feat(ui): improve controlnet-related config types

There are some bugs with it that I cannot figure out related to `floating-ui` and `downshift`'s handling of refs.

Will need to revisit this component in the future.

.coveragerc

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

.dockerignore

@@ -4,22 +4,22 @@
 !ldm
 !pyproject.toml
 
-# Guard against pulling in any models that might exist in the directory tree
-**/*.pt*
-**/*.ckpt
-
-# ignore frontend but whitelist dist
-invokeai/frontend/
-!invokeai/frontend/dist/
+# ignore frontend/web but whitelist dist
+invokeai/frontend/web/
+!invokeai/frontend/web/dist/
 
 # ignore invokeai/assets but whitelist invokeai/assets/web
 invokeai/assets/
 !invokeai/assets/web/
 
+# Guard against pulling in any models that might exist in the directory tree
+**/*.pt*
+**/*.ckpt
+
 # Byte-compiled / optimized / DLL files
 **/__pycache__/
 **/*.py[cod]
 
 # Distribution / packaging
-*.egg-info/
-*.egg
+**/*.egg-info/
+**/*.egg

.editorconfig

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

.flake8

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

.git-blame-ignore-revs

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

.github/CODEOWNERS

@@ -2,60 +2,33 @@
 /.github/workflows/  @lstein @blessedcoolant
 
 # documentation
-/docs/ @lstein  @blessedcoolant
-mkdocs.yml  @lstein @ebr
+/docs/ @lstein @blessedcoolant @hipsterusername
+/mkdocs.yml @lstein  @blessedcoolant
+
+# nodes
+/invokeai/app/ @Kyle0654 @blessedcoolant
 
 # installation and configuration
-/pyproject.toml  @lstein @ebr
-/docker/ @lstein
-/scripts/ @ebr @lstein @blessedcoolant
-/installer/ @ebr @lstein 
-ldm/invoke/config @lstein @ebr
-invokeai/assets @lstein @blessedcoolant
-invokeai/configs @lstein @ebr  @blessedcoolant
-/ldm/invoke/_version.py @lstein @blessedcoolant
+/pyproject.toml  @lstein @blessedcoolant
+/docker/  @lstein @blessedcoolant
+/scripts/ @ebr @lstein
+/installer/ @lstein @ebr
+/invokeai/assets @lstein @ebr
+/invokeai/configs @lstein
+/invokeai/version @lstein @blessedcoolant
 
 # web ui
-/invokeai/frontend @blessedcoolant @psychedelicious
-/invokeai/backend @blessedcoolant @psychedelicious
+/invokeai/frontend @blessedcoolant @psychedelicious @lstein @maryhipp
+/invokeai/backend @blessedcoolant @psychedelicious @lstein @maryhipp
 
-# generation and model management
-/ldm/*.py @lstein @blessedcoolant
-/ldm/generate.py @lstein @gregghelt2
-/ldm/invoke/args.py @lstein @blessedcoolant
-/ldm/invoke/ckpt* @lstein @blessedcoolant
-/ldm/invoke/ckpt_generator @lstein @blessedcoolant
-/ldm/invoke/CLI.py @lstein @blessedcoolant
-/ldm/invoke/config @lstein @ebr  @blessedcoolant
-/ldm/invoke/generator @gregghelt2 @damian0815
-/ldm/invoke/globals.py @lstein @blessedcoolant 
-/ldm/invoke/merge_diffusers.py @lstein @blessedcoolant
-/ldm/invoke/model_manager.py @lstein @blessedcoolant
-/ldm/invoke/txt2mask.py @lstein @blessedcoolant
-/ldm/invoke/patchmatch.py @Kyle0654 @lstein
-/ldm/invoke/restoration @lstein @blessedcoolant
+# generation, model management, postprocessing
+/invokeai/backend  @damian0815 @lstein @blessedcoolant @jpphoto @gregghelt2 @StAlKeR7779
 
-# attention, textual inversion, model configuration
-/ldm/models @damian0815 @gregghelt2 @blessedcoolant
-/ldm/modules/textual_inversion_manager.py @lstein @blessedcoolant
-/ldm/modules/attention.py @damian0815 @gregghelt2
-/ldm/modules/diffusionmodules @damian0815 @gregghelt2
-/ldm/modules/distributions @damian0815 @gregghelt2
-/ldm/modules/ema.py  @damian0815 @gregghelt2
-/ldm/modules/embedding_manager.py @lstein
-/ldm/modules/encoders @damian0815 @gregghelt2
-/ldm/modules/image_degradation @damian0815 @gregghelt2
-/ldm/modules/losses  @damian0815 @gregghelt2
-/ldm/modules/x_transformer.py @damian0815 @gregghelt2
-
-# Nodes
-apps/ @Kyle0654 @jpphoto
-
-# legacy REST API
-# these are dead code
-#/ldm/invoke/pngwriter.py @CapableWeb
-#/ldm/invoke/server_legacy.py @CapableWeb
-#/scripts/legacy_api.py @CapableWeb
-#/tests/legacy_tests.sh @CapableWeb
+# front ends
+/invokeai/frontend/CLI @lstein
+/invokeai/frontend/install @lstein @ebr  
+/invokeai/frontend/merge @lstein @blessedcoolant 
+/invokeai/frontend/training @lstein @blessedcoolant 
+/invokeai/frontend/web @psychedelicious @blessedcoolant @maryhipp 
 
 

.github/ISSUE_TEMPLATE/BUG_REPORT.yml

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

.github/stale.yaml

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

.github/workflows/build-container.yml

@@ -5,17 +5,20 @@ on:
       - 'main'
       - 'update/ci/docker/*'
       - 'update/docker/*'
+      - 'dev/ci/docker/*'
+      - 'dev/docker/*'
     paths:
       - 'pyproject.toml'
-      - 'ldm/**'
-      - 'invokeai/backend/**'
-      - 'invokeai/configs/**'
-      - 'invokeai/frontend/dist/**'
+      - '.dockerignore'
+      - 'invokeai/**'
       - 'docker/Dockerfile'
     tags:
       - 'v*.*.*'
   workflow_dispatch:
 
+permissions:
+  contents: write
+  packages: write
 
 jobs:
   docker:
@@ -24,11 +27,11 @@ jobs:
       fail-fast: false
       matrix:
         flavor:
-          - amd
+          - rocm
           - cuda
           - cpu
         include:
-          - flavor: amd
+          - flavor: rocm
             pip-extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
           - flavor: cuda
             pip-extra-index-url: ''
@@ -54,9 +57,9 @@ jobs:
           tags: |
             type=ref,event=branch
             type=ref,event=tag
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=semver,pattern={{major}}
+            type=pep440,pattern={{version}}
+            type=pep440,pattern={{major}}.{{minor}}
+            type=pep440,pattern={{major}}
             type=sha,enable=true,prefix=sha-,format=short
           flavor: |
             latest=${{ matrix.flavor == 'cuda' && github.ref == 'refs/heads/main' }}
@@ -92,7 +95,7 @@ jobs:
           context: .
           file: ${{ env.DOCKERFILE }}
           platforms: ${{ env.PLATFORMS }}
-          push: ${{ github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' }}
+          push: ${{ github.ref == 'refs/heads/main' || github.ref_type == 'tag' }}
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
           build-args: PIP_EXTRA_INDEX_URL=${{ matrix.pip-extra-index-url }}

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

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

.github/workflows/lint-frontend.yml

@@ -3,14 +3,22 @@ name: Lint frontend
 on:
   pull_request:
     paths:
-      - 'invokeai/frontend/**'
+      - 'invokeai/frontend/web/**'
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
   push:
+    branches:
+      - 'main'
     paths:
-      - 'invokeai/frontend/**'
+      - 'invokeai/frontend/web/**'
+  merge_group:
+  workflow_dispatch:
 
 defaults:
   run:
-    working-directory: invokeai/frontend
+    working-directory: invokeai/frontend/web
 
 jobs:
   lint-frontend:
@@ -23,7 +31,7 @@ jobs:
           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'
+      - run: 'yarn run lint:tsc'
+      - run: 'yarn run lint:madge'
+      - run: 'yarn run lint:eslint'
+      - run: 'yarn run lint:prettier'

.github/workflows/mkdocs-material.yml

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

.github/workflows/pypi-release.yml

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

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

@@ -1,12 +1,11 @@
 name: Test invoke.py pip
 on:
   pull_request:
-    paths-ignore:
-      - 'pyproject.toml'
-      - 'ldm/**'
-      - 'invokeai/backend/**'
-      - 'invokeai/configs/**'
-      - 'invokeai/frontend/dist/**'
+    paths:
+      - '**'
+      - '!pyproject.toml'
+      - '!invokeai/**'
+      - 'invokeai/frontend/web/**'
   merge_group:
   workflow_dispatch:
 

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

@@ -5,17 +5,13 @@ on:
       - 'main'
     paths:
       - 'pyproject.toml'
-      - 'ldm/**'
-      - 'invokeai/backend/**'
-      - 'invokeai/configs/**'
-      - 'invokeai/frontend/dist/**'
+      - 'invokeai/**'
+      - '!invokeai/frontend/web/**'
   pull_request:
     paths:
       - 'pyproject.toml'
-      - 'ldm/**'
-      - 'invokeai/backend/**'
-      - 'invokeai/configs/**'
-      - 'invokeai/frontend/dist/**'
+      - 'invokeai/**'
+      - '!invokeai/frontend/web/**'
     types:
       - 'ready_for_review'
       - 'opened'
@@ -84,11 +80,6 @@ jobs:
         uses: actions/checkout@v3
 
       - name: set test prompt to main branch validation
-        if: ${{ github.ref == 'refs/heads/main' }}
-        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> ${{ matrix.github-env }}
-
-      - name: set test prompt to Pull Request validation
-        if: ${{ github.ref != 'refs/heads/main' }}
         run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
 
       - name: setup python
@@ -109,12 +100,6 @@ jobs:
         id: run-pytest
         run: pytest
 
-      - name: set INVOKEAI_OUTDIR
-        run: >
-          python -c
-          "import os;from ldm.invoke.globals import Globals;OUTDIR=os.path.join(Globals.root,str('outputs'));print(f'INVOKEAI_OUTDIR={OUTDIR}')"
-          >> ${{ matrix.github-env }}
-
       - name: run invokeai-configure
         id: run-preload-models
         env:
@@ -133,15 +118,21 @@ jobs:
           HF_HUB_OFFLINE: 1
           HF_DATASETS_OFFLINE: 1
           TRANSFORMERS_OFFLINE: 1
+          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
         run: >
           invokeai
           --no-patchmatch
           --no-nsfw_checker
-          --from_file ${{ env.TEST_PROMPTS }}
+          --precision=float32
+          --always_use_cpu
+          --use_memory_db
           --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+          --from_file ${{ env.TEST_PROMPTS }}
 
       - name: Archive results
         id: archive-results
+        env:
+          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
         uses: actions/upload-artifact@v3
         with:
           name: results

.gitignore

@@ -9,6 +9,8 @@ models/ldm/stable-diffusion-v1/model.ckpt
 configs/models.user.yaml
 config/models.user.yml
 invokeai.init
+.version
+.last_model
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -63,6 +65,7 @@ pip-delete-this-directory.txt
 htmlcov/
 .tox/
 .nox/
+.coveragerc
 .coverage
 .coverage.*
 .cache
@@ -73,6 +76,7 @@ cov.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
+.pytest.ini
 cover/
 junit/
 
@@ -197,8 +201,10 @@ checkpoints
 # If it's a Mac
 .DS_Store
 
+invokeai/frontend/web/dist/*
+
 # Let the frontend manage its own gitignore
-!invokeai/frontend/*
+!invokeai/frontend/web/*
 
 # Scratch folder
 .scratch/
@@ -213,11 +219,6 @@ 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
 
@@ -232,4 +233,3 @@ installer/install.bat
 installer/install.sh
 installer/update.bat
 installer/update.sh
-

.pre-commit-config.yaml

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

.prettierignore

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

.prettierrc.yaml

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

.pytest.ini

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

README.md

@@ -33,6 +33,8 @@
 
 </div>
 
+_**Note: The UI is not fully functional on `main`. If you need a stable UI based on `main`, use the `pre-nodes` tag while we [migrate to a new backend](https://github.com/invoke-ai/InvokeAI/discussions/3246).**_
+
 InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
 
 **Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
@@ -84,7 +86,7 @@ installing lots of models.
 
 6. Wait while the installer does its thing. After installing the software,
 the installer will launch a script that lets you configure InvokeAI and
-select a set of starting image generaiton models.
+select a set of starting image generation models.
 
 7. Find the folder that InvokeAI was installed into (it is not the
 same as the unpacked zip file directory!) The default location of this
@@ -139,7 +141,7 @@ not supported.
     _For Windows/Linux with an NVIDIA GPU:_
 
     ```terminal
-    pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+    pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
     ```
 
     _For Linux with an AMD GPU:_
@@ -148,6 +150,11 @@ not supported.
     pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
     ```
 
+    _For non-GPU systems:_
+    ```terminal
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
+    ``` 
+
     _For Macintoshes, either Intel or M1/M2:_
 
     ```sh

coverage/.gitignore

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

docker/Dockerfile

@@ -4,15 +4,15 @@ ARG PYTHON_VERSION=3.9
 ##################
 ##  base image  ##
 ##################
-FROM python:${PYTHON_VERSION}-slim AS python-base
+FROM --platform=${TARGETPLATFORM} python:${PYTHON_VERSION}-slim AS python-base
 
 LABEL org.opencontainers.image.authors="mauwii@outlook.de"
 
-# prepare for buildkit cache
+# Prepare apt for buildkit cache
 RUN rm -f /etc/apt/apt.conf.d/docker-clean \
   && echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' >/etc/apt/apt.conf.d/keep-cache
 
-# Install necessary packages
+# Install dependencies
 RUN \
   --mount=type=cache,target=/var/cache/apt,sharing=locked \
   --mount=type=cache,target=/var/lib/apt,sharing=locked \
@@ -23,7 +23,7 @@ RUN \
     libglib2.0-0=2.66.* \
     libopencv-dev=4.5.*
 
-# set working directory and env
+# Set working directory and env
 ARG APPDIR=/usr/src
 ARG APPNAME=InvokeAI
 WORKDIR ${APPDIR}
@@ -32,7 +32,7 @@ ENV PATH ${APPDIR}/${APPNAME}/bin:$PATH
 ENV PYTHONDONTWRITEBYTECODE 1
 # Turns off buffering for easier container logging
 ENV PYTHONUNBUFFERED 1
-# don't fall back to legacy build system
+# Don't fall back to legacy build system
 ENV PIP_USE_PEP517=1
 
 #######################
@@ -40,7 +40,7 @@ ENV PIP_USE_PEP517=1
 #######################
 FROM python-base AS pyproject-builder
 
-# Install dependencies
+# Install build dependencies
 RUN \
   --mount=type=cache,target=/var/cache/apt,sharing=locked \
   --mount=type=cache,target=/var/lib/apt,sharing=locked \
@@ -51,26 +51,30 @@ RUN \
     gcc=4:10.2.* \
     python3-dev=3.9.*
 
-# prepare pip for buildkit cache
+# Prepare pip for buildkit cache
 ARG PIP_CACHE_DIR=/var/cache/buildkit/pip
 ENV PIP_CACHE_DIR ${PIP_CACHE_DIR}
 RUN mkdir -p ${PIP_CACHE_DIR}
 
-# create virtual environment
-RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+# Create virtual environment
+RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
   python3 -m venv "${APPNAME}" \
   --upgrade-deps
 
-# copy sources
-COPY --link . .
-
-# install pyproject.toml
+# Install requirements
+COPY --link pyproject.toml .
+COPY --link invokeai/version/invokeai_version.py invokeai/version/__init__.py invokeai/version/
 ARG PIP_EXTRA_INDEX_URL
 ENV PIP_EXTRA_INDEX_URL ${PIP_EXTRA_INDEX_URL}
-RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
+  "${APPNAME}"/bin/pip install .
+
+# Install pyproject.toml
+COPY --link . .
+RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
   "${APPNAME}/bin/pip" install .
 
-# build patchmatch
+# Build patchmatch
 RUN python3 -c "from patchmatch import patch_match"
 
 #####################
@@ -86,14 +90,14 @@ RUN useradd \
   -U \
   "${UNAME}"
 
-# create volume directory
+# Create volume directory
 ARG VOLUME_DIR=/data
 RUN mkdir -p "${VOLUME_DIR}" \
-  && chown -R "${UNAME}" "${VOLUME_DIR}"
+  && chown -hR "${UNAME}:${UNAME}" "${VOLUME_DIR}"
 
-# setup runtime environment
-USER ${UNAME}
-COPY --chown=${UNAME} --from=pyproject-builder ${APPDIR}/${APPNAME} ${APPNAME}
+# Setup runtime environment
+USER ${UNAME}:${UNAME}
+COPY --chown=${UNAME}:${UNAME} --from=pyproject-builder ${APPDIR}/${APPNAME} ${APPNAME}
 ENV INVOKEAI_ROOT ${VOLUME_DIR}
 ENV TRANSFORMERS_CACHE ${VOLUME_DIR}/.cache
 ENV INVOKE_MODEL_RECONFIGURE "--yes --default_only"

docker/build.sh

@@ -41,7 +41,7 @@ else
 fi
 
 # Build Container
-DOCKER_BUILDKIT=1 docker build \
+docker build \
     --platform="${PLATFORM:-linux/amd64}" \
     --tag="${CONTAINER_IMAGE:-invokeai}" \
     ${CONTAINER_FLAVOR:+--build-arg="CONTAINER_FLAVOR=${CONTAINER_FLAVOR}"} \

docker/env.sh

@@ -49,3 +49,6 @@ CONTAINER_FLAVOR="${CONTAINER_FLAVOR-cuda}"
 CONTAINER_TAG="${CONTAINER_TAG-"${INVOKEAI_BRANCH##*/}-${CONTAINER_FLAVOR}"}"
 CONTAINER_IMAGE="${CONTAINER_REGISTRY}/${CONTAINER_REPOSITORY}:${CONTAINER_TAG}"
 CONTAINER_IMAGE="${CONTAINER_IMAGE,,}"
+
+# enable docker buildkit
+export DOCKER_BUILDKIT=1

docker/run.sh

@@ -21,10 +21,10 @@ docker run \
   --tty \
   --rm \
   --platform="${PLATFORM}" \
-  --name="${REPOSITORY_NAME,,}" \
-  --hostname="${REPOSITORY_NAME,,}" \
-  --mount=source="${VOLUMENAME}",target=/data \
-  --mount type=bind,source="$(pwd)"/outputs,target=/data/outputs \
+  --name="${REPOSITORY_NAME}" \
+  --hostname="${REPOSITORY_NAME}" \
+  --mount type=volume,volume-driver=local,source="${VOLUMENAME}",target=/data \
+  --mount type=bind,source="$(pwd)"/outputs/,target=/data/outputs/ \
   ${MODELSPATH:+--mount="type=bind,source=${MODELSPATH},target=/data/models"} \
   ${HUGGING_FACE_HUB_TOKEN:+--env="HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN}"} \
   --publish=9090:9090 \
@@ -32,7 +32,7 @@ docker run \
   ${GPU_FLAGS:+--gpus="${GPU_FLAGS}"} \
   "${CONTAINER_IMAGE}" ${@:+$@}
 
-# Remove Trash folder
+echo -e "\nCleaning trash folder ..."
 for f in outputs/.Trash*; do
   if [ -e "$f" ]; then
     rm -Rf "$f"

docs/.markdownlint.jsonc

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

docs/contributing/INVOCATIONS.md

@@ -1,105 +1,277 @@
 # Invocations
 
-Invocations represent a single operation, its inputs, and its outputs. These operations and their outputs can be chained together to generate and modify images.
+Invocations represent a single operation, its inputs, and its outputs. These
+operations and their outputs can be chained together to generate and modify
+images.
 
 ## Creating a new invocation
 
-To create a new invocation, either find the appropriate module file in `/ldm/invoke/app/invocations` to add your invocation to, or create a new one in that folder. All invocations in that folder will be discovered and made available to the CLI and API automatically. Invocations make use of [typing](https://docs.python.org/3/library/typing.html) and [pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration into the CLI and API.
+To create a new invocation, either find the appropriate module file in
+`/ldm/invoke/app/invocations` to add your invocation to, or create a new one in
+that folder. All invocations in that folder will be discovered and made
+available to the CLI and API automatically. Invocations make use of
+[typing](https://docs.python.org/3/library/typing.html) and
+[pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration
+into the CLI and API.
 
 An invocation looks like this:
 
 ```py
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
-    type: Literal['upscale'] = 'upscale'
+
+    # fmt: off
+    type: Literal["upscale"] = "upscale"
 
     # Inputs
-    image: Union[ImageField,None] = Field(description="The input image")
-    strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
-    level: Literal[2,4]           = Field(default=2, description = "The upscale level")
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    strength: float                = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2, 4]           = Field(default=2, description="The upscale level")
+    # fmt: on
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["upscaling", "image"],
+            },
+        }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(self.image.image_type, self.image.image_name)
-        results = context.services.generate.upscale_and_reconstruct(
-            image_list     = [[image, 0]],
-            upscale        = (self.level, self.strength),
-            strength       = 0.0, # GFPGAN strength
-            save_original  = False,
-            image_callback = None,
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=(self.level, self.strength),
+            strength=0.0,  # GFPGAN strength
+            save_original=False,
+            image_callback=None,
         )
 
         # Results are image and seed, unwrap for now
         # TODO: can this return multiple results?
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
-        context.services.images.save(image_type, image_name, results[0][0])
-        return ImageOutput(
-            image = ImageField(image_type = image_type, image_name = image_name)
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
         )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
 ```
 
 Each portion is important to implement correctly.
 
 ### Class definition and type
+
 ```py
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
     type: Literal['upscale'] = 'upscale'
 ```
-All invocations must derive from `BaseInvocation`. They should have a docstring that declares what they do in a single, short line. They should also have a `type` with a type hint that's `Literal["command_name"]`, where `command_name` is what the user will type on the CLI or use in the API to create this invocation. The `command_name` must be unique. The `type` must be assigned to the value of the literal in the type hint.
+
+All invocations must derive from `BaseInvocation`. They should have a docstring
+that declares what they do in a single, short line. They should also have a
+`type` with a type hint that's `Literal["command_name"]`, where `command_name`
+is what the user will type on the CLI or use in the API to create this
+invocation. The `command_name` must be unique. The `type` must be assigned to
+the value of the literal in the type hint.
 
 ### Inputs
+
 ```py
     # Inputs
     image: Union[ImageField,None] = Field(description="The input image")
     strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
     level: Literal[2,4]           = Field(default=2, description="The upscale level")
 ```
-Inputs consist of three parts: a name, a type hint, and a `Field` with default, description, and validation information. For example:
-| Part | Value | Description |
-| ---- | ----- | ----------- |
-| Name | `strength` | This field is referred to as `strength` |
-| Type Hint | `float` | This field must be of type `float` |
-| Field | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
 
-Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this field to be parsed with `None` as a value, which enables linking to previous invocations. All fields should either provide a default value or allow `None` as a value, so that they can be overwritten with a linked output from another invocation.
+Inputs consist of three parts: a name, a type hint, and a `Field` with default,
+description, and validation information. For example:
 
-The special type `ImageField` is also used here. All images are passed as `ImageField`, which protects them from pydantic validation errors (since images only ever come from links).
+| Part      | Value                                                         | Description                                                                                                               |
+| --------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
+| Name      | `strength`                                                    | This field is referred to as `strength`                                                                                   |
+| Type Hint | `float`                                                       | This field must be of type `float`                                                                                        |
+| Field     | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
 
-Finally, note that for all linking, the `type` of the linked fields must match. If the `name` also matches, then the field can be **automatically linked** to a previous invocation by name and matching.
+Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this
+field to be parsed with `None` as a value, which enables linking to previous
+invocations. All fields should either provide a default value or allow `None` as
+a value, so that they can be overwritten with a linked output from another
+invocation.
+
+The special type `ImageField` is also used here. All images are passed as
+`ImageField`, which protects them from pydantic validation errors (since images
+only ever come from links).
+
+Finally, note that for all linking, the `type` of the linked fields must match.
+If the `name` also matches, then the field can be **automatically linked** to a
+previous invocation by name and matching.
+
+### Config
+
+```py
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["upscaling", "image"],
+            },
+        }
+```
+
+This is an optional configuration for the invocation. It inherits from
+pydantic's model `Config` class, and it used primarily to customize the
+autogenerated OpenAPI schema.
+
+The UI relies on the OpenAPI schema in two ways:
+
+- An API client & Typescript types are generated from it. This happens at build
+  time.
+- The node editor parses the schema into a template used by the UI to create the
+  node editor UI. This parsing happens at runtime.
+
+In this example, a `ui` key has been added to the `schema_extra` dict to provide
+some tags for the UI, to facilitate filtering nodes.
+
+See the Schema Generation section below for more information.
 
 ### Invoke Function
+
 ```py
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(self.image.image_type, self.image.image_name)
-        results = context.services.generate.upscale_and_reconstruct(
-            image_list     = [[image, 0]],
-            upscale        = (self.level, self.strength),
-            strength       = 0.0, # GFPGAN strength
-            save_original  = False,
-            image_callback = None,
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=(self.level, self.strength),
+            strength=0.0,  # GFPGAN strength
+            save_original=False,
+            image_callback=None,
         )
 
         # Results are image and seed, unwrap for now
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
-        context.services.images.save(image_type, image_name, results[0][0])
+        # TODO: can this return multiple results?
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
         return ImageOutput(
-            image = ImageField(image_type = image_type, image_name = image_name)
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
         )
 ```
-The `invoke` function is the last portion of an invocation. It is provided an `InvocationContext` which contains services to perform work as well as a `session_id` for use as needed. It should return a class with output values that derives from `BaseInvocationOutput`.
 
-Before being called, the invocation will have all of its fields set from defaults, inputs, and finally links (overriding in that order).
+The `invoke` function is the last portion of an invocation. It is provided an
+`InvocationContext` which contains services to perform work as well as a
+`session_id` for use as needed. It should return a class with output values that
+derives from `BaseInvocationOutput`.
 
-Assume that this invocation may be running simultaneously with other invocations, may be running on another machine, or in other interesting scenarios. If you need functionality, please provide it as a service in the `InvocationServices` class, and make sure it can be overridden.
+Before being called, the invocation will have all of its fields set from
+defaults, inputs, and finally links (overriding in that order).
+
+Assume that this invocation may be running simultaneously with other
+invocations, may be running on another machine, or in other interesting
+scenarios. If you need functionality, please provide it as a service in the
+`InvocationServices` class, and make sure it can be overridden.
 
 ### Outputs
+
 ```py
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
-    type: Literal['image'] = 'image'
 
-    image: ImageField = Field(default=None, description="The output image")
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+
+    class Config:
+        schema_extra = {"required": ["type", "image", "width", "height"]}
 ```
-Output classes look like an invocation class without the invoke method. Prefer to use an existing output class if available, and prefer to name inputs the same as outputs when possible, to promote automatic invocation linking.
+
+Output classes look like an invocation class without the invoke method. Prefer
+to use an existing output class if available, and prefer to name inputs the same
+as outputs when possible, to promote automatic invocation linking.
+
+## Schema Generation
+
+Invocation, output and related classes are used to generate an OpenAPI schema.
+
+### Required Properties
+
+The schema generation treat all properties with default values as optional. This
+makes sense internally, but when when using these classes via the generated
+schema, we end up with e.g. the `ImageOutput` class having its `image` property
+marked as optional.
+
+We know that this property will always be present, so the additional logic
+needed to always check if the property exists adds a lot of extraneous cruft.
+
+To fix this, we can leverage `pydantic`'s
+[schema customisation](https://docs.pydantic.dev/usage/schema/#schema-customization)
+to mark properties that we know will always be present as required.
+
+Here's that `ImageOutput` class, without the needed schema customisation:
+
+```python
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+```
+
+The OpenAPI schema that results from this `ImageOutput` will have the `type`,
+`image`, `width` and `height` properties marked as optional, even though we know
+they will always have a value.
+
+```python
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+
+    # Add schema customization
+    class Config:
+        schema_extra = {"required": ["type", "image", "width", "height"]}
+```
+
+With the customization in place, the schema will now show these properties as
+required, obviating the need for extensive null checks in client code.
+
+See this `pydantic` issue for discussion on this solution:
+<https://github.com/pydantic/pydantic/discussions/4577>

docs/contributing/LOCAL_DEVELOPMENT.md

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

docs/features/CONCEPTS.md

@@ -1,5 +1,5 @@
 ---
-title: Styles and Subjects
+title: Concepts Library
 ---
 
 # :material-library-shelves: The Hugging Face Concepts Library and Importing Textual Inversion files
@@ -25,14 +25,10 @@ library which downloads and merges TI files automatically upon request. You can
 also install your own or others' TI files by placing them in a designated
 directory.
 
-You may also be interested in using [LoRA Models](LORAS.md) to
-generate images with specialized styles and subjects.
-
 ### An Example
 
-Here are a few examples to illustrate how Textual Inversion works. All
-these images were generated using the command-line client and the
-Stable Diffusion 1.5 model:
+Here are a few examples to illustrate how it works. All these images were
+generated using the command-line client and the Stable Diffusion 1.5 model:
 
 |         Japanese gardener          | Japanese gardener <ghibli-face> | Japanese gardener <hoi4-leaders> | Japanese gardener <cartoona-animals> |
 | :--------------------------------: | :-----------------------------------: | :------------------------------------: | :----------------------------------------: |
@@ -113,50 +109,21 @@ For example, TI files generated by the Hugging Face toolkit share the named
 `learned_embedding.bin`. You can use subdirectories to keep them distinct.
 
 At startup time, InvokeAI will scan the `embeddings` directory and load any TI
-files it finds there. At startup you will see messages similar to these:
+files it finds there. At startup you will see a message similar to this one:
 
 ```bash
->> Loading embeddings from /data/lstein/invokeai-2.3/embeddings
-   | Loading v1 embedding file: style-hamunaptra
-   | Loading v4 embedding file: embeddings/learned_embeds-steps-500.bin
-   | Loading v2 embedding file: lfa
-   | Loading v3 embedding file: easynegative
-   | Loading v1 embedding file: rem_rezero
-   | Loading v2 embedding file: midj-strong
-   | Loading v4 embedding file: anime-background-style-v2/learned_embeds.bin
-   | Loading v4 embedding file: kamon-style/learned_embeds.bin
-   ** Notice: kamon-style/learned_embeds.bin was trained on a model with an incompatible token dimension: 768 vs 1024.
->> Textual inversion triggers: <anime-background-style-v2>, <easynegative>, <lfa>, <midj-strong>, <milo>, Rem3-2600, Style-Hamunaptra
+>> Current embedding manager terms: *, <HOI4-Leader>, <princess-knight>
 ```
 
-Textual Inversion embeddings trained on version 1.X stable diffusion
-models are incompatible with version 2.X models and vice-versa.
+Note the `*` trigger term. This is a placeholder term that many early TI
+tutorials taught people to use rather than a more descriptive term.
+Unfortunately, if you have multiple TI files that all use this term, only the
+first one loaded will be triggered by use of the term.
 
-After the embeddings load, InvokeAI will print out a list of all the
-recognized trigger terms. To trigger the term, include it in the
-prompt exactly as written, including angle brackets if any and
-respecting the capitalization.
-
-There are at least four different embedding file formats, and each uses
-a different convention for the trigger terms. In some cases, the
-trigger term is specified in the file contents and may or may not be
-surrounded by angle brackets. In the example above, `Rem3-2600`,
-`Style-Hamunaptra`, and `<midj-strong>` were specified this way and
-there is no easy way to change the term.
-
-In other cases the trigger term is not contained within the embedding
-file. In this case, InvokeAI constructs a trigger term consisting of
-the base name of the file (without the file extension) surrounded by
-angle brackets. In the example above `<easynegative`> is such a file
-(the filename was `easynegative.safetensors`). In such cases, you can
-change the trigger term simply by renaming the file.
-
-## Training your own Textual Inversion models
-
-InvokeAI provides a script that lets you train your own Textual
-Inversion embeddings using a small number (about a half-dozen) images
-of your desired style or subject. Please see [Textual
-Inversion](TEXTUAL_INVERSION.md) for details.
+To avoid this problem, you can use the `merge_embeddings.py` script to merge two
+or more TI files together. If it encounters a collision of terms, the script
+will prompt you to select new terms that do not collide. See
+[Textual Inversion](TEXTUAL_INVERSION.md) for details.
 
 ## Further Reading
 

docs/features/INPAINTING.md

@@ -168,11 +168,15 @@ used by Stable Diffusion 1.4 and 1.5.
 After installation, your `models.yaml` should contain an entry that looks like
 this one:
 
-inpainting-1.5: weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
-description: SD inpainting v1.5 config:
-configs/stable-diffusion/v1-inpainting-inference.yaml vae:
-models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt width: 512
-height: 512
+```yml
+inpainting-1.5:
+  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+  description: SD inpainting v1.5
+  config: configs/stable-diffusion/v1-inpainting-inference.yaml
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  width: 512
+  height: 512
+```
 
 As shown in the example, you may include a VAE fine-tuning weights file as well.
 This is strongly recommended.

docs/features/LOGGING.md

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

docs/features/LORAS.md

@@ -1,110 +0,0 @@
----
-title: Low-Rank Adaptation (LoRA) Models
----
-
-# :material-library-shelves: Using Low-Rank Adaptation (LoRA) Models
-
-## Introduction
-
-LoRA is a technique for fine-tuning Stable Diffusion models using much
-less time and memory than traditional training techniques. The
-resulting model files are much smaller than full model files, and can
-be used to generate specialized styles and subjects.
-
-LoRAs are built on top of Stable Diffusion v1.x or 2.x checkpoint or
-diffusers models. To load a LoRA, you include its name in the text
-prompt using a simple syntax described below. While you will generally
-get the best results when you use the same model the LoRA was trained
-on, they will work to a greater or lesser extent with other models.
-The major caveat is that a LoRA built on top of a SD v1.x model cannot
-be used with a v2.x model, and vice-versa. If you try, you will get an
-error! You may refer to multiple LoRAs in your prompt.
-
-When you apply a LoRA in a prompt you can specify a weight. The higher
-the weight, the more influence it will have on the image. Useful
-ranges for weights are usually in the 0.0 to 1.0 range (with ranges
-between 0.5 and 1.0 being most typical). However you can specify a
-higher weight if you wish. Like models, each LoRA has a slightly
-different useful weight range and will interact with other generation
-parameters such as the CFG, step count and sampler. The author of the
-LoRA will often provide guidance on the best settings, but feel free
-to experiment. Be aware that it often helps to reduce the CFG value
-when using LoRAs.
-
-## Installing LoRAs
-
-This is very easy! Download a LoRA model file from your favorite site
-(e.g. [CIVITAI](https://civitai.com) and place it in the `loras`
-folder in the InvokeAI root directory (usually `~invokeai/loras` on
-Linux/Macintosh machines, and `C:\Users\your-name\invokeai/loras` on
-Windows systems). If the `loras` folder does not already exist, just
-create it. The vast majority of LoRA models use the Kohya file format,
-which is a type of `.safetensors` file.
-
-!!! warning "LoRA Naming Restrictions"
-
-    InvokeAI will only recognize LoRA files that contain the
-    characters a-z, A-Z, 0-9 and the underscore character
-    _. Other characters, including the hyphen, will cause the
-    LoRA file not to load. These naming restrictions may be
-    relaxed in the future, but for now you will need to rename
-    files that contain hyphens, commas, brackets, and other
-    non-word characters.
-
-You may change where InvokeAI looks for the `loras` folder by passing the
-`--lora_directory` option to the `invoke.sh`/`invoke.bat` launcher, or
-by placing the option in `invokeai.init`. For example:
-
-```
-invoke.sh --lora_directory=C:\Users\your-name\SDModels\lora
-```
-
-## Using a LoRA in your prompt
-
-To activate a LoRA use the syntax `withLora(my-lora-name,weight)`
-somewhere in the text of the prompt. The position doesn't matter; use
-whatever is most comfortable for you.
-
-For example, if you have a LoRA named `parchment_people.safetensors`
-in your `loras` directory, you can load it with a weight of 0.9 with a
-prompt like this one:
-
-```
-family sitting at dinner table withLora(parchment_people,0.9)
-```
-
-Add additional `withLora()` phrases to load more LoRAs.
-
-You may omit the weight entirely to default to a weight of 1.0:
-
-```
-family sitting at dinner table withLora(parchment_people)
-```
-
-If you watch the console as your prompt executes, you will see
-messages relating to the loading and execution of the LoRA. If things
-don't work as expected, note down the console messages and report them
-on the InvokeAI Issues pages or Discord channel.
-
-That's pretty much all you need to know!
-
-## Training Kohya Models
-
-InvokeAI cannot currently train LoRA models, but it can load and use
-existing LoRA ones to generate images. While there are several LoRA
-model file formats, the predominant one is ["Kohya"
-format](https://github.com/kohya-ss/sd-scripts), written by [Kohya
-S.](https://github.com/kohya-ss). InvokeAI provides support for this
-format. For creating your own Kohya models, we recommend the Windows
-GUI written by former InvokeAI-team member
-[bmaltais](https://github.com/bmaltais), which can be found at
-[kohya_ss](https://github.com/bmaltais/kohya_ss).
-
-We can also recommend the [HuggingFace DreamBooth Training
-UI](https://huggingface.co/spaces/lora-library/LoRA-DreamBooth-Training-UI),
-a paid service that supports both Textual Inversion and LoRA training.
-
-You may also be interested in [Textual
-Inversion](TEXTUAL_INVERSION.md) training, which is supported by
-InvokeAI as a text console and command-line tool.
-

docs/features/NSFW.md

@@ -32,7 +32,7 @@ turned on and off on the command line using `--nsfw_checker` and
 At installation time, InvokeAI will ask whether the checker should be
 activated by default (neither argument given on the command line). The
 response is stored in the InvokeAI initialization file (usually
-`.invokeai` in your home directory). You can change the default at any
+`invokeai.init` in your home directory). You can change the default at any
 time by opening this file in a text editor and commenting or
 uncommenting the line `--nsfw_checker`.
 

docs/features/PROMPTS.md

@@ -268,7 +268,7 @@ model is so good at inpainting, a good substitute is to use the `clipseg` text
 masking option:
 
 ```bash
-invoke> a fluffy cat eating a hotdot
+invoke> a fluffy cat eating a hotdog
 Outputs:
 [1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
 invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat

docs/features/TEXTUAL_INVERSION.md

@@ -17,7 +17,7 @@ notebooks.
 
 You will need a GPU to perform training in a reasonable length of
 time, and at least 12 GB of VRAM. We recommend using the [`xformers`
-library](../installation/070_INSTALL_XFORMERS) to accelerate the
+library](../installation/070_INSTALL_XFORMERS.md) to accelerate the
 training process further. During training, about ~8 GB is temporarily
 needed in order to store intermediate models, checkpoints and logs.
 
@@ -154,11 +154,8 @@ training sets will converge with 2000-3000 steps.
 
 This adjusts how many training images are processed simultaneously in
 each step. Higher values will cause the training process to run more
-quickly, but use more memory. The default size is selected based on
-whether you have the `xformers` memory-efficient attention library
-installed. If `xformers` is available, the batch size will be 8,
-otherwise 3.  These values were chosen to allow training to run with
-GPUs with as little as 12 GB VRAM.
+quickly, but use more memory. The default size will run with GPUs with
+as little as 12 GB.
 
 ### Learning rate
 
@@ -175,10 +172,8 @@ learning rate to improve performance.
 
 ### Use xformers acceleration
 
-This will activate XFormers memory-efficient attention, which will
-reduce memory requirements by half or more and allow you to select a
-higher batch size. You need to have XFormers installed for this to
-have an effect.
+This will activate XFormers memory-efficient attention. You need to
+have XFormers installed for this to have an effect.
 
 ### Learning rate scheduler
 
@@ -255,49 +250,6 @@ invokeai-ti \
        --only_save_embeds
 ```
 
-## Using Distributed Training
-
-If you have multiple GPUs on one machine, or a cluster of GPU-enabled
-machines, you can activate distributed training. See the [HuggingFace
-Accelerate pages](https://huggingface.co/docs/accelerate/index) for
-full information, but the basic recipe is:
-
-1. Enter the InvokeAI developer's console command line by selecting
-option [8] from the `invoke.sh`/`invoke.bat` script.
-
-2. Configurate Accelerate using `accelerate config`:
-```sh
-accelerate config
-```
-This will guide you through the configuration process, including
-specifying how many machines you will run training on and the number
-of GPUs pe rmachine.
-
-You only need to do this once.
-
-3. Launch training from the command line using `accelerate launch`. Be sure
-that your current working directory is the InvokeAI root directory (usually
-named `invokeai` in your home directory):
-
-```sh
-accelerate launch .venv/bin/invokeai-ti \
-       --model=stable-diffusion-1.5 \
-       --resolution=512 \
-       --learnable_property=object \
-       --initializer_token='*' \
-       --placeholder_token='<shraddha>' \
-       --train_data_dir=/home/lstein/invokeai/text-inversion-training-data/shraddha \
-       --output_dir=/home/lstein/invokeai/text-inversion-training/shraddha \
-       --scale_lr \
-       --train_batch_size=10 \
-       --gradient_accumulation_steps=4 \
-       --max_train_steps=2000 \
-       --learning_rate=0.0005 \
-       --lr_scheduler=constant \
-       --mixed_precision=fp16 \
-       --only_save_embeds
-```
-
 ## Using Embeddings
 
 After training completes, the resultant embeddings will be saved into your `$INVOKEAI_ROOT/embeddings/<trigger word>/learned_embeds.bin`.

docs/features/index.md

@@ -2,89 +2,65 @@
 title: Overview
 ---
 
--   The Basics
+Here you can find the documentation for InvokeAI's various features.
 
-    -   The [Web User Interface](WEB.md)
+## The Basics
+### * The [Web User Interface](WEB.md)
+Guide to the Web interface. Also see the [WebUI Hotkeys Reference Guide](WEBUIHOTKEYS.md)
 
-        Guide to the Web interface. Also see the
-        [WebUI Hotkeys Reference Guide](WEBUIHOTKEYS.md)
+### * The [Unified Canvas](UNIFIED_CANVAS.md)
+Build complex scenes by combine and modifying multiple images in a stepwise
+fashion. This feature combines img2img, inpainting and outpainting in
+a single convenient digital artist-optimized user interface.
 
-    -   The [Unified Canvas](UNIFIED_CANVAS.md)
+### * The [Command Line Interface (CLI)](CLI.md)
+Scriptable access to InvokeAI's features.
 
-        Build complex scenes by combine and modifying multiple images in a
-        stepwise fashion. This feature combines img2img, inpainting and
-        outpainting in a single convenient digital artist-optimized user
-        interface.
+## Image Generation
+### * [Prompt Engineering](PROMPTS.md)
+Get the images you want with the InvokeAI  prompt engineering language.
 
-    -   The [Command Line Interface (CLI)](CLI.md)
+## * [Post-Processing](POSTPROCESS.md)
+Restore mangled faces and make images larger with upscaling. Also see the [Embiggen Upscaling Guide](EMBIGGEN.md).
 
-        Scriptable access to InvokeAI's features.
+## * The [Concepts Library](CONCEPTS.md)
+Add custom subjects and styles using HuggingFace's repository of embeddings.
 
-    -   [Visual Manual for InvokeAI](https://docs.google.com/presentation/d/e/2PACX-1vSE90aC7bVVg0d9KXVMhy-Wve-wModgPFp7AGVTOCgf4xE03SnV24mjdwldolfCr59D_35oheHe4Cow/pub?start=false&loop=true&delayms=60000) (contributed by Statcomm)
+### * [Image-to-Image Guide for the CLI](IMG2IMG.md)
+Use a seed image to build new creations in the CLI.
 
--   Image Generation
+### * [Inpainting Guide for the CLI](INPAINTING.md)
+Selectively erase and replace portions of an existing image in the CLI.
 
-    -   [Prompt Engineering](PROMPTS.md)
+### * [Outpainting Guide for the CLI](OUTPAINTING.md)
+Extend the borders of the image with an "outcrop" function within the CLI.
 
-        Get the images you want with the InvokeAI prompt engineering language.
+### * [Generating Variations](VARIATIONS.md)
+Have an image you like and want to generate many more like it? Variations
+are the ticket.
 
-    -   [Post-Processing](POSTPROCESS.md)
+## Model Management
 
-        Restore mangled faces and make images larger with upscaling. Also see
-        the [Embiggen Upscaling Guide](EMBIGGEN.md).
+## * [Model Installation](../installation/050_INSTALLING_MODELS.md)
+Learn how to import third-party models and switch among them. This
+guide also covers optimizing models to load quickly.
 
-    -   The [Using LoRA Models](LORAS.md)
+## * [Merging Models](MODEL_MERGING.md)
+Teach an old model new tricks. Merge 2-3 models together to create a
+new model that combines characteristics of the originals.
 
-        Add custom subjects and styles using HuggingFace's repository of
-        embeddings.
-	
-    -   The [Concepts Library](CONCEPTS.md)
+## * [Textual Inversion](TEXTUAL_INVERSION.md)
+Personalize models by adding your own style or subjects.
 
-        Add custom subjects and styles using HuggingFace's repository of
-        embeddings.
+# Other Features
 
-    -   [Image-to-Image Guide for the CLI](IMG2IMG.md)
+## * [The NSFW Checker](NSFW.md)
+Prevent InvokeAI from displaying unwanted racy images.
 
-        Use a seed image to build new creations in the CLI.
+## * [Controlling Logging](LOGGING.md)
+Control how InvokeAI logs status messages.
 
-    -   [Inpainting Guide for the CLI](INPAINTING.md)
-
-        Selectively erase and replace portions of an existing image in the CLI.
-
-    -   [Outpainting Guide for the CLI](OUTPAINTING.md)
-
-        Extend the borders of the image with an "outcrop" function within the
-        CLI.
-
-    -   [Generating Variations](VARIATIONS.md)
-
-        Have an image you like and want to generate many more like it?
-        Variations are the ticket.
-
--   Model Management
-
-    -   [Model Installation](../installation/050_INSTALLING_MODELS.md)
-
-        Learn how to import third-party models and switch among them. This guide
-        also covers optimizing models to load quickly.
-
-    -   [Merging Models](MODEL_MERGING.md)
-
-        Teach an old model new tricks. Merge 2-3 models together to create a new
-        model that combines characteristics of the originals.
-
-    -   [Textual Inversion](TEXTUAL_INVERSION.md)
-
-        Personalize models by adding your own style or subjects.
-
--   Other Features
-
-    -   [The NSFW Checker](NSFW.md)
-
-        Prevent InvokeAI from displaying unwanted racy images.
-
-    -   [Miscellaneous](OTHER.md)
-
-        Run InvokeAI on Google Colab, generate images with repeating patterns,
-        batch process a file of prompts, increase the "creativity" of image
-        generation by adding initial noise, and more!
+## * [Miscellaneous](OTHER.md)
+Run InvokeAI on Google Colab, generate images with repeating patterns,
+batch process a file of prompts, increase the "creativity" of image
+generation by adding initial noise, and more!

docs/help/IDE-Settings/index.md

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

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

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

docs/help/contributing/010_PULL_REQUEST.md

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

docs/help/contributing/020_ISSUES.md

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

docs/help/contributing/030_DOCS.md

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

docs/help/contributing/090_NODE_TRANSFORMATION.md

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

docs/help/contributing/index.md

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

docs/help/index.md

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

docs/index.md

@@ -2,8 +2,6 @@
 title: Home
 ---
 
-# :octicons-home-16: Home
-
 <!--
   The Docs you find here (/docs/*) are built and deployed via mkdocs. If you want to run a local version to verify your changes, it's as simple as::
 
@@ -31,36 +29,36 @@ title: Home
 [![github open prs badge]][github open prs link]
 
 [ci checks on dev badge]:
-    https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
+  https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
 [ci checks on dev link]:
-    https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
+  https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
 [ci checks on main badge]:
-    https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
+  https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
 [ci checks on main link]:
-    https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
+  https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
 [discord badge]: https://flat.badgen.net/discord/members/ZmtBAhwWhy?icon=discord
 [discord link]: https://discord.gg/ZmtBAhwWhy
 [github forks badge]:
-    https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
+  https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
 [github forks link]:
-    https://useful-forks.github.io/?repo=lstein%2Fstable-diffusion
+  https://useful-forks.github.io/?repo=lstein%2Fstable-diffusion
 [github open issues badge]:
-    https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
+  https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
 [github open issues link]:
-    https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
+  https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
 [github open prs badge]:
-    https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
+  https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
 [github open prs link]:
-    https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
+  https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
 [github stars badge]:
-    https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
+  https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
 [github stars link]: https://github.com/invoke-ai/InvokeAI/stargazers
 [latest commit to dev badge]:
-    https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
+  https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
 [latest commit to dev link]:
-    https://github.com/invoke-ai/InvokeAI/commits/development
+  https://github.com/invoke-ai/InvokeAI/commits/development
 [latest release badge]:
-    https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
+  https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
 
 </div>
@@ -89,24 +87,24 @@ Q&A</a>]
 
 You wil need one of the following:
 
--   :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
--   :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
-    only)
--   :fontawesome-brands-apple: An Apple computer with an M1 chip.
+- :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
+- :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
+  only)
+- :fontawesome-brands-apple: An Apple computer with an M1 chip.
 
 We do **not recommend** the following video cards due to issues with their
 running in half-precision mode and having insufficient VRAM to render 512x512
 images in full-precision mode:
 
--   NVIDIA 10xx series cards such as the 1080ti
--   GTX 1650 series cards
--   GTX 1660 series cards
+- NVIDIA 10xx series cards such as the 1080ti
+- GTX 1650 series cards
+- GTX 1660 series cards
 
 ### :fontawesome-solid-memory: Memory and Disk
 
--   At least 12 GB Main Memory RAM.
--   At least 18 GB of free disk space for the machine learning model, Python,
-    and all its dependencies.
+- At least 12 GB Main Memory RAM.
+- At least 18 GB of free disk space for the machine learning model, Python, and
+  all its dependencies.
 
 ## :octicons-package-dependencies-24: Installation
 
@@ -115,407 +113,133 @@ either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
 driver).
 
 ### [Installation Getting Started Guide](installation)
-
 #### [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
-
 This method is recommended for 1st time users
-
 #### [Manual Installation](installation/020_INSTALL_MANUAL.md)
-
 This method is recommended for experienced users and developers
-
 #### [Docker Installation](installation/040_INSTALL_DOCKER.md)
-
 This method is recommended for those familiar with running Docker containers
-
 ### Other Installation Guides
-
--   [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
--   [XFormers](installation/070_INSTALL_XFORMERS.md)
--   [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
--   [Installing New Models](installation/050_INSTALLING_MODELS.md)
+  - [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
+  - [XFormers](installation/070_INSTALL_XFORMERS.md)
+  - [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
+  - [Installing New Models](installation/050_INSTALLING_MODELS.md)
 
 ## :octicons-gift-24: InvokeAI Features
 
 ### The InvokeAI Web Interface
-
--   [WebUI overview](features/WEB.md)
--   [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
--   [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
--   [Visual Manual for InvokeAI v2.3.1](https://docs.google.com/presentation/d/e/2PACX-1vSE90aC7bVVg0d9KXVMhy-Wve-wModgPFp7AGVTOCgf4xE03SnV24mjdwldolfCr59D_35oheHe4Cow/pub?start=false&loop=true&delayms=60000) (contributed by Statcomm)
-
+- [WebUI overview](features/WEB.md)
+- [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
+- [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
 <!-- separator -->
-
-<!-- separator -->
-
 ### The InvokeAI Command Line Interface
-
--   [Command Line Interace Reference Guide](features/CLI.md)
+- [Command Line Interace Reference Guide](features/CLI.md)
 <!-- separator -->
-
 ### Image Management
-
--   [Image2Image](features/IMG2IMG.md)
--   [Inpainting](features/INPAINTING.md)
--   [Outpainting](features/OUTPAINTING.md)
--   [Adding custom styles and subjects](features/CONCEPTS.md)
--   [Using LoRA models](features/LORAS.md)
--   [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
--   [Embiggen upscaling](features/EMBIGGEN.md)
--   [Other Features](features/OTHER.md)
+- [Image2Image](features/IMG2IMG.md)
+- [Inpainting](features/INPAINTING.md)
+- [Outpainting](features/OUTPAINTING.md)
+- [Adding custom styles and subjects](features/CONCEPTS.md)
+- [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
+- [Embiggen upscaling](features/EMBIGGEN.md)
+- [Other Features](features/OTHER.md)
 
 <!-- separator -->
-
 ### Model Management
-
--   [Installing](installation/050_INSTALLING_MODELS.md)
--   [Model Merging](features/MODEL_MERGING.md)
--   [Adding custom styles and subjects via embeddings](features/CONCEPTS.md)
--   [Textual Inversion](features/TEXTUAL_INVERSION.md)
--   [Not Safe for Work (NSFW) Checker](features/NSFW.md)
+- [Installing](installation/050_INSTALLING_MODELS.md)
+- [Model Merging](features/MODEL_MERGING.md)
+- [Style/Subject Concepts and Embeddings](features/CONCEPTS.md)
+- [Textual Inversion](features/TEXTUAL_INVERSION.md)
+- [Not Safe for Work (NSFW) Checker](features/NSFW.md)
 <!-- seperator -->
-
 ### Prompt Engineering
-
--   [Prompt Syntax](features/PROMPTS.md)
--   [Generating Variations](features/VARIATIONS.md)
+- [Prompt Syntax](features/PROMPTS.md)
+- [Generating Variations](features/VARIATIONS.md)
 
 ## :octicons-log-16: Latest Changes
 
-### v2.3.3 <small>(29 March 2023)</small>
-
-#### Bug Fixes
-1. When using legacy checkpoints with an external VAE, the VAE file is now scanned for malware prior to loading. Previously only the main model weights file was scanned.
-2. Textual inversion will select an appropriate batchsize based on whether `xformers` is active, and will default to `xformers` enabled if the library is detected.
-3. The batch script log file names have been fixed to be compatible with Windows.
-4. Occasional corruption of the `.next_prefix` file (which stores the next output file name in sequence) on Windows systems is now detected and corrected.
-5. An infinite loop when opening the developer's console from within the `invoke.sh` script has been corrected.
-
-#### Enhancements
-1. It is now possible to load and run several community-contributed SD-2.0 based models, including the infamous "Illuminati" model.
-2. The "NegativePrompts" embedding file, and others like it, can now be loaded by placing it in the InvokeAI `embeddings` directory.
-3. If no `--model` is specified at launch time, InvokeAI will remember the last model used and restore it the next time it is launched.
-4. On Linux systems, the `invoke.sh` launcher now uses a prettier console-based interface. To take advantage of it, install the `dialog` package using your package manager (e.g. `sudo apt install dialog`).
-5. When loading legacy models (safetensors/ckpt) you can specify a custom config file and/or a VAE by placing like-named files in the same directory as the model following this example:
-```
-my-favorite-model.ckpt
-my-favorite-model.yaml
-my-favorite-model.vae.pt      # or my-favorite-model.vae.safetensors
-```
-
-### v2.3.2 <small>(13 March 2023)</small>
-
-#### Bugfixes
-
-Since version 2.3.1 the following bugs have been fixed:
-
-1. Black images appearing for potential NSFW images when generating with legacy checkpoint models and both `--no-nsfw_checker` and `--ckpt_convert` turned on.
-2. Black images appearing when generating from models fine-tuned on Stable-Diffusion-2-1-base. When importing V2-derived models, you may be asked to select whether the model was derived from a "base" model (512 pixels) or the 768-pixel SD-2.1 model.
-3. The "Use All" button was not restoring the Hi-Res Fix setting on the WebUI
-4. When using the model installer console app, models failed to import correctly when importing from directories with spaces in their names. A similar issue with the output directory was also fixed.
-5. Crashes that occurred during model merging.
-6. Restore previous naming of Stable Diffusion base and 768 models.
-7. Upgraded to latest versions of `diffusers`, `transformers`, `safetensors` and `accelerate` libraries upstream. We hope that this will fix the `assertion NDArray > 2**32` issue that MacOS users have had when generating images larger than 768x768 pixels. Please report back.
-
-As part of the upgrade to `diffusers`, the location of the diffusers-based models has changed from `models/diffusers` to `models/hub`. When you launch InvokeAI for the first time, it will prompt you to OK a one-time move. This should be quick and harmless, but if you have modified your `models/diffusers` directory in some way, for example using symlinks, you may wish to cancel the migration and make appropriate adjustments.
-
-#### New "Invokeai-batch" script
-
-2.3.2 introduces a new command-line only script called
-`invokeai-batch` that can be used to generate hundreds of images from
-prompts and settings that vary systematically. This can be used to try
-the same prompt across multiple combinations of models, steps, CFG
-settings and so forth. It also allows you to template prompts and
-generate a combinatorial list like: ``` a shack in the mountains,
-photograph a shack in the mountains, watercolor a shack in the
-mountains, oil painting a chalet in the mountains, photograph a chalet
-in the mountains, watercolor a chalet in the mountains, oil painting a
-shack in the desert, photograph ...  ```
-
-If you have a system with multiple GPUs, or a single GPU with lots of
-VRAM, you can parallelize generation across the combinatorial set,
-reducing wait times and using your system's resources efficiently
-(make sure you have good GPU cooling).
-
-To try `invokeai-batch` out. Launch the "developer's console" using
-the `invoke` launcher script, or activate the invokeai virtual
-environment manually. From the console, give the command
-`invokeai-batch --help` in order to learn how the script works and
-create your first template file for dynamic prompt generation.
-
-### v2.3.1 <small>(26 February 2023)</small>
-
-This is primarily a bugfix release, but it does provide several new features that will improve the user experience. 
-
-#### Enhanced support for model management
-
-InvokeAI now makes it convenient to add, remove and modify models. You can individually import models that are stored on your local system, scan an entire folder and its subfolders for models and import them automatically, and even directly import models from the internet by providing their download URLs. You also have the option of designating a local folder to scan for new models each time InvokeAI is restarted.
-
-There are three ways of accessing the model management features:
-
-1. ***From the WebUI***, click on the cube to the right of the model selection menu. This will bring up a form that allows you to import models individually from your local disk or scan a directory for models to import.
-
-![image](https://user-images.githubusercontent.com/111189/220638091-918492cc-0719-4194-b033-3741e8289b30.png)
-
-2. **Using the Model Installer App**
-
-Choose option (5) _download and install models_ from the `invoke` launcher script to start a new console-based application for model management. You can use this to select from a curated set of starter models, or import checkpoint, safetensors, and diffusers models from a local disk or the internet. The example below shows importing two checkpoint URLs from popular SD sites and a HuggingFace diffusers model using its Repository ID. It also shows how to designate a folder to be scanned at startup time for new models to import.
-
-Command-line users can start this app using the command `invokeai-model-install`.
-
-![image](https://user-images.githubusercontent.com/111189/220660363-22ff3a2e-8082-410e-a818-d2b3a0529bac.png)
-
-3. **Using the Command Line Client (CLI)**
-
-The `!install_model` and `!convert_model` commands have been enhanced to allow entering of URLs and local directories to scan and import. The first command installs .ckpt and .safetensors files as-is. The second one converts them into the faster diffusers format before installation.
-
-Internally InvokeAI is able to probe the contents of a .ckpt or .safetensors file to distinguish among v1.x, v2.x and inpainting models. This means that you do **not** need to include "inpaint" in your model names to use an inpainting model. Note that Stable Diffusion v2.x models will be autoconverted into a diffusers model the first time you use it.
-
-Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management.
-
-#### An Improved Installer Experience
-
-The installer now launches a console-based UI for setting and changing commonly-used startup options:
-
-![image](https://user-images.githubusercontent.com/111189/220644777-3d3a90ca-f9e2-4e6d-93da-cbdd66bf12f3.png)
-
-After selecting the desired options, the installer installs several support models needed by InvokeAI's face reconstruction and upscaling features and then launches the interface for selecting and installing models shown earlier. At any time,  you can edit the startup options by launching `invoke.sh`/`invoke.bat` and entering option (6) _change InvokeAI startup options_
-
-Command-line users can launch the new configure app using `invokeai-configure`.
-
-This release also comes with a renewed updater. To do an update without going through a whole reinstallation, launch `invoke.sh` or `invoke.bat` and choose option (9) _update InvokeAI_ . This will bring you to a screen that prompts you to update to the latest released version, to the most current development version, or any released or unreleased version you choose by selecting the tag or branch of the desired version.
-
-![image](https://user-images.githubusercontent.com/111189/220650124-30a77137-d9cd-406e-a87d-d8283f99a4b3.png)
-
-Command-line users can run this interface by typing `invokeai-configure`
-
-#### Image Symmetry Options
-
-There are now features to generate horizontal and vertical symmetry during generation. The way these work is to wait until a selected step in the generation process and then to turn on a mirror image effect. In addition to generating some cool images, you can also use this to make side-by-side comparisons of how an image will look with more or fewer steps. Access this option from the WebUI by selecting _Symmetry_ from the image generation settings, or within the CLI by using the options `--h_symmetry_time_pct` and `--v_symmetry_time_pct` (these can be abbreviated to `--h_sym` and `--v_sym` like all other options).
-
-![image](https://user-images.githubusercontent.com/111189/220658687-47fd0f2c-7069-4d95-aec9-7196fceb360d.png)
-
-#### A New Unified Canvas Look
-
-This release introduces a beta version of the WebUI Unified Canvas. To try it out, open up the settings dialogue in the WebUI (gear icon) and select _Use Canvas Beta Layout_:
-
-![image](https://user-images.githubusercontent.com/111189/220646958-b7eca95e-dc39-4cd2-b277-63eac98ed446.png)
-
-Refresh the screen and go to to Unified Canvas (left side of screen, third icon from the top). The new layout is designed to provide more space to work in and to keep the image controls close to the image itself:
-
-![image](https://user-images.githubusercontent.com/111189/220647560-4a9265a1-6926-44f9-9d08-e1ef2ce61ff8.png)
-
-#### Model conversion and merging within the WebUI
-
-The WebUI now has an intuitive interface for model merging, as well as for permanent conversion of models from legacy .ckpt/.safetensors formats into diffusers format. These options are also available directly from the `invoke.sh`/`invoke.bat` scripts.
-
-#### An easier way to contribute translations to the WebUI
-
-We have migrated our translation efforts to [Weblate](https://hosted.weblate.org/engage/invokeai/), a FOSS translation product. Maintaining the growing project's translations is now far simpler for the maintainers and community. Please review our brief [translation guide](https://github.com/invoke-ai/InvokeAI/blob/v2.3.1/docs/other/TRANSLATION.md) for more information on how to contribute.
-
-#### Numerous internal bugfixes and performance issues
-
-This releases quashes multiple bugs that were reported in 2.3.0. Major internal changes include upgrading to `diffusers 0.13.0`, and using the `compel` library for prompt parsing. See [Detailed Change Log](#full-change-log) for a detailed list of bugs caught and squished.
-
-#### Summary of InvokeAI command line scripts (all accessible via the launcher menu)
-
-| Command                  | Description                                                         |
-|--------------------------|---------------------------------------------------------------------|
-| `invokeai`               | Command line interface                                              |
-| `invokeai --web`         | Web interface                                                       |
-| `invokeai-model-install` | Model installer with console forms-based front end                  |
-| `invokeai-ti --gui`      | Textual inversion, with a console forms-based front end             |
-| `invokeai-merge --gui`   | Model merging, with a console forms-based front end                 |
-| `invokeai-configure`     | Startup configuration; can also be used to reinstall support models |
-| `invokeai-update`        | InvokeAI software updater                                           |
-
-
 ### v2.3.0 <small>(9 February 2023)</small>
 
 #### Migration to Stable Diffusion `diffusers` models
 
-Previous versions of InvokeAI supported the original model file format
-introduced with Stable Diffusion 1.4. In the original format, known variously as
-"checkpoint", or "legacy" format, there is a single large weights file ending
-with `.ckpt` or `.safetensors`. Though this format has served the community
-well, it has a number of disadvantages, including file size, slow loading times,
-and a variety of non-standard variants that require special-case code to handle.
-In addition, because checkpoint files are actually a bundle of multiple machine
-learning sub-models, it is hard to swap different sub-models in and out, or to
-share common sub-models. A new format, introduced by the StabilityAI company in
-collaboration with HuggingFace, is called `diffusers` and consists of a
-directory of individual models. The most immediate benefit of `diffusers` is
-that they load from disk very quickly. A longer term benefit is that in the near
-future `diffusers` models will be able to share common sub-models, dramatically
-reducing disk space when you have multiple fine-tune models derived from the
-same base.
+Previous versions of InvokeAI supported the original model file format introduced with Stable Diffusion 1.4. In the original format, known variously as "checkpoint", or "legacy" format, there is a single large weights file ending with `.ckpt` or `.safetensors`. Though this format has served the community well, it has a number of disadvantages, including file size, slow loading times, and a variety of non-standard variants that require special-case code to handle. In addition, because checkpoint files are actually a bundle of multiple machine learning sub-models, it is hard to swap different sub-models in and out, or to share common sub-models. A new format, introduced by the StabilityAI company in collaboration with HuggingFace, is called `diffusers` and consists of a directory of individual models. The most immediate benefit of `diffusers` is that they load from disk very quickly. A longer term benefit is that in the near future `diffusers` models will be able to share common sub-models, dramatically reducing disk space when you have multiple fine-tune models derived from the same base.
 
-When you perform a new install of version 2.3.0, you will be offered the option
-to install the `diffusers` versions of a number of popular SD models, including
-Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of
-2.1). These will act and work just like the checkpoint versions. Do not be
-concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk!
-InvokeAI 2.3.0 can still load these and generate images from them without any
-extra intervention on your part.
+When you perform a new install of version 2.3.0, you will be offered the option to install the `diffusers` versions of a number of popular SD models, including Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of 2.1). These will act and work just like the checkpoint versions. Do not be concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk! InvokeAI 2.3.0 can still load these and generate images from them without any extra intervention on your part.
 
-To take advantage of the optimized loading times of `diffusers` models, InvokeAI
-offers options to convert legacy checkpoint models into optimized `diffusers`
-models. If you use the `invokeai` command line interface, the relevant commands
-are:
+To take advantage of the optimized loading times of `diffusers` models, InvokeAI offers options to convert legacy checkpoint models into optimized `diffusers` models. If you use the `invokeai` command line interface, the relevant commands are:
 
--   `!convert_model` -- Take the path to a local checkpoint file or a URL that
-    is pointing to one, convert it into a `diffusers` model, and import it into
-    InvokeAI's models registry file.
--   `!optimize_model` -- If you already have a checkpoint model in your InvokeAI
-    models file, this command will accept its short name and convert it into a
-    like-named `diffusers` model, optionally deleting the original checkpoint
-    file.
--   `!import_model` -- Take the local path of either a checkpoint file or a
-    `diffusers` model directory and import it into InvokeAI's registry file. You
-    may also provide the ID of any diffusers model that has been published on
-    the
-    [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads)
-    and it will be downloaded and installed automatically.
+* `!convert_model` -- Take the path to a local checkpoint file or a URL that is pointing to one, convert it into a `diffusers` model, and import it into InvokeAI's models registry file.
+* `!optimize_model` -- If you already have a checkpoint model in your InvokeAI models file, this command will accept its short name and convert it into a like-named `diffusers` model, optionally deleting the original checkpoint file.
+* `!import_model` -- Take the local path of either a checkpoint file or a `diffusers` model directory and import it into InvokeAI's registry file. You may also provide the ID of any diffusers model that has been published on the [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads) and it will be downloaded and installed automatically.
 
 The WebGUI offers similar functionality for model management.
 
-For advanced users, new command-line options provide additional functionality.
-Launching `invokeai` with the argument `--autoconvert <path to directory>` takes
-the path to a directory of checkpoint files, automatically converts them into
-`diffusers` models and imports them. Each time the script is launched, the
-directory will be scanned for new checkpoint files to be loaded. Alternatively,
-the `--ckpt_convert` argument will cause any checkpoint or safetensors model
-that is already registered with InvokeAI to be converted into a `diffusers`
-model on the fly, allowing you to take advantage of future diffusers-only
-features without explicitly converting the model and saving it to disk.
+For advanced users, new command-line options provide additional functionality. Launching `invokeai` with the argument `--autoconvert <path to directory>` takes the path to a directory of checkpoint files, automatically converts them into `diffusers` models and imports them. Each time the script is launched, the directory will be scanned for new checkpoint files to be loaded. Alternatively, the `--ckpt_convert` argument will cause any checkpoint or safetensors model that is already registered with InvokeAI to be converted into a `diffusers` model on the fly, allowing you to take advantage of future diffusers-only features without explicitly converting the model and saving it to disk.
 
-Please see
-[INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/)
-for more information on model management in both the command-line and Web
-interfaces.
+Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management in both the command-line and Web interfaces.
 
 #### Support for the `XFormers` Memory-Efficient Crossattention Package
 
-On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once
-installed, the`xformers` package dramatically reduces the memory footprint of
-loaded Stable Diffusion models files and modestly increases image generation
-speed. `xformers` will be installed and activated automatically if you specify a
-CUDA system at install time.
+On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once installed,  the`xformers` package dramatically reduces the memory footprint of loaded Stable Diffusion models files and modestly increases image generation speed. `xformers` will be installed and activated automatically if you specify a CUDA system at install time.
 
-The caveat with using `xformers` is that it introduces slightly
-non-deterministic behavior, and images generated using the same seed and other
-settings will be subtly different between invocations. Generally the changes are
-unnoticeable unless you rapidly shift back and forth between images, but to
-disable `xformers` and restore fully deterministic behavior, you may launch
-InvokeAI using the `--no-xformers` option. This is most conveniently done by
-opening the file `invokeai/invokeai.init` with a text editor, and adding the
-line `--no-xformers` at the bottom.
+The caveat with using `xformers` is that it introduces slightly non-deterministic behavior, and images generated using the same seed and other settings will be subtly different between invocations. Generally the changes are unnoticeable unless you rapidly shift back and forth between images, but to disable `xformers` and restore fully deterministic behavior, you may launch InvokeAI using the `--no-xformers` option. This is most conveniently done by opening the file `invokeai/invokeai.init` with a text editor, and adding the line `--no-xformers` at the bottom.
 
 #### A Negative Prompt Box in the WebUI
 
-There is now a separate text input box for negative prompts in the WebUI. This
-is convenient for stashing frequently-used negative prompts ("mangled limbs, bad
-anatomy"). The `[negative prompt]` syntax continues to work in the main prompt
-box as well.
+There is now a separate text input box for negative prompts in the WebUI. This is convenient for stashing frequently-used negative prompts ("mangled limbs, bad anatomy"). The `[negative prompt]` syntax continues to work in the main prompt box as well.
 
-To see exactly how your prompts are being parsed, launch `invokeai` with the
-`--log_tokenization` option. The console window will then display the
-tokenization process for both positive and negative prompts.
+To see exactly how your prompts are being parsed, launch `invokeai` with the `--log_tokenization` option. The console window will then display the tokenization process for both positive and negative prompts.
 
 #### Model Merging
 
-Version 2.3.0 offers an intuitive user interface for merging up to three Stable
-Diffusion models using an intuitive user interface. Model merging allows you to
-mix the behavior of models to achieve very interesting effects. To use this,
-each of the models must already be imported into InvokeAI and saved in
-`diffusers` format, then launch the merger using a new menu item in the InvokeAI
-launcher script (`invoke.sh`, `invoke.bat`) or directly from the command line
-with `invokeai-merge --gui`. You will be prompted to select the models to merge,
-the proportions in which to mix them, and the mixing algorithm. The script will
-create a new merged `diffusers` model and import it into InvokeAI for your use.
+Version 2.3.0 offers an intuitive user interface for merging up to three Stable Diffusion models using an intuitive user interface. Model merging allows you to mix the behavior of models to achieve very interesting effects. To use this, each of the models must already be imported into InvokeAI and saved in `diffusers` format, then launch the merger using a new menu item in the InvokeAI launcher script (`invoke.sh`, `invoke.bat`) or directly from the command line with `invokeai-merge --gui`. You will be prompted to select the models to merge, the proportions in which to mix them, and the mixing algorithm. The script will create a new merged `diffusers` model and import it into InvokeAI for your use.
 
-See
-[MODEL MERGING](https://invoke-ai.github.io/InvokeAI/features/MODEL_MERGING/)
-for more details.
+See [MODEL MERGING](https://invoke-ai.github.io/InvokeAI/features/MODEL_MERGING/) for more details.
 
 #### Textual Inversion Training
 
-Textual Inversion (TI) is a technique for training a Stable Diffusion model to
-emit a particular subject or style when triggered by a keyword phrase. You can
-perform TI training by placing a small number of images of the subject or style
-in a directory, and choosing a distinctive trigger phrase, such as
-"pointillist-style". After successful training, The subject or style will be
-activated by including `<pointillist-style>` in your prompt.
+Textual Inversion (TI) is a technique for training a Stable Diffusion model to emit a particular subject or style when triggered by a keyword phrase. You can perform TI training by placing a small number of images of the subject or style in a directory, and choosing a distinctive trigger phrase, such as "pointillist-style". After successful training, The subject or style will be activated by including `<pointillist-style>` in your prompt.
 
-Previous versions of InvokeAI were able to perform TI, but it required using a
-command-line script with dozens of obscure command-line arguments. Version 2.3.0
-features an intuitive TI frontend that will build a TI model on top of any
-`diffusers` model. To access training you can launch from a new item in the
-launcher script or from the command line using `invokeai-ti --gui`.
+Previous versions of InvokeAI were able to perform TI, but it required using a command-line script with dozens of obscure command-line arguments. Version 2.3.0 features an intuitive TI frontend that will build a TI model on top of any `diffusers` model. To access training you can launch from a new item in the launcher script or from the command line using `invokeai-ti --gui`.
 
-See
-[TEXTUAL INVERSION](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/)
-for further details.
+See [TEXTUAL INVERSION](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/) for further details.
 
 #### A New Installer Experience
 
-The InvokeAI installer has been upgraded in order to provide a smoother and
-hopefully more glitch-free experience. In addition, InvokeAI is now packaged as
-a PyPi project, allowing developers and power-users to install InvokeAI with the
-command `pip install InvokeAI  --use-pep517`. Please see
-[Installation](#installation) for details.
+The InvokeAI installer has been upgraded in order to provide a smoother and hopefully more glitch-free experience. In addition, InvokeAI is now packaged as a PyPi project, allowing developers and power-users to install InvokeAI with the command `pip install InvokeAI  --use-pep517`. Please see [Installation](#installation) for details.
 
-Developers should be aware that the `pip` installation procedure has been
-simplified and that the `conda` method is no longer supported at all.
-Accordingly, the `environments_and_requirements` directory has been deleted from
-the repository.
+Developers should be aware that the `pip` installation procedure has been simplified and that the `conda` method is no longer supported at all. Accordingly, the `environments_and_requirements` directory has been deleted from the repository.
 
 #### Command-line name changes
 
-All of InvokeAI's functionality, including the WebUI, command-line interface,
-textual inversion training and model merging, can all be accessed from the
-`invoke.sh` and `invoke.bat` launcher scripts. The menu of options has been
-expanded to add the new functionality. For the convenience of developers and
-power users, we have normalized the names of the InvokeAI command-line scripts:
+All of InvokeAI's functionality, including the WebUI, command-line interface, textual inversion training and model merging, can all be accessed from the `invoke.sh` and `invoke.bat` launcher scripts. The menu of options has been expanded to add the new functionality. For the convenience of developers and power users, we have normalized the names of the InvokeAI command-line scripts:
 
--   `invokeai` -- Command-line client
--   `invokeai --web` -- Web GUI
--   `invokeai-merge --gui` -- Model merging script with graphical front end
--   `invokeai-ti --gui` -- Textual inversion script with graphical front end
--   `invokeai-configure` -- Configuration tool for initializing the `invokeai`
-    directory and selecting popular starter models.
+* `invokeai` -- Command-line client
+* `invokeai --web` -- Web GUI
+* `invokeai-merge --gui` -- Model merging script with graphical front end
+* `invokeai-ti --gui` -- Textual inversion script with graphical front end
+* `invokeai-configure` -- Configuration tool for initializing the `invokeai` directory and selecting popular starter models.
 
-For backward compatibility, the old command names are also recognized, including
-`invoke.py` and `configure-invokeai.py`. However, these are deprecated and will
-eventually be removed.
+For backward compatibility, the old command names are also recognized, including `invoke.py` and `configure-invokeai.py`. However, these are deprecated and will eventually be removed.
 
-Developers should be aware that the locations of the script's source code has
-been moved. The new locations are:
+Developers should be aware that the locations of the script's source code has been moved. The new locations are:
+* `invokeai` =>  `ldm/invoke/CLI.py`
+* `invokeai-configure` => `ldm/invoke/config/configure_invokeai.py`
+* `invokeai-ti`=> `ldm/invoke/training/textual_inversion.py`
+* `invokeai-merge` => `ldm/invoke/merge_diffusers`
 
--   `invokeai` => `ldm/invoke/CLI.py`
--   `invokeai-configure` => `ldm/invoke/config/configure_invokeai.py`
--   `invokeai-ti`=> `ldm/invoke/training/textual_inversion.py`
--   `invokeai-merge` => `ldm/invoke/merge_diffusers`
+Developers are strongly encouraged to perform an "editable" install of InvokeAI using `pip install -e .  --use-pep517` in the Git repository, and then to call the scripts using their 2.3.0 names, rather than executing the scripts directly. Developers should also be aware that the several important data files have been relocated into a new directory named `invokeai`. This includes the WebGUI's `frontend` and `backend` directories, and the `INITIAL_MODELS.yaml` files used by the installer to select starter models. Eventually all InvokeAI modules will be in subdirectories of `invokeai`.
 
-Developers are strongly encouraged to perform an "editable" install of InvokeAI
-using `pip install -e .  --use-pep517` in the Git repository, and then to call
-the scripts using their 2.3.0 names, rather than executing the scripts directly.
-Developers should also be aware that the several important data files have been
-relocated into a new directory named `invokeai`. This includes the WebGUI's
-`frontend` and `backend` directories, and the `INITIAL_MODELS.yaml` files used
-by the installer to select starter models. Eventually all InvokeAI modules will
-be in subdirectories of `invokeai`.
-
-Please see
-[2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0)
-for further details. For older changelogs, please visit the
+Please see [2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0) for further details.
+For older changelogs, please visit the
 **[CHANGELOG](CHANGELOG/#v223-2-december-2022)**.
 
 ## :material-target: Troubleshooting
 
-Please check out our
-**[:material-frequently-asked-questions: Troubleshooting Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)**
-to get solutions for common installation problems and other issues.
+Please check out our **[:material-frequently-asked-questions:
+Troubleshooting
+Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)** to
+get solutions for common installation problems and other issues.
 
 ## :octicons-repo-push-24: Contributing
 
@@ -541,8 +265,8 @@ thank them for their time, hard work and effort.
 For support, please use this repository's GitHub Issues tracking service. Feel
 free to send me an email if you use and like the script.
 
-Original portions of the software are Copyright (c) 2022-23 by
-[The InvokeAI Team](https://github.com/invoke-ai).
+Original portions of the software are Copyright (c) 2022-23
+by [The InvokeAI Team](https://github.com/invoke-ai).
 
 ## :octicons-book-24: Further Reading
 

docs/installation/010_INSTALL_AUTOMATED.md

@@ -89,7 +89,7 @@ experimental versions later.
          sudo apt update
          sudo apt install -y software-properties-common
          sudo add-apt-repository -y ppa:deadsnakes/ppa
-         sudo apt install python3.10 python3-pip python3.10-venv
+         sudo apt install -y python3.10 python3-pip python3.10-venv
          sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
          ```
 

docs/installation/020_INSTALL_MANUAL.md

@@ -148,13 +148,13 @@ manager, please follow these steps:
     === "CUDA (NVidia)"
 
         ```bash
-        pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+        pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
         ```
 
     === "ROCm (AMD)"
 
         ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -216,7 +216,7 @@ manager, please follow these steps:
 9.  Run the command-line- or the web- interface:
 
     From within INVOKEAI_ROOT, activate the environment
-    (with `source .venv/bin/activate` or `.venv\scripts\activate), and then run
+    (with `source .venv/bin/activate` or `.venv\scripts\activate`), and then run
     the script `invokeai`. If the virtual environment you selected is NOT inside
     INVOKEAI_ROOT, then you must specify the path to the root directory by adding
     `--root_dir \path\to\invokeai` to the commands below:
@@ -315,7 +315,7 @@ installation protocol (important!)
 
     === "ROCm (AMD)"
         ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -77,7 +77,7 @@ machine. To test, open up a terminal window and issue the following
 command:
 
 ```
-rocminfo
+rocm-smi
 ```
 
 If you get a table labeled "ROCm System Management Interface" the
@@ -95,17 +95,9 @@ recent version of Ubuntu, 22.04. However, this [community-contributed
 recipe](https://novaspirit.github.io/amdgpu-rocm-ubu22/) is reported
 to work well.
 
-After installation, please run `rocminfo` a second time to confirm
+After installation, please run `rocm-smi` a second time to confirm
 that the driver is present and the GPU is recognized. You may need to
-do a reboot in order to load the driver. In addition, if you see
-errors relating to your username not being a member of the `render`
-group, you may fix this by adding yourself to this group with the command:
-
-```
-sudo usermod -a -G render myUserName
-```
-
-(Thanks to @EgoringKosmos for the usermod recipe.)
+do a reboot in order to load the driver.
 
 ### Linux Install with a ROCm-docker Container
 

docs/installation/050_INSTALLING_MODELS.md

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

docs/installation/060_INSTALL_PATCHMATCH.md

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

docs/installation/deprecated_documentation/INSTALL_LINUX.md

@@ -79,7 +79,7 @@ title: Manual Installation, Linux
         and obtaining an access token for downloading. It will then download and
         install the weights files for you.
 
-        Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing
+        Please look [here](../INSTALL_MANUAL.md) for a manual process for doing
         the same thing.
 
 7.  Start generating images!

docs/installation/deprecated_documentation/INSTALL_WINDOWS.md

@@ -75,7 +75,7 @@ Note that you will need NVIDIA drivers, Python 3.10, and Git installed beforehan
           obtaining an access token for downloading. It will then download and install the
           weights files for you.
 
-          Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing the
+          Please look [here](../INSTALL_MANUAL.md) for a manual process for doing the
           same thing.
 
 8. Start generating images!

docs/other/CONTRIBUTORS.md

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

installer/create_installer.sh

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

installer/lib/installer.py

@@ -144,8 +144,8 @@ class Installer:
 
             from plumbum import FG, local
 
-            python = local[get_python_from_venv(venv_dir)]
-            python[ "-m", "pip", "install", "--upgrade", "pip"] & FG
+            pip = local[get_pip_from_venv(venv_dir)]
+            pip[ "install", "--upgrade", "pip"] & FG
 
         return venv_dir
 
@@ -241,9 +241,6 @@ class InvokeAiInstance:
 
         from plumbum import FG, local
 
-        # Note that we're installing pinned versions of torch and
-        # torchvision here, which *should* correspond to what is
-        # in pyproject.toml.
         pip = local[self.pip]
 
         (
@@ -294,7 +291,7 @@ class InvokeAiInstance:
                     src = Path(__file__).parents[1].expanduser().resolve()
                     # if the above directory contains one of these files, we'll do a source install
                     next(src.glob("pyproject.toml"))
-                    next(src.glob("ldm"))
+                    next(src.glob("invokeai"))
                 except StopIteration:
                     print("Unable to find a wheel or perform a source install. Giving up.")
 
@@ -345,14 +342,14 @@ class InvokeAiInstance:
 
         introduction()
 
-        from ldm.invoke.config import invokeai_configure
+        from invokeai.frontend.install import invokeai_configure
 
         # NOTE: currently the config script does its own arg parsing! this means the command-line switches
         # from the installer will also automatically propagate down to the config script.
         # this may change in the future with config refactoring!
         succeeded = False
         try:
-            invokeai_configure.main()
+            invokeai_configure()
             succeeded = True
         except requests.exceptions.ConnectionError as e:
             print(f'\nA network error was encountered during configuration and download: {str(e)}')
@@ -382,9 +379,6 @@ class InvokeAiInstance:
             shutil.copy(src, dest)
             os.chmod(dest, 0o0755)
 
-        if OS == "Linux":
-            shutil.copy(Path(__file__).parents[1] / "templates" / "dialogrc", self.runtime / '.dialogrc')
-
     def update(self):
         pass
 
@@ -411,22 +405,6 @@ def get_pip_from_venv(venv_path: Path) -> str:
     return str(venv_path.expanduser().resolve() / pip)
 
 
-def get_python_from_venv(venv_path: Path) -> str:
-    """
-    Given a path to a virtual environment, get the absolute path to the `python` executable
-    in a cross-platform fashion. Does not validate that the python executable
-    actually exists in the virtualenv.
-
-    :param venv_path: Path to the virtual environment
-    :type venv_path: Path
-    :return: Absolute path to the python executable
-    :rtype: str
-    """
-
-    python = "Scripts\python.exe" if OS == "Windows" else "bin/python"
-    return str(venv_path.expanduser().resolve() / python)
-
-
 def set_sys_path(venv_path: Path) -> None:
     """
     Given a path to a virtual environment, set the sys.path, in a cross-platform fashion,
@@ -478,7 +456,7 @@ def get_torch_source() -> (Union[str, None],str):
     optional_modules = None
     if OS == "Linux":
         if device == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.2"
+            url = "https://download.pytorch.org/whl/rocm5.4.2"
         elif device == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 

installer/templates/dialogrc

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

installer/templates/invoke.bat.in

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

installer/templates/invoke.sh.in

@@ -52,11 +52,11 @@ do_choice() {
     1)
         clear
         printf "Generate images with a browser-based interface\n"
-        invokeai --web $PARAMS
+        invokeai-web $PARAMS
         ;;
     2)
         clear
-        printf "Generate images using a command-line interface\n"
+        printf "Explore InvokeAI nodes using a command-line interface\n"
         invokeai $PARAMS
         ;;
     3)
@@ -130,7 +130,7 @@ do_dialog() {
     choice=$(dialog --clear \
         --backtitle "\Zb\Zu\Z3InvokeAI" \
         --colors \
-        --title "What would you like to run?" \
+        --title "What would you like to do?" \
         --ok-label "Run" \
         --cancel-label "Exit" \
         --help-button \
@@ -147,9 +147,9 @@ do_dialog() {
 do_line_input() {
     clear
     printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
-    printf "Do you want to generate images using the\n"
-    printf "1: Browser-based UI\n"
-    printf "2: Command-line interface\n"
+    printf "What would you like to do?\n"
+    printf "1: Generate images using the browser-based interface\n"
+    printf "2: Explore InvokeAI nodes using the command-line interface\n"
     printf "3: Run textual inversion training\n"
     printf "4: Merge models (diffusers type only)\n"
     printf "5: Download and install models\n"

invokeai/README

@@ -1,3 +1,11 @@
-After version 2.3 is released, the ldm/invoke modules will be migrated to this location
-so that we have a proper invokeai distribution. Currently it is only being used for
-data files.
+Organization of the source tree:
+
+app -- Home of nodes invocations and services
+assets -- Images and other data files used by InvokeAI
+backend -- Non-user facing libraries, including the rendering
+	core.
+configs -- Configuration files used at install and run times
+frontend -- User-facing scripts, including the CLI and the WebUI
+version -- Current InvokeAI version string, stored
+	in version/invokeai_version.py
+	

invokeai/app/api/dependencies.py

@@ -0,0 +1,108 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from logging import Logger
+import os
+from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
+from invokeai.app.services.images import ImageService
+from invokeai.app.services.metadata import CoreMetadataService
+from invokeai.app.services.resource_name import SimpleNameService
+from invokeai.app.services.urls import LocalUrlService
+from invokeai.backend.util.logging import InvokeAILogger
+
+from ..services.default_graphs import create_system_graphs
+from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
+from ..services.model_manager_initializer import get_model_manager
+from ..services.restoration_services import RestorationServices
+from ..services.graph import GraphExecutionState, LibraryGraph
+from ..services.image_file_storage import DiskImageFileStorage
+from ..services.invocation_queue import MemoryInvocationQueue
+from ..services.invocation_services import InvocationServices
+from ..services.invoker import Invoker
+from ..services.processor import DefaultInvocationProcessor
+from ..services.sqlite import SqliteItemStorage
+from .events import FastAPIEventService
+
+
+# TODO: is there a better way to achieve this?
+def check_internet() -> bool:
+    """
+    Return true if the internet is reachable.
+    It does this by pinging huggingface.co.
+    """
+    import urllib.request
+
+    host = "http://huggingface.co"
+    try:
+        urllib.request.urlopen(host, timeout=1)
+        return True
+    except:
+        return False
+
+
+logger = InvokeAILogger.getLogger()
+
+
+class ApiDependencies:
+    """Contains and initializes all dependencies for the API"""
+
+    invoker: Invoker = None
+
+    @staticmethod
+    def initialize(config, event_handler_id: int, logger: Logger = logger):
+        logger.info(f"Internet connectivity is {config.internet_available}")
+
+        events = FastAPIEventService(event_handler_id)
+
+        output_folder = config.output_path
+
+        # TODO: build a file/path manager?
+        db_location = config.db_path
+        db_location.parent.mkdir(parents=True,exist_ok=True)
+
+        graph_execution_manager = SqliteItemStorage[GraphExecutionState](
+            filename=db_location, table_name="graph_executions"
+        )
+
+        urls = LocalUrlService()
+        metadata = CoreMetadataService()
+        image_record_storage = SqliteImageRecordStorage(db_location)
+        image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
+        names = SimpleNameService()
+        latents = ForwardCacheLatentsStorage(
+            DiskLatentsStorage(f"{output_folder}/latents")
+        )
+
+        images = ImageService(
+            image_record_storage=image_record_storage,
+            image_file_storage=image_file_storage,
+            metadata=metadata,
+            url=urls,
+            logger=logger,
+            names=names,
+            graph_execution_manager=graph_execution_manager,
+        )
+
+        services = InvocationServices(
+            model_manager=get_model_manager(config, logger),
+            events=events,
+            latents=latents,
+            images=images,
+            queue=MemoryInvocationQueue(),
+            graph_library=SqliteItemStorage[LibraryGraph](
+                filename=db_location, table_name="graphs"
+            ),
+            graph_execution_manager=graph_execution_manager,
+            processor=DefaultInvocationProcessor(),
+            restoration=RestorationServices(config, logger),
+            configuration=config,
+            logger=logger,
+        )
+
+        create_system_graphs(services.graph_library)
+
+        ApiDependencies.invoker = Invoker(services)
+
+    @staticmethod
+    def shutdown():
+        if ApiDependencies.invoker:
+            ApiDependencies.invoker.stop()

invokeai/app/api/events.py

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

invokeai/app/api/routers/images.py

@@ -0,0 +1,250 @@
+import io
+from typing import Optional
+from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
+from fastapi.routing import APIRouter
+from fastapi.responses import FileResponse
+from PIL import Image
+from invokeai.app.models.image import (
+    ImageCategory,
+    ResourceOrigin,
+)
+from invokeai.app.services.image_record_storage import OffsetPaginatedResults
+from invokeai.app.services.models.image_record import (
+    ImageDTO,
+    ImageRecordChanges,
+    ImageUrlsDTO,
+)
+from invokeai.app.services.item_storage import PaginatedResults
+
+from ..dependencies import ApiDependencies
+
+images_router = APIRouter(prefix="/v1/images", tags=["images"])
+
+
+@images_router.post(
+    "/",
+    operation_id="upload_image",
+    responses={
+        201: {"description": "The image was uploaded successfully"},
+        415: {"description": "Image upload failed"},
+    },
+    status_code=201,
+    response_model=ImageDTO,
+)
+async def upload_image(
+    file: UploadFile,
+    request: Request,
+    response: Response,
+    image_category: ImageCategory = Query(description="The category of the image"),
+    is_intermediate: bool = Query(description="Whether this is an intermediate image"),
+    session_id: Optional[str] = Query(
+        default=None, description="The session ID associated with this upload, if any"
+    ),
+) -> ImageDTO:
+    """Uploads an image"""
+    if not file.content_type.startswith("image"):
+        raise HTTPException(status_code=415, detail="Not an image")
+
+    contents = await file.read()
+
+    try:
+        pil_image = Image.open(io.BytesIO(contents))
+    except:
+        # Error opening the image
+        raise HTTPException(status_code=415, detail="Failed to read image")
+
+    try:
+        image_dto = ApiDependencies.invoker.services.images.create(
+            image=pil_image,
+            image_origin=ResourceOrigin.EXTERNAL,
+            image_category=image_category,
+            session_id=session_id,
+            is_intermediate=is_intermediate,
+        )
+
+        response.status_code = 201
+        response.headers["Location"] = image_dto.image_url
+
+        return image_dto
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to create image")
+
+
+@images_router.delete("/{image_origin}/{image_name}", operation_id="delete_image")
+async def delete_image(
+    image_origin: ResourceOrigin = Path(description="The origin of image to delete"),
+    image_name: str = Path(description="The name of the image to delete"),
+) -> None:
+    """Deletes an image"""
+
+    try:
+        ApiDependencies.invoker.services.images.delete(image_origin, image_name)
+    except Exception as e:
+        # TODO: Does this need any exception handling at all?
+        pass
+
+
+@images_router.patch(
+    "/{image_origin}/{image_name}",
+    operation_id="update_image",
+    response_model=ImageDTO,
+)
+async def update_image(
+    image_origin: ResourceOrigin = Path(description="The origin of image to update"),
+    image_name: str = Path(description="The name of the image to update"),
+    image_changes: ImageRecordChanges = Body(
+        description="The changes to apply to the image"
+    ),
+) -> ImageDTO:
+    """Updates an image"""
+
+    try:
+        return ApiDependencies.invoker.services.images.update(
+            image_origin, image_name, image_changes
+        )
+    except Exception as e:
+        raise HTTPException(status_code=400, detail="Failed to update image")
+
+
+@images_router.get(
+    "/{image_origin}/{image_name}/metadata",
+    operation_id="get_image_metadata",
+    response_model=ImageDTO,
+)
+async def get_image_metadata(
+    image_origin: ResourceOrigin = Path(description="The origin of image to get"),
+    image_name: str = Path(description="The name of image to get"),
+) -> ImageDTO:
+    """Gets an image's metadata"""
+
+    try:
+        return ApiDependencies.invoker.services.images.get_dto(image_origin, image_name)
+    except Exception as e:
+        raise HTTPException(status_code=404)
+
+
+@images_router.get(
+    "/{image_origin}/{image_name}",
+    operation_id="get_image_full",
+    response_class=Response,
+    responses={
+        200: {
+            "description": "Return the full-resolution image",
+            "content": {"image/png": {}},
+        },
+        404: {"description": "Image not found"},
+    },
+)
+async def get_image_full(
+    image_origin: ResourceOrigin = Path(
+        description="The type of full-resolution image file to get"
+    ),
+    image_name: str = Path(description="The name of full-resolution image file to get"),
+) -> FileResponse:
+    """Gets a full-resolution image file"""
+
+    try:
+        path = ApiDependencies.invoker.services.images.get_path(image_origin, image_name)
+
+        if not ApiDependencies.invoker.services.images.validate_path(path):
+            raise HTTPException(status_code=404)
+
+        return FileResponse(
+            path,
+            media_type="image/png",
+            filename=image_name,
+            content_disposition_type="inline",
+        )
+    except Exception as e:
+        raise HTTPException(status_code=404)
+
+
+@images_router.get(
+    "/{image_origin}/{image_name}/thumbnail",
+    operation_id="get_image_thumbnail",
+    response_class=Response,
+    responses={
+        200: {
+            "description": "Return the image thumbnail",
+            "content": {"image/webp": {}},
+        },
+        404: {"description": "Image not found"},
+    },
+)
+async def get_image_thumbnail(
+    image_origin: ResourceOrigin = Path(description="The origin of thumbnail image file to get"),
+    image_name: str = Path(description="The name of thumbnail image file to get"),
+) -> FileResponse:
+    """Gets a thumbnail image file"""
+
+    try:
+        path = ApiDependencies.invoker.services.images.get_path(
+            image_origin, image_name, thumbnail=True
+        )
+        if not ApiDependencies.invoker.services.images.validate_path(path):
+            raise HTTPException(status_code=404)
+
+        return FileResponse(
+            path, media_type="image/webp", content_disposition_type="inline"
+        )
+    except Exception as e:
+        raise HTTPException(status_code=404)
+
+
+@images_router.get(
+    "/{image_origin}/{image_name}/urls",
+    operation_id="get_image_urls",
+    response_model=ImageUrlsDTO,
+)
+async def get_image_urls(
+    image_origin: ResourceOrigin = Path(description="The origin of the image whose URL to get"),
+    image_name: str = Path(description="The name of the image whose URL to get"),
+) -> ImageUrlsDTO:
+    """Gets an image and thumbnail URL"""
+
+    try:
+        image_url = ApiDependencies.invoker.services.images.get_url(
+            image_origin, image_name
+        )
+        thumbnail_url = ApiDependencies.invoker.services.images.get_url(
+            image_origin, image_name, thumbnail=True
+        )
+        return ImageUrlsDTO(
+            image_origin=image_origin,
+            image_name=image_name,
+            image_url=image_url,
+            thumbnail_url=thumbnail_url,
+        )
+    except Exception as e:
+        raise HTTPException(status_code=404)
+
+
+@images_router.get(
+    "/",
+    operation_id="list_images_with_metadata",
+    response_model=OffsetPaginatedResults[ImageDTO],
+)
+async def list_images_with_metadata(
+    image_origin: Optional[ResourceOrigin] = Query(
+        default=None, description="The origin of images to list"
+    ),
+    categories: Optional[list[ImageCategory]] = Query(
+        default=None, description="The categories of image to include"
+    ),
+    is_intermediate: Optional[bool] = Query(
+        default=None, description="Whether to list intermediate images"
+    ),
+    offset: int = Query(default=0, description="The page offset"),
+    limit: int = Query(default=10, description="The number of images per page"),
+) -> OffsetPaginatedResults[ImageDTO]:
+    """Gets a list of images"""
+
+    image_dtos = ApiDependencies.invoker.services.images.get_many(
+        offset,
+        limit,
+        image_origin,
+        categories,
+        is_intermediate,
+    )
+
+    return image_dtos

invokeai/app/api/routers/models.py

@@ -0,0 +1,248 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and 2023 Kent Keirsey (https://github.com/hipsterusername)
+
+import shutil
+import asyncio
+from typing import Annotated, Any, List, Literal, Optional, Union
+
+from fastapi.routing import APIRouter, HTTPException
+from pydantic import BaseModel, Field, parse_obj_as
+from pathlib import Path
+from ..dependencies import ApiDependencies
+
+models_router = APIRouter(prefix="/v1/models", tags=["models"])
+
+
+class VaeRepo(BaseModel):
+    repo_id: str = Field(description="The repo ID to use for this VAE")
+    path: Optional[str] = Field(description="The path to the VAE")
+    subfolder: Optional[str] = Field(description="The subfolder to use for this VAE")
+
+class ModelInfo(BaseModel):
+    description: Optional[str] = Field(description="A description of the model")
+    
+class CkptModelInfo(ModelInfo):
+    format: Literal['ckpt'] = 'ckpt'
+
+    config: str = Field(description="The path to the model config")
+    weights: str = Field(description="The path to the model weights")
+    vae: str = Field(description="The path to the model VAE")
+    width: Optional[int] = Field(description="The width of the model")
+    height: Optional[int] = Field(description="The height of the model")
+
+class DiffusersModelInfo(ModelInfo):
+    format: Literal['diffusers'] = 'diffusers'
+
+    vae: Optional[VaeRepo] = Field(description="The VAE repo to use for this model")
+    repo_id: Optional[str] = Field(description="The repo ID to use for this model")
+    path: Optional[str] = Field(description="The path to the model")
+
+class CreateModelRequest(BaseModel):
+    name: str = Field(description="The name of the model")
+    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
+
+class CreateModelResponse(BaseModel):
+    name: str = Field(description="The name of the new model")
+    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
+    status: str = Field(description="The status of the API response")
+
+class ConversionRequest(BaseModel):
+    name: str = Field(description="The name of the new model")
+    info: CkptModelInfo = Field(description="The converted model info")
+    save_location: str = Field(description="The path to save the converted model weights")
+    
+
+class ConvertedModelResponse(BaseModel):
+    name: str = Field(description="The name of the new model")
+    info: DiffusersModelInfo = Field(description="The converted model info")
+
+class ModelsList(BaseModel):
+    models: dict[str, Annotated[Union[(CkptModelInfo,DiffusersModelInfo)], Field(discriminator="format")]]
+
+
+@models_router.get(
+    "/",
+    operation_id="list_models",
+    responses={200: {"model": ModelsList }},
+)
+async def list_models() -> ModelsList:
+    """Gets a list of models"""
+    models_raw = ApiDependencies.invoker.services.model_manager.list_models()
+    models = parse_obj_as(ModelsList, { "models": models_raw })
+    return models
+
+
+@models_router.post(
+    "/",
+    operation_id="update_model",
+    responses={200: {"status": "success"}},
+)
+async def update_model(
+    model_request: CreateModelRequest
+) -> CreateModelResponse:
+    """ Add Model """
+    model_request_info = model_request.info
+    info_dict = model_request_info.dict()
+    model_response = CreateModelResponse(name=model_request.name, info=model_request.info, status="success")
+
+    ApiDependencies.invoker.services.model_manager.add_model(
+        model_name=model_request.name,
+        model_attributes=info_dict,
+        clobber=True,
+    )
+
+    return model_response
+
+
+@models_router.delete(
+    "/{model_name}",
+    operation_id="del_model",
+    responses={
+        204: {
+        "description": "Model deleted successfully"
+        }, 
+        404: {
+        "description": "Model not found"
+        }
+    },
+)
+async def delete_model(model_name: str) -> None:
+    """Delete Model"""
+    model_names = ApiDependencies.invoker.services.model_manager.model_names()
+    logger = ApiDependencies.invoker.services.logger
+    model_exists = model_name in model_names
+
+    # check if model exists
+    logger.info(f"Checking for model {model_name}...")
+           
+    if model_exists:
+        logger.info(f"Deleting Model: {model_name}")
+        ApiDependencies.invoker.services.model_manager.del_model(model_name, delete_files=True)
+        logger.info(f"Model Deleted: {model_name}")
+        raise HTTPException(status_code=204, detail=f"Model '{model_name}' deleted successfully")
+    
+    else:
+        logger.error(f"Model not found")
+        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
+    
+
+            # @socketio.on("convertToDiffusers")
+        # def convert_to_diffusers(model_to_convert: dict):
+        #     try:
+        #         if model_info := self.generate.model_manager.model_info(
+        #             model_name=model_to_convert["model_name"]
+        #         ):
+        #             if "weights" in model_info:
+        #                 ckpt_path = Path(model_info["weights"])
+        #                 original_config_file = Path(model_info["config"])
+        #                 model_name = model_to_convert["model_name"]
+        #                 model_description = model_info["description"]
+        #             else:
+        #                 self.socketio.emit(
+        #                     "error", {"message": "Model is not a valid checkpoint file"}
+        #                 )
+        #         else:
+        #             self.socketio.emit(
+        #                 "error", {"message": "Could not retrieve model info."}
+        #             )
+
+        #         if not ckpt_path.is_absolute():
+        #             ckpt_path = Path(Globals.root, ckpt_path)
+
+        #         if original_config_file and not original_config_file.is_absolute():
+        #             original_config_file = Path(Globals.root, original_config_file)
+
+        #         diffusers_path = Path(
+        #             ckpt_path.parent.absolute(), f"{model_name}_diffusers"
+        #         )
+
+        #         if model_to_convert["save_location"] == "root":
+        #             diffusers_path = Path(
+        #                 global_converted_ckpts_dir(), f"{model_name}_diffusers"
+        #             )
+
+        #         if (
+        #             model_to_convert["save_location"] == "custom"
+        #             and model_to_convert["custom_location"] is not None
+        #         ):
+        #             diffusers_path = Path(
+        #                 model_to_convert["custom_location"], f"{model_name}_diffusers"
+        #             )
+
+        #         if diffusers_path.exists():
+        #             shutil.rmtree(diffusers_path)
+
+        #         self.generate.model_manager.convert_and_import(
+        #             ckpt_path,
+        #             diffusers_path,
+        #             model_name=model_name,
+        #             model_description=model_description,
+        #             vae=None,
+        #             original_config_file=original_config_file,
+        #             commit_to_conf=opt.conf,
+        #         )
+
+        #         new_model_list = self.generate.model_manager.list_models()
+        #         socketio.emit(
+        #             "modelConverted",
+        #             {
+        #                 "new_model_name": model_name,
+        #                 "model_list": new_model_list,
+        #                 "update": True,
+        #             },
+        #         )
+        #         print(f">> Model Converted: {model_name}")
+        #     except Exception as e:
+        #         self.handle_exceptions(e)
+
+        # @socketio.on("mergeDiffusersModels")
+        # def merge_diffusers_models(model_merge_info: dict):
+        #     try:
+        #         models_to_merge = model_merge_info["models_to_merge"]
+        #         model_ids_or_paths = [
+        #             self.generate.model_manager.model_name_or_path(x)
+        #             for x in models_to_merge
+        #         ]
+        #         merged_pipe = merge_diffusion_models(
+        #             model_ids_or_paths,
+        #             model_merge_info["alpha"],
+        #             model_merge_info["interp"],
+        #             model_merge_info["force"],
+        #         )
+
+        #         dump_path = global_models_dir() / "merged_models"
+        #         if model_merge_info["model_merge_save_path"] is not None:
+        #             dump_path = Path(model_merge_info["model_merge_save_path"])
+
+        #         os.makedirs(dump_path, exist_ok=True)
+        #         dump_path = dump_path / model_merge_info["merged_model_name"]
+        #         merged_pipe.save_pretrained(dump_path, safe_serialization=1)
+
+        #         merged_model_config = dict(
+        #             model_name=model_merge_info["merged_model_name"],
+        #             description=f'Merge of models {", ".join(models_to_merge)}',
+        #             commit_to_conf=opt.conf,
+        #         )
+
+        #         if vae := self.generate.model_manager.config[models_to_merge[0]].get(
+        #             "vae", None
+        #         ):
+        #             print(f">> Using configured VAE assigned to {models_to_merge[0]}")
+        #             merged_model_config.update(vae=vae)
+
+        #         self.generate.model_manager.import_diffuser_model(
+        #             dump_path, **merged_model_config
+        #         )
+        #         new_model_list = self.generate.model_manager.list_models()
+
+        #         socketio.emit(
+        #             "modelsMerged",
+        #             {
+        #                 "merged_models": models_to_merge,
+        #                 "merged_model_name": model_merge_info["merged_model_name"],
+        #                 "model_list": new_model_list,
+        #                 "update": True,
+        #             },
+        #         )
+        #         print(f">> Models Merged: {models_to_merge}")
+        #         print(f">> New Model Added: {model_merge_info['merged_model_name']}")
+        #     except Exception as e:

invokeai/app/api/routers/sessions.py

@@ -0,0 +1,286 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Annotated, List, Optional, Union
+
+from fastapi import Body, HTTPException, Path, Query, Response
+from fastapi.routing import APIRouter
+from pydantic.fields import Field
+
+from ...invocations import *
+from ...invocations.baseinvocation import BaseInvocation
+from ...services.graph import (
+    Edge,
+    EdgeConnection,
+    Graph,
+    GraphExecutionState,
+    NodeAlreadyExecutedError,
+)
+from ...services.item_storage import PaginatedResults
+from ..dependencies import ApiDependencies
+
+session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
+
+
+@session_router.post(
+    "/",
+    operation_id="create_session",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid json"},
+    },
+)
+async def create_session(
+    graph: Optional[Graph] = Body(
+        default=None, description="The graph to initialize the session with"
+    )
+) -> GraphExecutionState:
+    """Creates a new session, optionally initializing it with an invocation graph"""
+    session = ApiDependencies.invoker.create_execution_state(graph)
+    return session
+
+
+@session_router.get(
+    "/",
+    operation_id="list_sessions",
+    responses={200: {"model": PaginatedResults[GraphExecutionState]}},
+)
+async def list_sessions(
+    page: int = Query(default=0, description="The page of results to get"),
+    per_page: int = Query(default=10, description="The number of results per page"),
+    query: str = Query(default="", description="The query string to search for"),
+) -> PaginatedResults[GraphExecutionState]:
+    """Gets a list of sessions, optionally searching"""
+    if query == "":
+        result = ApiDependencies.invoker.services.graph_execution_manager.list(
+            page, per_page
+        )
+    else:
+        result = ApiDependencies.invoker.services.graph_execution_manager.search(
+            query, page, per_page
+        )
+    return result
+
+
+@session_router.get(
+    "/{session_id}",
+    operation_id="get_session",
+    responses={
+        200: {"model": GraphExecutionState},
+        404: {"description": "Session not found"},
+    },
+)
+async def get_session(
+    session_id: str = Path(description="The id of the session to get"),
+) -> GraphExecutionState:
+    """Gets a session"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+    else:
+        return session
+
+
+@session_router.post(
+    "/{session_id}/nodes",
+    operation_id="add_node",
+    responses={
+        200: {"model": str},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def add_node(
+    session_id: str = Path(description="The id of the session"),
+    node: Annotated[
+        Union[BaseInvocation.get_invocations()], Field(discriminator="type") # type: ignore
+    ] = Body(description="The node to add"),
+) -> str:
+    """Adds a node to the graph"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        session.add_node(node)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session.id
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+@session_router.put(
+    "/{session_id}/nodes/{node_path}",
+    operation_id="update_node",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def update_node(
+    session_id: str = Path(description="The id of the session"),
+    node_path: str = Path(description="The path to the node in the graph"),
+    node: Annotated[
+        Union[BaseInvocation.get_invocations()], Field(discriminator="type") # type: ignore
+    ] = Body(description="The new node"),
+) -> GraphExecutionState:
+    """Updates a node in the graph and removes all linked edges"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        session.update_node(node_path, node)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+@session_router.delete(
+    "/{session_id}/nodes/{node_path}",
+    operation_id="delete_node",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def delete_node(
+    session_id: str = Path(description="The id of the session"),
+    node_path: str = Path(description="The path to the node to delete"),
+) -> GraphExecutionState:
+    """Deletes a node in the graph and removes all linked edges"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        session.delete_node(node_path)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+@session_router.post(
+    "/{session_id}/edges",
+    operation_id="add_edge",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def add_edge(
+    session_id: str = Path(description="The id of the session"),
+    edge: Edge = Body(description="The edge to add"),
+) -> GraphExecutionState:
+    """Adds an edge to the graph"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        session.add_edge(edge)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+# TODO: the edge being in the path here is really ugly, find a better solution
+@session_router.delete(
+    "/{session_id}/edges/{from_node_id}/{from_field}/{to_node_id}/{to_field}",
+    operation_id="delete_edge",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def delete_edge(
+    session_id: str = Path(description="The id of the session"),
+    from_node_id: str = Path(description="The id of the node the edge is coming from"),
+    from_field: str = Path(description="The field of the node the edge is coming from"),
+    to_node_id: str = Path(description="The id of the node the edge is going to"),
+    to_field: str = Path(description="The field of the node the edge is going to"),
+) -> GraphExecutionState:
+    """Deletes an edge from the graph"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        edge = Edge(
+            source=EdgeConnection(node_id=from_node_id, field=from_field),
+            destination=EdgeConnection(node_id=to_node_id, field=to_field)
+        )
+        session.delete_edge(edge)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+@session_router.put(
+    "/{session_id}/invoke",
+    operation_id="invoke_session",
+    responses={
+        200: {"model": None},
+        202: {"description": "The invocation is queued"},
+        400: {"description": "The session has no invocations ready to invoke"},
+        404: {"description": "Session not found"},
+    },
+)
+async def invoke_session(
+    session_id: str = Path(description="The id of the session to invoke"),
+    all: bool = Query(
+        default=False, description="Whether or not to invoke all remaining invocations"
+    ),
+) -> Response:
+    """Invokes a session"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    if session.is_complete():
+        raise HTTPException(status_code=400)
+
+    ApiDependencies.invoker.invoke(session, invoke_all=all)
+    return Response(status_code=202)
+
+
+@session_router.delete(
+    "/{session_id}/invoke",
+    operation_id="cancel_session_invoke",
+    responses={
+        202: {"description": "The invocation is canceled"}
+    },
+)
+async def cancel_session_invoke(
+    session_id: str = Path(description="The id of the session to cancel"),
+) -> Response:
+    """Invokes a session"""
+    ApiDependencies.invoker.cancel(session_id)
+    return Response(status_code=202)

invokeai/app/api/sockets.py

@@ -0,0 +1,38 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from fastapi import FastAPI
+from fastapi_events.handlers.local import local_handler
+from fastapi_events.typing import Event
+from fastapi_socketio import SocketManager
+
+from ..services.events import EventServiceBase
+
+
+class SocketIO:
+    __sio: SocketManager
+
+    def __init__(self, app: FastAPI):
+        self.__sio = SocketManager(app=app)
+        self.__sio.on("subscribe", handler=self._handle_sub)
+        self.__sio.on("unsubscribe", handler=self._handle_unsub)
+
+        local_handler.register(
+            event_name=EventServiceBase.session_event, _func=self._handle_session_event
+        )
+
+    async def _handle_session_event(self, event: Event):
+        await self.__sio.emit(
+            event=event[1]["event"],
+            data=event[1]["data"],
+            room=event[1]["data"]["graph_execution_state_id"],
+        )
+
+    async def _handle_sub(self, sid, data, *args, **kwargs):
+        if "session" in data:
+            self.__sio.enter_room(sid, data["session"])
+
+        # @app.sio.on('unsubscribe')
+
+    async def _handle_unsub(self, sid, data, *args, **kwargs):
+        if "session" in data:
+            self.__sio.leave_room(sid, data["session"])

invokeai/app/api_app.py

@@ -0,0 +1,162 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+import asyncio
+from inspect import signature
+
+import uvicorn
+
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
+from fastapi.openapi.utils import get_openapi
+from fastapi.staticfiles import StaticFiles
+from fastapi_events.handlers.local import local_handler
+from fastapi_events.middleware import EventHandlerASGIMiddleware
+from pathlib import Path
+from pydantic.schema import schema
+
+#This should come early so that modules can log their initialization properly
+from .services.config import InvokeAIAppConfig
+from ..backend.util.logging import InvokeAILogger
+app_config = InvokeAIAppConfig.get_config()
+app_config.parse_args()
+logger = InvokeAILogger.getLogger(config=app_config)
+
+import invokeai.frontend.web as web_dir
+
+from .api.dependencies import ApiDependencies
+from .api.routers import sessions, models, images
+from .api.sockets import SocketIO
+from .invocations.baseinvocation import BaseInvocation
+
+# Create the app
+# TODO: create this all in a method so configuration/etc. can be passed in?
+app = FastAPI(title="Invoke AI", docs_url=None, redoc_url=None)
+
+# Add event handler
+event_handler_id: int = id(app)
+app.add_middleware(
+    EventHandlerASGIMiddleware,
+    handlers=[
+        local_handler
+    ],  # TODO: consider doing this in services to support different configurations
+    middleware_id=event_handler_id,
+)
+
+socket_io = SocketIO(app)
+
+# Add startup event to load dependencies
+@app.on_event("startup")
+async def startup_event():
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=app_config.allow_origins,
+        allow_credentials=app_config.allow_credentials,
+        allow_methods=app_config.allow_methods,
+        allow_headers=app_config.allow_headers,
+    )
+
+    ApiDependencies.initialize(
+        config=app_config, event_handler_id=event_handler_id, logger=logger
+    )
+
+
+# Shut down threads
+@app.on_event("shutdown")
+async def shutdown_event():
+    ApiDependencies.shutdown()
+
+
+# Include all routers
+# TODO: REMOVE
+# app.include_router(
+#     invocation.invocation_router,
+#     prefix = '/api')
+
+app.include_router(sessions.session_router, prefix="/api")
+
+app.include_router(models.models_router, prefix="/api")
+
+app.include_router(images.images_router, prefix="/api")
+
+# Build a custom OpenAPI to include all outputs
+# TODO: can outputs be included on metadata of invocation schemas somehow?
+def custom_openapi():
+    if app.openapi_schema:
+        return app.openapi_schema
+    openapi_schema = get_openapi(
+        title=app.title,
+        description="An API for invoking AI image operations",
+        version="1.0.0",
+        routes=app.routes,
+    )
+
+    # Add all outputs
+    all_invocations = BaseInvocation.get_invocations()
+    output_types = set()
+    output_type_titles = dict()
+    for invoker in all_invocations:
+        output_type = signature(invoker.invoke).return_annotation
+        output_types.add(output_type)
+
+    output_schemas = schema(output_types, ref_prefix="#/components/schemas/")
+    for schema_key, output_schema in output_schemas["definitions"].items():
+        openapi_schema["components"]["schemas"][schema_key] = output_schema
+
+        # TODO: note that we assume the schema_key here is the TYPE.__name__
+        # This could break in some cases, figure out a better way to do it
+        output_type_titles[schema_key] = output_schema["title"]
+
+    # Add a reference to the output type to additionalProperties of the invoker schema
+    for invoker in all_invocations:
+        invoker_name = invoker.__name__
+        output_type = signature(invoker.invoke).return_annotation
+        output_type_title = output_type_titles[output_type.__name__]
+        invoker_schema = openapi_schema["components"]["schemas"][invoker_name]
+        outputs_ref = {"$ref": f"#/components/schemas/{output_type_title}"}
+
+        invoker_schema["output"] = outputs_ref
+
+    app.openapi_schema = openapi_schema
+    return app.openapi_schema
+
+
+app.openapi = custom_openapi
+
+# Override API doc favicons
+app.mount("/static", StaticFiles(directory=Path(web_dir.__path__[0], 'static/dream_web')), name="static")
+
+@app.get("/docs", include_in_schema=False)
+def overridden_swagger():
+    return get_swagger_ui_html(
+        openapi_url=app.openapi_url,
+        title=app.title,
+        swagger_favicon_url="/static/favicon.ico",
+    )
+
+
+@app.get("/redoc", include_in_schema=False)
+def overridden_redoc():
+    return get_redoc_html(
+        openapi_url=app.openapi_url,
+        title=app.title,
+        redoc_favicon_url="/static/favicon.ico",
+    )
+
+
+# Must mount *after* the other routes else it borks em
+app.mount("/", 
+          StaticFiles(directory=Path(web_dir.__path__[0],"dist"), 
+                      html=True
+                     ), name="ui"
+         )
+
+def invoke_api():
+    # Start our own event loop for eventing usage
+    loop = asyncio.new_event_loop()
+    config = uvicorn.Config(app=app, host=app_config.host, port=app_config.port, loop=loop)
+    # Use access_log to turn off logging
+    server = uvicorn.Server(config)
+    loop.run_until_complete(server.serve())
+
+if __name__ == "__main__":
+    invoke_api()

invokeai/app/cli/commands.py

@@ -0,0 +1,303 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from abc import ABC, abstractmethod
+import argparse
+from typing import Any, Callable, Iterable, Literal, Union, get_args, get_origin, get_type_hints
+from pydantic import BaseModel, Field
+import networkx as nx
+import matplotlib.pyplot as plt
+
+import invokeai.backend.util.logging as logger
+from ..invocations.baseinvocation import BaseInvocation
+from ..invocations.image import ImageField
+from ..services.graph import GraphExecutionState, LibraryGraph, Edge
+from ..services.invoker import Invoker
+
+
+def add_field_argument(command_parser, name: str, field, default_override = None):
+    default = default_override if default_override is not None else field.default if field.default_factory is None else field.default_factory()
+    if get_origin(field.type_) == Literal:
+        allowed_values = get_args(field.type_)
+        allowed_types = set()
+        for val in allowed_values:
+            allowed_types.add(type(val))
+        allowed_types_list = list(allowed_types)
+        field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
+
+        command_parser.add_argument(
+            f"--{name}",
+            dest=name,
+            type=field_type,
+            default=default,
+            choices=allowed_values,
+            help=field.field_info.description,
+        )
+    else:
+        command_parser.add_argument(
+            f"--{name}",
+            dest=name,
+            type=field.type_,
+            default=default,
+            help=field.field_info.description,
+        )
+
+
+def add_parsers(
+    subparsers,
+    commands: list[type],
+    command_field: str = "type",
+    exclude_fields: list[str] = ["id", "type"],
+    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+    ):
+    """Adds parsers for each command to the subparsers"""
+
+    # Create subparsers for each command
+    for command in commands:
+        hints = get_type_hints(command)
+        cmd_name = get_args(hints[command_field])[0]
+        command_parser = subparsers.add_parser(cmd_name, help=command.__doc__)
+
+        if add_arguments is not None:
+            add_arguments(command_parser)
+
+        # Convert all fields to arguments
+        fields = command.__fields__ # type: ignore
+        for name, field in fields.items():
+            if name in exclude_fields:
+                continue
+
+            add_field_argument(command_parser, name, field)
+
+
+def add_graph_parsers(
+    subparsers,
+    graphs: list[LibraryGraph],
+    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+):
+    for graph in graphs:
+        command_parser = subparsers.add_parser(graph.name, help=graph.description)
+        
+        if add_arguments is not None:
+            add_arguments(command_parser)
+
+        # Add arguments for inputs
+        for exposed_input in graph.exposed_inputs:
+            node = graph.graph.get_node(exposed_input.node_path)
+            field = node.__fields__[exposed_input.field]
+            default_override = getattr(node, exposed_input.field)
+            add_field_argument(command_parser, exposed_input.alias, field, default_override)
+
+
+class CliContext:
+    invoker: Invoker
+    session: GraphExecutionState
+    parser: argparse.ArgumentParser
+    defaults: dict[str, Any]
+    graph_nodes: dict[str, str]
+    nodes_added: list[str]
+
+    def __init__(self, invoker: Invoker, session: GraphExecutionState, parser: argparse.ArgumentParser):
+        self.invoker = invoker
+        self.session = session
+        self.parser = parser
+        self.defaults = dict()
+        self.graph_nodes = dict()
+        self.nodes_added = list()
+
+    def get_session(self):
+        self.session = self.invoker.services.graph_execution_manager.get(self.session.id)
+        return self.session
+
+    def reset(self):
+        self.session = self.invoker.create_execution_state()
+        self.graph_nodes = dict()
+        self.nodes_added = list()
+        # Leave defaults unchanged
+
+    def add_node(self, node: BaseInvocation):
+        self.get_session()
+        self.session.graph.add_node(node)
+        self.nodes_added.append(node.id)
+        self.invoker.services.graph_execution_manager.set(self.session)
+
+    def add_edge(self, edge: Edge):
+        self.get_session()
+        self.session.add_edge(edge)
+        self.invoker.services.graph_execution_manager.set(self.session)
+
+
+class ExitCli(Exception):
+    """Exception to exit the CLI"""
+    pass
+
+
+class BaseCommand(ABC, BaseModel):
+    """A CLI command"""
+
+    # All commands must include a type name like this:
+    # type: Literal['your_command_name'] = 'your_command_name'
+
+    @classmethod
+    def get_all_subclasses(cls):
+        subclasses = []
+        toprocess = [cls]
+        while len(toprocess) > 0:
+            next = toprocess.pop(0)
+            next_subclasses = next.__subclasses__()
+            subclasses.extend(next_subclasses)
+            toprocess.extend(next_subclasses)
+        return subclasses
+
+    @classmethod
+    def get_commands(cls):
+        return tuple(BaseCommand.get_all_subclasses())
+
+    @classmethod
+    def get_commands_map(cls):
+        # Get the type strings out of the literals and into a dictionary
+        return dict(map(lambda t: (get_args(get_type_hints(t)['type'])[0], t),BaseCommand.get_all_subclasses()))
+
+    @abstractmethod
+    def run(self, context: CliContext) -> None:
+        """Run the command. Raise ExitCli to exit."""
+        pass
+
+
+class ExitCommand(BaseCommand):
+    """Exits the CLI"""
+    type: Literal['exit'] = 'exit'
+
+    def run(self, context: CliContext) -> None:
+        raise ExitCli()
+
+
+class HelpCommand(BaseCommand):
+    """Shows help"""
+    type: Literal['help'] = 'help'
+
+    def run(self, context: CliContext) -> None:
+        context.parser.print_help()
+
+
+def get_graph_execution_history(
+    graph_execution_state: GraphExecutionState,
+) -> Iterable[str]:
+    """Gets the history of fully-executed invocations for a graph execution"""
+    return (
+        n
+        for n in reversed(graph_execution_state.executed_history)
+        if n in graph_execution_state.graph.nodes
+    )
+
+
+def get_invocation_command(invocation) -> str:
+    fields = invocation.__fields__.items()
+    type_hints = get_type_hints(type(invocation))
+    command = [invocation.type]
+    for name, field in fields:
+        if name in ["id", "type"]:
+            continue
+
+        # TODO: add links
+
+        # Skip image fields when serializing command
+        type_hint = type_hints.get(name) or None
+        if type_hint is ImageField or ImageField in get_args(type_hint):
+            continue
+
+        field_value = getattr(invocation, name)
+        field_default = field.default
+        if field_value != field_default:
+            if type_hint is str or str in get_args(type_hint):
+                command.append(f'--{name} "{field_value}"')
+            else:
+                command.append(f"--{name} {field_value}")
+
+    return " ".join(command)
+
+
+class HistoryCommand(BaseCommand):
+    """Shows the invocation history"""
+    type: Literal['history'] = 'history'
+
+    # Inputs
+    # fmt: off
+    count: int = Field(default=5, gt=0, description="The number of history entries to show")
+    # fmt: on
+
+    def run(self, context: CliContext) -> None:
+        history = list(get_graph_execution_history(context.get_session()))
+        for i in range(min(self.count, len(history))):
+            entry_id = history[-1 - i]
+            entry = context.get_session().graph.get_node(entry_id)
+            logger.info(f"{entry_id}: {get_invocation_command(entry)}")
+
+
+class SetDefaultCommand(BaseCommand):
+    """Sets a default value for a field"""
+    type: Literal['default'] = 'default'
+
+    # Inputs
+    # fmt: off
+    field: str = Field(description="The field to set the default for")
+    value: str = Field(description="The value to set the default to, or None to clear the default")
+    # fmt: on
+
+    def run(self, context: CliContext) -> None:
+        if self.value is None:
+            if self.field in context.defaults:
+                del context.defaults[self.field]
+        else:
+            context.defaults[self.field] = self.value
+
+
+class DrawGraphCommand(BaseCommand):
+    """Debugs a graph"""
+    type: Literal['draw_graph'] = 'draw_graph'
+
+    def run(self, context: CliContext) -> None:
+        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
+        nxgraph = session.graph.nx_graph_flat()
+
+        # Draw the networkx graph
+        plt.figure(figsize=(20, 20))
+        pos = nx.spectral_layout(nxgraph)
+        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
+        nx.draw_networkx_edges(nxgraph, pos, width=2)
+        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
+        plt.axis("off")
+        plt.show()
+
+
+class DrawExecutionGraphCommand(BaseCommand):
+    """Debugs an execution graph"""
+    type: Literal['draw_xgraph'] = 'draw_xgraph'
+
+    def run(self, context: CliContext) -> None:
+        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
+        nxgraph = session.execution_graph.nx_graph_flat()
+
+        # Draw the networkx graph
+        plt.figure(figsize=(20, 20))
+        pos = nx.spectral_layout(nxgraph)
+        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
+        nx.draw_networkx_edges(nxgraph, pos, width=2)
+        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
+        plt.axis("off")
+        plt.show()
+
+class SortedHelpFormatter(argparse.HelpFormatter):
+    def _iter_indented_subactions(self, action):
+        try:
+            get_subactions = action._get_subactions
+        except AttributeError:
+            pass
+        else:
+            self._indent()
+            if isinstance(action, argparse._SubParsersAction):
+                for subaction in sorted(get_subactions(), key=lambda x: x.dest):
+                    yield subaction
+            else:
+                for subaction in get_subactions():
+                    yield subaction
+                self._dedent()

invokeai/app/cli/completer.py

@@ -0,0 +1,169 @@
+"""
+Readline helper functions for cli_app.py
+You may import the global singleton `completer` to get access to the
+completer object.
+"""
+import atexit
+import readline
+import shlex
+
+from pathlib import Path
+from typing import List, Dict, Literal, get_args, get_type_hints, get_origin
+
+import invokeai.backend.util.logging as logger
+from ...backend import ModelManager
+from ..invocations.baseinvocation import BaseInvocation
+from .commands import BaseCommand
+from ..services.invocation_services import InvocationServices
+
+# singleton object, class variable
+completer = None
+
+class Completer(object):
+    
+    def __init__(self, model_manager: ModelManager):
+        self.commands = self.get_commands()
+        self.matches = None
+        self.linebuffer = None
+        self.manager = model_manager
+        return
+
+    def complete(self, text, state):
+        """
+        Complete commands and switches fromm the node CLI command line.
+        Switches are determined in a context-specific manner.
+        """
+
+        buffer = readline.get_line_buffer()
+        if state == 0:
+            options = None
+            try:
+                current_command, current_switch = self.get_current_command(buffer)
+                options = self.get_command_options(current_command, current_switch)
+            except IndexError:
+                pass
+            options = options or list(self.parse_commands().keys())
+            
+            if not text:  # first time
+                self.matches = options
+            else:
+                self.matches = [s for s in options if s and s.startswith(text)]
+
+        try:
+            match = self.matches[state]
+        except IndexError:
+            match = None
+        return match
+
+    @classmethod
+    def get_commands(self)->List[object]:
+        """
+        Return a list of all the client commands and invocations.
+        """
+        return BaseCommand.get_commands() + BaseInvocation.get_invocations()
+
+    def get_current_command(self, buffer: str)->tuple[str, str]:
+        """
+        Parse the readline buffer to find the most recent command and its switch.
+        """
+        if len(buffer)==0:
+            return None, None
+        tokens = shlex.split(buffer)
+        command = None
+        switch = None
+        for t in tokens:
+            if t[0].isalpha():
+                if switch is None:
+                    command = t
+            else:
+                switch = t
+        # don't try to autocomplete switches that are already complete
+        if switch and buffer.endswith(' '):
+            switch=None
+        return command or '', switch or ''
+
+    def parse_commands(self)->Dict[str, List[str]]:
+        """
+        Return a dict in which the keys are the command name
+        and the values are the parameters the command takes.
+        """
+        result = dict()
+        for command in self.commands:
+            hints = get_type_hints(command)
+            name = get_args(hints['type'])[0]
+            result.update({name:hints})
+        return result
+
+    def get_command_options(self, command: str, switch: str)->List[str]:
+        """
+        Return all the parameters that can be passed to the command as
+        command-line switches. Returns None if the command is unrecognized.
+        """
+        parsed_commands = self.parse_commands()
+        if command not in parsed_commands:
+            return None
+        
+        # handle switches in the format "-foo=bar"
+        argument = None
+        if switch and '=' in switch:
+            switch, argument = switch.split('=')
+            
+        parameter = switch.strip('-')
+        if parameter in parsed_commands[command]:
+            if argument is None:
+                return self.get_parameter_options(parameter, parsed_commands[command][parameter])
+            else:
+                return [f"--{parameter}={x}" for x in self.get_parameter_options(parameter, parsed_commands[command][parameter])]
+        else:
+            return [f"--{x}" for x in parsed_commands[command].keys()]
+
+    def get_parameter_options(self, parameter: str, typehint)->List[str]:
+        """
+        Given a parameter type (such as Literal), offers autocompletions.
+        """
+        if get_origin(typehint) == Literal:
+            return get_args(typehint)
+        if parameter == 'model':
+            return self.manager.model_names()
+        
+    def _pre_input_hook(self):
+        if self.linebuffer:
+            readline.insert_text(self.linebuffer)
+            readline.redisplay()
+            self.linebuffer = None
+    
+def set_autocompleter(services: InvocationServices) -> Completer:
+    global completer
+    
+    if completer:
+        return completer
+    
+    completer = Completer(services.model_manager)
+
+    readline.set_completer(completer.complete)
+    # pyreadline3 does not have a set_auto_history() method
+    try:
+        readline.set_auto_history(True)
+    except:
+        pass
+    readline.set_pre_input_hook(completer._pre_input_hook)
+    readline.set_completer_delims(" ")
+    readline.parse_and_bind("tab: complete")
+    readline.parse_and_bind("set print-completions-horizontally off")
+    readline.parse_and_bind("set page-completions on")
+    readline.parse_and_bind("set skip-completed-text on")
+    readline.parse_and_bind("set show-all-if-ambiguous on")
+
+    histfile = Path(services.configuration.root_dir / ".invoke_history")
+    try:
+        readline.read_history_file(histfile)
+        readline.set_history_length(1000)
+    except FileNotFoundError:
+        pass
+    except OSError:  # file likely corrupted
+        newname = f"{histfile}.old"
+        logger.error(
+            f"Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}"
+        )
+        histfile.replace(Path(newname))
+    atexit.register(readline.write_history_file, histfile)

invokeai/app/cli_app.py

@@ -0,0 +1,427 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import argparse
+import os
+import re
+import shlex
+import sys
+import time
+from typing import (
+    Union,
+    get_type_hints,
+)
+
+from pydantic import BaseModel, ValidationError
+from pydantic.fields import Field
+
+# This should come early so that the logger can pick up its configuration options
+from .services.config import InvokeAIAppConfig
+from invokeai.backend.util.logging import InvokeAILogger
+config = InvokeAIAppConfig.get_config()
+config.parse_args()
+logger = InvokeAILogger().getLogger(config=config)
+
+from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
+from invokeai.app.services.images import ImageService
+from invokeai.app.services.metadata import CoreMetadataService
+from invokeai.app.services.resource_name import SimpleNameService
+from invokeai.app.services.urls import LocalUrlService
+
+from .services.default_graphs import create_system_graphs
+from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
+
+from .cli.commands import BaseCommand, CliContext, ExitCli, add_graph_parsers, add_parsers, SortedHelpFormatter
+from .cli.completer import set_autocompleter
+from .invocations.baseinvocation import BaseInvocation
+from .services.events import EventServiceBase
+from .services.model_manager_initializer import get_model_manager
+from .services.restoration_services import RestorationServices
+from .services.graph import Edge, EdgeConnection, GraphExecutionState, GraphInvocation, LibraryGraph, are_connection_types_compatible
+from .services.default_graphs import default_text_to_image_graph_id
+from .services.image_file_storage import DiskImageFileStorage
+from .services.invocation_queue import MemoryInvocationQueue
+from .services.invocation_services import InvocationServices
+from .services.invoker import Invoker
+from .services.processor import DefaultInvocationProcessor
+from .services.sqlite import SqliteItemStorage
+
+
+class CliCommand(BaseModel):
+    command: Union[BaseCommand.get_commands() + BaseInvocation.get_invocations()] = Field(discriminator="type")  # type: ignore
+
+
+class InvalidArgs(Exception):
+    pass
+
+def add_invocation_args(command_parser):
+    # Add linking capability
+    command_parser.add_argument(
+        "--link",
+        "-l",
+        action="append",
+        nargs=3,
+        help="A link in the format 'source_node source_field dest_field'. source_node can be relative to history (e.g. -1)",
+    )
+
+    command_parser.add_argument(
+        "--link_node",
+        "-ln",
+        action="append",
+        help="A link from all fields in the specified node. Node can be relative to history (e.g. -1)",
+    )
+
+
+def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
+    # Create invocation parser
+    parser = argparse.ArgumentParser(formatter_class=SortedHelpFormatter)
+
+    def exit(*args, **kwargs):
+        raise InvalidArgs
+
+    parser.exit = exit
+    subparsers = parser.add_subparsers(dest="type")
+
+    # Create subparsers for each invocation
+    invocations = BaseInvocation.get_all_subclasses()
+    add_parsers(subparsers, invocations, add_arguments=add_invocation_args)
+
+    # Create subparsers for each command
+    commands = BaseCommand.get_all_subclasses()
+    add_parsers(subparsers, commands, exclude_fields=["type"])
+
+    # Create subparsers for exposed CLI graphs
+    # TODO: add a way to identify these graphs
+    text_to_image = services.graph_library.get(default_text_to_image_graph_id)
+    add_graph_parsers(subparsers, [text_to_image], add_arguments=add_invocation_args)
+
+    return parser
+
+
+class NodeField():
+    alias: str
+    node_path: str
+    field: str
+    field_type: type
+
+    def __init__(self, alias: str, node_path: str, field: str, field_type: type):
+        self.alias = alias
+        self.node_path = node_path
+        self.field = field
+        self.field_type = field_type
+
+
+def fields_from_type_hints(hints: dict[str, type], node_path: str) -> dict[str,NodeField]:
+    return {k:NodeField(alias=k, node_path=node_path, field=k, field_type=v) for k, v in hints.items()}
+
+
+def get_node_input_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
+    """Gets the node field for the specified field alias"""
+    exposed_input = next(e for e in graph.exposed_inputs if e.alias == field_alias)
+    node_type = type(graph.graph.get_node(exposed_input.node_path))
+    return NodeField(alias=exposed_input.alias, node_path=f'{node_id}.{exposed_input.node_path}', field=exposed_input.field, field_type=get_type_hints(node_type)[exposed_input.field])
+
+
+def get_node_output_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
+    """Gets the node field for the specified field alias"""
+    exposed_output = next(e for e in graph.exposed_outputs if e.alias == field_alias)
+    node_type = type(graph.graph.get_node(exposed_output.node_path))
+    node_output_type = node_type.get_output_type()
+    return NodeField(alias=exposed_output.alias, node_path=f'{node_id}.{exposed_output.node_path}', field=exposed_output.field, field_type=get_type_hints(node_output_type)[exposed_output.field])
+
+
+def get_node_inputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
+    """Gets the inputs for the specified invocation from the context"""
+    node_type = type(invocation)
+    if node_type is not GraphInvocation:
+        return fields_from_type_hints(get_type_hints(node_type), invocation.id)
+    else:
+        graph: LibraryGraph = context.invoker.services.graph_library.get(context.graph_nodes[invocation.id])
+        return {e.alias: get_node_input_field(graph, e.alias, invocation.id) for e in graph.exposed_inputs}
+
+
+def get_node_outputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
+    """Gets the outputs for the specified invocation from the context"""
+    node_type = type(invocation)
+    if node_type is not GraphInvocation:
+        return fields_from_type_hints(get_type_hints(node_type.get_output_type()), invocation.id)
+    else:
+        graph: LibraryGraph = context.invoker.services.graph_library.get(context.graph_nodes[invocation.id])
+        return {e.alias: get_node_output_field(graph, e.alias, invocation.id) for e in graph.exposed_outputs}
+
+
+def generate_matching_edges(
+    a: BaseInvocation, b: BaseInvocation, context: CliContext
+) -> list[Edge]:
+    """Generates all possible edges between two invocations"""
+    afields = get_node_outputs(a, context)
+    bfields = get_node_inputs(b, context)
+
+    matching_fields = set(afields.keys()).intersection(bfields.keys())
+
+    # Remove invalid fields
+    invalid_fields = set(["type", "id"])
+    matching_fields = matching_fields.difference(invalid_fields)
+
+    # Validate types
+    matching_fields = [f for f in matching_fields if are_connection_types_compatible(afields[f].field_type, bfields[f].field_type)]
+
+    edges = [
+        Edge(
+            source=EdgeConnection(node_id=afields[alias].node_path, field=afields[alias].field),
+            destination=EdgeConnection(node_id=bfields[alias].node_path, field=bfields[alias].field)
+        )
+        for alias in matching_fields
+    ]
+    return edges
+
+
+class SessionError(Exception):
+    """Raised when a session error has occurred"""
+    pass
+
+
+def invoke_all(context: CliContext):
+    """Runs all invocations in the specified session"""
+    context.invoker.invoke(context.session, invoke_all=True)
+    while not context.get_session().is_complete():
+        # Wait some time
+        time.sleep(0.1)
+
+    # Print any errors
+    if context.session.has_error():
+        for n in context.session.errors:
+            context.invoker.services.logger.error(
+                f"Error in node {n} (source node {context.session.prepared_source_mapping[n]}): {context.session.errors[n]}"
+            )
+        
+        raise SessionError()
+
+def invoke_cli():
+    
+    # get the optional list of invocations to execute on the command line
+    parser = config.get_parser()
+    parser.add_argument('commands',nargs='*')
+    invocation_commands = parser.parse_args().commands
+
+    # get the optional file to read commands from.
+    # Simplest is to use it for STDIN
+    if infile := config.from_file:
+        sys.stdin = open(infile,"r")
+    
+    model_manager = get_model_manager(config,logger=logger)
+    
+    events = EventServiceBase()
+    output_folder = config.output_path
+
+    # TODO: build a file/path manager?
+    if config.use_memory_db:
+        db_location = ":memory:"
+    else:
+        db_location = config.db_path
+        db_location.parent.mkdir(parents=True,exist_ok=True)
+
+    logger.info(f'InvokeAI database location is "{db_location}"')
+
+    graph_execution_manager = SqliteItemStorage[GraphExecutionState](
+            filename=db_location, table_name="graph_executions"
+        )
+
+    urls = LocalUrlService()
+    metadata = CoreMetadataService()
+    image_record_storage = SqliteImageRecordStorage(db_location)
+    image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
+    names = SimpleNameService()
+
+    images = ImageService(
+        image_record_storage=image_record_storage,
+        image_file_storage=image_file_storage,
+        metadata=metadata,
+        url=urls,
+        logger=logger,
+        names=names,
+        graph_execution_manager=graph_execution_manager,
+    )
+
+    services = InvocationServices(
+        model_manager=model_manager,
+        events=events,
+        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
+        images=images,
+        queue=MemoryInvocationQueue(),
+        graph_library=SqliteItemStorage[LibraryGraph](
+            filename=db_location, table_name="graphs"
+        ),
+        graph_execution_manager=graph_execution_manager,
+        processor=DefaultInvocationProcessor(),
+        restoration=RestorationServices(config,logger=logger),
+        logger=logger,
+        configuration=config,
+    )
+
+    system_graphs = create_system_graphs(services.graph_library)
+    system_graph_names = set([g.name for g in system_graphs])
+
+    invoker = Invoker(services)
+    session: GraphExecutionState = invoker.create_execution_state()
+    parser = get_command_parser(services)
+
+    re_negid = re.compile('^-[0-9]+$')
+
+    # Uncomment to print out previous sessions at startup
+    # print(services.session_manager.list())
+
+    context = CliContext(invoker, session, parser)
+    set_autocompleter(services)
+
+    command_line_args_exist = len(invocation_commands) > 0
+    done = False
+    
+    while not done:
+        try:
+            if command_line_args_exist:
+                cmd_input = invocation_commands.pop(0)
+                done = len(invocation_commands) == 0
+            else:
+                cmd_input = input("invoke> ")
+        except (KeyboardInterrupt, EOFError):
+            # Ctrl-c exits
+            break
+
+        try:
+            # Refresh the state of the session
+            #history = list(get_graph_execution_history(context.session))
+            history = list(reversed(context.nodes_added))
+
+            # Split the command for piping
+            cmds = cmd_input.split("|")
+            start_id = len(context.nodes_added)
+            current_id = start_id
+            new_invocations = list()
+            for cmd in cmds:
+                if cmd is None or cmd.strip() == "":
+                    raise InvalidArgs("Empty command")
+
+                # Parse args to create invocation
+                args = vars(context.parser.parse_args(shlex.split(cmd.strip())))
+
+                # Override defaults
+                for field_name, field_default in context.defaults.items():
+                    if field_name in args:
+                        args[field_name] = field_default
+
+                # Parse invocation
+                command: CliCommand = None # type:ignore
+                system_graph: LibraryGraph|None = None
+                if args['type'] in system_graph_names:
+                    system_graph = next(filter(lambda g: g.name == args['type'], system_graphs))
+                    invocation = GraphInvocation(graph=system_graph.graph, id=str(current_id))
+                    for exposed_input in system_graph.exposed_inputs:
+                        if exposed_input.alias in args:
+                            node = invocation.graph.get_node(exposed_input.node_path)
+                            field = exposed_input.field
+                            setattr(node, field, args[exposed_input.alias])
+                    command = CliCommand(command = invocation)
+                    context.graph_nodes[invocation.id] = system_graph.id
+                else:
+                    args["id"] = current_id
+                    command = CliCommand(command=args)
+
+                if command is None:
+                    continue
+
+                # Run any CLI commands immediately
+                if isinstance(command.command, BaseCommand):
+                    # Invoke all current nodes to preserve operation order
+                    invoke_all(context)
+
+                    # Run the command
+                    command.command.run(context)
+                    continue
+
+                # TODO: handle linking with library graphs
+                # Pipe previous command output (if there was a previous command)
+                edges: list[Edge] = list()
+                if len(history) > 0 or current_id != start_id:
+                    from_id = (
+                        history[0] if current_id == start_id else str(current_id - 1)
+                    )
+                    from_node = (
+                        next(filter(lambda n: n[0].id == from_id, new_invocations))[0]
+                        if current_id != start_id
+                        else context.session.graph.get_node(from_id)
+                    )
+                    matching_edges = generate_matching_edges(
+                        from_node, command.command, context
+                    )
+                    edges.extend(matching_edges)
+
+                # Parse provided links
+                if "link_node" in args and args["link_node"]:
+                    for link in args["link_node"]:
+                        node_id = link
+                        if re_negid.match(node_id):
+                            node_id = str(current_id + int(node_id))
+
+                        link_node = context.session.graph.get_node(node_id)
+                        matching_edges = generate_matching_edges(
+                            link_node, command.command, context
+                        )
+                        matching_destinations = [e.destination for e in matching_edges]
+                        edges = [e for e in edges if e.destination not in matching_destinations]
+                        edges.extend(matching_edges)
+
+                if "link" in args and args["link"]:
+                    for link in args["link"]:
+                        edges = [e for e in edges if e.destination.node_id != command.command.id or e.destination.field != link[2]]
+
+                        node_id = link[0]
+                        if re_negid.match(node_id):
+                            node_id = str(current_id + int(node_id))
+
+                        # TODO: handle missing input/output
+                        node_output = get_node_outputs(context.session.graph.get_node(node_id), context)[link[1]]
+                        node_input = get_node_inputs(command.command, context)[link[2]]
+
+                        edges.append(
+                            Edge(
+                                source=EdgeConnection(node_id=node_output.node_path, field=node_output.field),
+                                destination=EdgeConnection(node_id=node_input.node_path, field=node_input.field)
+                            )
+                        )
+
+                new_invocations.append((command.command, edges))
+
+                current_id = current_id + 1
+
+                # Add the node to the session
+                context.add_node(command.command)
+                for edge in edges:
+                    print(edge)
+                    context.add_edge(edge)
+
+            # Execute all remaining nodes
+            invoke_all(context)
+
+        except InvalidArgs:
+            invoker.services.logger.warning('Invalid command, use "help" to list commands')
+            continue
+
+        except ValidationError:
+            invoker.services.logger.warning('Invalid command arguments, run "<command> --help" for summary')
+
+        except SessionError:
+            # Start a new session
+            invoker.services.logger.warning("Session error: creating a new session")
+            context.reset()
+
+        except ExitCli:
+            break
+
+        except SystemExit:
+            continue
+
+    invoker.stop()
+
+
+if __name__ == "__main__":
+    invoke_cli()

invokeai/app/invocations/__init__.py

@@ -0,0 +1,12 @@
+import os
+
+__all__ = []
+
+dirname = os.path.dirname(os.path.abspath(__file__))
+for f in os.listdir(dirname):
+    if (
+        f != "__init__.py"
+        and os.path.isfile("%s/%s" % (dirname, f))
+        and f[-3:] == ".py"
+    ):
+        __all__.append(f[:-3])

invokeai/app/invocations/baseinvocation.py

@@ -0,0 +1,136 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from inspect import signature
+from typing import get_args, get_type_hints, Dict, List, Literal, TypedDict, TYPE_CHECKING
+
+from pydantic import BaseModel, Field
+
+if TYPE_CHECKING:
+    from ..services.invocation_services import InvocationServices
+
+
+class InvocationContext:
+    services: InvocationServices
+    graph_execution_state_id: str
+
+    def __init__(self, services: InvocationServices, graph_execution_state_id: str):
+        self.services = services
+        self.graph_execution_state_id = graph_execution_state_id
+
+
+class BaseInvocationOutput(BaseModel):
+    """Base class for all invocation outputs"""
+
+    # All outputs must include a type name like this:
+    # type: Literal['your_output_name']
+
+    @classmethod
+    def get_all_subclasses_tuple(cls):
+        subclasses = []
+        toprocess = [cls]
+        while len(toprocess) > 0:
+            next = toprocess.pop(0)
+            next_subclasses = next.__subclasses__()
+            subclasses.extend(next_subclasses)
+            toprocess.extend(next_subclasses)
+        return tuple(subclasses)
+
+
+class BaseInvocation(ABC, BaseModel):
+    """A node to process inputs and produce outputs.
+    May use dependency injection in __init__ to receive providers.
+    """
+
+    # All invocations must include a type name like this:
+    # type: Literal['your_output_name']
+
+    @classmethod
+    def get_all_subclasses(cls):
+        subclasses = []
+        toprocess = [cls]
+        while len(toprocess) > 0:
+            next = toprocess.pop(0)
+            next_subclasses = next.__subclasses__()
+            subclasses.extend(next_subclasses)
+            toprocess.extend(next_subclasses)
+        return subclasses
+
+    @classmethod
+    def get_invocations(cls):
+        return tuple(BaseInvocation.get_all_subclasses())
+
+    @classmethod
+    def get_invocations_map(cls):
+        # Get the type strings out of the literals and into a dictionary
+        return dict(map(lambda t: (get_args(get_type_hints(t)['type'])[0], t),BaseInvocation.get_all_subclasses()))
+    
+    @classmethod
+    def get_output_type(cls):
+        return signature(cls.invoke).return_annotation
+
+    @abstractmethod
+    def invoke(self, context: InvocationContext) -> BaseInvocationOutput:
+        """Invoke with provided context and return outputs."""
+        pass
+    
+    #fmt: off
+    id: str = Field(description="The id of this node. Must be unique among all nodes.")
+    is_intermediate: bool = Field(default=False, description="Whether or not this node is an intermediate node.")
+    #fmt: on
+
+
+# TODO: figure out a better way to provide these hints
+# TODO: when we can upgrade to python 3.11, we can use the`NotRequired` type instead of `total=False`
+class UIConfig(TypedDict, total=False):
+    type_hints: Dict[
+        str,
+        Literal[
+            "integer",
+            "float",
+            "boolean",
+            "string",
+            "enum",
+            "image",
+            "latents",
+            "model",
+            "control",
+        ],
+    ]
+    tags: List[str]
+    title: str
+
+class CustomisedSchemaExtra(TypedDict):
+    ui: UIConfig
+
+
+class InvocationConfig(BaseModel.Config):
+    """Customizes pydantic's BaseModel.Config class for use by Invocations.
+
+    Provide `schema_extra` a `ui` dict to add hints for generated UIs.
+
+    `tags`
+    - A list of strings, used to categorise invocations.
+
+    `type_hints`
+    - A dict of field types which override the types in the invocation definition.
+    - Each key should be the name of one of the invocation's fields.
+    - Each value should be one of the valid types:
+      - `integer`, `float`, `boolean`, `string`, `enum`, `image`, `latents`, `model`
+
+    ```python
+    class Config(InvocationConfig):
+      schema_extra = {
+          "ui": {
+              "tags": ["stable-diffusion", "image"],
+              "type_hints": {
+                  "initial_image": "image",
+              },
+          },
+      }
+    ```
+    """
+
+    schema_extra: CustomisedSchemaExtra

invokeai/app/invocations/collections.py

@@ -0,0 +1,94 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+
+from typing import Literal
+
+import numpy as np
+from pydantic import Field, validator
+
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+
+from .baseinvocation import (
+    BaseInvocation,
+    InvocationContext,
+    BaseInvocationOutput,
+)
+
+
+class IntCollectionOutput(BaseInvocationOutput):
+    """A collection of integers"""
+
+    type: Literal["int_collection"] = "int_collection"
+
+    # Outputs
+    collection: list[int] = Field(default=[], description="The int collection")
+
+class FloatCollectionOutput(BaseInvocationOutput):
+    """A collection of floats"""
+
+    type: Literal["float_collection"] = "float_collection"
+
+    # Outputs
+    collection: list[float] = Field(default=[], description="The float collection")
+
+
+class RangeInvocation(BaseInvocation):
+    """Creates a range of numbers from start to stop with step"""
+
+    type: Literal["range"] = "range"
+
+    # Inputs
+    start: int = Field(default=0, description="The start of the range")
+    stop: int = Field(default=10, description="The stop of the range")
+    step: int = Field(default=1, description="The step of the range")
+
+    @validator("stop")
+    def stop_gt_start(cls, v, values):
+        if "start" in values and v <= values["start"]:
+            raise ValueError("stop must be greater than start")
+        return v
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        return IntCollectionOutput(
+            collection=list(range(self.start, self.stop, self.step))
+        )
+
+
+class RangeOfSizeInvocation(BaseInvocation):
+    """Creates a range from start to start + size with step"""
+
+    type: Literal["range_of_size"] = "range_of_size"
+
+    # Inputs
+    start: int = Field(default=0, description="The start of the range")
+    size: int = Field(default=1, description="The number of values")
+    step: int = Field(default=1, description="The step of the range")
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        return IntCollectionOutput(
+            collection=list(range(self.start, self.start + self.size, self.step))
+        )
+
+
+class RandomRangeInvocation(BaseInvocation):
+    """Creates a collection of random numbers"""
+
+    type: Literal["random_range"] = "random_range"
+
+    # Inputs
+    low: int = Field(default=0, description="The inclusive low value")
+    high: int = Field(
+        default=np.iinfo(np.int32).max, description="The exclusive high value"
+    )
+    size: int = Field(default=1, description="The number of values to generate")
+    seed: int = Field(
+        ge=0,
+        le=SEED_MAX,
+        description="The seed for the RNG (omit for random)",
+        default_factory=get_random_seed,
+    )
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        rng = np.random.default_rng(self.seed)
+        return IntCollectionOutput(
+            collection=list(rng.integers(low=self.low, high=self.high, size=self.size))
+        )

invokeai/app/invocations/compel.py

@@ -0,0 +1,266 @@
+from typing import Literal, Optional, Union
+from pydantic import BaseModel, Field
+
+from invokeai.app.invocations.util.choose_model import choose_model
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+from ...backend.prompting.conditioning import try_parse_legacy_blend
+
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
+from ...backend.stable_diffusion.textual_inversion_manager import TextualInversionManager
+
+from compel import Compel
+from compel.prompt_parser import (
+    Blend,
+    CrossAttentionControlSubstitute,
+    FlattenedPrompt,
+    Fragment, Conjunction,
+)
+
+
+class ConditioningField(BaseModel):
+    conditioning_name: Optional[str] = Field(default=None, description="The name of conditioning data")
+    class Config:
+        schema_extra = {"required": ["conditioning_name"]}
+
+
+class CompelOutput(BaseInvocationOutput):
+    """Compel parser output"""
+
+    #fmt: off
+    type: Literal["compel_output"] = "compel_output"
+
+    conditioning: ConditioningField = Field(default=None, description="Conditioning")
+    #fmt: on
+
+
+class CompelInvocation(BaseInvocation):
+    """Parse prompt using compel package to conditioning."""
+
+    type: Literal["compel"] = "compel"
+
+    prompt: str = Field(default="", description="Prompt")
+    model: str = Field(default="", description="Model to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Prompt (Compel)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {
+                  "model": "model"
+                }
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+
+        # TODO: load without model
+        model = choose_model(context.services.model_manager, self.model)
+        pipeline = model["model"]
+        tokenizer = pipeline.tokenizer
+        text_encoder = pipeline.text_encoder
+
+        # TODO: global? input?
+        #use_full_precision = precision == "float32" or precision == "autocast"
+        #use_full_precision = False
+
+        # TODO: redo TI when separate model loding implemented
+        #textual_inversion_manager = TextualInversionManager(
+        #    tokenizer=tokenizer,
+        #    text_encoder=text_encoder,
+        #    full_precision=use_full_precision,
+        #)
+
+        def load_huggingface_concepts(concepts: list[str]):
+            pipeline.textual_inversion_manager.load_huggingface_concepts(concepts)
+
+        # apply the concepts library to the prompt
+        prompt_str = pipeline.textual_inversion_manager.hf_concepts_library.replace_concepts_with_triggers(
+            self.prompt,
+            lambda concepts: load_huggingface_concepts(concepts),
+            pipeline.textual_inversion_manager.get_all_trigger_strings(),
+        )
+
+        # lazy-load any deferred textual inversions.
+        # this might take a couple of seconds the first time a textual inversion is used.
+        pipeline.textual_inversion_manager.create_deferred_token_ids_for_any_trigger_terms(
+            prompt_str
+        )
+
+        compel = Compel(
+            tokenizer=tokenizer,
+            text_encoder=text_encoder,
+            textual_inversion_manager=pipeline.textual_inversion_manager,
+            dtype_for_device_getter=torch_dtype,
+            truncate_long_prompts=False,
+        )
+
+        legacy_blend = try_parse_legacy_blend(prompt_str, skip_normalize=False)
+        if legacy_blend is not None:
+            conjunction = legacy_blend
+        else:
+            conjunction = Compel.parse_prompt_string(prompt_str)
+
+        if context.services.configuration.log_tokenization:
+            log_tokenization_for_conjunction(conjunction, tokenizer)
+
+        c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
+
+        ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
+            tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
+            cross_attention_control_args=options.get("cross_attention_control", None),
+        )
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+
+        # TODO: hacky but works ;D maybe rename latents somehow?
+        context.services.latents.save(conditioning_name, (c, ec))
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+
+def get_max_token_count(
+    tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction], truncate_if_too_long=False
+) -> int:
+    if type(prompt) is Blend:
+        blend: Blend = prompt
+        return max(
+            [
+                get_max_token_count(tokenizer, p, truncate_if_too_long)
+                for p in blend.prompts
+            ]
+        )
+    elif type(prompt) is Conjunction:
+        conjunction: Conjunction = prompt
+        return sum(
+            [
+                get_max_token_count(tokenizer, p, truncate_if_too_long)
+                for p in conjunction.prompts
+            ]
+        )
+    else:
+        return len(
+            get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long)
+        )
+
+
+def get_tokens_for_prompt_object(
+    tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True
+) -> [str]:
+    if type(parsed_prompt) is Blend:
+        raise ValueError(
+            "Blend is not supported here - you need to get tokens for each of its .children"
+        )
+
+    text_fragments = [
+        x.text
+        if type(x) is Fragment
+        else (
+            " ".join([f.text for f in x.original])
+            if type(x) is CrossAttentionControlSubstitute
+            else str(x)
+        )
+        for x in parsed_prompt.children
+    ]
+    text = " ".join(text_fragments)
+    tokens = tokenizer.tokenize(text)
+    if truncate_if_too_long:
+        max_tokens_length = tokenizer.model_max_length - 2  # typically 75
+        tokens = tokens[0:max_tokens_length]
+    return tokens
+
+
+def log_tokenization_for_conjunction(
+    c: Conjunction, tokenizer, display_label_prefix=None
+):
+    display_label_prefix = display_label_prefix or ""
+    for i, p in enumerate(c.prompts):
+        if len(c.prompts)>1:
+            this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
+        else:
+            this_display_label_prefix = display_label_prefix
+        log_tokenization_for_prompt_object(
+            p,
+            tokenizer,
+            display_label_prefix=this_display_label_prefix
+        )
+
+
+def log_tokenization_for_prompt_object(
+    p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None
+):
+    display_label_prefix = display_label_prefix or ""
+    if type(p) is Blend:
+        blend: Blend = p
+        for i, c in enumerate(blend.prompts):
+            log_tokenization_for_prompt_object(
+                c,
+                tokenizer,
+                display_label_prefix=f"{display_label_prefix}(blend part {i + 1}, weight={blend.weights[i]})",
+            )
+    elif type(p) is FlattenedPrompt:
+        flattened_prompt: FlattenedPrompt = p
+        if flattened_prompt.wants_cross_attention_control:
+            original_fragments = []
+            edited_fragments = []
+            for f in flattened_prompt.children:
+                if type(f) is CrossAttentionControlSubstitute:
+                    original_fragments += f.original
+                    edited_fragments += f.edited
+                else:
+                    original_fragments.append(f)
+                    edited_fragments.append(f)
+
+            original_text = " ".join([x.text for x in original_fragments])
+            log_tokenization_for_text(
+                original_text,
+                tokenizer,
+                display_label=f"{display_label_prefix}(.swap originals)",
+            )
+            edited_text = " ".join([x.text for x in edited_fragments])
+            log_tokenization_for_text(
+                edited_text,
+                tokenizer,
+                display_label=f"{display_label_prefix}(.swap replacements)",
+            )
+        else:
+            text = " ".join([x.text for x in flattened_prompt.children])
+            log_tokenization_for_text(
+                text, tokenizer, display_label=display_label_prefix
+            )
+
+
+def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
+    """shows how the prompt is tokenized
+    # usually tokens have '</w>' to indicate end-of-word,
+    # but for readability it has been replaced with ' '
+    """
+    tokens = tokenizer.tokenize(text)
+    tokenized = ""
+    discarded = ""
+    usedTokens = 0
+    totalTokens = len(tokens)
+
+    for i in range(0, totalTokens):
+        token = tokens[i].replace("</w>", " ")
+        # alternate color
+        s = (usedTokens % 6) + 1
+        if truncate_if_too_long and i >= tokenizer.model_max_length:
+            discarded = discarded + f"\x1b[0;3{s};40m{token}"
+        else:
+            tokenized = tokenized + f"\x1b[0;3{s};40m{token}"
+            usedTokens += 1
+
+    if usedTokens > 0:
+        print(f'\n>> [TOKENLOG] Tokens {display_label or ""} ({usedTokens}):')
+        print(f"{tokenized}\x1b[0m")
+
+    if discarded != "":
+        print(f"\n>> [TOKENLOG] Tokens Discarded ({totalTokens - usedTokens}):")
+        print(f"{discarded}\x1b[0m")

invokeai/app/invocations/controlnet_image_processors.py

@@ -0,0 +1,459 @@
+# InvokeAI nodes for ControlNet image preprocessors
+# initial implementation by Gregg Helt, 2023
+# heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
+from builtins import float
+
+import numpy as np
+from typing import Literal, Optional, Union, List
+from PIL import Image, ImageFilter, ImageOps
+from pydantic import BaseModel, Field, validator
+
+from ..models.image import ImageField, ImageCategory, ResourceOrigin
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
+
+from controlnet_aux import (
+    CannyDetector,
+    HEDdetector,
+    LineartDetector,
+    LineartAnimeDetector,
+    MidasDetector,
+    MLSDdetector,
+    NormalBaeDetector,
+    OpenposeDetector,
+    PidiNetDetector,
+    ContentShuffleDetector,
+    ZoeDetector,
+    MediapipeFaceDetector,
+)
+
+from .image import ImageOutput, PILInvocationConfig
+
+CONTROLNET_DEFAULT_MODELS = [
+    ###########################################
+    # lllyasviel sd v1.5, ControlNet v1.0 models
+    ##############################################
+    "lllyasviel/sd-controlnet-canny",
+    "lllyasviel/sd-controlnet-depth",
+    "lllyasviel/sd-controlnet-hed",
+    "lllyasviel/sd-controlnet-seg",
+    "lllyasviel/sd-controlnet-openpose",
+    "lllyasviel/sd-controlnet-scribble",
+    "lllyasviel/sd-controlnet-normal",
+    "lllyasviel/sd-controlnet-mlsd",
+
+    #############################################
+    # lllyasviel sd v1.5, ControlNet v1.1 models
+    #############################################
+    "lllyasviel/control_v11p_sd15_canny",
+    "lllyasviel/control_v11p_sd15_openpose",
+    "lllyasviel/control_v11p_sd15_seg",
+    # "lllyasviel/control_v11p_sd15_depth",  # broken
+    "lllyasviel/control_v11f1p_sd15_depth",
+    "lllyasviel/control_v11p_sd15_normalbae",
+    "lllyasviel/control_v11p_sd15_scribble",
+    "lllyasviel/control_v11p_sd15_mlsd",
+    "lllyasviel/control_v11p_sd15_softedge",
+    "lllyasviel/control_v11p_sd15s2_lineart_anime",
+    "lllyasviel/control_v11p_sd15_lineart",
+    "lllyasviel/control_v11p_sd15_inpaint",
+    # "lllyasviel/control_v11u_sd15_tile",
+    # problem (temporary?) with huffingface "lllyasviel/control_v11u_sd15_tile",
+    # so for now replace  "lllyasviel/control_v11f1e_sd15_tile",
+    "lllyasviel/control_v11e_sd15_shuffle",
+    "lllyasviel/control_v11e_sd15_ip2p",
+    "lllyasviel/control_v11f1e_sd15_tile",
+
+     #################################################
+     #  thibaud sd v2.1 models (ControlNet v1.0? or v1.1?
+     ##################################################
+     "thibaud/controlnet-sd21-openpose-diffusers",
+     "thibaud/controlnet-sd21-canny-diffusers",
+     "thibaud/controlnet-sd21-depth-diffusers",
+     "thibaud/controlnet-sd21-scribble-diffusers",
+     "thibaud/controlnet-sd21-hed-diffusers",
+     "thibaud/controlnet-sd21-zoedepth-diffusers",
+     "thibaud/controlnet-sd21-color-diffusers",
+     "thibaud/controlnet-sd21-openposev2-diffusers",
+     "thibaud/controlnet-sd21-lineart-diffusers",
+     "thibaud/controlnet-sd21-normalbae-diffusers",
+     "thibaud/controlnet-sd21-ade20k-diffusers",
+
+     ##############################################
+     #  ControlNetMediaPipeface, ControlNet v1.1
+     ##############################################
+     # ["CrucibleAI/ControlNetMediaPipeFace", "diffusion_sd15"],  # SD 1.5
+     #    diffusion_sd15 needs to be passed to from_pretrained() as subfolder arg
+     #    hacked t2l to split to model & subfolder if format is "model,subfolder"
+     "CrucibleAI/ControlNetMediaPipeFace,diffusion_sd15",  # SD 1.5
+     "CrucibleAI/ControlNetMediaPipeFace",  # SD 2.1?
+]
+
+CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)]
+
+class ControlField(BaseModel):
+    image: ImageField = Field(default=None, description="The control image")
+    control_model: Optional[str] = Field(default=None, description="The ControlNet model to use")
+    # control_weight: Optional[float] = Field(default=1, description="weight given to controlnet")
+    control_weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
+    begin_step_percent: float = Field(default=0, ge=0, le=1,
+                                      description="When the ControlNet is first applied (% of total steps)")
+    end_step_percent: float = Field(default=1, ge=0, le=1,
+                                    description="When the ControlNet is last applied (% of total steps)")
+    @validator("control_weight")
+    def abs_le_one(cls, v):
+        """validate that all abs(values) are <=1"""
+        if isinstance(v, list):
+            for i in v:
+                if abs(i) > 1:
+                    raise ValueError('all abs(control_weight) must be <= 1')
+        else:
+            if abs(v) > 1:
+                raise ValueError('abs(control_weight) must be <= 1')
+        return v
+    class Config:
+        schema_extra = {
+            "required": ["image", "control_model", "control_weight", "begin_step_percent", "end_step_percent"],
+            "ui": {
+                "type_hints": {
+                    "control_weight": "float",
+                    # "control_weight": "number",
+                }
+            }
+        }
+
+
+class ControlOutput(BaseInvocationOutput):
+    """node output for ControlNet info"""
+    # fmt: off
+    type: Literal["control_output"] = "control_output"
+    control: ControlField = Field(default=None, description="The control info")
+    # fmt: on
+
+
+class ControlNetInvocation(BaseInvocation):
+    """Collects ControlNet info to pass to other nodes"""
+    # fmt: off
+    type: Literal["controlnet"] = "controlnet"
+    # Inputs
+    image: ImageField = Field(default=None, description="The control image")
+    control_model: CONTROLNET_NAME_VALUES = Field(default="lllyasviel/sd-controlnet-canny",
+                                                  description="control model used")
+    control_weight: Union[float, List[float]] = Field(default=1.0, description="The weight given to the ControlNet")
+    # TODO: add support in backend core for begin_step_percent, end_step_percent, guess_mode
+    begin_step_percent: float = Field(default=0, ge=0, le=1,
+                                      description="When the ControlNet is first applied (% of total steps)")
+    end_step_percent: float = Field(default=1, ge=0, le=1,
+                                    description="When the ControlNet is last applied (% of total steps)")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                  "model": "model",
+                  "control": "control",
+                  # "cfg_scale": "float",
+                  "cfg_scale": "number",
+                  "control_weight": "float",
+                }
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> ControlOutput:
+
+        return ControlOutput(
+            control=ControlField(
+                image=self.image,
+                control_model=self.control_model,
+                control_weight=self.control_weight,
+                begin_step_percent=self.begin_step_percent,
+                end_step_percent=self.end_step_percent,
+            ),
+        )
+
+# TODO: move image processors to separate file (image_analysis.py
+class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
+    """Base class for invocations that preprocess images for ControlNet"""
+
+    # fmt: off
+    type: Literal["image_processor"] = "image_processor"
+    # Inputs
+    image: ImageField = Field(default=None, description="The image to process")
+    # fmt: on
+
+
+    def run_processor(self, image):
+        # superclass just passes through image without processing
+        return image
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        raw_image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        # image type should be PIL.PngImagePlugin.PngImageFile ?
+        processed_image = self.run_processor(raw_image)
+
+        # FIXME: what happened to image metadata?
+        # metadata = context.services.metadata.build_metadata(
+        #     session_id=context.graph_execution_state_id, node=self
+        # )
+
+        # currently can't see processed image in node UI without a showImage node,
+        #    so for now setting image_type to RESULT instead of INTERMEDIATE so will get saved in gallery
+        image_dto = context.services.images.create(
+            image=processed_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.CONTROL,
+            session_id=context.graph_execution_state_id,
+            node_id=self.id,
+            is_intermediate=self.is_intermediate
+        )
+
+        """Builds an ImageOutput and its ImageField"""
+        processed_image_field = ImageField(
+            image_name=image_dto.image_name,
+            image_origin=image_dto.image_origin,
+        )
+        return ImageOutput(
+            image=processed_image_field,
+            # width=processed_image.width,
+            width = image_dto.width,
+            # height=processed_image.height,
+            height = image_dto.height,
+            # mode=processed_image.mode,
+        )
+
+
+class CannyImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Canny edge detection for ControlNet"""
+    # fmt: off
+    type: Literal["canny_image_processor"] = "canny_image_processor"
+    # Input
+    low_threshold: int = Field(default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)")
+    high_threshold: int = Field(default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)")
+    # fmt: on
+
+    def run_processor(self, image):
+        canny_processor = CannyDetector()
+        processed_image = canny_processor(image, self.low_threshold, self.high_threshold)
+        return processed_image
+
+
+class HedImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies HED edge detection to image"""
+    # fmt: off
+    type: Literal["hed_image_processor"] = "hed_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # safe not supported in controlnet_aux v0.0.3
+    # safe: bool = Field(default=False, description="whether to use safe mode")
+    scribble: bool = Field(default=False, description="Whether to use scribble mode")
+    # fmt: on
+
+    def run_processor(self, image):
+        hed_processor = HEDdetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = hed_processor(image,
+                                        detect_resolution=self.detect_resolution,
+                                        image_resolution=self.image_resolution,
+                                        # safe not supported in controlnet_aux v0.0.3
+                                        # safe=self.safe,
+                                        scribble=self.scribble,
+                                        )
+        return processed_image
+
+
+class LineartImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies line art processing to image"""
+    # fmt: off
+    type: Literal["lineart_image_processor"] = "lineart_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    coarse: bool = Field(default=False, description="Whether to use coarse mode")
+    # fmt: on
+
+    def run_processor(self, image):
+        lineart_processor = LineartDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = lineart_processor(image,
+                                            detect_resolution=self.detect_resolution,
+                                            image_resolution=self.image_resolution,
+                                            coarse=self.coarse)
+        return processed_image
+
+
+class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies line art anime processing to image"""
+    # fmt: off
+    type: Literal["lineart_anime_image_processor"] = "lineart_anime_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    def run_processor(self, image):
+        processor = LineartAnimeDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = processor(image,
+                                    detect_resolution=self.detect_resolution,
+                                    image_resolution=self.image_resolution,
+                                    )
+        return processed_image
+
+
+class OpenposeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies Openpose processing to image"""
+    # fmt: off
+    type: Literal["openpose_image_processor"] = "openpose_image_processor"
+    # Inputs
+    hand_and_face: bool = Field(default=False, description="Whether to use hands and face mode")
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    def run_processor(self, image):
+        openpose_processor = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = openpose_processor(image,
+                                             detect_resolution=self.detect_resolution,
+                                             image_resolution=self.image_resolution,
+                                             hand_and_face=self.hand_and_face,
+                                             )
+        return processed_image
+
+
+class MidasDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies Midas depth processing to image"""
+    # fmt: off
+    type: Literal["midas_depth_image_processor"] = "midas_depth_image_processor"
+    # Inputs
+    a_mult: float = Field(default=2.0, ge=0, description="Midas parameter `a_mult` (a = a_mult * PI)")
+    bg_th: float = Field(default=0.1, ge=0, description="Midas parameter `bg_th`")
+    # depth_and_normal not supported in controlnet_aux v0.0.3
+    # depth_and_normal: bool = Field(default=False, description="whether to use depth and normal mode")
+    # fmt: on
+
+    def run_processor(self, image):
+        midas_processor = MidasDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = midas_processor(image,
+                                          a=np.pi * self.a_mult,
+                                          bg_th=self.bg_th,
+                                          # dept_and_normal not supported in controlnet_aux v0.0.3
+                                          # depth_and_normal=self.depth_and_normal,
+                                          )
+        return processed_image
+
+
+class NormalbaeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies NormalBae processing to image"""
+    # fmt: off
+    type: Literal["normalbae_image_processor"] = "normalbae_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    def run_processor(self, image):
+        normalbae_processor = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = normalbae_processor(image,
+                                              detect_resolution=self.detect_resolution,
+                                              image_resolution=self.image_resolution)
+        return processed_image
+
+
+class MlsdImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies MLSD processing to image"""
+    # fmt: off
+    type: Literal["mlsd_image_processor"] = "mlsd_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    thr_v: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_v`")
+    thr_d: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_d`")
+    # fmt: on
+
+    def run_processor(self, image):
+        mlsd_processor = MLSDdetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = mlsd_processor(image,
+                                         detect_resolution=self.detect_resolution,
+                                         image_resolution=self.image_resolution,
+                                         thr_v=self.thr_v,
+                                         thr_d=self.thr_d)
+        return processed_image
+
+
+class PidiImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies PIDI processing to image"""
+    # fmt: off
+    type: Literal["pidi_image_processor"] = "pidi_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    safe: bool = Field(default=False, description="Whether to use safe mode")
+    scribble: bool = Field(default=False, description="Whether to use scribble mode")
+    # fmt: on
+
+    def run_processor(self, image):
+        pidi_processor = PidiNetDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = pidi_processor(image,
+                                         detect_resolution=self.detect_resolution,
+                                         image_resolution=self.image_resolution,
+                                         safe=self.safe,
+                                         scribble=self.scribble)
+        return processed_image
+
+
+class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies content shuffle processing to image"""
+    # fmt: off
+    type: Literal["content_shuffle_image_processor"] = "content_shuffle_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    h: Union[int, None] = Field(default=512, ge=0, description="Content shuffle `h` parameter")
+    w: Union[int, None] = Field(default=512, ge=0, description="Content shuffle `w` parameter")
+    f: Union[int, None] = Field(default=256, ge=0, description="Content shuffle `f` parameter")
+    # fmt: on
+
+    def run_processor(self, image):
+        content_shuffle_processor = ContentShuffleDetector()
+        processed_image = content_shuffle_processor(image,
+                                                    detect_resolution=self.detect_resolution,
+                                                    image_resolution=self.image_resolution,
+                                                    h=self.h,
+                                                    w=self.w,
+                                                    f=self.f
+                                                    )
+        return processed_image
+
+
+# should work with controlnet_aux >= 0.0.4 and timm <= 0.6.13
+class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies Zoe depth processing to image"""
+    # fmt: off
+    type: Literal["zoe_depth_image_processor"] = "zoe_depth_image_processor"
+    # fmt: on
+
+    def run_processor(self, image):
+        zoe_depth_processor = ZoeDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = zoe_depth_processor(image)
+        return processed_image
+
+
+class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies mediapipe face processing to image"""
+    # fmt: off
+    type: Literal["mediapipe_face_processor"] = "mediapipe_face_processor"
+    # Inputs
+    max_faces: int = Field(default=1, ge=1, description="Maximum number of faces to detect")
+    min_confidence: float = Field(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
+    # fmt: on
+
+    def run_processor(self, image):
+        mediapipe_face_processor = MediapipeFaceDetector()
+        processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence)
+        return processed_image

invokeai/app/invocations/cv.py

@@ -0,0 +1,74 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal
+
+import cv2 as cv
+import numpy
+from PIL import Image, ImageOps
+from pydantic import BaseModel, Field
+
+from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput
+
+
+class CvInvocationConfig(BaseModel):
+    """Helper class to provide all OpenCV invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["cv", "image"],
+            },
+        }
+
+
+class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
+    """Simple inpaint using opencv."""
+
+    # fmt: off
+    type: Literal["cv_inpaint"] = "cv_inpaint"
+
+    # Inputs
+    image: ImageField = Field(default=None, description="The image to inpaint")
+    mask: ImageField = Field(default=None, description="The mask to use when inpainting")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        mask = context.services.images.get_pil_image(
+            self.mask.image_origin, self.mask.image_name
+        )
+
+        # Convert to cv image/mask
+        # TODO: consider making these utility functions
+        cv_image = cv.cvtColor(numpy.array(image.convert("RGB")), cv.COLOR_RGB2BGR)
+        cv_mask = numpy.array(ImageOps.invert(mask.convert("L")))
+
+        # Inpaint
+        cv_inpainted = cv.inpaint(cv_image, cv_mask, 3, cv.INPAINT_TELEA)
+
+        # Convert back to Pillow
+        # TODO: consider making a utility function
+        image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
+
+        image_dto = context.services.images.create(
+            image=image_inpainted,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/generate.py

@@ -0,0 +1,334 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from functools import partial
+from typing import Literal, Optional, Union, get_args
+
+import numpy as np
+from diffusers import ControlNetModel
+from torch import Tensor
+import torch
+
+from pydantic import BaseModel, Field
+
+from invokeai.app.models.image import ColorField, ImageField, ResourceOrigin
+from invokeai.app.invocations.util.choose_model import choose_model
+from invokeai.app.models.image import ImageCategory, ResourceOrigin
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.generator.inpaint import infill_methods
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput
+from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
+from ...backend.stable_diffusion import PipelineIntermediateState
+from ..util.step_callback import stable_diffusion_step_callback
+
+SAMPLER_NAME_VALUES = Literal[tuple(InvokeAIGenerator.schedulers())]
+INFILL_METHODS = Literal[tuple(infill_methods())]
+DEFAULT_INFILL_METHOD = (
+    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
+)
+
+
+class SDImageInvocation(BaseModel):
+    """Helper class to provide all Stable Diffusion raster image invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["stable-diffusion", "image"],
+                "type_hints": {
+                    "model": "model",
+                },
+            },
+        }
+
+
+# Text to image
+class TextToImageInvocation(BaseInvocation, SDImageInvocation):
+    """Generates an image using text2img."""
+
+    type: Literal["txt2img"] = "txt2img"
+
+    # Inputs
+    # TODO: consider making prompt optional to enable providing prompt through a link
+    # fmt: off
+    prompt: Optional[str] = Field(description="The prompt to generate an image from")
+    seed:        int = Field(ge=0, le=SEED_MAX, description="The seed to use (omit for random)", default_factory=get_random_seed)
+    steps:       int = Field(default=30, gt=0, description="The number of steps to use to generate the image")
+    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting image", )
+    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting image", )
+    cfg_scale: float = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
+    model:       str = Field(default="", description="The model to use (currently ignored)")
+    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
+    control_model: Optional[str] = Field(default=None, description="The control model to use")
+    control_image: Optional[ImageField] = Field(default=None, description="The processed control image")
+    # fmt: on
+
+    # TODO: pass this an emitter method or something? or a session for dispatching?
+    def dispatch_progress(
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Handle invalid model parameter
+        model = choose_model(context.services.model_manager, self.model)
+
+        # loading controlnet image (currently requires pre-processed image)
+        control_image = (
+            None if self.control_image is None
+            else context.services.images.get_pil_image(
+                self.control_image.image_origin, self.control_image.image_name
+            )
+        )
+        # loading controlnet model
+        if (self.control_model is None or self.control_model==''):
+            control_model = None
+        else:
+            # FIXME: change this to dropdown menu?
+            # FIXME: generalize so don't have to hardcode torch_dtype and device
+            control_model = ControlNetModel.from_pretrained(self.control_model,
+                                                            torch_dtype=torch.float16).to("cuda")
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id
+        )
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        txt2img = Txt2Img(model, control_model=control_model)
+        outputs = txt2img.generate(
+            prompt=self.prompt,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            control_image=control_image,
+            **self.dict(
+                exclude={"prompt", "control_image" }
+            ),  # Shorthand for passing all of the parameters above manually
+        )
+        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
+        # each time it is called. We only need the first one.
+        generate_output = next(outputs)
+
+        image_dto = context.services.images.create(
+            image=generate_output.image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            session_id=context.graph_execution_state_id,
+            node_id=self.id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageToImageInvocation(TextToImageInvocation):
+    """Generates an image using img2img."""
+
+    type: Literal["img2img"] = "img2img"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image")
+    strength: float = Field(
+        default=0.75, gt=0, le=1, description="The strength of the original image"
+    )
+    fit: bool = Field(
+        default=True,
+        description="Whether or not the result should be fit to the aspect ratio of the input image",
+    )
+
+    def dispatch_progress(
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = (
+            None
+            if self.image is None
+            else context.services.images.get_pil_image(
+                self.image.image_origin, self.image.image_name
+            )
+        )
+
+        if self.fit:
+            image = image.resize((self.width, self.height))
+
+        # Handle invalid model parameter
+        model = choose_model(context.services.model_manager, self.model)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id
+        )
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        outputs = Img2Img(model).generate(
+            prompt=self.prompt,
+            init_image=image,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            **self.dict(
+                exclude={"prompt", "image", "mask"}
+            ),  # Shorthand for passing all of the parameters above manually
+        )
+
+        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
+        # each time it is called. We only need the first one.
+        generator_output = next(outputs)
+
+        image_dto = context.services.images.create(
+            image=generator_output.image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            session_id=context.graph_execution_state_id,
+            node_id=self.id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class InpaintInvocation(ImageToImageInvocation):
+    """Generates an image using inpaint."""
+
+    type: Literal["inpaint"] = "inpaint"
+
+    # Inputs
+    mask: Union[ImageField, None] = Field(description="The mask")
+    seam_size: int = Field(default=96, ge=1, description="The seam inpaint size (px)")
+    seam_blur: int = Field(
+        default=16, ge=0, description="The seam inpaint blur radius (px)"
+    )
+    seam_strength: float = Field(
+        default=0.75, gt=0, le=1, description="The seam inpaint strength"
+    )
+    seam_steps: int = Field(
+        default=30, ge=1, description="The number of steps to use for seam inpaint"
+    )
+    tile_size: int = Field(
+        default=32, ge=1, description="The tile infill method size (px)"
+    )
+    infill_method: INFILL_METHODS = Field(
+        default=DEFAULT_INFILL_METHOD,
+        description="The method used to infill empty regions (px)",
+    )
+    inpaint_width: Optional[int] = Field(
+        default=None,
+        multiple_of=8,
+        gt=0,
+        description="The width of the inpaint region (px)",
+    )
+    inpaint_height: Optional[int] = Field(
+        default=None,
+        multiple_of=8,
+        gt=0,
+        description="The height of the inpaint region (px)",
+    )
+    inpaint_fill: Optional[ColorField] = Field(
+        default=ColorField(r=127, g=127, b=127, a=255),
+        description="The solid infill method color",
+    )
+    inpaint_replace: float = Field(
+        default=0.0,
+        ge=0.0,
+        le=1.0,
+        description="The amount by which to replace masked areas with latent noise",
+    )
+
+    def dispatch_progress(
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = (
+            None
+            if self.image is None
+            else context.services.images.get_pil_image(
+                self.image.image_origin, self.image.image_name
+            )
+        )
+        mask = (
+            None
+            if self.mask is None
+            else context.services.images.get_pil_image(self.mask.image_origin, self.mask.image_name)
+        )
+
+        # Handle invalid model parameter
+        model = choose_model(context.services.model_manager, self.model)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id
+        )
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        outputs = Inpaint(model).generate(
+            prompt=self.prompt,
+            init_image=image,
+            mask_image=mask,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            **self.dict(
+                exclude={"prompt", "image", "mask"}
+            ),  # Shorthand for passing all of the parameters above manually
+        )
+
+        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
+        # each time it is called. We only need the first one.
+        generator_output = next(outputs)
+
+        image_dto = context.services.images.create(
+            image=generator_output.image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            session_id=context.graph_execution_state_id,
+            node_id=self.id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/image.py

@@ -0,0 +1,612 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import io
+from typing import Literal, Optional, Union
+
+import numpy
+from PIL import Image, ImageFilter, ImageOps, ImageChops
+from pydantic import BaseModel, Field
+
+from ..models.image import ImageCategory, ImageField, ResourceOrigin
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
+
+
+class PILInvocationConfig(BaseModel):
+    """Helper class to provide all PIL invocations with additional config"""
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["PIL", "image"],
+            },
+        }
+
+
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+
+    class Config:
+        schema_extra = {"required": ["type", "image", "width", "height"]}
+
+
+class MaskOutput(BaseInvocationOutput):
+    """Base class for invocations that output a mask"""
+
+    # fmt: off
+    type: Literal["mask"] = "mask"
+    mask:      ImageField = Field(default=None, description="The output mask")
+    width:            int = Field(description="The width of the mask in pixels")
+    height:           int = Field(description="The height of the mask in pixels")
+    # fmt: on
+
+    class Config:
+        schema_extra = {
+            "required": [
+                "type",
+                "mask",
+            ]
+        }
+
+
+class LoadImageInvocation(BaseInvocation):
+    """Load an image and provide it as output."""
+
+    # fmt: off
+    type: Literal["load_image"] = "load_image"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(
+        default=None, description="The image to load"
+    )
+    # fmt: on
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=self.image.image_name,
+                image_origin=self.image.image_origin,
+            ),
+            width=image.width,
+            height=image.height,
+        )
+
+
+class ShowImageInvocation(BaseInvocation):
+    """Displays a provided image, and passes it forward in the pipeline."""
+
+    type: Literal["show_image"] = "show_image"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(
+        default=None, description="The image to show"
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        if image:
+            image.show()
+
+        # TODO: how to handle failure?
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=self.image.image_name,
+                image_origin=self.image.image_origin,
+            ),
+            width=image.width,
+            height=image.height,
+        )
+
+
+class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
+    """Crops an image to a specified box. The box can be outside of the image."""
+
+    # fmt: off
+    type: Literal["img_crop"] = "img_crop"
+
+    # Inputs
+    image: Union[ImageField, None]  = Field(default=None, description="The image to crop")
+    x:      int = Field(default=0, description="The left x coordinate of the crop rectangle")
+    y:      int = Field(default=0, description="The top y coordinate of the crop rectangle")
+    width:  int = Field(default=512, gt=0, description="The width of the crop rectangle")
+    height: int = Field(default=512, gt=0, description="The height of the crop rectangle")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        image_crop = Image.new(
+            mode="RGBA", size=(self.width, self.height), color=(0, 0, 0, 0)
+        )
+        image_crop.paste(image, (-self.x, -self.y))
+
+        image_dto = context.services.images.create(
+            image=image_crop,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
+    """Pastes an image into another image."""
+
+    # fmt: off
+    type: Literal["img_paste"] = "img_paste"
+
+    # Inputs
+    base_image:     Union[ImageField, None]  = Field(default=None, description="The base image")
+    image:          Union[ImageField, None]  = Field(default=None, description="The image to paste")
+    mask: Optional[ImageField] = Field(default=None, description="The mask to use when pasting")
+    x:                     int = Field(default=0, description="The left x coordinate at which to paste the image")
+    y:                     int = Field(default=0, description="The top y coordinate at which to paste the image")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        base_image = context.services.images.get_pil_image(
+            self.base_image.image_origin, self.base_image.image_name
+        )
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        mask = (
+            None
+            if self.mask is None
+            else ImageOps.invert(
+                context.services.images.get_pil_image(
+                    self.mask.image_origin, self.mask.image_name
+                )
+            )
+        )
+        # TODO: probably shouldn't invert mask here... should user be required to do it?
+
+        min_x = min(0, self.x)
+        min_y = min(0, self.y)
+        max_x = max(base_image.width, image.width + self.x)
+        max_y = max(base_image.height, image.height + self.y)
+
+        new_image = Image.new(
+            mode="RGBA", size=(max_x - min_x, max_y - min_y), color=(0, 0, 0, 0)
+        )
+        new_image.paste(base_image, (abs(min_x), abs(min_y)))
+        new_image.paste(image, (max(0, self.x), max(0, self.y)), mask=mask)
+
+        image_dto = context.services.images.create(
+            image=new_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
+    """Extracts the alpha channel of an image as a mask."""
+
+    # fmt: off
+    type: Literal["tomask"] = "tomask"
+
+    # Inputs
+    image: Union[ImageField, None]  = Field(default=None, description="The image to create the mask from")
+    invert:      bool = Field(default=False, description="Whether or not to invert the mask")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        image_mask = image.split()[-1]
+        if self.invert:
+            image_mask = ImageOps.invert(image_mask)
+
+        image_dto = context.services.images.create(
+            image=image_mask,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.MASK,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return MaskOutput(
+            mask=ImageField(
+                image_origin=image_dto.image_origin, image_name=image_dto.image_name
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageMultiplyInvocation(BaseInvocation, PILInvocationConfig):
+    """Multiplies two images together using `PIL.ImageChops.multiply()`."""
+
+    # fmt: off
+    type: Literal["img_mul"] = "img_mul"
+
+    # Inputs
+    image1: Union[ImageField, None]  = Field(default=None, description="The first image to multiply")
+    image2: Union[ImageField, None]  = Field(default=None, description="The second image to multiply")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image1 = context.services.images.get_pil_image(
+            self.image1.image_origin, self.image1.image_name
+        )
+        image2 = context.services.images.get_pil_image(
+            self.image2.image_origin, self.image2.image_name
+        )
+
+        multiply_image = ImageChops.multiply(image1, image2)
+
+        image_dto = context.services.images.create(
+            image=multiply_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_origin=image_dto.image_origin, image_name=image_dto.image_name
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+IMAGE_CHANNELS = Literal["A", "R", "G", "B"]
+
+
+class ImageChannelInvocation(BaseInvocation, PILInvocationConfig):
+    """Gets a channel from an image."""
+
+    # fmt: off
+    type: Literal["img_chan"] = "img_chan"
+
+    # Inputs
+    image: Union[ImageField, None]  = Field(default=None, description="The image to get the channel from")
+    channel: IMAGE_CHANNELS  = Field(default="A", description="The channel to get")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        channel_image = image.getchannel(self.channel)
+
+        image_dto = context.services.images.create(
+            image=channel_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_origin=image_dto.image_origin, image_name=image_dto.image_name
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
+
+
+class ImageConvertInvocation(BaseInvocation, PILInvocationConfig):
+    """Converts an image to a different mode."""
+
+    # fmt: off
+    type: Literal["img_conv"] = "img_conv"
+
+    # Inputs
+    image: Union[ImageField, None]  = Field(default=None, description="The image to convert")
+    mode: IMAGE_MODES  = Field(default="L", description="The mode to convert to")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        converted_image = image.convert(self.mode)
+
+        image_dto = context.services.images.create(
+            image=converted_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_origin=image_dto.image_origin, image_name=image_dto.image_name
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
+    """Blurs an image"""
+
+    # fmt: off
+    type: Literal["img_blur"] = "img_blur"
+
+    # Inputs
+    image: Union[ImageField, None]  = Field(default=None, description="The image to blur")
+    radius:     float = Field(default=8.0, ge=0, description="The blur radius")
+    blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        blur = (
+            ImageFilter.GaussianBlur(self.radius)
+            if self.blur_type == "gaussian"
+            else ImageFilter.BoxBlur(self.radius)
+        )
+        blur_image = image.filter(blur)
+
+        image_dto = context.services.images.create(
+            image=blur_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+PIL_RESAMPLING_MODES = Literal[
+    "nearest",
+    "box",
+    "bilinear",
+    "hamming",
+    "bicubic",
+    "lanczos",
+]
+
+
+PIL_RESAMPLING_MAP = {
+    "nearest": Image.Resampling.NEAREST,
+    "box": Image.Resampling.BOX,
+    "bilinear": Image.Resampling.BILINEAR,
+    "hamming": Image.Resampling.HAMMING,
+    "bicubic": Image.Resampling.BICUBIC,
+    "lanczos": Image.Resampling.LANCZOS,
+}
+
+
+class ImageResizeInvocation(BaseInvocation, PILInvocationConfig):
+    """Resizes an image to specific dimensions"""
+
+    # fmt: off
+    type: Literal["img_resize"] = "img_resize"
+
+    # Inputs
+    image: Union[ImageField, None]  = Field(default=None, description="The image to resize")
+    width:                         int = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
+    height:                        int = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
+    resample_mode:  PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
+
+        resize_image = image.resize(
+            (self.width, self.height),
+            resample=resample_mode,
+        )
+
+        image_dto = context.services.images.create(
+            image=resize_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageScaleInvocation(BaseInvocation, PILInvocationConfig):
+    """Scales an image by a factor"""
+
+    # fmt: off
+    type: Literal["img_scale"] = "img_scale"
+
+    # Inputs
+    image:       Union[ImageField, None] = Field(default=None, description="The image to scale")
+    scale_factor:                  float = Field(gt=0, description="The factor by which to scale the image")
+    resample_mode:  PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
+        width = int(image.width * self.scale_factor)
+        height = int(image.height * self.scale_factor)
+
+        resize_image = image.resize(
+            (width, height),
+            resample=resample_mode,
+        )
+
+        image_dto = context.services.images.create(
+            image=resize_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageLerpInvocation(BaseInvocation, PILInvocationConfig):
+    """Linear interpolation of all pixels of an image"""
+
+    # fmt: off
+    type: Literal["img_lerp"] = "img_lerp"
+
+    # Inputs
+    image: Union[ImageField, None]  = Field(default=None, description="The image to lerp")
+    min: int = Field(default=0, ge=0, le=255, description="The minimum output value")
+    max: int = Field(default=255, ge=0, le=255, description="The maximum output value")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        image_arr = numpy.asarray(image, dtype=numpy.float32) / 255
+        image_arr = image_arr * (self.max - self.min) + self.max
+
+        lerp_image = Image.fromarray(numpy.uint8(image_arr))
+
+        image_dto = context.services.images.create(
+            image=lerp_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
+    """Inverse linear interpolation of all pixels of an image"""
+
+    # fmt: off
+    type: Literal["img_ilerp"] = "img_ilerp"
+
+    # Inputs
+    image: Union[ImageField, None]  = Field(default=None, description="The image to lerp")
+    min: int = Field(default=0, ge=0, le=255, description="The minimum input value")
+    max: int = Field(default=255, ge=0, le=255, description="The maximum input value")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        image_arr = numpy.asarray(image, dtype=numpy.float32)
+        image_arr = (
+            numpy.minimum(
+                numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1
+            )
+            * 255
+        )
+
+        ilerp_image = Image.fromarray(numpy.uint8(image_arr))
+
+        image_dto = context.services.images.create(
+            image=ilerp_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/infill.py

@@ -0,0 +1,245 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+
+from typing import Literal, Union, get_args
+
+import numpy as np
+import math
+from PIL import Image, ImageOps
+from pydantic import Field
+
+from invokeai.app.invocations.image import ImageOutput
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.image_util.patchmatch import PatchMatch
+
+from ..models.image import ColorField, ImageCategory, ImageField, ResourceOrigin
+from .baseinvocation import (
+    BaseInvocation,
+    InvocationContext,
+)
+
+
+def infill_methods() -> list[str]:
+    methods = [
+        "tile",
+        "solid",
+    ]
+    if PatchMatch.patchmatch_available():
+        methods.insert(0, "patchmatch")
+    return methods
+
+
+INFILL_METHODS = Literal[tuple(infill_methods())]
+DEFAULT_INFILL_METHOD = (
+    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
+)
+
+
+def infill_patchmatch(im: Image.Image) -> Image.Image:
+    if im.mode != "RGBA":
+        return im
+
+    # Skip patchmatch if patchmatch isn't available
+    if not PatchMatch.patchmatch_available():
+        return im
+
+    # Patchmatch (note, we may want to expose patch_size? Increasing it significantly impacts performance though)
+    im_patched_np = PatchMatch.inpaint(
+        im.convert("RGB"), ImageOps.invert(im.split()[-1]), patch_size=3
+    )
+    im_patched = Image.fromarray(im_patched_np, mode="RGB")
+    return im_patched
+
+
+def get_tile_images(image: np.ndarray, width=8, height=8):
+    _nrows, _ncols, depth = image.shape
+    _strides = image.strides
+
+    nrows, _m = divmod(_nrows, height)
+    ncols, _n = divmod(_ncols, width)
+    if _m != 0 or _n != 0:
+        return None
+
+    return np.lib.stride_tricks.as_strided(
+        np.ravel(image),
+        shape=(nrows, ncols, height, width, depth),
+        strides=(height * _strides[0], width * _strides[1], *_strides),
+        writeable=False,
+    )
+
+
+def tile_fill_missing(
+    im: Image.Image, tile_size: int = 16, seed: Union[int, None] = None
+) -> Image.Image:
+    # Only fill if there's an alpha layer
+    if im.mode != "RGBA":
+        return im
+
+    a = np.asarray(im, dtype=np.uint8)
+
+    tile_size_tuple = (tile_size, tile_size)
+
+    # Get the image as tiles of a specified size
+    tiles = get_tile_images(a, *tile_size_tuple).copy()
+
+    # Get the mask as tiles
+    tiles_mask = tiles[:, :, :, :, 3]
+
+    # Find any mask tiles with any fully transparent pixels (we will be replacing these later)
+    tmask_shape = tiles_mask.shape
+    tiles_mask = tiles_mask.reshape(math.prod(tiles_mask.shape))
+    n, ny = (math.prod(tmask_shape[0:2])), math.prod(tmask_shape[2:])
+    tiles_mask = tiles_mask > 0
+    tiles_mask = tiles_mask.reshape((n, ny)).all(axis=1)
+
+    # Get RGB tiles in single array and filter by the mask
+    tshape = tiles.shape
+    tiles_all = tiles.reshape((math.prod(tiles.shape[0:2]), *tiles.shape[2:]))
+    filtered_tiles = tiles_all[tiles_mask]
+
+    if len(filtered_tiles) == 0:
+        return im
+
+    # Find all invalid tiles and replace with a random valid tile
+    replace_count = (tiles_mask == False).sum()
+    rng = np.random.default_rng(seed=seed)
+    tiles_all[np.logical_not(tiles_mask)] = filtered_tiles[
+        rng.choice(filtered_tiles.shape[0], replace_count), :, :, :
+    ]
+
+    # Convert back to an image
+    tiles_all = tiles_all.reshape(tshape)
+    tiles_all = tiles_all.swapaxes(1, 2)
+    st = tiles_all.reshape(
+        (
+            math.prod(tiles_all.shape[0:2]),
+            math.prod(tiles_all.shape[2:4]),
+            tiles_all.shape[4],
+        )
+    )
+    si = Image.fromarray(st, mode="RGBA")
+
+    return si
+
+
+class InfillColorInvocation(BaseInvocation):
+    """Infills transparent areas of an image with a solid color"""
+
+    type: Literal["infill_rgba"] = "infill_rgba"
+    image: Union[ImageField, None] = Field(
+        default=None, description="The image to infill"
+    )
+    color: ColorField = Field(
+        default=ColorField(r=127, g=127, b=127, a=255),
+        description="The color to use to infill",
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        solid_bg = Image.new("RGBA", image.size, self.color.tuple())
+        infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
+
+        infilled.paste(image, (0, 0), image.split()[-1])
+
+        image_dto = context.services.images.create(
+            image=infilled,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class InfillTileInvocation(BaseInvocation):
+    """Infills transparent areas of an image with tiles of the image"""
+
+    type: Literal["infill_tile"] = "infill_tile"
+
+    image: Union[ImageField, None] = Field(
+        default=None, description="The image to infill"
+    )
+    tile_size: int = Field(default=32, ge=1, description="The tile size (px)")
+    seed: int = Field(
+        ge=0,
+        le=SEED_MAX,
+        description="The seed to use for tile generation (omit for random)",
+        default_factory=get_random_seed,
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        infilled = tile_fill_missing(
+            image.copy(), seed=self.seed, tile_size=self.tile_size
+        )
+        infilled.paste(image, (0, 0), image.split()[-1])
+
+        image_dto = context.services.images.create(
+            image=infilled,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class InfillPatchMatchInvocation(BaseInvocation):
+    """Infills transparent areas of an image using the PatchMatch algorithm"""
+
+    type: Literal["infill_patchmatch"] = "infill_patchmatch"
+
+    image: Union[ImageField, None] = Field(
+        default=None, description="The image to infill"
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        if PatchMatch.patchmatch_available():
+            infilled = infill_patchmatch(image.copy())
+        else:
+            raise ValueError("PatchMatch is not available on this system")
+
+        image_dto = context.services.images.create(
+            image=infilled,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/latent.py

@@ -0,0 +1,626 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+import random
+import einops
+from typing import Literal, Optional, Union, List
+
+from compel import Compel
+from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_controlnet import MultiControlNetModel
+
+from pydantic import BaseModel, Field, validator
+import torch
+
+from invokeai.app.invocations.util.choose_model import choose_model
+from invokeai.app.models.image import ImageCategory
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+
+from invokeai.app.util.step_callback import stable_diffusion_step_callback
+from .controlnet_image_processors import ControlField
+
+from ...backend.model_management.model_manager import ModelManager
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
+from ...backend.image_util.seamless import configure_model_padding
+from ...backend.prompting.conditioning import get_uc_and_c_and_ec
+
+from ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline, image_resized_to_grid_as_tensor
+from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
+from ...backend.stable_diffusion.diffusers_pipeline import ControlNetData
+
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+import numpy as np
+from ..services.image_file_storage import ResourceOrigin
+from .baseinvocation import BaseInvocation, InvocationContext
+from .image import ImageField, ImageOutput
+from .compel import ConditioningField
+from ...backend.stable_diffusion import PipelineIntermediateState
+from diffusers.schedulers import SchedulerMixin as Scheduler
+import diffusers
+from diffusers import DiffusionPipeline, ControlNetModel
+
+
+class LatentsField(BaseModel):
+    """A latents field used for passing latents between invocations"""
+
+    latents_name: Optional[str] = Field(default=None, description="The name of the latents")
+
+    class Config:
+        schema_extra = {"required": ["latents_name"]}
+
+class LatentsOutput(BaseInvocationOutput):
+    """Base class for invocations that output latents"""
+    #fmt: off
+    type: Literal["latents_output"] = "latents_output"
+
+    # Inputs
+    latents: LatentsField          = Field(default=None, description="The output latents")
+    width:                     int = Field(description="The width of the latents in pixels")
+    height:                    int = Field(description="The height of the latents in pixels")
+    #fmt: on
+
+
+def build_latents_output(latents_name: str, latents: torch.Tensor):
+      return LatentsOutput(
+          latents=LatentsField(latents_name=latents_name),
+          width=latents.size()[3] * 8,
+          height=latents.size()[2] * 8,
+      )
+
+class NoiseOutput(BaseInvocationOutput):
+    """Invocation noise output"""
+    #fmt: off
+    type:  Literal["noise_output"] = "noise_output"
+
+    # Inputs
+    noise: LatentsField            = Field(default=None, description="The output noise")
+    width:                     int = Field(description="The width of the noise in pixels")
+    height:                    int = Field(description="The height of the noise in pixels")
+    #fmt: on
+
+def build_noise_output(latents_name: str, latents: torch.Tensor):
+      return NoiseOutput(
+          noise=LatentsField(latents_name=latents_name),
+          width=latents.size()[3] * 8,
+          height=latents.size()[2] * 8,
+      )
+
+
+SAMPLER_NAME_VALUES = Literal[
+    tuple(list(SCHEDULER_MAP.keys()))
+]
+
+
+def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
+    scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
+
+    scheduler_config = model.scheduler.config
+    if "_backup" in scheduler_config:
+        scheduler_config = scheduler_config["_backup"]
+    scheduler_config = {**scheduler_config, **scheduler_extra_config, "_backup": scheduler_config}
+    scheduler = scheduler_class.from_config(scheduler_config)
+
+    # hack copied over from generate.py
+    if not hasattr(scheduler, 'uses_inpainting_model'):
+        scheduler.uses_inpainting_model = lambda: False
+    return scheduler
+
+
+def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_channels:int=4, use_mps_noise:bool=False, downsampling_factor:int = 8):
+    # limit noise to only the diffusion image channels, not the mask channels
+    input_channels = min(latent_channels, 4)
+    use_device = "cpu" if (use_mps_noise or device.type == "mps") else device
+    generator = torch.Generator(device=use_device).manual_seed(seed)
+    x = torch.randn(
+        [
+            1,
+            input_channels,
+            height // downsampling_factor,
+            width //  downsampling_factor,
+        ],
+        dtype=torch_dtype(device),
+        device=use_device,
+        generator=generator,
+    ).to(device)
+    # if self.perlin > 0.0:
+    #     perlin_noise = self.get_perlin_noise(
+    #         width // self.downsampling_factor, height // self.downsampling_factor
+    #     )
+    #     x = (1 - self.perlin) * x + self.perlin * perlin_noise
+    return x
+
+
+class NoiseInvocation(BaseInvocation):
+    """Generates latent noise."""
+
+    type: Literal["noise"] = "noise"
+
+    # Inputs
+    seed:       int = Field(ge=0, le=SEED_MAX, description="The seed to use", default_factory=get_random_seed)
+    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting noise", )
+    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting noise", )
+
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "noise"],
+            },
+        }
+
+    @validator("seed", pre=True)
+    def modulo_seed(cls, v):
+        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
+        return v % SEED_MAX
+
+    def invoke(self, context: InvocationContext) -> NoiseOutput:
+        device = torch.device(choose_torch_device())
+        noise = get_noise(self.width, self.height, device, self.seed)
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.save(name, noise)
+        return build_noise_output(latents_name=name, latents=noise)
+
+
+# Text to image
+class TextToLatentsInvocation(BaseInvocation):
+    """Generates latents from conditionings."""
+
+    type: Literal["t2l"] = "t2l"
+
+    # Inputs
+    # fmt: off
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
+    noise: Optional[LatentsField] = Field(description="The noise to use")
+    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
+    cfg_scale: Union[float, List[float]] = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
+    model:       str = Field(default="", description="The model to use (currently ignored)")
+    control: Union[ControlField, List[ControlField]] = Field(default=None, description="The control to use")
+    # seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    # seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
+    # fmt: on
+
+    @validator("cfg_scale")
+    def ge_one(cls, v):
+        """validate that all cfg_scale values are >= 1"""
+        if isinstance(v, list):
+            for i in v:
+                if i < 1:
+                    raise ValueError('cfg_scale must be greater than 1')
+        else:
+            if v < 1:
+                raise ValueError('cfg_scale must be greater than 1')
+        return v
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                  "model": "model",
+                  "control": "control",
+                  # "cfg_scale": "float",
+                  "cfg_scale": "number"
+                }
+            },
+        }
+
+    # TODO: pass this an emitter method or something? or a session for dispatching?
+    def dispatch_progress(
+        self, context: InvocationContext, source_node_id: str, intermediate_state: PipelineIntermediateState
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
+
+    def get_model(self, model_manager: ModelManager) -> StableDiffusionGeneratorPipeline:
+        model_info = choose_model(model_manager, self.model)
+        model_name = model_info['model_name']
+        model_hash = model_info['hash']
+        model: StableDiffusionGeneratorPipeline = model_info['model']
+        model.scheduler = get_scheduler(
+            model=model,
+            scheduler_name=self.scheduler
+        )
+
+        # if isinstance(model, DiffusionPipeline):
+        #     for component in [model.unet, model.vae]:
+        #         configure_model_padding(component,
+        #                                 self.seamless,
+        #                                 self.seamless_axes
+        #                                 )
+        # else:
+        #     configure_model_padding(model,
+        #                             self.seamless,
+        #                             self.seamless_axes
+        #                             )
+
+        return model
+
+
+    def get_conditioning_data(self, context: InvocationContext, model: StableDiffusionGeneratorPipeline) -> ConditioningData:
+        c, extra_conditioning_info = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
+
+        compel = Compel(
+            tokenizer=model.tokenizer,
+            text_encoder=model.text_encoder,
+            textual_inversion_manager=model.textual_inversion_manager,
+            dtype_for_device_getter=torch_dtype,
+            truncate_long_prompts=False,
+        )
+        [c, uc] = compel.pad_conditioning_tensors_to_same_length([c, uc])
+
+        conditioning_data = ConditioningData(
+            unconditioned_embeddings=uc,
+            text_embeddings=c,
+            guidance_scale=self.cfg_scale,
+            extra=extra_conditioning_info,
+            postprocessing_settings=PostprocessingSettings(
+                threshold=0.0,#threshold,
+                warmup=0.2,#warmup,
+                h_symmetry_time_pct=None,#h_symmetry_time_pct,
+                v_symmetry_time_pct=None#v_symmetry_time_pct,
+            ),
+        ).add_scheduler_args_if_applicable(model.scheduler, eta=0.0)#ddim_eta)
+        return conditioning_data
+
+    def prep_control_data(self,
+                          context: InvocationContext,
+                          model: StableDiffusionGeneratorPipeline, # really only need model for dtype and device
+                          control_input: List[ControlField],
+                          latents_shape: List[int],
+                          do_classifier_free_guidance: bool = True,
+                          ) -> List[ControlNetData]:
+        # assuming fixed dimensional scaling of 8:1 for image:latents
+        control_height_resize = latents_shape[2] * 8
+        control_width_resize = latents_shape[3] * 8
+        if control_input is None:
+            # print("control input is None")
+            control_list = None
+        elif isinstance(control_input, list) and len(control_input) == 0:
+            # print("control input is empty list")
+            control_list = None
+        elif isinstance(control_input, ControlField):
+            # print("control input is ControlField")
+            control_list = [control_input]
+        elif isinstance(control_input, list) and len(control_input) > 0 and isinstance(control_input[0], ControlField):
+            # print("control input is list[ControlField]")
+            control_list = control_input
+        else:
+            # print("input control is unrecognized:", type(self.control))
+            control_list = None
+        if (control_list is None):
+            control_data = None
+            # from above handling, any control that is not None should now be of type list[ControlField]
+        else:
+            # FIXME: add checks to skip entry if model or image is None
+            #        and if weight is None, populate with default 1.0?
+            control_data = []
+            control_models = []
+            for control_info in control_list:
+                # handle control models
+                if ("," in control_info.control_model):
+                    control_model_split = control_info.control_model.split(",")
+                    control_name = control_model_split[0]
+                    control_subfolder = control_model_split[1]
+                    print("Using HF model subfolders")
+                    print("    control_name: ", control_name)
+                    print("    control_subfolder: ", control_subfolder)
+                    control_model = ControlNetModel.from_pretrained(control_name,
+                                                                    subfolder=control_subfolder,
+                                                                    torch_dtype=model.unet.dtype).to(model.device)
+                else:
+                    control_model = ControlNetModel.from_pretrained(control_info.control_model,
+                                                                    torch_dtype=model.unet.dtype).to(model.device)
+                control_models.append(control_model)
+                control_image_field = control_info.image
+                input_image = context.services.images.get_pil_image(control_image_field.image_origin,
+                                                                    control_image_field.image_name)
+                # self.image.image_type, self.image.image_name
+                # FIXME: still need to test with different widths, heights, devices, dtypes
+                #        and add in batch_size, num_images_per_prompt?
+                #        and do real check for classifier_free_guidance?
+                # prepare_control_image should return torch.Tensor of shape(batch_size, 3, height, width)
+                control_image = model.prepare_control_image(
+                    image=input_image,
+                    do_classifier_free_guidance=do_classifier_free_guidance,
+                    width=control_width_resize,
+                    height=control_height_resize,
+                    # batch_size=batch_size * num_images_per_prompt,
+                    # num_images_per_prompt=num_images_per_prompt,
+                    device=control_model.device,
+                    dtype=control_model.dtype,
+                )
+                control_item = ControlNetData(model=control_model,
+                                              image_tensor=control_image,
+                                              weight=control_info.control_weight,
+                                              begin_step_percent=control_info.begin_step_percent,
+                                              end_step_percent=control_info.end_step_percent)
+                control_data.append(control_item)
+                # MultiControlNetModel has been refactored out, just need list[ControlNetData]
+        return control_data
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        noise = context.services.latents.get(self.noise.latents_name)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        def step_callback(state: PipelineIntermediateState):
+            self.dispatch_progress(context, source_node_id, state)
+
+        model = self.get_model(context.services.model_manager)
+        conditioning_data = self.get_conditioning_data(context, model)
+
+        control_data = self.prep_control_data(model=model, context=context, control_input=self.control,
+                                              latents_shape=noise.shape,
+                                              # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
+                                              do_classifier_free_guidance=True,)
+
+        # TODO: Verify the noise is the right size
+        result_latents, result_attention_map_saver = model.latents_from_embeddings(
+            latents=torch.zeros_like(noise, dtype=torch_dtype(model.device)),
+            noise=noise,
+            num_inference_steps=self.steps,
+            conditioning_data=conditioning_data,
+            control_data=control_data,  # list[ControlNetData]
+            callback=step_callback,
+        )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.empty_cache()
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.save(name, result_latents)
+        return build_latents_output(latents_name=name, latents=result_latents)
+
+
+class LatentsToLatentsInvocation(TextToLatentsInvocation):
+    """Generates latents using latents as base image."""
+
+    type: Literal["l2l"] = "l2l"
+
+    # Inputs
+    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
+    strength: float = Field(default=0.7, ge=0, le=1, description="The strength of the latents to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                    "model": "model",
+                    "control": "control",
+                    "cfg_scale": "number",
+                }
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        noise = context.services.latents.get(self.noise.latents_name)
+        latent = context.services.latents.get(self.latents.latents_name)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        def step_callback(state: PipelineIntermediateState):
+            self.dispatch_progress(context, source_node_id, state)
+
+        model = self.get_model(context.services.model_manager)
+        conditioning_data = self.get_conditioning_data(context, model)
+
+        control_data = self.prep_control_data(model=model, context=context, control_input=self.control,
+                                              latents_shape=noise.shape,
+                                              # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
+                                              do_classifier_free_guidance=True,
+                                              )
+
+        # TODO: Verify the noise is the right size
+
+        initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
+            latent, device=model.device, dtype=latent.dtype
+        )
+
+        timesteps, _ = model.get_img2img_timesteps(self.steps, self.strength)
+
+        result_latents, result_attention_map_saver = model.latents_from_embeddings(
+            latents=initial_latents,
+            timesteps=timesteps,
+            noise=noise,
+            num_inference_steps=self.steps,
+            conditioning_data=conditioning_data,
+            control_data=control_data,  # list[ControlNetData]
+            callback=step_callback
+        )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.empty_cache()
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.save(name, result_latents)
+        return build_latents_output(latents_name=name, latents=result_latents)
+
+
+# Latent to image
+class LatentsToImageInvocation(BaseInvocation):
+    """Generates an image from latents."""
+
+    type: Literal["l2i"] = "l2i"
+
+    # Inputs
+    latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
+    model: str = Field(default="", description="The model to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+                "type_hints": {
+                  "model": "model"
+                }
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        # TODO: this only really needs the vae
+        model_info = choose_model(context.services.model_manager, self.model)
+        model: StableDiffusionGeneratorPipeline = model_info['model']
+
+        with torch.inference_mode():
+            np_image = model.decode_latents(latents)
+            image = model.numpy_to_pil(np_image)[0]
+
+            # what happened to metadata?
+            # metadata = context.services.metadata.build_metadata(
+            #     session_id=context.graph_execution_state_id, node=self
+
+            torch.cuda.empty_cache()
+
+            # new (post Image service refactor) way of using services to save image
+            #     and gnenerate unique image_name
+            image_dto = context.services.images.create(
+                image=image,
+                image_origin=ResourceOrigin.INTERNAL,
+                image_category=ImageCategory.GENERAL,
+                session_id=context.graph_execution_state_id,
+                node_id=self.id,
+                is_intermediate=self.is_intermediate
+            )
+
+            return ImageOutput(
+                image=ImageField(
+                    image_name=image_dto.image_name,
+                    image_origin=image_dto.image_origin,
+                ),
+                width=image_dto.width,
+                height=image_dto.height,
+            )
+
+
+LATENTS_INTERPOLATION_MODE = Literal[
+    "nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"
+]
+
+
+class ResizeLatentsInvocation(BaseInvocation):
+    """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
+
+    type: Literal["lresize"] = "lresize"
+
+    # Inputs
+    latents:    Optional[LatentsField] = Field(description="The latents to resize")
+    width:                         int = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
+    height:                        int = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
+    mode:   LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
+    antialias:                    bool = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        resized_latents = torch.nn.functional.interpolate(
+            latents,
+            size=(self.height // 8, self.width // 8),
+            mode=self.mode,
+            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
+        )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.empty_cache()
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        # context.services.latents.set(name, resized_latents)
+        context.services.latents.save(name, resized_latents)
+        return build_latents_output(latents_name=name, latents=resized_latents)
+
+
+class ScaleLatentsInvocation(BaseInvocation):
+    """Scales latents by a given factor."""
+
+    type: Literal["lscale"] = "lscale"
+
+    # Inputs
+    latents:   Optional[LatentsField] = Field(description="The latents to scale")
+    scale_factor:               float = Field(gt=0, description="The factor by which to scale the latents")
+    mode:  LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
+    antialias:                   bool = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        # resizing
+        resized_latents = torch.nn.functional.interpolate(
+            latents,
+            scale_factor=self.scale_factor,
+            mode=self.mode,
+            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
+        )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.empty_cache()
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        # context.services.latents.set(name, resized_latents)
+        context.services.latents.save(name, resized_latents)
+        return build_latents_output(latents_name=name, latents=resized_latents)
+
+
+class ImageToLatentsInvocation(BaseInvocation):
+    """Encodes an image into latents."""
+
+    type: Literal["i2l"] = "i2l"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The image to encode")
+    model: str = Field(default="", description="The model to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        # image = context.services.images.get(
+        #     self.image.image_type, self.image.image_name
+        # )
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+
+        # TODO: this only really needs the vae
+        model_info = choose_model(context.services.model_manager, self.model)
+        model: StableDiffusionGeneratorPipeline = model_info["model"]
+
+        image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+
+        if image_tensor.dim() == 3:
+            image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
+
+        latents = model.non_noised_latents_from_image(
+            image_tensor,
+            device=model._model_group.device_for(model.unet),
+            dtype=model.unet.dtype,
+        )
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        # context.services.latents.set(name, latents)
+        context.services.latents.save(name, latents)
+        return build_latents_output(latents_name=name, latents=latents)

invokeai/app/invocations/math.py

@@ -0,0 +1,109 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal
+
+from pydantic import BaseModel, Field
+import numpy as np
+
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
+
+
+class MathInvocationConfig(BaseModel):
+    """Helper class to provide all math invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["math"],
+            }
+        }
+
+
+class IntOutput(BaseInvocationOutput):
+    """An integer output"""
+
+    # fmt: off
+    type: Literal["int_output"] = "int_output"
+    a: int = Field(default=None, description="The output integer")
+    # fmt: on
+
+
+class FloatOutput(BaseInvocationOutput):
+    """A float output"""
+
+    # fmt: off
+    type: Literal["float_output"] = "float_output"
+    param: float = Field(default=None, description="The output float")
+    # fmt: on
+
+
+class AddInvocation(BaseInvocation, MathInvocationConfig):
+    """Adds two numbers"""
+
+    # fmt: off
+    type: Literal["add"] = "add"
+    a: int = Field(default=0, description="The first number")
+    b: int = Field(default=0, description="The second number")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a + self.b)
+
+
+class SubtractInvocation(BaseInvocation, MathInvocationConfig):
+    """Subtracts two numbers"""
+
+    # fmt: off
+    type: Literal["sub"] = "sub"
+    a: int = Field(default=0, description="The first number")
+    b: int = Field(default=0, description="The second number")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a - self.b)
+
+
+class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
+    """Multiplies two numbers"""
+
+    # fmt: off
+    type: Literal["mul"] = "mul"
+    a: int = Field(default=0, description="The first number")
+    b: int = Field(default=0, description="The second number")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a * self.b)
+
+
+class DivideInvocation(BaseInvocation, MathInvocationConfig):
+    """Divides two numbers"""
+
+    # fmt: off
+    type: Literal["div"] = "div"
+    a: int = Field(default=0, description="The first number")
+    b: int = Field(default=0, description="The second number")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=int(self.a / self.b))
+
+
+class RandomIntInvocation(BaseInvocation):
+    """Outputs a single random integer."""
+
+    # fmt: off
+    type: Literal["rand_int"] = "rand_int"
+    low: int = Field(default=0, description="The inclusive low value")
+    high: int = Field(
+        default=np.iinfo(np.int32).max, description="The exclusive high value"
+    )
+    # fmt: on
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=np.random.randint(self.low, self.high))

invokeai/app/invocations/param_easing.py

@@ -0,0 +1,237 @@
+import io
+from typing import Literal, Optional, Any
+
+# from PIL.Image import Image
+import PIL.Image
+from matplotlib.ticker import MaxNLocator
+from matplotlib.figure import Figure
+
+from pydantic import BaseModel, Field
+import numpy as np
+import matplotlib.pyplot as plt
+
+from easing_functions import (
+    LinearInOut,
+    QuadEaseInOut, QuadEaseIn, QuadEaseOut,
+    CubicEaseInOut, CubicEaseIn, CubicEaseOut,
+    QuarticEaseInOut, QuarticEaseIn, QuarticEaseOut,
+    QuinticEaseInOut, QuinticEaseIn, QuinticEaseOut,
+    SineEaseInOut, SineEaseIn, SineEaseOut,
+    CircularEaseIn, CircularEaseInOut, CircularEaseOut,
+    ExponentialEaseInOut, ExponentialEaseIn, ExponentialEaseOut,
+    ElasticEaseIn, ElasticEaseInOut, ElasticEaseOut,
+    BackEaseIn, BackEaseInOut, BackEaseOut,
+    BounceEaseIn, BounceEaseInOut, BounceEaseOut)
+
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
+from ...backend.util.logging import InvokeAILogger
+from .collections import FloatCollectionOutput
+
+
+class FloatLinearRangeInvocation(BaseInvocation):
+    """Creates a range"""
+
+    type: Literal["float_range"] = "float_range"
+
+    # Inputs
+    start: float = Field(default=5, description="The first value of the range")
+    stop: float = Field(default=10, description="The last value of the range")
+    steps: int = Field(default=30, description="number of values to interpolate over (including start and stop)")
+
+    def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
+        param_list = list(np.linspace(self.start, self.stop, self.steps))
+        return FloatCollectionOutput(
+            collection=param_list
+        )
+
+
+EASING_FUNCTIONS_MAP = {
+    "Linear": LinearInOut,
+    "QuadIn": QuadEaseIn,
+    "QuadOut": QuadEaseOut,
+    "QuadInOut": QuadEaseInOut,
+    "CubicIn": CubicEaseIn,
+    "CubicOut": CubicEaseOut,
+    "CubicInOut": CubicEaseInOut,
+    "QuarticIn": QuarticEaseIn,
+    "QuarticOut": QuarticEaseOut,
+    "QuarticInOut": QuarticEaseInOut,
+    "QuinticIn": QuinticEaseIn,
+    "QuinticOut": QuinticEaseOut,
+    "QuinticInOut": QuinticEaseInOut,
+    "SineIn": SineEaseIn,
+    "SineOut": SineEaseOut,
+    "SineInOut": SineEaseInOut,
+    "CircularIn": CircularEaseIn,
+    "CircularOut": CircularEaseOut,
+    "CircularInOut": CircularEaseInOut,
+    "ExponentialIn": ExponentialEaseIn,
+    "ExponentialOut": ExponentialEaseOut,
+    "ExponentialInOut": ExponentialEaseInOut,
+    "ElasticIn": ElasticEaseIn,
+    "ElasticOut": ElasticEaseOut,
+    "ElasticInOut": ElasticEaseInOut,
+    "BackIn": BackEaseIn,
+    "BackOut": BackEaseOut,
+    "BackInOut": BackEaseInOut,
+    "BounceIn": BounceEaseIn,
+    "BounceOut": BounceEaseOut,
+    "BounceInOut": BounceEaseInOut,
+}
+
+EASING_FUNCTION_KEYS: Any = Literal[
+    tuple(list(EASING_FUNCTIONS_MAP.keys()))
+]
+
+
+# actually I think for now could just use CollectionOutput (which is list[Any]
+class StepParamEasingInvocation(BaseInvocation):
+    """Experimental per-step parameter easing for denoising steps"""
+
+    type: Literal["step_param_easing"] = "step_param_easing"
+
+    # Inputs
+    # fmt: off
+    easing: EASING_FUNCTION_KEYS = Field(default="Linear", description="The easing function to use")
+    num_steps: int = Field(default=20, description="number of denoising steps")
+    start_value: float = Field(default=0.0, description="easing starting value")
+    end_value: float = Field(default=1.0, description="easing ending value")
+    start_step_percent: float = Field(default=0.0, description="fraction of steps at which to start easing")
+    end_step_percent: float = Field(default=1.0, description="fraction of steps after which to end easing")
+    # if None, then start_value is used prior to easing start
+    pre_start_value: Optional[float] = Field(default=None, description="value before easing start")
+    # if None, then end value is used prior to easing end
+    post_end_value: Optional[float] = Field(default=None, description="value after easing end")
+    mirror: bool = Field(default=False, description="include mirror of easing function")
+    # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
+    # alt_mirror: bool = Field(default=False, description="alternative mirroring by dual easing")
+    show_easing_plot: bool = Field(default=False, description="show easing plot")
+    # fmt: on
+
+
+    def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
+        log_diagnostics = False
+        # convert from start_step_percent to nearest step <= (steps * start_step_percent)
+        # start_step = int(np.floor(self.num_steps * self.start_step_percent))
+        start_step = int(np.round(self.num_steps * self.start_step_percent))
+        # convert from end_step_percent to nearest step >= (steps * end_step_percent)
+        # end_step = int(np.ceil((self.num_steps - 1) * self.end_step_percent))
+        end_step = int(np.round((self.num_steps - 1) * self.end_step_percent))
+
+        # end_step = int(np.ceil(self.num_steps * self.end_step_percent))
+        num_easing_steps = end_step - start_step + 1
+
+        # num_presteps = max(start_step - 1, 0)
+        num_presteps = start_step
+        num_poststeps = self.num_steps - (num_presteps + num_easing_steps)
+        prelist = list(num_presteps * [self.pre_start_value])
+        postlist = list(num_poststeps * [self.post_end_value])
+
+        if log_diagnostics:
+            logger = InvokeAILogger.getLogger(name="StepParamEasing")
+            logger.debug("start_step: " + str(start_step))
+            logger.debug("end_step: " + str(end_step))
+            logger.debug("num_easing_steps: " + str(num_easing_steps))
+            logger.debug("num_presteps: " + str(num_presteps))
+            logger.debug("num_poststeps: " + str(num_poststeps))
+            logger.debug("prelist size: " + str(len(prelist)))
+            logger.debug("postlist size: " + str(len(postlist)))
+            logger.debug("prelist: " + str(prelist))
+            logger.debug("postlist: " + str(postlist))
+
+        easing_class = EASING_FUNCTIONS_MAP[self.easing]
+        if log_diagnostics:
+            logger.debug("easing class: " + str(easing_class))
+        easing_list = list()
+        if self.mirror:  # "expected" mirroring
+            # if number of steps is even, squeeze duration down to (number_of_steps)/2
+            # and create reverse copy of list to append
+            # if number of steps is odd, squeeze duration down to ceil(number_of_steps/2)
+            # and create reverse copy of list[1:end-1]
+            # but if even then number_of_steps/2 === ceil(number_of_steps/2), so can just use ceil always
+
+            base_easing_duration = int(np.ceil(num_easing_steps/2.0))
+            if log_diagnostics: logger.debug("base easing duration: " + str(base_easing_duration))
+            even_num_steps = (num_easing_steps % 2 == 0)  # even number of steps
+            easing_function = easing_class(start=self.start_value,
+                                           end=self.end_value,
+                                           duration=base_easing_duration - 1)
+            base_easing_vals = list()
+            for step_index in range(base_easing_duration):
+                easing_val = easing_function.ease(step_index)
+                base_easing_vals.append(easing_val)
+                if log_diagnostics:
+                    logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
+            if even_num_steps:
+                mirror_easing_vals = list(reversed(base_easing_vals))
+            else:
+                mirror_easing_vals = list(reversed(base_easing_vals[0:-1]))
+            if log_diagnostics:
+                logger.debug("base easing vals: " + str(base_easing_vals))
+                logger.debug("mirror easing vals: " + str(mirror_easing_vals))
+            easing_list = base_easing_vals + mirror_easing_vals
+
+        # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
+        # elif self.alt_mirror:  # function mirroring (unintuitive behavior (at least to me))
+        #     # half_ease_duration = round(num_easing_steps - 1 / 2)
+        #     half_ease_duration = round((num_easing_steps - 1) / 2)
+        #     easing_function = easing_class(start=self.start_value,
+        #                                    end=self.end_value,
+        #                                    duration=half_ease_duration,
+        #                                    )
+        #
+        #     mirror_function = easing_class(start=self.end_value,
+        #                                    end=self.start_value,
+        #                                    duration=half_ease_duration,
+        #                                    )
+        #     for step_index in range(num_easing_steps):
+        #         if step_index <= half_ease_duration:
+        #             step_val = easing_function.ease(step_index)
+        #         else:
+        #             step_val = mirror_function.ease(step_index - half_ease_duration)
+        #         easing_list.append(step_val)
+        #         if log_diagnostics: logger.debug(step_index, step_val)
+        #
+
+        else:  # no mirroring (default)
+            easing_function = easing_class(start=self.start_value,
+                                           end=self.end_value,
+                                           duration=num_easing_steps - 1)
+            for step_index in range(num_easing_steps):
+                step_val = easing_function.ease(step_index)
+                easing_list.append(step_val)
+                if log_diagnostics:
+                    logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
+
+        if log_diagnostics:
+            logger.debug("prelist size: " + str(len(prelist)))
+            logger.debug("easing_list size: " + str(len(easing_list)))
+            logger.debug("postlist size: " + str(len(postlist)))
+
+        param_list = prelist + easing_list + postlist
+
+        if self.show_easing_plot:
+            plt.figure()
+            plt.xlabel("Step")
+            plt.ylabel("Param Value")
+            plt.title("Per-Step Values Based On Easing: " + self.easing)
+            plt.bar(range(len(param_list)), param_list)
+            # plt.plot(param_list)
+            ax = plt.gca()
+            ax.xaxis.set_major_locator(MaxNLocator(integer=True))
+            buf = io.BytesIO()
+            plt.savefig(buf, format='png')
+            buf.seek(0)
+            im = PIL.Image.open(buf)
+            im.show()
+            buf.close()
+
+        # output array of size steps, each entry list[i] is param value for step i
+        return FloatCollectionOutput(
+            collection=param_list
+        )

invokeai/app/invocations/params.py

@@ -0,0 +1,28 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal
+from pydantic import Field
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
+from .math import IntOutput, FloatOutput
+
+# Pass-through parameter nodes - used by subgraphs
+
+class ParamIntInvocation(BaseInvocation):
+    """An integer parameter"""
+    #fmt: off
+    type: Literal["param_int"] = "param_int"
+    a: int = Field(default=0, description="The integer value")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a)
+
+class ParamFloatInvocation(BaseInvocation):
+    """A float parameter"""
+    #fmt: off
+    type: Literal["param_float"] = "param_float"
+    param: float = Field(default=0.0, description="The float value")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> FloatOutput:
+        return FloatOutput(param=self.param)

invokeai/app/invocations/prompt.py

@@ -0,0 +1,22 @@
+from typing import Literal
+
+from pydantic.fields import Field
+
+from .baseinvocation import BaseInvocationOutput
+
+
+class PromptOutput(BaseInvocationOutput):
+    """Base class for invocations that output a prompt"""
+    #fmt: off
+    type: Literal["prompt"] = "prompt"
+
+    prompt: str = Field(default=None, description="The output prompt")
+    #fmt: on
+
+    class Config:
+        schema_extra = {
+            'required': [
+                'type',
+                'prompt',
+            ]
+        }

invokeai/app/invocations/reconstruct.py

@@ -0,0 +1,60 @@
+from typing import Literal, Union
+
+from pydantic import Field
+
+from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
+
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput
+
+
+class RestoreFaceInvocation(BaseInvocation):
+    """Restores faces in an image."""
+
+    # fmt: off
+    type:  Literal["restore_face"] = "restore_face"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image")
+    strength:                float = Field(default=0.75, gt=0, le=1, description="The strength of the restoration"  )
+    # fmt: on
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["restoration", "image"],
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=None,
+            strength=self.strength,  # GFPGAN strength
+            save_original=False,
+            image_callback=None,
+        )
+
+        # Results are image and seed, unwrap for now
+        # TODO: can this return multiple results?
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/upscale.py

@@ -0,0 +1,62 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal, Union
+
+from pydantic import Field
+
+from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput
+
+
+class UpscaleInvocation(BaseInvocation):
+    """Upscales an image."""
+
+    # fmt: off
+    type: Literal["upscale"] = "upscale"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    strength: float = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2, 4] = Field(default=2, description="The upscale level")
+    # fmt: on
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["upscaling", "image"],
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=(self.level, self.strength),
+            strength=0.0,  # GFPGAN strength
+            save_original=False,
+            image_callback=None,
+        )
+
+        # Results are image and seed, unwrap for now
+        # TODO: can this return multiple results?
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/util/choose_model.py

@@ -0,0 +1,14 @@
+from invokeai.backend.model_management.model_manager import ModelManager
+
+
+def choose_model(model_manager: ModelManager, model_name: str):
+    """Returns the default model if the `model_name` not a valid model, else returns the selected model."""
+    logger = model_manager.logger
+    if model_name and not model_manager.valid_model(model_name):
+        default_model_name = model_manager.default_model()
+        logger.warning(f"\'{model_name}\' is not a valid model name. Using default model \'{default_model_name}\' instead.")
+        model = model_manager.get_model()
+    else:
+        model = model_manager.get_model(model_name)
+
+    return model

invokeai/app/models/exceptions.py

@@ -0,0 +1,3 @@
+class CanceledException(Exception):
+    """Execution canceled by user."""
+    pass

invokeai/app/models/image.py

@@ -0,0 +1,93 @@
+from enum import Enum
+from typing import Optional, Tuple
+from pydantic import BaseModel, Field
+
+from invokeai.app.util.metaenum import MetaEnum
+
+
+class ResourceOrigin(str, Enum, metaclass=MetaEnum):
+    """The origin of a resource (eg image).
+
+    - INTERNAL: The resource was created by the application.
+    - EXTERNAL: The resource was not created by the application.
+    This may be a user-initiated upload, or an internal application upload (eg Canvas init image).
+    """
+
+    INTERNAL = "internal"
+    """The resource was created by the application."""
+    EXTERNAL = "external"
+    """The resource was not created by the application.
+    This may be a user-initiated upload, or an internal application upload (eg Canvas init image).
+    """
+
+
+class InvalidOriginException(ValueError):
+    """Raised when a provided value is not a valid ResourceOrigin.
+
+    Subclasses `ValueError`.
+    """
+
+    def __init__(self, message="Invalid resource origin."):
+        super().__init__(message)
+
+
+class ImageCategory(str, Enum, metaclass=MetaEnum):
+    """The category of an image.
+
+    - GENERAL: The image is an output, init image, or otherwise an image without a specialized purpose.
+    - MASK: The image is a mask image.
+    - CONTROL: The image is a ControlNet control image.
+    - USER: The image is a user-provide image.
+    - OTHER: The image is some other type of image with a specialized purpose. To be used by external nodes.
+    """
+
+    GENERAL = "general"
+    """GENERAL: The image is an output, init image, or otherwise an image without a specialized purpose."""
+    MASK = "mask"
+    """MASK: The image is a mask image."""
+    CONTROL = "control"
+    """CONTROL: The image is a ControlNet control image."""
+    USER = "user"
+    """USER: The image is a user-provide image."""
+    OTHER = "other"
+    """OTHER: The image is some other type of image with a specialized purpose. To be used by external nodes."""
+
+
+class InvalidImageCategoryException(ValueError):
+    """Raised when a provided value is not a valid ImageCategory.
+
+    Subclasses `ValueError`.
+    """
+
+    def __init__(self, message="Invalid image category."):
+        super().__init__(message)
+
+
+class ImageField(BaseModel):
+    """An image field used for passing image objects between invocations"""
+
+    image_origin: ResourceOrigin = Field(
+        default=ResourceOrigin.INTERNAL, description="The type of the image"
+    )
+    image_name: Optional[str] = Field(default=None, description="The name of the image")
+
+    class Config:
+        schema_extra = {"required": ["image_origin", "image_name"]}
+
+
+class ColorField(BaseModel):
+    r: int = Field(ge=0, le=255, description="The red component")
+    g: int = Field(ge=0, le=255, description="The green component")
+    b: int = Field(ge=0, le=255, description="The blue component")
+    a: int = Field(ge=0, le=255, description="The alpha component")
+
+    def tuple(self) -> Tuple[int, int, int, int]:
+        return (self.r, self.g, self.b, self.a)
+
+
+class ProgressImage(BaseModel):
+    """The progress image sent intermittently during processing"""
+
+    width: int = Field(description="The effective width of the image in pixels")
+    height: int = Field(description="The effective height of the image in pixels")
+    dataURL: str = Field(description="The image data as a b64 data URL")

invokeai/app/models/metadata.py

@@ -0,0 +1,93 @@
+from typing import Optional, Union, List
+from pydantic import BaseModel, Extra, Field, StrictFloat, StrictInt, StrictStr
+
+
+class ImageMetadata(BaseModel):
+    """
+    Core generation metadata for an image/tensor generated in InvokeAI.
+
+    Also includes any metadata from the image's PNG tEXt chunks.
+
+    Generated by traversing the execution graph, collecting the parameters of the nearest ancestors
+    of a given node.
+
+    Full metadata may be accessed by querying for the session in the `graph_executions` table.
+    """
+
+    class Config:
+        extra = Extra.allow
+        """
+        This lets the ImageMetadata class accept arbitrary additional fields. The CoreMetadataService
+        won't add any fields that are not already defined, but other a different metadata service
+        implementation might.
+        """
+
+    type: Optional[StrictStr] = Field(
+        default=None,
+        description="The type of the ancestor node of the image output node.",
+    )
+    """The type of the ancestor node of the image output node."""
+    positive_conditioning: Optional[StrictStr] = Field(
+        default=None, description="The positive conditioning."
+    )
+    """The positive conditioning"""
+    negative_conditioning: Optional[StrictStr] = Field(
+        default=None, description="The negative conditioning."
+    )
+    """The negative conditioning"""
+    width: Optional[StrictInt] = Field(
+        default=None, description="Width of the image/latents in pixels."
+    )
+    """Width of the image/latents in pixels"""
+    height: Optional[StrictInt] = Field(
+        default=None, description="Height of the image/latents in pixels."
+    )
+    """Height of the image/latents in pixels"""
+    seed: Optional[StrictInt] = Field(
+        default=None, description="The seed used for noise generation."
+    )
+    """The seed used for noise generation"""
+    # cfg_scale: Optional[StrictFloat] = Field(
+    # cfg_scale: Union[float, list[float]] = Field(
+    cfg_scale: Union[StrictFloat, List[StrictFloat]] = Field(
+        default=None, description="The classifier-free guidance scale."
+    )
+    """The classifier-free guidance scale"""
+    steps: Optional[StrictInt] = Field(
+        default=None, description="The number of steps used for inference."
+    )
+    """The number of steps used for inference"""
+    scheduler: Optional[StrictStr] = Field(
+        default=None, description="The scheduler used for inference."
+    )
+    """The scheduler used for inference"""
+    model: Optional[StrictStr] = Field(
+        default=None, description="The model used for inference."
+    )
+    """The model used for inference"""
+    strength: Optional[StrictFloat] = Field(
+        default=None,
+        description="The strength used for image-to-image/latents-to-latents.",
+    )
+    """The strength used for image-to-image/latents-to-latents."""
+    latents: Optional[StrictStr] = Field(
+        default=None, description="The ID of the initial latents."
+    )
+    """The ID of the initial latents"""
+    vae: Optional[StrictStr] = Field(
+        default=None, description="The VAE used for decoding."
+    )
+    """The VAE used for decoding"""
+    unet: Optional[StrictStr] = Field(
+        default=None, description="The UNet used dor inference."
+    )
+    """The UNet used dor inference"""
+    clip: Optional[StrictStr] = Field(
+        default=None, description="The CLIP Encoder used for conditioning."
+    )
+    """The CLIP Encoder used for conditioning"""
+    extra: Optional[StrictStr] = Field(
+        default=None,
+        description="Uploaded image metadata, extracted from the PNG tEXt chunk.",
+    )
+    """Uploaded image metadata, extracted from the PNG tEXt chunk."""

invokeai/app/services/config.py

@@ -0,0 +1,581 @@
+# Copyright (c) 2023 Lincoln Stein (https://github.com/lstein) and the InvokeAI Development Team
+
+'''Invokeai configuration system.
+
+Arguments and fields are taken from the pydantic definition of the
+model.  Defaults can be set by creating a yaml configuration file that
+has a top-level key of "InvokeAI" and subheadings for each of the
+categories returned by `invokeai --help`. The file looks like this:
+
+[file: invokeai.yaml]
+
+InvokeAI:
+  Paths:
+    root: /home/lstein/invokeai-main
+    conf_path: configs/models.yaml
+    legacy_conf_dir: configs/stable-diffusion
+    outdir: outputs
+    embedding_dir: embeddings
+    lora_dir: loras
+    autoconvert_dir: null
+    gfpgan_model_dir: models/gfpgan/GFPGANv1.4.pth
+  Models:
+    model: stable-diffusion-1.5
+    embeddings: true
+  Memory/Performance:
+    xformers_enabled: false
+    sequential_guidance: false
+    precision: float16
+    max_loaded_models: 4
+    always_use_cpu: false
+    free_gpu_mem: false
+  Features:
+    nsfw_checker: true
+    restore: true
+    esrgan: true
+    patchmatch: true
+    internet_available: true
+    log_tokenization: false
+  Web Server:
+    host: 127.0.0.1
+    port: 8081
+    allow_origins: []
+    allow_credentials: true
+    allow_methods:
+    - '*'
+    allow_headers:
+    - '*'
+
+The default name of the configuration file is `invokeai.yaml`, located
+in INVOKEAI_ROOT. You can replace supersede this by providing any
+OmegaConf dictionary object initialization time:
+
+ omegaconf = OmegaConf.load('/tmp/init.yaml')
+ conf = InvokeAIAppConfig()
+ conf.parse_args(conf=omegaconf)
+
+InvokeAIAppConfig.parse_args() will parse the contents of `sys.argv`
+at initialization time. You may pass a list of strings in the optional
+`argv` argument to use instead of the system argv:
+
+ conf.parse_args(argv=['--xformers_enabled'])
+
+It is also possible to set a value at initialization time. However, if
+you call parse_args() it may be overwritten.
+
+ conf = InvokeAIAppConfig(xformers_enabled=True)
+ conf.parse_args(argv=['--no-xformers'])
+ conf.xformers_enabled
+ # False
+
+
+To avoid this, use `get_config()` to retrieve the application-wide
+configuration object. This will retain any properties set at object
+creation time:
+
+ conf = InvokeAIAppConfig.get_config(xformers_enabled=True)
+ conf.parse_args(argv=['--no-xformers'])
+ conf.xformers_enabled
+ # True
+
+Any setting can be overwritten by setting an environment variable of
+form: "INVOKEAI_<setting>", as in:
+
+  export INVOKEAI_port=8080
+
+Order of precedence (from highest):
+   1) initialization options
+   2) command line options
+   3) environment variable options
+   4) config file options
+   5) pydantic defaults
+
+Typical usage at the top level file:
+
+ from invokeai.app.services.config import InvokeAIAppConfig
+
+ # get global configuration and print its nsfw_checker value
+ conf = InvokeAIAppConfig.get_config()
+ conf.parse_args()
+ print(conf.nsfw_checker)
+
+Typical usage in a backend module:
+
+ from invokeai.app.services.config import InvokeAIAppConfig
+
+ # get global configuration and print its nsfw_checker value
+ conf = InvokeAIAppConfig.get_config()
+ print(conf.nsfw_checker)
+
+
+Computed properties:
+
+The InvokeAIAppConfig object has a series of properties that
+resolve paths relative to the runtime root directory. They each return
+a Path object:
+
+ root_path          - path to InvokeAI root
+ output_path        - path to default outputs directory
+ model_conf_path    - path to models.yaml
+ conf               - alias for the above
+ embedding_path     - path to the embeddings directory
+ lora_path          - path to the LoRA directory
+
+In most cases, you will want to create a single InvokeAIAppConfig
+object for the entire application. The InvokeAIAppConfig.get_config() function
+does this:
+
+  config = InvokeAIAppConfig.get_config()
+  config.parse_args()   # read values from the command line/config file
+  print(config.root)
+
+# Subclassing
+
+If you wish to create a similar class, please subclass the
+`InvokeAISettings` class and define a Literal field named "type",
+which is set to the desired top-level name.  For example, to create a
+"InvokeBatch" configuration, define like this:
+
+  class InvokeBatch(InvokeAISettings):
+     type: Literal["InvokeBatch"] = "InvokeBatch"
+     node_count : int = Field(default=1, description="Number of nodes to run on", category='Resources')
+     cpu_count  : int = Field(default=8, description="Number of GPUs to run on per node", category='Resources')
+
+This will now read and write from the "InvokeBatch" section of the
+config file, look for environment variables named INVOKEBATCH_*, and
+accept the command-line arguments `--node_count` and `--cpu_count`. The
+two configs are kept in separate sections of the config file:
+
+  # invokeai.yaml
+
+  InvokeBatch:
+     Resources:
+        node_count: 1
+        cpu_count: 8
+
+  InvokeAI:
+     Paths:
+        root: /home/lstein/invokeai-main
+        conf_path: configs/models.yaml
+        legacy_conf_dir: configs/stable-diffusion
+        outdir: outputs
+     ...
+
+'''
+from __future__ import annotations
+import argparse
+import pydoc
+import os
+import sys
+from argparse import ArgumentParser
+from omegaconf import OmegaConf, DictConfig
+from pathlib import Path
+from pydantic import BaseSettings, Field, parse_obj_as
+from typing import ClassVar, Dict, List, Literal, Type, Union, get_origin, get_type_hints, get_args
+
+INIT_FILE = Path('invokeai.yaml')
+DB_FILE   = Path('invokeai.db')
+LEGACY_INIT_FILE = Path('invokeai.init')
+
+class InvokeAISettings(BaseSettings):
+    '''
+    Runtime configuration settings in which default values are
+    read from an omegaconf .yaml file.
+    '''
+    initconf             : ClassVar[DictConfig] = None
+    argparse_groups      : ClassVar[Dict] = {}
+
+    def parse_args(self, argv: list=sys.argv[1:]):
+        parser = self.get_parser()
+        opt = parser.parse_args(argv)
+        for name in self.__fields__:
+            if name not in self._excluded():
+                setattr(self, name, getattr(opt,name))
+
+    def to_yaml(self)->str:
+        """
+        Return a YAML string representing our settings. This can be used
+        as the contents of `invokeai.yaml` to restore settings later.
+        """
+        cls = self.__class__
+        type = get_args(get_type_hints(cls)['type'])[0]
+        field_dict = dict({type:dict()})
+        for name,field in self.__fields__.items():
+            if name in cls._excluded():
+                continue
+            category = field.field_info.extra.get("category") or "Uncategorized"
+            value = getattr(self,name)
+            if category not in field_dict[type]:
+                field_dict[type][category] = dict()
+            # keep paths as strings to make it easier to read
+            field_dict[type][category][name] = str(value) if isinstance(value,Path) else value
+        conf = OmegaConf.create(field_dict)
+        return OmegaConf.to_yaml(conf)
+
+    @classmethod
+    def add_parser_arguments(cls, parser):
+        if 'type' in get_type_hints(cls):
+            settings_stanza = get_args(get_type_hints(cls)['type'])[0]
+        else:
+            settings_stanza = "Uncategorized"
+
+        env_prefix = cls.Config.env_prefix if hasattr(cls.Config,'env_prefix') else settings_stanza.upper()
+
+        initconf = cls.initconf.get(settings_stanza) \
+            if cls.initconf and settings_stanza in cls.initconf \
+               else OmegaConf.create()
+
+        # create an upcase version of the environment in
+        # order to achieve case-insensitive environment
+        # variables (the way Windows does)
+        upcase_environ = dict()
+        for key,value in os.environ.items():
+            upcase_environ[key.upper()] = value
+        
+        fields = cls.__fields__
+        cls.argparse_groups = {}
+        
+        for name, field in fields.items():
+            if name not in cls._excluded():
+                current_default = field.default
+
+                category = field.field_info.extra.get("category","Uncategorized")
+                env_name = env_prefix + '_' + name
+                if category in initconf and name in initconf.get(category):
+                    field.default = initconf.get(category).get(name)
+                if env_name.upper() in upcase_environ:
+                    field.default = upcase_environ[env_name.upper()]
+                cls.add_field_argument(parser, name, field)
+
+                field.default = current_default
+
+    @classmethod
+    def cmd_name(self, command_field: str='type')->str:
+        hints = get_type_hints(self)
+        if command_field in hints:
+            return get_args(hints[command_field])[0]
+        else:
+            return 'Uncategorized'
+
+    @classmethod
+    def get_parser(cls)->ArgumentParser:
+        parser = PagingArgumentParser(
+            prog=cls.cmd_name(),
+            description=cls.__doc__,
+        )
+        cls.add_parser_arguments(parser)
+        return parser
+
+    @classmethod
+    def add_subparser(cls, parser: argparse.ArgumentParser):
+        parser.add_parser(cls.cmd_name(), help=cls.__doc__)
+
+    @classmethod
+    def _excluded(self)->List[str]:
+        return ['type','initconf']
+
+    class Config:
+        env_file_encoding = 'utf-8'
+        arbitrary_types_allowed = True
+        case_sensitive = True
+
+    @classmethod
+    def add_field_argument(cls, command_parser, name: str, field, default_override = None):
+        field_type = get_type_hints(cls).get(name)
+        default = default_override if default_override is not None else field.default if field.default_factory is None else field.default_factory()
+        if category := field.field_info.extra.get("category"):
+            if category not in cls.argparse_groups:
+                cls.argparse_groups[category] = command_parser.add_argument_group(category)
+            argparse_group = cls.argparse_groups[category]
+        else:
+            argparse_group = command_parser
+
+        if get_origin(field_type) == Literal:
+            allowed_values = get_args(field.type_)
+            allowed_types = set()
+            for val in allowed_values:
+                allowed_types.add(type(val))
+            allowed_types_list = list(allowed_types)
+            field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
+
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field_type,
+                default=default,
+                choices=allowed_values,
+                help=field.field_info.description,
+            )
+
+        elif get_origin(field_type) == list:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                nargs='*',
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
+                help=field.field_info.description,
+            )
+        else:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
+                help=field.field_info.description,
+            )
+def _find_root()->Path:
+    if os.environ.get("INVOKEAI_ROOT"):
+        root = Path(os.environ.get("INVOKEAI_ROOT")).resolve()
+    elif (
+            os.environ.get("VIRTUAL_ENV")
+            and (Path(os.environ.get("VIRTUAL_ENV"), "..", INIT_FILE).exists()
+                 or
+                 Path(os.environ.get("VIRTUAL_ENV"), "..", LEGACY_INIT_FILE).exists()
+                 )
+    ):
+        root = Path(os.environ.get("VIRTUAL_ENV"), "..").resolve()
+    else:
+        root = Path("~/invokeai").expanduser().resolve()
+    return root
+
+class InvokeAIAppConfig(InvokeAISettings):
+    '''
+Generate images using Stable Diffusion. Use "invokeai" to launch
+the command-line client (recommended for experts only), or
+"invokeai-web" to launch the web server. Global options
+can be changed by editing the file "INVOKEAI_ROOT/invokeai.yaml" or by
+setting environment variables INVOKEAI_<setting>.
+     '''
+    singleton_config: ClassVar[InvokeAIAppConfig] = None
+    singleton_init: ClassVar[Dict] = None
+    
+    #fmt: off
+    type: Literal["InvokeAI"] = "InvokeAI"
+    host                : str = Field(default="127.0.0.1", description="IP address to bind to", category='Web Server')
+    port                : int = Field(default=9090, description="Port to bind to", category='Web Server')
+    allow_origins       : List[str] = Field(default=[], description="Allowed CORS origins", category='Web Server')
+    allow_credentials   : bool = Field(default=True, description="Allow CORS credentials", category='Web Server')
+    allow_methods       : List[str] = Field(default=["*"], description="Methods allowed for CORS", category='Web Server')
+    allow_headers       : List[str] = Field(default=["*"], description="Headers allowed for CORS", category='Web Server')
+
+    esrgan              : bool = Field(default=True, description="Enable/disable upscaling code", category='Features')
+    internet_available  : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", category='Features')
+    log_tokenization    : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", category='Features')
+    nsfw_checker        : bool = Field(default=True, description="Enable/disable the NSFW checker", category='Features')
+    patchmatch          : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", category='Features')
+    restore             : bool = Field(default=True, description="Enable/disable face restoration code", category='Features')
+
+    always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
+    free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
+    max_loaded_models   : int = Field(default=2, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
+    precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
+    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
+    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
+
+
+    root                : Path = Field(default=_find_root(), description='InvokeAI runtime root directory', category='Paths')
+    autoconvert_dir     : Path = Field(default=None, description='Path to a directory of ckpt files to be converted into diffusers and imported on startup.', category='Paths')
+    conf_path           : Path = Field(default='configs/models.yaml', description='Path to models definition file', category='Paths')
+    embedding_dir       : Path = Field(default='embeddings', description='Path to InvokeAI textual inversion aembeddings directory', category='Paths')
+    gfpgan_model_dir    : Path = Field(default="./models/gfpgan/GFPGANv1.4.pth", description='Path to GFPGAN models directory.', category='Paths')
+    controlnet_dir      : Path = Field(default="controlnets", description='Path to directory of ControlNet models.', category='Paths')
+    legacy_conf_dir     : Path = Field(default='configs/stable-diffusion', description='Path to directory of legacy checkpoint config files', category='Paths')
+    lora_dir            : Path = Field(default='loras', description='Path to InvokeAI LoRA model directory', category='Paths')
+    db_dir              : Path = Field(default='databases', description='Path to InvokeAI databases directory', category='Paths')
+    outdir              : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
+    from_file           : Path = Field(default=None, description='Take command input from the indicated file (command-line client only)', category='Paths')
+    use_memory_db       : bool = Field(default=False, description='Use in-memory database for storing image metadata', category='Paths')
+
+    model               : str = Field(default='stable-diffusion-1.5', description='Initial model name', category='Models')
+    embeddings          : bool = Field(default=True, description='Load contents of embeddings directory', category='Models')
+
+    log_handlers        : List[str] = Field(default=["console"], description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>"', category="Logging")
+    # note - would be better to read the log_format values from logging.py, but this creates circular dependencies issues
+    log_format          : Literal[tuple(['plain','color','syslog','legacy'])] = Field(default="color", description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style', category="Logging")
+    log_level           : Literal[tuple(["debug","info","warning","error","critical"])] = Field(default="debug", description="Emit logging messages at this level or  higher", category="Logging")
+    #fmt: on
+
+    def parse_args(self, argv: List[str]=None, conf: DictConfig = None, clobber=False):
+        '''
+        Update settings with contents of init file, environment, and 
+        command-line settings.
+        :param conf: alternate Omegaconf dictionary object
+        :param argv: aternate sys.argv list
+        :param clobber: ovewrite any initialization parameters passed during initialization
+        '''
+        # Set the runtime root directory. We parse command-line switches here
+        # in order to pick up the --root_dir option.
+        super().parse_args(argv)
+        if conf is None:
+            try:
+                conf = OmegaConf.load(self.root_dir / INIT_FILE)
+            except:
+                pass
+        InvokeAISettings.initconf = conf
+        
+        # parse args again in order to pick up settings in configuration file
+        super().parse_args(argv)
+
+        if self.singleton_init and not clobber:
+            hints = get_type_hints(self.__class__)
+            for k in self.singleton_init:
+                setattr(self,k,parse_obj_as(hints[k],self.singleton_init[k]))
+
+    @classmethod
+    def get_config(cls,**kwargs)->InvokeAIAppConfig:
+        '''
+        This returns a singleton InvokeAIAppConfig configuration object.
+        '''
+        if cls.singleton_config is None \
+           or type(cls.singleton_config)!=cls \
+           or (kwargs and cls.singleton_init != kwargs):
+            cls.singleton_config = cls(**kwargs)
+            cls.singleton_init = kwargs
+        return cls.singleton_config
+        
+    @property
+    def root_path(self)->Path:
+        '''
+        Path to the runtime root directory
+        '''
+        if self.root:
+            return Path(self.root).expanduser()
+        else:
+            return self.find_root()
+
+    @property
+    def root_dir(self)->Path:
+        '''
+        Alias for above.
+        '''
+        return self.root_path
+
+    def _resolve(self,partial_path:Path)->Path:
+        return (self.root_path / partial_path).resolve()
+
+    @property
+    def init_file_path(self)->Path:
+        '''
+        Path to invokeai.yaml
+        '''
+        return self._resolve(INIT_FILE)
+
+    @property
+    def output_path(self)->Path:
+        '''
+        Path to defaults outputs directory.
+        '''
+        return self._resolve(self.outdir)
+
+    @property
+    def db_path(self)->Path:
+        '''
+        Path to the invokeai.db file.
+        '''
+        return self._resolve(self.db_dir) / DB_FILE
+
+    @property
+    def model_conf_path(self)->Path:
+        '''
+        Path to models configuration file.
+        '''
+        return self._resolve(self.conf_path)
+
+    @property
+    def legacy_conf_path(self)->Path:
+        '''
+        Path to directory of legacy configuration files (e.g. v1-inference.yaml)
+        '''
+        return self._resolve(self.legacy_conf_dir)
+
+    @property
+    def cache_dir(self)->Path:
+        '''
+        Path to the global cache directory for HuggingFace hub-managed models
+        '''
+        return self.models_dir / "hub"
+
+    @property
+    def models_dir(self)->Path:
+        '''
+        Path to the models directory
+        '''
+        return self._resolve("models")
+
+    @property
+    def embedding_path(self)->Path:
+        '''
+        Path to the textual inversion embeddings directory.
+        '''
+        return self._resolve(self.embedding_dir) if self.embedding_dir else None
+
+    @property
+    def lora_path(self)->Path:
+        '''
+        Path to the LoRA models directory.
+        '''
+        return self._resolve(self.lora_dir) if self.lora_dir else None
+
+    @property
+    def controlnet_path(self)->Path:
+        '''
+        Path to the controlnet models directory.
+        '''
+        return self._resolve(self.controlnet_dir) if self.controlnet_dir else None
+
+    @property
+    def autoconvert_path(self)->Path:
+        '''
+        Path to the directory containing models to be imported automatically at startup.
+        '''
+        return self._resolve(self.autoconvert_dir) if self.autoconvert_dir else None
+
+    @property
+    def gfpgan_model_path(self)->Path:
+        '''
+        Path to the GFPGAN model.
+        '''
+        return self._resolve(self.gfpgan_model_dir) if self.gfpgan_model_dir else None
+
+    # the following methods support legacy calls leftover from the Globals era
+    @property
+    def full_precision(self)->bool:
+        """Return true if precision set to float32"""
+        return self.precision=='float32'
+
+    @property
+    def disable_xformers(self)->bool:
+        """Return true if xformers_enabled is false"""
+        return not self.xformers_enabled
+
+    @property
+    def try_patchmatch(self)->bool:
+        """Return true if patchmatch true"""
+        return self.patchmatch
+
+    @staticmethod
+    def find_root()->Path:
+        '''
+        Choose the runtime root directory when not specified on command line or
+        init file.
+        '''
+        return _find_root()
+
+
+class PagingArgumentParser(argparse.ArgumentParser):
+    '''
+    A custom ArgumentParser that uses pydoc to page its output.
+    It also supports reading defaults from an init file.
+    '''
+    def print_help(self, file=None):
+        text = self.format_help()
+        pydoc.pager(text)
+
+def get_invokeai_config(**kwargs)->InvokeAIAppConfig:
+    '''
+    Legacy function which returns InvokeAIAppConfig.get_config()
+    '''
+    return InvokeAIAppConfig.get_config(**kwargs)

invokeai/app/services/default_graphs.py

@@ -0,0 +1,64 @@
+from ..invocations.latent import LatentsToImageInvocation, NoiseInvocation, TextToLatentsInvocation
+from ..invocations.compel import CompelInvocation
+from ..invocations.params import ParamIntInvocation
+from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph
+from .item_storage import ItemStorageABC
+
+
+default_text_to_image_graph_id = '539b2af5-2b4d-4d8c-8071-e54a3255fc74'
+
+
+def create_text_to_image() -> LibraryGraph:
+    return LibraryGraph(
+        id=default_text_to_image_graph_id,
+        name='t2i',
+        description='Converts text to an image',
+        graph=Graph(
+            nodes={
+                'width': ParamIntInvocation(id='width', a=512),
+                'height': ParamIntInvocation(id='height', a=512),
+                'seed': ParamIntInvocation(id='seed', a=-1),
+                '3': NoiseInvocation(id='3'),
+                '4': CompelInvocation(id='4'),
+                '5': CompelInvocation(id='5'),
+                '6': TextToLatentsInvocation(id='6'),
+                '7': LatentsToImageInvocation(id='7'),
+            },
+            edges=[
+                Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='3', field='width')),
+                Edge(source=EdgeConnection(node_id='height', field='a'), destination=EdgeConnection(node_id='3', field='height')),
+                Edge(source=EdgeConnection(node_id='seed', field='a'), destination=EdgeConnection(node_id='3', field='seed')),
+                Edge(source=EdgeConnection(node_id='3', field='noise'), destination=EdgeConnection(node_id='6', field='noise')),
+                Edge(source=EdgeConnection(node_id='6', field='latents'), destination=EdgeConnection(node_id='7', field='latents')),
+                Edge(source=EdgeConnection(node_id='4', field='conditioning'), destination=EdgeConnection(node_id='6', field='positive_conditioning')),
+                Edge(source=EdgeConnection(node_id='5', field='conditioning'), destination=EdgeConnection(node_id='6', field='negative_conditioning')),
+            ]
+        ),
+        exposed_inputs=[
+            ExposedNodeInput(node_path='4', field='prompt', alias='positive_prompt'),
+            ExposedNodeInput(node_path='5', field='prompt', alias='negative_prompt'),
+            ExposedNodeInput(node_path='width', field='a', alias='width'),
+            ExposedNodeInput(node_path='height', field='a', alias='height'),
+            ExposedNodeInput(node_path='seed', field='a', alias='seed'),
+        ],
+        exposed_outputs=[
+            ExposedNodeOutput(node_path='7', field='image', alias='image')
+        ])
+
+
+def create_system_graphs(graph_library: ItemStorageABC[LibraryGraph]) -> list[LibraryGraph]:
+    """Creates the default system graphs, or adds new versions if the old ones don't match"""
+    
+    # TODO: Uncomment this when we are ready to fix this up to prevent breaking changes
+    graphs: list[LibraryGraph] = list()
+
+    # text_to_image = graph_library.get(default_text_to_image_graph_id)
+    
+    # # TODO: Check if the graph is the same as the default one, and if not, update it
+    # #if text_to_image is None:
+    text_to_image = create_text_to_image()
+    graph_library.set(text_to_image)
+
+    graphs.append(text_to_image)
+
+    return graphs

invokeai/app/services/events.py

@@ -0,0 +1,103 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Any
+from invokeai.app.models.image import ProgressImage
+from invokeai.app.util.misc import get_timestamp
+
+
+class EventServiceBase:
+    session_event: str = "session_event"
+
+    """Basic event bus, to have an empty stand-in when not needed"""
+
+    def dispatch(self, event_name: str, payload: Any) -> None:
+        pass
+
+    def __emit_session_event(self, event_name: str, payload: dict) -> None:
+        payload["timestamp"] = get_timestamp()
+        self.dispatch(
+            event_name=EventServiceBase.session_event,
+            payload=dict(event=event_name, data=payload),
+        )
+
+    # Define events here for every event in the system.
+    # This will make them easier to integrate until we find a schema generator.
+    def emit_generator_progress(
+        self,
+        graph_execution_state_id: str,
+        node: dict,
+        source_node_id: str,
+        progress_image: ProgressImage | None,
+        step: int,
+        total_steps: int,
+    ) -> None:
+        """Emitted when there is generation progress"""
+        self.__emit_session_event(
+            event_name="generator_progress",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+                progress_image=progress_image.dict() if progress_image is not None else None,
+                step=step,
+                total_steps=total_steps,
+            ),
+        )
+
+    def emit_invocation_complete(
+        self,
+        graph_execution_state_id: str,
+        result: dict,
+        node: dict,
+        source_node_id: str,
+    ) -> None:
+        """Emitted when an invocation has completed"""
+        self.__emit_session_event(
+            event_name="invocation_complete",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+                result=result,
+            ),
+        )
+
+    def emit_invocation_error(
+        self,
+        graph_execution_state_id: str,
+        node: dict,
+        source_node_id: str,
+        error: str,
+    ) -> None:
+        """Emitted when an invocation has completed"""
+        self.__emit_session_event(
+            event_name="invocation_error",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+                error=error,
+            ),
+        )
+
+    def emit_invocation_started(
+        self, graph_execution_state_id: str, node: dict, source_node_id: str
+    ) -> None:
+        """Emitted when an invocation has started"""
+        self.__emit_session_event(
+            event_name="invocation_started",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+            ),
+        )
+
+    def emit_graph_execution_complete(self, graph_execution_state_id: str) -> None:
+        """Emitted when a session has completed all invocations"""
+        self.__emit_session_event(
+            event_name="graph_execution_state_complete",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+            ),
+        )

invokeai/app/services/image_file_storage.py

@@ -0,0 +1,204 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+import os
+from abc import ABC, abstractmethod
+from pathlib import Path
+from queue import Queue
+from typing import Dict, Optional
+
+from PIL.Image import Image as PILImageType
+from PIL import Image, PngImagePlugin
+from send2trash import send2trash
+
+from invokeai.app.models.image import ResourceOrigin
+from invokeai.app.models.metadata import ImageMetadata
+from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
+
+
+# TODO: Should these excpetions subclass existing python exceptions?
+class ImageFileNotFoundException(Exception):
+    """Raised when an image file is not found in storage."""
+
+    def __init__(self, message="Image file not found"):
+        super().__init__(message)
+
+
+class ImageFileSaveException(Exception):
+    """Raised when an image cannot be saved."""
+
+    def __init__(self, message="Image file not saved"):
+        super().__init__(message)
+
+
+class ImageFileDeleteException(Exception):
+    """Raised when an image cannot be deleted."""
+
+    def __init__(self, message="Image file not deleted"):
+        super().__init__(message)
+
+
+class ImageFileStorageBase(ABC):
+    """Low-level service responsible for storing and retrieving image files."""
+
+    @abstractmethod
+    def get(self, image_origin: ResourceOrigin, image_name: str) -> PILImageType:
+        """Retrieves an image as PIL Image."""
+        pass
+
+    @abstractmethod
+    def get_path(
+        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
+    ) -> str:
+        """Gets the internal path to an image or thumbnail."""
+        pass
+
+    # TODO: We need to validate paths before starlette makes the FileResponse, else we get a
+    # 500 internal server error. I don't like having this method on the service.
+    @abstractmethod
+    def validate_path(self, path: str) -> bool:
+        """Validates the path given for an image or thumbnail."""
+        pass
+
+    @abstractmethod
+    def save(
+        self,
+        image: PILImageType,
+        image_origin: ResourceOrigin,
+        image_name: str,
+        metadata: Optional[ImageMetadata] = None,
+        thumbnail_size: int = 256,
+    ) -> None:
+        """Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image name, thumbnail name, and created timestamp."""
+        pass
+
+    @abstractmethod
+    def delete(self, image_origin: ResourceOrigin, image_name: str) -> None:
+        """Deletes an image and its thumbnail (if one exists)."""
+        pass
+
+
+class DiskImageFileStorage(ImageFileStorageBase):
+    """Stores images on disk"""
+
+    __output_folder: str
+    __cache_ids: Queue  # TODO: this is an incredibly naive cache
+    __cache: Dict[str, PILImageType]
+    __max_cache_size: int
+
+    def __init__(self, output_folder: str):
+        self.__output_folder = output_folder
+        self.__cache = dict()
+        self.__cache_ids = Queue()
+        self.__max_cache_size = 10  # TODO: get this from config
+
+        Path(output_folder).mkdir(parents=True, exist_ok=True)
+
+        # TODO: don't hard-code. get/save/delete should maybe take subpath?
+        for image_origin in ResourceOrigin:
+            Path(os.path.join(output_folder, image_origin)).mkdir(
+                parents=True, exist_ok=True
+            )
+            Path(os.path.join(output_folder, image_origin, "thumbnails")).mkdir(
+                parents=True, exist_ok=True
+            )
+
+    def get(self, image_origin: ResourceOrigin, image_name: str) -> PILImageType:
+        try:
+            image_path = self.get_path(image_origin, image_name)
+            cache_item = self.__get_cache(image_path)
+            if cache_item:
+                return cache_item
+
+            image = Image.open(image_path)
+            self.__set_cache(image_path, image)
+            return image
+        except FileNotFoundError as e:
+            raise ImageFileNotFoundException from e
+
+    def save(
+        self,
+        image: PILImageType,
+        image_origin: ResourceOrigin,
+        image_name: str,
+        metadata: Optional[ImageMetadata] = None,
+        thumbnail_size: int = 256,
+    ) -> None:
+        try:
+            image_path = self.get_path(image_origin, image_name)
+
+            if metadata is not None:
+                pnginfo = PngImagePlugin.PngInfo()
+                pnginfo.add_text("invokeai", metadata.json())
+                image.save(image_path, "PNG", pnginfo=pnginfo)
+            else:
+                image.save(image_path, "PNG")
+
+            thumbnail_name = get_thumbnail_name(image_name)
+            thumbnail_path = self.get_path(image_origin, thumbnail_name, thumbnail=True)
+            thumbnail_image = make_thumbnail(image, thumbnail_size)
+            thumbnail_image.save(thumbnail_path)
+
+            self.__set_cache(image_path, image)
+            self.__set_cache(thumbnail_path, thumbnail_image)
+        except Exception as e:
+            raise ImageFileSaveException from e
+
+    def delete(self, image_origin: ResourceOrigin, image_name: str) -> None:
+        try:
+            basename = os.path.basename(image_name)
+            image_path = self.get_path(image_origin, basename)
+
+            if os.path.exists(image_path):
+                send2trash(image_path)
+            if image_path in self.__cache:
+                del self.__cache[image_path]
+
+            thumbnail_name = get_thumbnail_name(image_name)
+            thumbnail_path = self.get_path(image_origin, thumbnail_name, True)
+
+            if os.path.exists(thumbnail_path):
+                send2trash(thumbnail_path)
+            if thumbnail_path in self.__cache:
+                del self.__cache[thumbnail_path]
+        except Exception as e:
+            raise ImageFileDeleteException from e
+
+    # TODO: make this a bit more flexible for e.g. cloud storage
+    def get_path(
+        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
+    ) -> str:
+        # strip out any relative path shenanigans
+        basename = os.path.basename(image_name)
+
+        if thumbnail:
+            thumbnail_name = get_thumbnail_name(basename)
+            path = os.path.join(
+                self.__output_folder, image_origin, "thumbnails", thumbnail_name
+            )
+        else:
+            path = os.path.join(self.__output_folder, image_origin, basename)
+
+        abspath = os.path.abspath(path)
+
+        return abspath
+
+    def validate_path(self, path: str) -> bool:
+        """Validates the path given for an image or thumbnail."""
+        try:
+            os.stat(path)
+            return True
+        except:
+            return False
+
+    def __get_cache(self, image_name: str) -> PILImageType | None:
+        return None if image_name not in self.__cache else self.__cache[image_name]
+
+    def __set_cache(self, image_name: str, image: PILImageType):
+        if not image_name in self.__cache:
+            self.__cache[image_name] = image
+            self.__cache_ids.put(
+                image_name
+            )  # TODO: this should refresh position for LRU cache
+            if len(self.__cache) > self.__max_cache_size:
+                cache_id = self.__cache_ids.get()
+                if cache_id in self.__cache:
+                    del self.__cache[cache_id]