downloading micromamba from $MICROMAMBA_DOWNLOAD_URL to micromamba *****\n"
+
+    curl -L "$MICROMAMBA_DOWNLOAD_URL" | tar -xvjO bin/micromamba > micromamba
+
+    chmod u+x ./micromamba
+
+    # test the mamba binary
+    echo -e "\n***** Micromamba version: *****\n"
+    ./micromamba --version
+
+    # create the installer env
+    if [ ! -e "$INSTALL_ENV_DIR" ]; then
+        ./micromamba create -y --prefix "$INSTALL_ENV_DIR"
+    fi
+
+    echo -e "\n***** Packages to install:$PACKAGES_TO_INSTALL *****\n"
+
+    ./micromamba install -y --prefix "$INSTALL_ENV_DIR" -c conda-forge "$PACKAGES_TO_INSTALL"
+
+    if [ ! -e "$INSTALL_ENV_DIR" ]; then
+        echo -e "\n----- There was a problem while initializing micromamba. Cannot continue. -----\n"
+        exit
+    fi
+fi
+
+rm -f micromamba.exe
+
+export PATH="$INSTALL_ENV_DIR/bin:$PATH"
+
+# Download/unpack/clean up InvokeAI release sourceball
+_err_msg="\n----- InvokeAI source download failed -----\n"
+curl -L $RELEASE_URL/$RELEASE_SOURCEBALL --output InvokeAI.tgz
+_err_exit $? _err_msg
+_err_msg="\n----- InvokeAI source unpack failed -----\n"
+tar -zxf InvokeAI.tgz
+_err_exit $? _err_msg
+
+rm -f InvokeAI.tgz
+
+_err_msg="\n----- InvokeAI source copy failed -----\n"
+cd InvokeAI-*
+cp -r . ..
+_err_exit $? _err_msg
+cd ..
+
+# cleanup
+rm -rf InvokeAI-*/
+rm -rf .dev_scripts/ .github/ docker-build/ tests/ requirements.in requirements-mkdocs.txt shell.nix
+
+echo -e "\n***** Unpacked InvokeAI source *****\n"
+
+# Download/unpack/clean up python-build-standalone
+_err_msg="\n----- Python download failed -----\n"
+curl -L $PYTHON_BUILD_STANDALONE_URL/$PYTHON_BUILD_STANDALONE --output python.tgz
+_err_exit $? _err_msg
+_err_msg="\n----- Python unpack failed -----\n"
+tar -zxf python.tgz
+_err_exit $? _err_msg
+
+rm -f python.tgz
+
+echo -e "\n***** Unpacked python-build-standalone *****\n"
+
+# create venv
+_err_msg="\n----- problem creating venv -----\n"
+
+if [ "$OS_NAME" == "darwin" ]; then
+    # patch sysconfig so that extensions can build properly
+    # adapted from https://github.com/cashapp/hermit-packages/commit/fcba384663892f4d9cfb35e8639ff7a28166ee43
+    PYTHON_INSTALL_DIR="$(pwd)/python"
+    SYSCONFIG="$(echo python/lib/python*/_sysconfigdata_*.py)"
+    TMPFILE="$(mktemp)"
+    chmod +w "${SYSCONFIG}"
+    cp "${SYSCONFIG}" "${TMPFILE}"
+    sed "s,'/install,'${PYTHON_INSTALL_DIR},g" "${TMPFILE}" > "${SYSCONFIG}"
+    rm -f "${TMPFILE}"
+fi
+
+./python/bin/python3 -E -s -m venv .venv
+_err_exit $? _err_msg
+source .venv/bin/activate
+
+echo -e "\n***** Created Python virtual environment *****\n"
+
+# Print venv's Python version
+_err_msg="\n----- problem calling venv's python -----\n"
+echo -e "We're running under"
+.venv/bin/python3 --version
+_err_exit $? _err_msg
+
+_err_msg="\n----- pip update failed -----\n"
+.venv/bin/python3 -m pip install $no_cache_dir --no-warn-script-location --upgrade pip
+_err_exit $? _err_msg
+
+echo -e "\n***** Updated pip *****\n"
+
+_err_msg="\n----- requirements file copy failed -----\n"
+cp binary_installer/py3.10-${OS_NAME}-"${OS_ARCH}"-${CD}-reqs.txt requirements.txt
+_err_exit $? _err_msg
+
+_err_msg="\n----- main pip install failed -----\n"
+.venv/bin/python3 -m pip install $no_cache_dir --no-warn-script-location -r requirements.txt
+_err_exit $? _err_msg
+
+echo -e "\n***** Installed Python dependencies *****\n"
+
+_err_msg="\n----- InvokeAI setup failed -----\n"
+.venv/bin/python3 -m pip install $no_cache_dir --no-warn-script-location -e .
+_err_exit $? _err_msg
+
+echo -e "\n***** Installed InvokeAI *****\n"
+
+cp binary_installer/invoke.sh.in ./invoke.sh
+chmod a+rx ./invoke.sh
+echo -e "\n***** Installed invoke launcher script ******\n"
+
+# more cleanup
+rm -rf binary_installer/ installer_files/
+
+# preload the models
+.venv/bin/python3 scripts/configure_invokeai.py
+_err_msg="\n----- model download clone failed -----\n"
+_err_exit $? _err_msg
+deactivate
+
+echo -e "\n***** Finished downloading models *****\n"
+
+echo "All done! Run the command"
+echo "  $scriptdir/invoke.sh"
+echo "to start InvokeAI."
+read -p "Press any key to exit..."
+exit

binary_installer/invoke.bat.in

@@ -0,0 +1,36 @@
+@echo off
+
+PUSHD "%~dp0"
+call .venv\Scripts\activate.bat
+
+echo Do you want to generate images using the
+echo 1. command-line
+echo 2. browser-based UI
+echo OR
+echo 3. open the developer console
+set /p choice="Please enter 1, 2 or 3: "
+if /i "%choice%" == "1" (
+    echo Starting the InvokeAI command-line.
+    .venv\Scripts\python scripts\invoke.py %*
+) else if /i "%choice%" == "2" (
+    echo Starting the InvokeAI browser-based UI.
+    .venv\Scripts\python scripts\invoke.py --web %*
+) else if /i "%choice%" == "3" (
+    echo Developer Console
+    echo Python command is:
+    where python
+    echo Python version is:
+    python --version
+    echo *************************
+    echo You are now in the system shell, with the local InvokeAI Python virtual environment activated,
+    echo so that you can troubleshoot this InvokeAI installation as necessary.
+    echo *************************
+    echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
+    call cmd /k
+) else (
+    echo Invalid selection
+    pause
+    exit /b
+)
+
+deactivate

binary_installer/invoke.sh.in

@@ -0,0 +1,46 @@
+#!/usr/bin/env sh
+
+set -eu
+
+. .venv/bin/activate
+
+# set required env var for torch on mac MPS
+ if [ "$(uname -s)" == "Darwin" ]; then
+     export PYTORCH_ENABLE_MPS_FALLBACK=1
+ fi
+
+echo "Do you want to generate images using the"
+echo "1. command-line"
+echo "2. browser-based UI"
+echo "OR"
+echo "3. open the developer console"
+echo "Please enter 1, 2, or 3:"
+read choice
+
+case $choice in
+    1)
+        printf "\nStarting the InvokeAI command-line..\n";
+        .venv/bin/python scripts/invoke.py $*;
+    ;;
+    2)
+        printf "\nStarting the InvokeAI browser-based UI..\n";
+        .venv/bin/python scripts/invoke.py --web $*;
+    ;;
+    3)
+        printf "\nDeveloper Console:\n";
+        printf "Python command is:\n\t";
+        which python;
+        printf "Python version is:\n\t";
+        python --version;
+        echo "*************************"
+        echo "You are now in your user shell ($SHELL) with the local InvokeAI Python virtual environment activated,";
+        echo "so that you can troubleshoot this InvokeAI installation as necessary.";
+        printf "*************************\n"
+        echo "*** Type \`exit\` to quit this shell and deactivate the Python virtual environment *** ";
+        /usr/bin/env "$SHELL";
+    ;;
+    *)
+        echo "Invalid selection";
+        exit
+    ;;
+esac

binary_installer/readme.txt

@@ -0,0 +1,17 @@
+InvokeAI
+
+Project homepage: https://github.com/invoke-ai/InvokeAI
+
+Installation on Windows:
+    NOTE: You might need to enable Windows Long Paths. If you're not sure,
+    then you almost certainly need to. Simply double-click the 'WinLongPathsEnabled.reg'
+    file. Note that you will need to have admin privileges in order to
+    do this.
+
+    Please double-click the 'install.bat' file (while keeping it inside the invokeAI folder).
+
+Installation on Linux and Mac:
+    Please open the terminal, and run './install.sh' (while keeping it inside the invokeAI folder).
+
+After installation, please run the 'invoke.bat' file (on Windows) or 'invoke.sh'
+file (on Linux/Mac) to start InvokeAI.

binary_installer/requirements.in

@@ -0,0 +1,32 @@
+--prefer-binary
+--extra-index-url https://download.pytorch.org/whl/torch_stable.html
+--extra-index-url https://download.pytorch.org/whl/cu116
+--trusted-host https://download.pytorch.org
+accelerate~=0.14
+albumentations
+diffusers
+eventlet
+flask_cors
+flask_socketio
+flaskwebgui==1.0.3
+getpass_asterisk
+imageio-ffmpeg
+pyreadline3
+realesrgan
+send2trash
+streamlit
+taming-transformers-rom1504
+test-tube
+torch-fidelity
+torch==1.12.1 ; platform_system == 'Darwin'
+torch==1.12.0+cu116 ; platform_system == 'Linux' or platform_system == 'Windows'
+torchvision==0.13.1 ; platform_system == 'Darwin'
+torchvision==0.13.0+cu116 ; platform_system == 'Linux' or platform_system == 'Windows'
+transformers
+picklescan
+https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip
+https://github.com/invoke-ai/clipseg/archive/1f754751c85d7d4255fa681f4491ff5711c1c288.zip
+https://github.com/invoke-ai/GFPGAN/archive/3f5d2397361199bc4a91c08bb7d80f04d7805615.zip ; platform_system=='Windows'
+https://github.com/invoke-ai/GFPGAN/archive/c796277a1cf77954e5fc0b288d7062d162894248.zip ; platform_system=='Linux' or platform_system=='Darwin'
+https://github.com/Birch-san/k-diffusion/archive/363386981fee88620709cf8f6f2eea167bd6cd74.zip
+https://github.com/invoke-ai/PyPatchMatch/archive/129863937a8ab37f6bbcec327c994c0f932abdbc.zip

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 GB)
+   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/autoencoder/autoencoder_kl_16x16x16.yaml

@@ -1,54 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 16
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 16
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,1,2,2,4]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [16]
-      dropout: 0.0
-
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_32x32x4.yaml

@@ -1,53 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 4
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 4
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [ ]
-      dropout: 0.0
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_64x64x3.yaml

@@ -1,54 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 3
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 3
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,2,4 ]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [ ]
-      dropout: 0.0
-
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_8x8x64.yaml

@@ -1,53 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 64
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 64
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,1,2,2,4,4]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [16,8]
-      dropout: 0.0
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/latent-diffusion/celebahq-ldm-vq-4.yaml

@@ -1,86 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ckpt_path: models/first_stage_models/vq-f4/model.ckpt
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 48
-    num_workers: 5
-    wrap: false
-    train:
-      target: taming.data.faceshq.CelebAHQTrain
-      params:
-        size: 256
-    validation:
-      target: taming.data.faceshq.CelebAHQValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/cin-ldm-vq-f8.yaml

@@ -1,98 +0,0 @@
-model:
-  base_learning_rate: 1.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: class_label
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 256
-        attention_resolutions:
-        #note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 32 for f8
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 4
-        num_head_channels: 32
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 512
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 4
-        n_embed: 16384
-        ckpt_path: configs/first_stage_models/vq-f8/model.yaml
-        ddconfig:
-          double_z: false
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions:
-          - 32
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.ClassEmbedder
-      params:
-        embed_dim: 512
-        key: class_label
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 64
-    num_workers: 12
-    wrap: false
-    train:
-      target: ldm.data.imagenet.ImageNetTrain
-      params:
-        config:
-          size: 256
-    validation:
-      target: ldm.data.imagenet.ImageNetValidation
-      params:
-        config:
-          size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/cin256-v2.yaml

@@ -1,68 +0,0 @@
-model:
-  base_learning_rate: 0.0001
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: class_label
-    image_size: 64
-    channels: 3
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss
-    use_ema: False
-    
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 192
-        attention_resolutions:
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 5
-        num_heads: 1
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 512
-    
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.ClassEmbedder
-      params:
-        n_classes: 1001
-        embed_dim: 512
-        key: class_label

configs/latent-diffusion/ffhq-ldm-vq-4.yaml

@@ -1,85 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ckpt_path: configs/first_stage_models/vq-f4/model.yaml
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 42
-    num_workers: 5
-    wrap: false
-    train:
-      target: taming.data.faceshq.FFHQTrain
-      params:
-        size: 256
-    validation:
-      target: taming.data.faceshq.FFHQValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/lsun_bedrooms-ldm-vq-4.yaml

@@ -1,85 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        ckpt_path: configs/first_stage_models/vq-f4/model.yaml
-        embed_dim: 3
-        n_embed: 8192
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 48
-    num_workers: 5
-    wrap: false
-    train:
-      target: ldm.data.lsun.LSUNBedroomsTrain
-      params:
-        size: 256
-    validation:
-      target: ldm.data.lsun.LSUNBedroomsValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/lsun_churches-ldm-kl-8.yaml

@@ -1,91 +0,0 @@
-model:
-  base_learning_rate: 5.0e-5   # set to target_lr by starting main.py with '--scale_lr False'
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0155
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    loss_type: l1
-    first_stage_key: "image"
-    cond_stage_key: "image"
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: False
-    concat_mode: False
-    scale_by_std: True
-    monitor: 'val/loss_simple_ema'
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [10000]
-        cycle_lengths: [10000000000000]
-        f_start: [1.e-6]
-        f_max: [1.]
-        f_min: [ 1.]
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 192
-        attention_resolutions: [ 1, 2, 4, 8 ]   # 32, 16, 8, 4
-        num_res_blocks: 2
-        channel_mult: [ 1,2,2,4,4 ]  # 32, 16, 8, 4, 2
-        num_heads: 8
-        use_scale_shift_norm: True
-        resblock_updown: True
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: "val/rec_loss"
-        ckpt_path: "models/first_stage_models/kl-f8/model.ckpt"
-        ddconfig:
-          double_z: True
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
-          num_res_blocks: 2
-          attn_resolutions: [ ]
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config: "__is_unconditional__"
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 96
-    num_workers: 5
-    wrap: False
-    train:
-      target: ldm.data.lsun.LSUNChurchesTrain
-      params:
-        size: 256
-    validation:
-      target: ldm.data.lsun.LSUNChurchesValidation
-      params:
-        size: 256
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/txt2img-1p4B-eval.yaml

@@ -1,71 +0,0 @@
-model:
-  base_learning_rate: 5.0e-05
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.012
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: caption
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        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: 1280
-        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.BERTEmbedder
-      params:
-        n_embed: 1280
-        n_layer: 32

configs/models.yaml

@@ -1,18 +0,0 @@
-# This file describes the alternative machine learning models
-#  available to the dream 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.
-
-laion400m:
-    config:  configs/latent-diffusion/txt2img-1p4B-eval.yaml
-    weights: models/ldm/text2img-large/model.ckpt
-    width: 256
-    height: 256
-stable-diffusion-1.4:
-    config:  configs/stable-diffusion/v1-inference.yaml
-    weights: models/ldm/stable-diffusion-v1/model.ckpt
-    width: 512
-    height: 512

configs/models.yaml.example

@@ -0,0 +1,29 @@
+# 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
+  width: 512
+  height: 512

configs/retrieval-augmented-diffusion/768x768.yaml

@@ -1,68 +0,0 @@
-model:
-  base_learning_rate: 0.0001
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.015
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: jpg
-    cond_stage_key: nix
-    image_size: 48
-    channels: 16
-    cond_stage_trainable: false
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_by_std: false
-    scale_factor: 0.22765929
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 48
-        in_channels: 16
-        out_channels: 16
-        model_channels: 448
-        attention_resolutions:
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        use_scale_shift_norm: false
-        resblock_updown: false
-        num_head_channels: 32
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 768
-        use_checkpoint: true
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        monitor: val/rec_loss
-        embed_dim: 16
-        ddconfig:
-          double_z: true
-          z_channels: 16
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 1
-          - 2
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions:
-          - 16
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config:
-      target: torch.nn.Identity

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

@@ -107,4 +107,4 @@ lightning:
     benchmark: True
     max_steps: 4000000
 #    max_steps: 4000
-    
+

configs/stable-diffusion/v1-inference.yaml

@@ -30,9 +30,9 @@ model:
       target: ldm.modules.embedding_manager.EmbeddingManager
       params:
         placeholder_strings: ["*"]
-        initializer_words: ['face', 'man', 'photo', 'africanmale']
+        initializer_words: ['sculpture']
         per_image_tokens: false
-        num_vectors_per_token: 6
+        num_vectors_per_token: 1
         progressive_words: False
 
     unet_config:
@@ -76,4 +76,4 @@ model:
           target: torch.nn.Identity
 
     cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+      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

@@ -22,7 +22,7 @@ model:
       target: ldm.modules.embedding_manager.EmbeddingManager
       params:
         placeholder_strings: ["*"]
-        initializer_words: ['face', 'man', 'photo', 'africanmale']
+        initializer_words: ['sculpture']
         per_image_tokens: false
         num_vectors_per_token: 6
         progressive_words: False
@@ -107,4 +107,4 @@ lightning:
     benchmark: False
     max_steps: 6200
 #    max_steps: 4000
-    
+

docker-build/Dockerfile

@@ -1,57 +1,65 @@
-FROM        debian 
+FROM python:3.10-slim AS builder
 
-ARG         gsd
-ENV         GITHUB_STABLE_DIFFUSION $gsd
+# use bash
+SHELL [ "/bin/bash", "-c" ]
 
-ARG         rsd
-ENV         REQS $rsd
+# Install necesarry packages
+RUN apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    gcc=4:10.2.* \
+    libgl1-mesa-glx=20.3.* \
+    libglib2.0-0=2.66.* \
+    python3-dev=3.9.* \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
 
-ARG         cs
-ENV         CONDA_SUBDIR $cs
+# set WORKDIR, PATH and copy sources
+ARG APPDIR=/usr/src/app
+WORKDIR ${APPDIR}
+ENV PATH ${APPDIR}/.venv/bin:$PATH
+ARG PIP_REQUIREMENTS=requirements-lin-cuda.txt
+COPY . ./environments-and-requirements/${PIP_REQUIREMENTS} ./
 
-ENV         PIP_EXISTS_ACTION="w"
+# install requirements
+RUN python3 -m venv .venv \
+  && pip install \
+    --upgrade \
+    --no-cache-dir \
+    'wheel>=0.38.4' \
+  && pip install \
+    --no-cache-dir \
+    -r ${PIP_REQUIREMENTS}
 
-# TODO: Optimize image size
+FROM python:3.10-slim AS runtime
 
-SHELL       ["/bin/bash", "-c"]
+# setup environment
+ARG APPDIR=/usr/src/app
+WORKDIR ${APPDIR}
+COPY --from=builder ${APPDIR} .
+ENV \
+  PATH=${APPDIR}/.venv/bin:$PATH \
+  INVOKEAI_ROOT=/data \
+  INVOKE_MODEL_RECONFIGURE=--yes
 
-WORKDIR     /
-RUN         apt update && apt upgrade -y \
-            && apt install -y \
-            git \
-            libgl1-mesa-glx \
-            libglib2.0-0 \
-            pip \
-            python3 \
-            && git clone $GITHUB_STABLE_DIFFUSION
+# Install necesarry packages
+RUN apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    build-essential=12.9 \
+    libgl1-mesa-glx=20.3.* \
+    libglib2.0-0=2.66.* \
+    libopencv-dev=4.5.* \
+  && ln -sf \
+    /usr/lib/"$(arch)"-linux-gnu/pkgconfig/opencv4.pc \
+    /usr/lib/"$(arch)"-linux-gnu/pkgconfig/opencv.pc \
+  && python3 -c "from patchmatch import patch_match" \
+  && apt-get remove -y \
+    --autoremove \
+    build-essential \
+  && apt-get autoclean \
+  && rm -rf /var/lib/apt/lists/*
 
-# Install Anaconda or Miniconda
-COPY        anaconda.sh .
-RUN         bash anaconda.sh -b -u -p /anaconda && /anaconda/bin/conda init bash
-
-# SD 
-WORKDIR     /stable-diffusion 
-RUN         source ~/.bashrc \
-            && conda create -y --name ldm && conda activate ldm \
-            && conda config --env --set subdir $CONDA_SUBDIR \
-            && pip3 install -r $REQS \   
-            && pip3 install basicsr facexlib realesrgan \          
-            && mkdir models/ldm/stable-diffusion-v1 \
-            && ln -s "/data/sd-v1-4.ckpt" models/ldm/stable-diffusion-v1/model.ckpt 
-
-# Face restoreation
-# by default expected in a sibling directory to stable-diffusion
-WORKDIR     /       
-RUN         git clone https://github.com/TencentARC/GFPGAN.git 
-
-WORKDIR     /GFPGAN 
-RUN         pip3 install -r requirements.txt \
-            && python3 setup.py develop \
-            && ln -s "/data/GFPGANv1.4.pth" experiments/pretrained_models/GFPGANv1.4.pth
-
-WORKDIR     /stable-diffusion 
-RUN         python3 scripts/preload_models.py         
-
-WORKDIR     /
-COPY        entrypoint.sh .
-ENTRYPOINT ["/entrypoint.sh"]
+# set Entrypoint and default CMD
+ENTRYPOINT [ "python3", "scripts/invoke.py" ]
+CMD [ "--web", "--host=0.0.0.0" ]

docker-build/Dockerfile.cloud

@@ -0,0 +1,86 @@
+#######################
+#### Builder stage ####
+
+FROM library/ubuntu:22.04 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 \
+        libglib2.0-0 \
+        libgl1-mesa-glx \
+        python3-venv \
+        python3-pip \
+        build-essential \
+        python3-opencv \
+        libopencv-dev
+
+# This is needed for patchmatch support
+RUN cd /usr/lib/x86_64-linux-gnu/pkgconfig/ &&\
+   ln -sf opencv4.pc opencv.pc
+
+ARG WORKDIR=/invokeai
+WORKDIR ${WORKDIR}
+
+ENV VIRTUAL_ENV=${WORKDIR}/.venv
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+    python3 -m venv ${VIRTUAL_ENV} &&\
+    pip install --extra-index-url https://download.pytorch.org/whl/cu116 \
+        torch==1.12.0+cu116 \
+        torchvision==0.13.0+cu116 &&\
+    pip install -e git+https://github.com/invoke-ai/PyPatchMatch@0.1.3#egg=pypatchmatch
+
+COPY . .
+RUN --mount=type=cache,target=/root/.cache/pip \
+    cp environments-and-requirements/requirements-lin-cuda.txt requirements.txt && \
+    pip install -r requirements.txt &&\
+    pip install -e .
+
+
+#######################
+#### Runtime stage ####
+
+FROM library/ubuntu:22.04 as runtime
+
+ARG DEBIAN_FRONTEND=noninteractive
+ENV PYTHONUNBUFFERED=1
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
+    apt update && apt install -y --no-install-recommends \
+        git \
+        curl \
+        ncdu \
+        iotop \
+        bzip2 \
+        libglib2.0-0 \
+        libgl1-mesa-glx \
+        python3-venv \
+        python3-pip \
+        build-essential \
+        python3-opencv \
+        libopencv-dev &&\
+    apt-get clean && apt-get autoclean
+
+ARG WORKDIR=/invokeai
+WORKDIR ${WORKDIR}
+
+ENV INVOKEAI_ROOT=/mnt/invokeai
+ENV VIRTUAL_ENV=${WORKDIR}/.venv
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+COPY --from=builder ${WORKDIR} ${WORKDIR}
+COPY --from=builder /usr/lib/x86_64-linux-gnu/pkgconfig /usr/lib/x86_64-linux-gnu/pkgconfig
+
+# build patchmatch
+RUN python -c "from patchmatch import patch_match"
+
+## workaround for non-existent initfile when runtime directory is mounted; see #1613
+RUN touch /root/.invokeai
+
+ENTRYPOINT ["bash"]
+
+CMD ["-c", "python3 scripts/invoke.py --web --host 0.0.0.0"]

docker-build/Makefile

@@ -0,0 +1,44 @@
+# Directory in the container where the INVOKEAI_ROOT (runtime dir) will be mounted
+INVOKEAI_ROOT=/mnt/invokeai
+# Host directory to contain the runtime dir. Will be mounted at INVOKEAI_ROOT path in the container
+HOST_MOUNT_PATH=${HOME}/invokeai
+
+IMAGE=local/invokeai:latest
+
+USER=$(shell id -u)
+GROUP=$(shell id -g)
+
+# All downloaded models, config, etc will end up in ${HOST_MOUNT_PATH} on the host.
+# This is consistent with the expected non-Docker behaviour.
+# Contents can be moved to a persistent storage and used to prime the cache on another host.
+
+build:
+	DOCKER_BUILDKIT=1 docker build -t local/invokeai:latest -f Dockerfile.cloud ..
+
+configure:
+	docker run --rm -it --runtime=nvidia --gpus=all \
+		-v ${HOST_MOUNT_PATH}:${INVOKEAI_ROOT} \
+		-e INVOKEAI_ROOT=${INVOKEAI_ROOT} \
+		${IMAGE} -c "python scripts/configure_invokeai.py"
+
+# Run the container with the runtime dir mounted and the web server exposed on port 9090
+web:
+	docker run --rm -it --runtime=nvidia --gpus=all \
+		-v ${HOST_MOUNT_PATH}:${INVOKEAI_ROOT} \
+		-e INVOKEAI_ROOT=${INVOKEAI_ROOT} \
+		-p 9090:9090 \
+		${IMAGE} -c "python scripts/invoke.py --web --host 0.0.0.0"
+
+# Run the cli with the runtime dir mounted
+cli:
+	docker run --rm -it --runtime=nvidia --gpus=all \
+		-v ${HOST_MOUNT_PATH}:${INVOKEAI_ROOT} \
+		-e INVOKEAI_ROOT=${INVOKEAI_ROOT} \
+		${IMAGE} -c "python scripts/invoke.py"
+
+# Run the container with the runtime dir mounted and open a bash shell
+shell:
+	docker run --rm -it --runtime=nvidia --gpus=all \
+		-v ${HOST_MOUNT_PATH}:${INVOKEAI_ROOT} ${IMAGE} --
+
+.PHONY: build configure web cli shell

docker-build/build.sh

@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+set -e
+
+# How to use: https://invoke-ai.github.io/InvokeAI/installation/INSTALL_DOCKER/#setup
+
+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 -e "You are using these values:\n"
+echo -e "Dockerfile:\t ${DOCKERFILE}"
+echo -e "Requirements:\t ${PIP_REQUIREMENTS}"
+echo -e "Volumename:\t ${VOLUMENAME}"
+echo -e "arch:\t\t ${ARCH}"
+echo -e "Platform:\t ${PLATFORM}"
+echo -e "Invokeai_tag:\t ${INVOKEAI_TAG}\n"
+
+if [[ -n "$(docker volume ls -f name="${VOLUMENAME}" -q)" ]]; then
+  echo -e "Volume already exists\n"
+else
+  echo -n "createing docker volume "
+  docker volume create "${VOLUMENAME}"
+fi
+
+# Build Container
+docker build \
+  --platform="${PLATFORM}" \
+  --tag="${INVOKEAI_TAG}" \
+  --build-arg="PIP_REQUIREMENTS=${PIP_REQUIREMENTS}" \
+  --file="${DOCKERFILE}" \
+  .

docker-build/entrypoint.sh

@@ -1,10 +0,0 @@
-#!/bin/bash
-
-cd /stable-diffusion
-
-if [ $# -eq 0 ]; then
-    python3 scripts/dream.py --full_precision -o /data
-    # bash
-else
-    python3 scripts/dream.py --full_precision -o /data "$@"
-fi

docker-build/env.sh

@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+
+# Variables shared by build.sh and run.sh
+REPOSITORY_NAME=${REPOSITORY_NAME:-$(basename "$(git rev-parse --show-toplevel)")}
+VOLUMENAME=${VOLUMENAME:-${REPOSITORY_NAME,,}_data}
+ARCH=${ARCH:-$(uname -m)}
+PLATFORM=${PLATFORM:-Linux/${ARCH}}
+CONTAINER_FLAVOR=${CONTAINER_FLAVOR:-cuda}
+INVOKEAI_BRANCH=$(git branch --show)
+INVOKEAI_TAG=${REPOSITORY_NAME,,}-${CONTAINER_FLAVOR}:${INVOKEAI_TAG:-${INVOKEAI_BRANCH/\//-}}

docker-build/run.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+set -e
+
+# How to use: https://invoke-ai.github.io/InvokeAI/installation/INSTALL_DOCKER/#run-the-container
+# IMPORTANT: You need to have a token on huggingface.co to be able to download the checkpoints!!!
+
+source ./docker-build/env.sh \
+  || echo "please run from repository root" \
+  || exit 1
+
+# check if HUGGINGFACE_TOKEN is available
+# You must have accepted the terms of use for required models
+HUGGINGFACE_TOKEN=${HUGGINGFACE_TOKEN:?Please set your token for Huggingface as HUGGINGFACE_TOKEN}
+
+echo -e "You are using these values:\n"
+echo -e "Volumename:\t ${VOLUMENAME}"
+echo -e "Invokeai_tag:\t ${INVOKEAI_TAG}\n"
+
+docker run \
+  --interactive \
+  --tty \
+  --rm \
+  --platform="$PLATFORM" \
+  --name="${REPOSITORY_NAME,,}" \
+  --hostname="${REPOSITORY_NAME,,}" \
+  --mount="source=$VOLUMENAME,target=/data" \
+  --env="HUGGINGFACE_TOKEN=${HUGGINGFACE_TOKEN}" \
+  --publish=9090:9090 \
+  --cap-add=sys_nice \
+  ${GPU_FLAGS:+--gpus=${GPU_FLAGS}} \
+  "$INVOKEAI_TAG" ${1:+$@}

docs/CHANGELOG.md

@@ -1,64 +1,408 @@
-# **Changelog**
+---
+title: Changelog
+---
 
-## v1.13 (in process)
+# :octicons-log-16: **Changelog**
 
-- Supports a Google Colab notebook for a standalone server running on Google hardware [Arturo Mendivil](https://github.com/artmen1516)
-- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling [Kevin Gibbons](https://github.com/bakkot)
-- WebUI supports incremental display of in-progress images during generation [Kevin Gibbons](https://github.com/bakkot)
-- Output directory can be specified on the dream> command line.
-- The grid was displaying duplicated images when not enough images to fill the final row [Muhammad Usama](https://github.com/SMUsamaShah)
-- Can specify --grid on dream.py command line as the default.
+## v2.2.4 <small>(11 December 2022)</small>
+
+**the `invokeai` directory**
+
+Previously there were two directories to worry about, the directory that
+contained the InvokeAI source code and the launcher scripts, and the `invokeai`
+directory that contained the models files, embeddings, configuration and
+outputs. With the 2.2.4 release, this dual system is done away with, and
+everything, including the `invoke.bat` and `invoke.sh` launcher scripts, now
+live in a directory named `invokeai`. By default this directory is located in
+your home directory (e.g. `\Users\yourname` on Windows), but you can select
+where it goes at install time.
+
+After installation, you can delete the install directory (the one that the zip
+file creates when it unpacks). Do **not** delete or move the `invokeai`
+directory!
+
+**Initialization file `invokeai/invokeai.init`**
+
+You can place frequently-used startup options in this file, such as the default
+number of steps or your preferred sampler. To keep everything in one place, this
+file has now been moved into the `invokeai` directory and is named
+`invokeai.init`.
+
+**To update from Version 2.2.3**
+
+The easiest route is to download and unpack one of the 2.2.4 installer files.
+When it asks you for the location of the `invokeai` runtime directory, respond
+with the path to the directory that contains your 2.2.3 `invokeai`. That is, if
+`invokeai` lives at `C:\Users\fred\invokeai`, then answer with `C:\Users\fred`
+and answer "Y" when asked if you want to reuse the directory.
+
+The `update.sh` (`update.bat`) script that came with the 2.2.3 source installer
+does not know about the new directory layout and won't be fully functional.
+
+**To update to 2.2.5 (and beyond) there's now an update path**
+
+As they become available, you can update to more recent versions of InvokeAI
+using an `update.sh` (`update.bat`) script located in the `invokeai` directory.
+Running it without any arguments will install the most recent version of
+InvokeAI. Alternatively, you can get set releases by running the `update.sh`
+script with an argument in the command shell. This syntax accepts the path to
+the desired release's zip file, which you can find by clicking on the green
+"Code" button on this repository's home page.
+
+**Other 2.2.4 Improvements**
+
+- Fix InvokeAI GUI initialization by @addianto in #1687
+- fix link in documentation by @lstein in #1728
+- Fix broken link by @ShawnZhong in #1736
+- Remove reference to binary installer by @lstein in #1731
+- documentation fixes for 2.2.3 by @lstein in #1740
+- Modify installer links to point closer to the source installer by @ebr in
+  #1745
+- add documentation warning about 1650/60 cards by @lstein in #1753
+- Fix Linux source URL in installation docs by @andybearman in #1756
+- Make install instructions discoverable in readme by @damian0815 in #1752
+- typo fix by @ofirkris in #1755
+- Non-interactive model download (support HUGGINGFACE_TOKEN) by @ebr in #1578
+- fix(srcinstall): shell installer - cp scripts instead of linking by @tildebyte
+  in #1765
+- stability and usage improvements to binary & source installers by @lstein in
+  #1760
+- fix off-by-one bug in cross-attention-control by @damian0815 in #1774
+- Eventually update APP_VERSION to 2.2.3 by @spezialspezial in #1768
+- invoke script cds to its location before running by @lstein in #1805
+- Make PaperCut and VoxelArt models load again by @lstein in #1730
+- Fix --embedding_directory / --embedding_path not working by @blessedcoolant in
+  #1817
+- Clean up readme by @hipsterusername in #1820
+- Optimized Docker build with support for external working directory by @ebr in
+  #1544
+- disable pushing the cloud container by @mauwii in #1831
+- Fix docker push github action and expand with additional metadata by @ebr in
+  #1837
+- Fix Broken Link To Notebook by @VedantMadane in #1821
+- Account for flat models by @spezialspezial in #1766
+- Update invoke.bat.in isolate environment variables by @lynnewu in #1833
+- Arch Linux Specific PatchMatch Instructions & fixing conda install on linux by
+  @SammCheese in #1848
+- Make force free GPU memory work in img2img by @addianto in #1844
+- New installer by @lstein
+
+## v2.2.3 <small>(2 December 2022)</small>
+
+!!! Note
+
+    This point release removes references to the binary installer from the
+    installation guide. The binary installer is not stable at the current
+    time. First time users are encouraged to use the "source" installer as
+    described in [Installing InvokeAI with the Source Installer](installation/INSTALL_SOURCE.md)
+
+With InvokeAI 2.2, this project now provides enthusiasts and professionals a
+robust workflow solution for creating AI-generated and human facilitated
+compositions. Additional enhancements have been made as well, improving safety,
+ease of use, and installation.
+
+Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a
+512x768 image (and less for smaller images), and is compatible with
+Windows/Linux/Mac (M1 & M2).
+
+You can see the [release video](https://youtu.be/hIYBfDtKaus) here, which
+introduces the main WebUI enhancement for version 2.2 -
+[The Unified Canvas](features/UNIFIED_CANVAS.md). This new workflow is the
+biggest enhancement added to the WebUI to date, and unlocks a stunning amount of
+potential for users to create and iterate on their creations. The following
+sections describe what's new for InvokeAI.
+
+## v2.2.2 <small>(30 November 2022)</small>
+
+!!! note
+
+    The binary installer is not ready for prime time. First time users are recommended to install via the "source" installer accessible through the links at the bottom of this page.****
+
+With InvokeAI 2.2, this project now provides enthusiasts and professionals a
+robust workflow solution for creating AI-generated and human facilitated
+compositions. Additional enhancements have been made as well, improving safety,
+ease of use, and installation.
+
+Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a
+512x768 image (and less for smaller images), and is compatible with
+Windows/Linux/Mac (M1 & M2).
+
+You can see the [release video](https://youtu.be/hIYBfDtKaus) here, which
+introduces the main WebUI enhancement for version 2.2 -
+[The Unified Canvas](https://invoke-ai.github.io/InvokeAI/features/UNIFIED_CANVAS/).
+This new workflow is the biggest enhancement added to the WebUI to date, and
+unlocks a stunning amount of potential for users to create and iterate on their
+creations. The following sections describe what's new for InvokeAI.
+
+## v2.2.0 <small>(2 December 2022)</small>
+
+With InvokeAI 2.2, this project now provides enthusiasts and professionals a
+robust workflow solution for creating AI-generated and human facilitated
+compositions. Additional enhancements have been made as well, improving safety,
+ease of use, and installation.
+
+Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a
+512x768 image (and less for smaller images), and is compatible with
+Windows/Linux/Mac (M1 & M2).
+
+You can see the [release video](https://youtu.be/hIYBfDtKaus) here, which
+introduces the main WebUI enhancement for version 2.2 -
+[The Unified Canvas](features/UNIFIED_CANVAS.md). This new workflow is the
+biggest enhancement added to the WebUI to date, and unlocks a stunning amount of
+potential for users to create and iterate on their creations. The following
+sections describe what's new for InvokeAI.
+
+## v2.1.3 <small>(13 November 2022)</small>
+
+- A choice of installer scripts that automate installation and configuration.
+  See
+  [Installation](installation/index.md).
+- A streamlined manual installation process that works for both Conda and
+  PIP-only installs. See
+  [Manual Installation](installation/INSTALL_MANUAL.md).
+- The ability to save frequently-used startup options (model to load, steps,
+  sampler, etc) in a `.invokeai` file. See
+  [Client](features/CLI.md)
+- Support for AMD GPU cards (non-CUDA) on Linux machines.
+- Multiple bugs and edge cases squashed.
+
+## v2.1.0 <small>(2 November 2022)</small>
+
+- update mac instructions to use invokeai for env name by @willwillems in #1030
+- Update .gitignore by @blessedcoolant in #1040
+- reintroduce fix for m1 from #579 missing after merge by @skurovec in #1056
+- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in #1060
+- Print out the device type which is used by @manzke in #1073
+- Hires Addition by @hipsterusername in #1063
+- fix for "1 leaked semaphore objects to clean up at shutdown" on M1 by
+  @skurovec in #1081
+- Forward dream.py to invoke.py using the same interpreter, add deprecation
+  warning by @db3000 in #1077
+- fix noisy images at high step counts by @lstein in #1086
+- Generalize facetool strength argument by @db3000 in #1078
+- Enable fast switching among models at the invoke> command line by @lstein in
+  #1066
+- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in #1095
+- Update generate.py by @unreleased in #1109
+- Update 'ldm' env to 'invokeai' in troubleshooting steps by @19wolf in #1125
+- Fixed documentation typos and resolved merge conflicts by @rupeshs in #1123
+- Fix broken doc links, fix malaprop in the project subtitle by @majick in #1131
+- Only output facetool parameters if enhancing faces by @db3000 in #1119
+- Update gitignore to ignore codeformer weights at new location by
+  @spezialspezial in #1136
+- fix links to point to invoke-ai.github.io #1117 by @mauwii in #1143
+- Rework-mkdocs by @mauwii in #1144
+- add option to CLI and pngwriter that allows user to set PNG compression level
+  by @lstein in #1127
+- Fix img2img DDIM index out of bound by @wfng92 in #1137
+- Fix gh actions by @mauwii in #1128
+- update mac instructions to use invokeai for env name by @willwillems in #1030
+- Update .gitignore by @blessedcoolant in #1040
+- reintroduce fix for m1 from #579 missing after merge by @skurovec in #1056
+- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in #1060
+- Print out the device type which is used by @manzke in #1073
+- Hires Addition by @hipsterusername in #1063
+- fix for "1 leaked semaphore objects to clean up at shutdown" on M1 by
+  @skurovec in #1081
+- Forward dream.py to invoke.py using the same interpreter, add deprecation
+  warning by @db3000 in #1077
+- fix noisy images at high step counts by @lstein in #1086
+- Generalize facetool strength argument by @db3000 in #1078
+- Enable fast switching among models at the invoke> command line by @lstein in
+  #1066
+- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in #1095
+- Fixed documentation typos and resolved merge conflicts by @rupeshs in #1123
+- Only output facetool parameters if enhancing faces by @db3000 in #1119
+- add option to CLI and pngwriter that allows user to set PNG compression level
+  by @lstein in #1127
+- Fix img2img DDIM index out of bound by @wfng92 in #1137
+- Add text prompt to inpaint mask support by @lstein in #1133
+- Respect http[s] protocol when making socket.io middleware by @damian0815 in
+  #976
+- WebUI: Adds Codeformer support by @psychedelicious in #1151
+- Skips normalizing prompts for web UI metadata by @psychedelicious in #1165
+- Add Asymmetric Tiling by @carson-katri in #1132
+- Web UI: Increases max CFG Scale to 200 by @psychedelicious in #1172
+- Corrects color channels in face restoration; Fixes #1167 by @psychedelicious
+  in #1175
+- Flips channels using array slicing instead of using OpenCV by @psychedelicious
+  in #1178
+- Fix typo in docs: s/Formally/Formerly by @noodlebox in #1176
+- fix clipseg loading problems by @lstein in #1177
+- Correct color channels in upscale using array slicing by @wfng92 in #1181
+- Web UI: Filters existing images when adding new images; Fixes #1085 by
+  @psychedelicious in #1171
+- fix a number of bugs in textual inversion by @lstein in #1190
+- Improve !fetch, add !replay command by @ArDiouscuros in #882
+- Fix generation of image with s>1000 by @holstvoogd in #951
+- Web UI: Gallery improvements by @psychedelicious in #1198
+- Update CLI.md by @krummrey in #1211
+- outcropping improvements by @lstein in #1207
+- add support for loading VAE autoencoders by @lstein in #1216
+- remove duplicate fix_func for MPS by @wfng92 in #1210
+- Metadata storage and retrieval fixes by @lstein in #1204
+- nix: add shell.nix file by @Cloudef in #1170
+- Web UI: Changes vite dist asset paths to relative by @psychedelicious in #1185
+- Web UI: Removes isDisabled from PromptInput by @psychedelicious in #1187
+- Allow user to generate images with initial noise as on M1 / mps system by
+  @ArDiouscuros in #981
+- feat: adding filename format template by @plucked in #968
+- Web UI: Fixes broken bundle by @psychedelicious in #1242
+- Support runwayML custom inpainting model by @lstein in #1243
+- Update IMG2IMG.md by @talitore in #1262
+- New dockerfile - including a build- and a run- script as well as a GH-Action
+  by @mauwii in #1233
+- cut over from karras to model noise schedule for higher steps by @lstein in
+  #1222
+- Prompt tweaks by @lstein in #1268
+- Outpainting implementation by @Kyle0654 in #1251
+- fixing aspect ratio on hires by @tjennings in #1249
+- Fix-build-container-action by @mauwii in #1274
+- handle all unicode characters by @damian0815 in #1276
+- adds models.user.yml to .gitignore by @JakeHL in #1281
+- remove debug branch, set fail-fast to false by @mauwii in #1284
+- Protect-secrets-on-pr by @mauwii in #1285
+- Web UI: Adds initial inpainting implementation by @psychedelicious in #1225
+- fix environment-mac.yml - tested on x64 and arm64 by @mauwii in #1289
+- Use proper authentication to download model by @mauwii in #1287
+- Prevent indexing error for mode RGB by @spezialspezial in #1294
+- Integrate sd-v1-5 model into test matrix (easily expandable), remove
+  unecesarry caches by @mauwii in #1293
+- add --no-interactive to configure_invokeai step by @mauwii in #1302
+- 1-click installer and updater. Uses micromamba to install git and conda into a
+  contained environment (if necessary) before running the normal installation
+  script by @cmdr2 in #1253
+- configure_invokeai.py script downloads the weight files by @lstein in #1290
+
+## v2.0.1 <small>(13 October 2022)</small>
+
+- 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 <small>(9 October 2022)</small>
+
+- `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for
+  backward compatibility.
+- Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
+- Support for [inpainting](features/INPAINTING.md) and
+  [outpainting](features/OUTPAINTING.md)
+- img2img runs on all k\* samplers
+- Support for
+  [negative prompts](features/PROMPTS.md#negative-and-unconditioned-prompts)
+- Support for CodeFormer face reconstruction
+- Support for Textual Inversion on Macintoshes
+- Support in both WebGUI and CLI for
+  [post-processing of previously-generated images](features/POSTPROCESS.md)
+  using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E
+  infinite canvas), and "embiggen" upscaling. See the `!fix` command.
+- New `--hires` option on `invoke>` line allows
+  [larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img),
+  at the cost of some performance.
+- New `--perlin` and `--threshold` options allow you to add and control
+  variation during image generation (see
+  [Thresholding and Perlin Noise Initialization](features/OTHER.md#thresholding-and-perlin-noise-initialization-options))
+- 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 [command-line completion behavior](features/CLI.md) 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`.
+
+## v1.14 <small>(11 September 2022)</small>
+
+- Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
+- Full support for Apple hardware with M1 or M2 chips.
+- Add "seamless mode" for circular tiling of image. Generates beautiful effects.
+  ([prixt](https://github.com/prixt)).
+- Inpainting support.
+- Improved web server GUI.
+- Lots of code and documentation cleanups.
+
+## v1.13 <small>(3 September 2022)</small>
+
+- Support image variations (see [VARIATIONS](features/VARIATIONS.md)
+  ([Kevin Gibbons](https://github.com/bakkot) and many contributors and
+  reviewers)
+- Supports a Google Colab notebook for a standalone server running on Google
+  hardware [Arturo Mendivil](https://github.com/artmen1516)
+- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling
+  [Kevin Gibbons](https://github.com/bakkot)
+- WebUI supports incremental display of in-progress images during generation
+  [Kevin Gibbons](https://github.com/bakkot)
+- A new configuration file scheme that allows new models (including upcoming
+  stable-diffusion-v1.5) to be added without altering the code.
+  ([David Wager](https://github.com/maddavid12))
+- Can specify --grid on invoke.py command line as the default.
 - Miscellaneous internal bug and stability fixes.
+- Works on M1 Apple hardware.
+- Multiple bug fixes.
 
 ---
 
-## v1.12 (28 August 2022)
+## v1.12 <small>(28 August 2022)</small>
 
 - Improved file handling, including ability to read prompts from standard input.
   (kudos to [Yunsaki](https://github.com/yunsaki)
-- The web server is now integrated with the dream.py script. Invoke by adding --web to
-  the dream.py command arguments.
+- The web server is now integrated with the invoke.py script. Invoke by adding
+  --web to the invoke.py command arguments.
 - Face restoration and upscaling via GFPGAN and Real-ESGAN are now automatically
   enabled if the GFPGAN directory is located as a sibling to Stable Diffusion.
-  VRAM requirements are modestly reduced. Thanks to both [Blessedcoolant](https://github.com/blessedcoolant) and
+  VRAM requirements are modestly reduced. Thanks to both
+  [Blessedcoolant](https://github.com/blessedcoolant) and
   [Oceanswave](https://github.com/oceanswave) for their work on this.
-- You can now swap samplers on the dream> command line. [Blessedcoolant](https://github.com/blessedcoolant)
+- You can now swap samplers on the invoke> command line.
+  [Blessedcoolant](https://github.com/blessedcoolant)
 
 ---
 
-## v1.11 (26 August 2022)
+## v1.11 <small>(26 August 2022)</small>
 
-- NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module. (kudos to [Oceanswave](https://github.com/Oceanswave)
-- You now can specify a seed of -1 to use the previous image's seed, -2 to use the seed for the image generated before that, etc.
-  Seed memory only extends back to the previous command, but will work on all images generated with the -n# switch.
+- NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module.
+  (kudos to [Oceanswave](https://github.com/Oceanswave)
+- You now can specify a seed of -1 to use the previous image's seed, -2 to use
+  the seed for the image generated before that, etc. Seed memory only extends
+  back to the previous command, but will work on all images generated with the
+  -n# switch.
 - Variant generation support temporarily disabled pending more general solution.
-- Created a feature branch named **yunsaki-morphing-dream** which adds experimental support for
-  iteratively modifying the prompt and its parameters. Please see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86)
-  for a synopsis of how this works. Note that when this feature is eventually added to the main branch, it will may be modified
-  significantly.
+- Created a feature branch named **yunsaki-morphing-invoke** which adds
+  experimental support for iteratively modifying the prompt and its parameters.
+  Please
+  see[Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86) for
+  a synopsis of how this works. Note that when this feature is eventually added
+  to the main branch, it will may be modified significantly.
 
 ---
 
-## v1.10 (25 August 2022)
+## v1.10 <small>(25 August 2022)</small>
 
-- A barebones but fully functional interactive web server for online generation of txt2img and img2img.
+- A barebones but fully functional interactive web server for online generation
+  of txt2img and img2img.
 
 ---
 
-## v1.09 (24 August 2022)
+## v1.09 <small>(24 August 2022)</small>
 
 - A new -v option allows you to generate multiple variants of an initial image
-  in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [
-  See this discussion in the PR for examples and details on use](https://github.com/lstein/stable-diffusion/pull/71#issuecomment-1226700810))
-- Added ability to personalize text to image generation (kudos to [Oceanswave](https://github.com/Oceanswave) and [nicolai256](https://github.com/nicolai256))
+  in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave).
+  [ See this discussion in the PR for examples and details on use](https://github.com/lstein/stable-diffusion/pull/71#issuecomment-1226700810))
+- Added ability to personalize text to image generation (kudos to
+  [Oceanswave](https://github.com/Oceanswave) and
+  [nicolai256](https://github.com/nicolai256))
 - Enabled all of the samplers from k_diffusion
 
 ---
 
-## v1.08 (24 August 2022)
+## v1.08 <small>(24 August 2022)</small>
 
-- Escape single quotes on the dream> command before trying to parse. This avoids
-  parse errors.
+- Escape single quotes on the invoke> command before trying to parse. This
+  avoids parse errors.
 - Removed instruction to get Python3.8 as first step in Windows install.
   Anaconda3 does it for you.
 - Added bounds checks for numeric arguments that could cause crashes.
@@ -66,40 +410,42 @@
 
 ---
 
-## v1.07 (23 August 2022)
+## v1.07 <small>(23 August 2022)</small>
 
-- Image filenames will now never fill gaps in the sequence, but will be assigned the
-  next higher name in the chosen directory. This ensures that the alphabetic and chronological
-  sort orders are the same.
+- Image filenames will now never fill gaps in the sequence, but will be assigned
+  the next higher name in the chosen directory. This ensures that the alphabetic
+  and chronological sort orders are the same.
 
 ---
 
-## v1.06 (23 August 2022)
+## v1.06 <small>(23 August 2022)</small>
 
-- Added weighted prompt support contributed by [xraxra](https://github.com/xraxra)
-- Example of using weighted prompts to tweak a demonic figure contributed by [bmaltais](https://github.com/bmaltais)
+- Added weighted prompt support contributed by
+  [xraxra](https://github.com/xraxra)
+- Example of using weighted prompts to tweak a demonic figure contributed by
+  [bmaltais](https://github.com/bmaltais)
 
 ---
 
-## v1.05 (22 August 2022 - after the drop)
+## v1.05 <small>(22 August 2022 - after the drop)</small>
 
-- Filenames now use the following formats:
-  000010.95183149.png -- Two files produced by the same command (e.g. -n2),
-  000010.26742632.png -- distinguished by a different seed.
+- Filenames now use the following formats: 000010.95183149.png -- Two files
+  produced by the same command (e.g. -n2), 000010.26742632.png -- distinguished
+  by a different seed.
 
   000011.455191342.01.png -- Two files produced by the same command using
   000011.455191342.02.png -- a batch size>1 (e.g. -b2). They have the same seed.
 
-  000011.4160627868.grid#1-4.png -- a grid of four images (-g); the whole grid can
-  be regenerated with the indicated key
+  000011.4160627868.grid#1-4.png -- a grid of four images (-g); the whole grid
+  can be regenerated with the indicated key
 
 - It should no longer be possible for one image to overwrite another
-- You can use the "cd" and "pwd" commands at the dream> prompt to set and retrieve
-  the path of the output directory.
+- You can use the "cd" and "pwd" commands at the invoke> prompt to set and
+  retrieve the path of the output directory.
 
 ---
 
-## v1.04 (22 August 2022 - after the drop)
+## v1.04 <small>(22 August 2022 - after the drop)</small>
 
 - Updated README to reflect installation of the released weights.
 - Suppressed very noisy and inconsequential warning when loading the frozen CLIP
@@ -107,31 +453,33 @@
 
 ---
 
-## v1.03 (22 August 2022)
+## v1.03 <small>(22 August 2022)</small>
 
-- The original txt2img and img2img scripts from the CompViz repository have been moved into
-  a subfolder named "orig_scripts", to reduce confusion.
+- The original txt2img and img2img scripts from the CompViz repository have been
+  moved into a subfolder named "orig_scripts", to reduce confusion.
 
 ---
 
-## v1.02 (21 August 2022)
+## v1.02 <small>(21 August 2022)</small>
 
-- A copy of the prompt and all of its switches and options is now stored in the corresponding
-  image in a tEXt metadata field named "Dream". You can read the prompt using scripts/images2prompt.py,
-  or an image editor that allows you to explore the full metadata.
-  **Please run "conda env update" to load the k_lms dependencies!!**
+- A copy of the prompt and all of its switches and options is now stored in the
+  corresponding image in a tEXt metadata field named "Dream". You can read the
+  prompt using scripts/images2prompt.py, or an image editor that allows you to
+  explore the full metadata. **Please run "conda env update" to load the k_lms
+  dependencies!!**
 
 ---
 
-## v1.01 (21 August 2022)
+## v1.01 <small>(21 August 2022)</small>
 
-- added k_lms sampling.
-  **Please run "conda env update" to load the k_lms dependencies!!**
-- use half precision arithmetic by default, resulting in faster execution and lower memory requirements
-  Pass argument --full_precision to dream.py to get slower but more accurate image generation
+- added k_lms sampling. **Please run "conda env update" to load the k_lms
+  dependencies!!**
+- use half precision arithmetic by default, resulting in faster execution and
+  lower memory requirements Pass argument --full_precision to invoke.py to get
+  slower but more accurate image generation
 
 ---
 
 ## Links
 
-- **[Read Me](../readme.md)**
+- **[Read Me](index.md)**