Update model_sym_links to indicate it requires admin/developer mode in windows

## What type of PR is this? (check all applicable)

- [ ] Refactor
- [X] Feature
- [ ] Bug Fix
- [ ] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission


## Have you discussed this change with the InvokeAI team?
- [X] Yes
- [ ] No, because:

      
## Have you updated all relevant documentation?
- [ ] Yes
- [ ] No


## Description


## Related Tickets & Documents

<!--
For pull requests that relate or close an issue, please include them
below. 

For example having the text: "closes #1234" would connect the current
pull
request to issue 1234.  And when we merge the pull request, Github will
automatically close the issue.
-->

- Related Issue #
- Closes #

## QA Instructions, Screenshots, Recordings

<!-- 
Please provide steps on how to test changes, any hardware or 
software specifications as well as any other pertinent information. 
-->

## Merge Plan

<!--
A merge plan describes how this PR should be handled after it is
approved.

Example merge plans:
- "This PR can be merged when approved"
- "This must be squash-merged when approved"
- "DO NOT MERGE - I will rebase and tidy commits before merging"
- "#dev-chat on discord needs to be advised of this change when it is
merged"

A merge plan is particularly important for large PRs or PRs that touch
the
database in any way.
-->

## Added/updated tests?

- [ ] Yes
- [ ] No : _please replace this line with details on why tests
      have not been included_

## [optional] Are there any post deployment tasks we need to perform?

.github/CODEOWNERS

@@ -1,5 +1,5 @@
 # continuous integration
-/.github/workflows/  @lstein @blessedcoolant @hipsterusername
+/.github/workflows/  @lstein @blessedcoolant @hipsterusername @ebr
 
 # documentation
 /docs/ @lstein @blessedcoolant @hipsterusername @Millu
@@ -10,7 +10,7 @@
 
 # installation and configuration
 /pyproject.toml  @lstein @blessedcoolant @hipsterusername
-/docker/  @lstein @blessedcoolant @hipsterusername
+/docker/  @lstein @blessedcoolant @hipsterusername @ebr
 /scripts/ @ebr @lstein @hipsterusername
 /installer/ @lstein @ebr @hipsterusername
 /invokeai/assets @lstein @ebr @hipsterusername
@@ -26,9 +26,7 @@
 
 # front ends
 /invokeai/frontend/CLI @lstein @hipsterusername
-/invokeai/frontend/install @lstein @ebr @hipsterusername 
+/invokeai/frontend/install @lstein @ebr @hipsterusername
 /invokeai/frontend/merge @lstein @blessedcoolant @hipsterusername
 /invokeai/frontend/training @lstein @blessedcoolant @hipsterusername
 /invokeai/frontend/web @psychedelicious @blessedcoolant @maryhipp @hipsterusername
-
-

.github/ISSUE_TEMPLATE/BUG_REPORT.yml

@@ -6,10 +6,6 @@ title: '[bug]: '
 
 labels: ['bug']
 
-# assignees:
-#   - moderator_bot
-#   - lstein
-
 body:
   - type: markdown
     attributes:
@@ -18,10 +14,9 @@ body:
 
   - type: checkboxes
     attributes:
-      label: Is there an existing issue for this?
+      label: Is there an existing issue for this problem?
       description: |
-        Please use the [search function](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
-        irst to see if an issue already exists for the bug you encountered.
+        Please [search](https://github.com/invoke-ai/InvokeAI/issues) first to see if an issue already exists for the problem.
       options:
         - label: I have searched the existing issues
           required: true
@@ -33,80 +28,119 @@ body:
   - type: dropdown
     id: os_dropdown
     attributes:
-      label: OS
-      description: Which operating System did you use when the bug occured
+      label: Operating system
+      description: Your computer's operating system.
       multiple: false
       options:
         - 'Linux'
         - 'Windows'
         - 'macOS'
+        - 'other'
     validations:
       required: true
 
   - type: dropdown
     id: gpu_dropdown
     attributes:
-      label: GPU
-      description: Which kind of Graphic-Adapter is your System using
+      label: GPU vendor
+      description: Your GPU's vendor.
       multiple: false
       options:
-        - 'cuda'
-        - 'amd'
-        - 'mps'
-        - 'cpu'
+        - 'Nvidia (CUDA)'
+        - 'AMD (ROCm)'
+        - 'Apple Silicon (MPS)'
+        - 'None (CPU)'
     validations:
       required: true
 
+  - type: input
+    id: gpu_model
+    attributes:
+      label: GPU model
+      description: Your GPU's model. If on Apple Silicon, this is your Mac's chip. Leave blank if on CPU.
+      placeholder: ex. RTX 2080 Ti, Mac M1 Pro
+    validations:
+      required: false
+
   - type: input
     id: vram
     attributes:
-      label: VRAM
-      description: Size of the VRAM if known
+      label: GPU VRAM
+      description: Your GPU's VRAM. If on Apple Silicon, this is your Mac's unified memory. Leave blank if on CPU.
       placeholder: 8GB
     validations:
       required: false
-      
+
   - type: input
     id: version-number
     attributes:
-      label: What version did you experience this issue on?
+      label: Version number
       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
+        The version of Invoke you have installed. If it is not the latest version, please update and try again to confirm the issue still exists. If you are testing main, please include the commit hash instead.
+      placeholder: ex. 3.6.1
     validations:
       required: true
 
+  - type: input
+    id: browser-version
+    attributes:
+      label: Browser
+      description: Your web browser and version.
+      placeholder: ex. Firefox 123.0b3
+    validations:
+      required: true
+
+  - type: textarea
+    id: python-deps
+    attributes:
+      label: Python dependencies
+      description: |
+        If the problem occurred during image generation, click the gear icon at the bottom left corner, click "About", click the copy button and then paste here.
+    validations:
+      required: false
+
   - type: textarea
     id: what-happened
     attributes:
-      label: What happened?
+      label: What happened
       description: |
-        Briefly describe what happened, what you expected to happen and how to reproduce this bug.
-      placeholder: When using the webinterface and right-clicking on button X instead of the popup-menu there error Y appears
+        Describe what happened. Include any relevant error messages, stack traces and screenshots here.
+      placeholder: I clicked button X and then Y happened.
     validations:
       required: true
 
   - type: textarea
+    id: what-you-expected
     attributes:
-      label: Screenshots
-      description: If applicable, add screenshots to help explain your problem
-      placeholder: this is what the result looked like <screenshot>
+      label: What you expected to happen
+      description: Describe what you expected to happen.
+      placeholder: I expected Z to happen.
+    validations:
+      required: true
+
+  - type: textarea
+    id: how-to-repro
+    attributes:
+      label: How to reproduce the problem
+      description: List steps to reproduce the problem.
+      placeholder: Start the app, generate an image with these settings, then click button X.
     validations:
       required: false
 
   - type: textarea
+    id: additional-context
     attributes:
       label: Additional context
-      description: Add any other context about the problem here
+      description: Any other context that might help us to understand the problem.
       placeholder: Only happens when there is full moon and Friday the 13th on Christmas Eve 🎅🏻
     validations:
       required: false
 
   - type: input
-    id: contact
+    id: discord-username
     attributes:
-      label: Contact Details
-      description: __OPTIONAL__ How can we get in touch with you if we need more info (besides this issue)?
-      placeholder: ex. email@example.com, discordname, twitter, ...
+      label: Discord username
+      description: If you are on the Invoke discord and would prefer to be contacted there, please provide your username.
+      placeholder: supercoolusername123
     validations:
       required: false

.github/pr_labels.yml

@@ -0,0 +1,59 @@
+Root:
+- changed-files:
+  - any-glob-to-any-file: '*'
+
+PythonDeps:
+- changed-files:
+  - any-glob-to-any-file: 'pyproject.toml'
+
+Python:
+- changed-files:
+  - all-globs-to-any-file: 
+    - 'invokeai/**'
+    - '!invokeai/frontend/web/**'
+
+PythonTests:
+- changed-files:
+  - any-glob-to-any-file: 'tests/**'
+
+CICD:
+- changed-files:
+  - any-glob-to-any-file: .github/**
+
+Docker:
+- changed-files:
+  - any-glob-to-any-file: docker/**
+
+Installer:
+- changed-files:
+  - any-glob-to-any-file: installer/**
+
+Documentation:
+- changed-files:
+  - any-glob-to-any-file: docs/**
+
+Invocations:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/app/invocations/**'
+
+Backend:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/backend/**'
+
+Api:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/app/api/**'
+
+Services:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/app/services/**'
+
+FrontendDeps:
+- changed-files:
+  - any-glob-to-any-file:
+    - '**/*/package.json'
+    - '**/*/pnpm-lock.yaml'
+
+Frontend:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/frontend/web/**'

.github/pull_request_template.md

@@ -42,6 +42,21 @@ Please provide steps on how to test changes, any hardware or
 software specifications as well as any other pertinent information. 
 -->
 
+## Merge Plan
+
+<!--
+A merge plan describes how this PR should be handled after it is approved.
+
+Example merge plans:
+- "This PR can be merged when approved"
+- "This must be squash-merged when approved"
+- "DO NOT MERGE - I will rebase and tidy commits before merging"
+- "#dev-chat on discord needs to be advised of this change when it is merged"
+
+A merge plan is particularly important for large PRs or PRs that touch the
+database in any way.
+-->
+
 ## Added/updated tests?
 
 - [ ] Yes

.github/workflows/build-container.yml

@@ -40,10 +40,14 @@ jobs:
       - name: Free up more disk space on the runner
         # https://github.com/actions/runner-images/issues/2840#issuecomment-1284059930
         run: |
+          echo "----- Free space before cleanup"
+          df -h
           sudo rm -rf /usr/share/dotnet
           sudo rm -rf "$AGENT_TOOLSDIRECTORY"
           sudo swapoff /mnt/swapfile
           sudo rm -rf /mnt/swapfile
+          echo "----- Free space after cleanup"
+          df -h
 
       - name: Checkout
         uses: actions/checkout@v3
@@ -91,6 +95,7 @@ jobs:
       #     password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Build container
+        timeout-minutes: 40
         id: docker_build
         uses: docker/build-push-action@v4
         with:

.github/workflows/label-pr.yml

@@ -0,0 +1,16 @@
+name: "Pull Request Labeler"
+on:
+- pull_request_target
+
+jobs:
+  labeler:
+    permissions:
+      contents: read
+      pull-requests: write
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - uses: actions/labeler@v5
+        with:
+          configuration-path: .github/pr_labels.yml

.github/workflows/lint-frontend.yml

@@ -22,12 +22,24 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Setup Node 18
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: '18'
-      - uses: actions/checkout@v3
-      - run: 'yarn install --frozen-lockfile'
-      - run: 'yarn run lint:tsc'
-      - run: 'yarn run lint:madge'
-      - run: 'yarn run lint:eslint'
-      - run: 'yarn run lint:prettier'
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v2
+        with:
+          version: '8.12.1'
+      - name: Install dependencies
+        run: 'pnpm install --prefer-frozen-lockfile'
+      - name: Typescript
+        run: 'pnpm run lint:tsc'
+      - name: Madge
+        run: 'pnpm run lint:dpdm'
+      - name: ESLint
+        run: 'pnpm run lint:eslint'
+      - name: Prettier
+        run: 'pnpm run lint:prettier'
+      - name: Knip
+        run: 'pnpm run lint:knip'

.github/workflows/pypi-release.yml

@@ -1,13 +1,15 @@
 name: PyPI Release
 
 on:
-  push:
-    paths:
-      - 'invokeai/version/invokeai_version.py'
   workflow_dispatch:
+    inputs:
+      publish_package:
+        description: 'Publish build on PyPi? [true/false]'
+        required: true
+        default: 'false'
 
 jobs:
-  release:
+  build-and-release:
     if: github.repository == 'invoke-ai/InvokeAI'
     runs-on: ubuntu-22.04
     env:
@@ -15,19 +17,43 @@ jobs:
       TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
       TWINE_NON_INTERACTIVE: 1
     steps:
-      - name: checkout sources
-        uses: actions/checkout@v3
+      - name: Checkout
+        uses: actions/checkout@v4
 
-      - name: install deps
+      - name: Setup Node 18
+        uses: actions/setup-node@v4
+        with:
+          node-version: '18'
+
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v2
+        with:
+          version: '8.12.1'
+
+      - name: Install frontend dependencies
+        run: pnpm install --prefer-frozen-lockfile
+        working-directory: invokeai/frontend/web
+
+      - name: Build frontend
+        run: pnpm run build
+        working-directory: invokeai/frontend/web
+
+      - name: Install python dependencies
         run: pip install --upgrade build twine
 
-      - name: build package
+      - name: Build python package
         run: python3 -m build
 
-      - name: check distribution
+      - name: Upload build as workflow artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist
+
+      - name: Check distribution
         run: twine check dist/*
 
-      - name: check PyPI versions
+      - name: Check PyPI versions
         if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
         run: |
           pip install --upgrade requests
@@ -36,6 +62,6 @@ jobs:
           EXISTS=scripts.pypi_helper.local_on_pypi(); \
           print(f'PACKAGE_EXISTS={EXISTS}')" >> $GITHUB_ENV
 
-      - name: upload package
-        if: env.PACKAGE_EXISTS == 'False' && env.TWINE_PASSWORD != ''
+      - name: Publish build on PyPi
+        if: env.PACKAGE_EXISTS == 'False' && env.TWINE_PASSWORD != '' && github.event.inputs.publish_package == 'true'
         run: twine upload dist/*

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

@@ -58,7 +58,7 @@ jobs:
 
       - name: Check for changed python files
         id: changed-files
-        uses: tj-actions/changed-files@v37
+        uses: tj-actions/changed-files@v41
         with:
           files_yaml: |
             python:

.gitignore

@@ -16,7 +16,7 @@ __pycache__/
 .Python
 build/
 develop-eggs/
-# dist/
+dist/
 downloads/
 eggs/
 .eggs/
@@ -187,3 +187,4 @@ installer/install.bat
 installer/install.sh
 installer/update.bat
 installer/update.sh
+installer/InvokeAI-Installer/

Makefile

@@ -1,21 +1,63 @@
 # simple Makefile with scripts that are otherwise hard to remember
 # to use, run from the repo root `make <command>`
 
+default: help
+
+help:
+	@echo Developer commands:
+	@echo
+	@echo "ruff              Run ruff, fixing any safely-fixable errors and formatting"
+	@echo "ruff-unsafe       Run ruff, fixing all fixable errors and formatting"
+	@echo "mypy              Run mypy using the config in pyproject.toml to identify type mismatches and other coding errors"
+	@echo "mypy-all          Run mypy ignoring the config in pyproject.tom but still ignoring missing imports"
+	@echo "test"             Run the unit tests.
+	@echo "frontend-install" Install the pnpm modules needed for the front end
+	@echo "frontend-build    Build the frontend in order to run on localhost:9090"
+	@echo "frontend-dev      Run the frontend in developer mode on localhost:5173"
+	@echo "installer-zip     Build the installer .zip file for the current version"
+	@echo "tag-release       Tag the GitHub repository with the current version (use at release time only!)"
+
 # Runs ruff, fixing any safely-fixable errors and formatting
 ruff:
-		ruff check . --fix
-		ruff format .
+	ruff check . --fix
+	ruff format .
 
 # Runs ruff, fixing all errors it can fix and formatting
 ruff-unsafe:
-		ruff check . --fix --unsafe-fixes
-		ruff format .
+	ruff check . --fix --unsafe-fixes
+	ruff format .
 
 # Runs mypy, using the config in pyproject.toml
 mypy:
-		mypy scripts/invokeai-web.py
+	mypy scripts/invokeai-web.py
 
 # Runs mypy, ignoring the config in pyproject.toml but still ignoring missing (untyped) imports
 # (many files are ignored by the config, so this is useful for checking all files)
 mypy-all:
-		mypy scripts/invokeai-web.py --config-file= --ignore-missing-imports
+	mypy scripts/invokeai-web.py --config-file= --ignore-missing-imports
+
+# Run the unit tests
+test:
+	pytest ./tests
+
+# Install the pnpm modules needed for the front end
+frontend-install:
+	rm -rf invokeai/frontend/web/node_modules
+	cd invokeai/frontend/web && pnpm install
+
+# Build the frontend
+frontend-build:
+	cd invokeai/frontend/web && pnpm build
+
+# Run the frontend in dev mode
+frontend-dev:
+	cd invokeai/frontend/web && pnpm dev
+
+# Installer zip file
+installer-zip:
+	cd installer && ./create_installer.sh
+
+# Tag the release
+tag-release:
+	cd installer && ./tag_release.sh
+

README.md

@@ -1,10 +1,10 @@
 <div align="center">
 
-![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/1a917d94-e099-4fa1-a70f-7dd8d0691018)
+![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/6e3728c7-e90e-4711-905c-3b55844ff5be)
 
-# Invoke AI - Generative AI for Professional Creatives
-## Professional Creative Tools for Stable Diffusion, Custom-Trained Models, and more. 
-  To learn more about Invoke AI, get started instantly, or implement our Business solutions, visit [invoke.ai](https://invoke.ai)
+# Invoke - Professional Creative AI Tools for Visual Media 
+##  To learn more about Invoke, or implement our Business solutions, visit [invoke.com](https://www.invoke.com/about)
+  
 
 
 [![discord badge]][discord link]
@@ -56,7 +56,9 @@ the foundation for multiple commercial products.
 
 <div align="center">
 
-![canvas preview](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/canvas_preview.png)
+
+![Highlighted Features - Canvas and Workflows](https://github.com/invoke-ai/InvokeAI/assets/31807370/708f7a82-084f-4860-bfbe-e2588c53548d)
+
 
 </div>
 
@@ -125,8 +127,8 @@ and go to http://localhost:9090.
 
 You must have Python 3.10 through 3.11 installed on your machine. Earlier or
 later versions are not supported.
-Node.js also needs to be installed along with yarn (can be installed with
-the command `npm install -g yarn` if needed)
+Node.js also needs to be installed along with `pnpm` (can be installed with
+the command `npm install -g pnpm` if needed)
 
 1. Open a command-line window on your machine. The PowerShell is recommended for Windows.
 2. Create a directory to install InvokeAI into. You'll need at least 15 GB of free space:
@@ -167,7 +169,7 @@ the command `npm install -g yarn` if needed)
     _For Linux with an AMD GPU:_
 
     ```sh
-    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
     ```
 
     _For non-GPU systems:_
@@ -270,7 +272,7 @@ upgrade script.** See the next section for a Windows recipe.
 3. Select option [1] to upgrade to the latest release.
 
 4. Once the upgrade is finished you will be returned to the launcher
-menu. Select option [7] "Re-run the configure script to fix a broken
+menu. Select option [6] "Re-run the configure script to fix a broken
 install or to complete a major upgrade".
 
 This will run the configure script against the v2.3 directory and

docker/.env.sample

@@ -2,14 +2,17 @@
 ## Any environment variables supported by InvokeAI can be specified here,
 ## in addition to the examples below.
 
-# INVOKEAI_ROOT is the path to a path on the local filesystem where InvokeAI will store data.
+# HOST_INVOKEAI_ROOT is the path on the docker host's filesystem where InvokeAI will store data.
 # Outputs will also be stored here by default.
-# This **must** be an absolute path.
-INVOKEAI_ROOT=
+# If relative, it will be relative to the docker directory in which the docker-compose.yml file is located
+#HOST_INVOKEAI_ROOT=../../invokeai-data
+
+# INVOKEAI_ROOT is the path to the root of the InvokeAI repository within the container.
+# INVOKEAI_ROOT=~/invokeai
 
 # Get this value from your HuggingFace account settings page.
 # HUGGING_FACE_HUB_TOKEN=
 
 ## optional variables specific to the docker setup.
-# GPU_DRIVER=cuda # or rocm
+# GPU_DRIVER=nvidia #| rocm
 # CONTAINER_UID=1000

docker/Dockerfile

@@ -18,8 +18,8 @@ ENV INVOKEAI_SRC=/opt/invokeai
 ENV VIRTUAL_ENV=/opt/venv/invokeai
 
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-ARG TORCH_VERSION=2.1.0
-ARG TORCHVISION_VERSION=0.16
+ARG TORCH_VERSION=2.1.2
+ARG TORCHVISION_VERSION=0.16.2
 ARG GPU_DRIVER=cuda
 ARG TARGETPLATFORM="linux/amd64"
 # unused but available
@@ -35,7 +35,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ] || [ "$GPU_DRIVER" = "cpu" ]; then \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cpu"; \
     elif [ "$GPU_DRIVER" = "rocm" ]; then \
-        extra_index_url_arg="--index-url https://download.pytorch.org/whl/rocm5.6"; \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm5.6"; \
     else \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
     fi &&\
@@ -54,19 +54,21 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$GPU_DRIVER" = "cuda" ] && [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
         pip install -e ".[xformers]"; \
     else \
-        pip install -e "."; \
+        pip install $extra_index_url_arg -e "."; \
     fi
 
 # #### Build the Web UI ------------------------------------
 
-FROM node:18 AS web-builder
+FROM node:20-slim AS web-builder
+ENV PNPM_HOME="/pnpm"
+ENV PATH="$PNPM_HOME:$PATH"
+RUN corepack enable
+
 WORKDIR /build
 COPY invokeai/frontend/web/ ./
-RUN --mount=type=cache,target=/usr/lib/node_modules \
-    npm install --include dev
-RUN --mount=type=cache,target=/usr/lib/node_modules \
-    yarn vite build
-
+RUN --mount=type=cache,target=/pnpm/store \
+    pnpm install --frozen-lockfile
+RUN npx vite build
 
 #### Runtime stage ---------------------------------------
 
@@ -100,6 +102,8 @@ ENV INVOKEAI_SRC=/opt/invokeai
 ENV VIRTUAL_ENV=/opt/venv/invokeai
 ENV INVOKEAI_ROOT=/invokeai
 ENV PATH="$VIRTUAL_ENV/bin:$INVOKEAI_SRC:$PATH"
+ENV CONTAINER_UID=${CONTAINER_UID:-1000}
+ENV CONTAINER_GID=${CONTAINER_GID:-1000}
 
 # --link requires buldkit w/ dockerfile syntax 1.4
 COPY --link --from=builder ${INVOKEAI_SRC} ${INVOKEAI_SRC}
@@ -117,7 +121,7 @@ WORKDIR ${INVOKEAI_SRC}
 RUN cd /usr/lib/$(uname -p)-linux-gnu/pkgconfig/ && ln -sf opencv4.pc opencv.pc
 RUN python3 -c "from patchmatch import patch_match"
 
-RUN mkdir -p ${INVOKEAI_ROOT} && chown -R 1000:1000 ${INVOKEAI_ROOT}
+RUN mkdir -p ${INVOKEAI_ROOT} && chown -R ${CONTAINER_UID}:${CONTAINER_GID} ${INVOKEAI_ROOT}
 
 COPY docker/docker-entrypoint.sh ./
 ENTRYPOINT ["/opt/invokeai/docker-entrypoint.sh"]

docker/README.md

@@ -1,6 +1,14 @@
 # InvokeAI Containerized
 
-All commands are to be run from the `docker` directory: `cd docker`
+All commands should be run within the `docker` directory: `cd docker`
+
+## Quickstart :rocket:
+
+On a known working Linux+Docker+CUDA (Nvidia) system, execute `./run.sh` in this directory. It will take a few minutes - depending on your internet speed - to install the core models. Once the application starts up, open `http://localhost:9090` in your browser to Invoke!
+
+For more configuration options (using an AMD GPU, custom root directory location, etc): read on.
+
+## Detailed setup
 
 #### Linux
 
@@ -18,12 +26,12 @@ All commands are to be run from the `docker` directory: `cd docker`
 
 This is done via Docker Desktop preferences
 
-## Quickstart
+### Configure Invoke environment
 
-1. Make a copy of `env.sample` and name it `.env` (`cp env.sample .env` (Mac/Linux) or `copy example.env .env` (Windows)). Make changes as necessary. Set `INVOKEAI_ROOT` to an absolute path to:
+1. Make a copy of `.env.sample` and name it `.env` (`cp .env.sample .env` (Mac/Linux) or `copy example.env .env` (Windows)). Make changes as necessary. Set `INVOKEAI_ROOT` to an absolute path to:
     a. the desired location of the InvokeAI runtime directory, or
     b. an existing, v3.0.0 compatible runtime directory.
-1. `docker compose up`
+1. Execute `run.sh`
 
 The image will be built automatically if needed.
 
@@ -37,19 +45,21 @@ The runtime directory (holding models and outputs) will be created in the locati
 
 The Docker daemon on the system must be already set up to use the GPU. In case of Linux, this involves installing `nvidia-docker-runtime` and configuring the `nvidia` runtime as default. Steps will be different for AMD. Please see Docker documentation for the most up-to-date instructions for using your GPU with Docker.
 
+To use an AMD GPU, set `GPU_DRIVER=rocm` in your `.env` file.
+
 ## Customize
 
-Check the `.env.sample` file. It contains some environment variables for running in Docker. Copy it, name it `.env`, and fill it in with your own values. Next time you run `docker compose up`, your custom values will be used.
+Check the `.env.sample` file. It contains some environment variables for running in Docker. Copy it, name it `.env`, and fill it in with your own values. Next time you run `run.sh`, your custom values will be used.
 
 You can also set these values in `docker-compose.yml` directly, but `.env` will help avoid conflicts when code is updated.
 
-Example (values are optional, but setting `INVOKEAI_ROOT` is highly recommended):
+Values are optional, but setting `INVOKEAI_ROOT` is highly recommended. The default is `~/invokeai`. Example:
 
 ```bash
 INVOKEAI_ROOT=/Volumes/WorkDrive/invokeai
 HUGGINGFACE_TOKEN=the_actual_token
 CONTAINER_UID=1000
-GPU_DRIVER=cuda
+GPU_DRIVER=nvidia
 ```
 
 Any environment variables supported by InvokeAI can be set here - please see the [Configuration docs](https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/) for further detail.

docker/build.sh

@@ -1,11 +0,0 @@
-#!/usr/bin/env bash
-set -e
-
-build_args=""
-
-[[ -f ".env" ]] && build_args=$(awk '$1 ~ /\=[^$]/ {print "--build-arg " $0 " "}' .env)
-
-echo "docker compose build args:"
-echo $build_args
-
-docker compose build $build_args

docker/docker-compose.yml

@@ -2,23 +2,8 @@
 
 version: '3.8'
 
-services:
-  invokeai:
+x-invokeai: &invokeai
     image: "local/invokeai:latest"
-    # edit below to run on a container runtime other than nvidia-container-runtime.
-    # not yet tested with rocm/AMD GPUs
-    # Comment out the "deploy" section to run on CPU only
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: 1
-              capabilities: [gpu]
-    # For AMD support, comment out the deploy section above and uncomment the devices section below:
-    #devices:
-    #  - /dev/kfd:/dev/kfd
-    #  - /dev/dri:/dev/dri
     build:
       context: ..
       dockerfile: docker/Dockerfile
@@ -36,7 +21,9 @@ services:
     ports:
       - "${INVOKEAI_PORT:-9090}:9090"
     volumes:
-      - ${INVOKEAI_ROOT:-~/invokeai}:${INVOKEAI_ROOT:-/invokeai}
+      - type: bind
+        source: ${HOST_INVOKEAI_ROOT:-${INVOKEAI_ROOT:-~/invokeai}}
+        target: ${INVOKEAI_ROOT:-/invokeai}
       - ${HF_HOME:-~/.cache/huggingface}:${HF_HOME:-/invokeai/.cache/huggingface}
       # - ${INVOKEAI_MODELS_DIR:-${INVOKEAI_ROOT:-/invokeai/models}}
       # - ${INVOKEAI_MODELS_CONFIG_PATH:-${INVOKEAI_ROOT:-/invokeai/configs/models.yaml}}
@@ -50,3 +37,27 @@ services:
     #   - |
     #     invokeai-model-install --yes --default-only --config_file ${INVOKEAI_ROOT}/config_custom.yaml
     #     invokeai-nodes-web --host 0.0.0.0
+
+services:
+  invokeai-nvidia:
+    <<: *invokeai
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+
+  invokeai-cpu:
+    <<: *invokeai
+    profiles:
+      - cpu
+
+  invokeai-rocm:
+    <<: *invokeai
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    profiles:
+      - rocm

docker/run.sh

@@ -1,11 +1,32 @@
 #!/usr/bin/env bash
-set -e
+set -e -o pipefail
 
-# This script is provided for backwards compatibility with the old docker setup.
-# it doesn't do much aside from wrapping the usual docker compose CLI.
+run() {
+  local scriptdir=$(dirname "${BASH_SOURCE[0]}")
+  cd "$scriptdir" || exit 1
 
-SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
-cd "$SCRIPTDIR" || exit 1
+  local build_args=""
+  local profile=""
 
-docker compose up -d
-docker compose logs -f
+  touch .env
+  build_args=$(awk '$1 ~ /=[^$]/ && $0 !~ /^#/ {print "--build-arg " $0 " "}' .env) &&
+  profile="$(awk -F '=' '/GPU_DRIVER/ {print $2}' .env)"
+
+  [[ -z "$profile" ]] && profile="nvidia"
+
+  local service_name="invokeai-$profile"
+
+  if [[ ! -z "$build_args" ]]; then
+    printf "%s\n" "docker compose build args:"
+    printf "%s\n" "$build_args"
+  fi
+
+  docker compose build $build_args $service_name
+  unset build_args
+
+  printf "%s\n" "starting service $service_name"
+  docker compose --profile "$profile" up -d "$service_name"
+  docker compose logs -f
+}
+
+run

docs/contributing/DOWNLOAD_QUEUE.md

@@ -0,0 +1,277 @@
+# The InvokeAI Download Queue
+
+The DownloadQueueService provides a multithreaded parallel download
+queue for arbitrary URLs, with queue prioritization, event handling,
+and restart capabilities.
+
+## Simple Example
+
+```
+from invokeai.app.services.download import DownloadQueueService, TqdmProgress
+
+download_queue = DownloadQueueService()
+for url in ['https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/assets/a-painting-of-a-fire.png?raw=true',
+            'https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/assets/birdhouse.png?raw=true',
+            'https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/assets/missing.png',
+            'https://civitai.com/api/download/models/152309?type=Model&format=SafeTensor',
+            ]:
+
+    # urls start downloading as soon as download() is called
+    download_queue.download(source=url,
+                            dest='/tmp/downloads',
+                            on_progress=TqdmProgress().update
+                            )
+
+download_queue.join()  # wait for all downloads to finish
+for job in download_queue.list_jobs():
+    print(job.model_dump_json(exclude_none=True, indent=4),"\n")
+```
+
+Output:
+
+```
+{
+    "source": "https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/assets/a-painting-of-a-fire.png?raw=true",
+    "dest": "/tmp/downloads",
+    "id": 0,
+    "priority": 10,
+    "status": "completed",
+    "download_path": "/tmp/downloads/a-painting-of-a-fire.png",
+    "job_started": "2023-12-04T05:34:41.742174",
+    "job_ended": "2023-12-04T05:34:42.592035",
+    "bytes": 666734,
+    "total_bytes": 666734
+} 
+
+{
+    "source": "https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/assets/birdhouse.png?raw=true",
+    "dest": "/tmp/downloads",
+    "id": 1,
+    "priority": 10,
+    "status": "completed",
+    "download_path": "/tmp/downloads/birdhouse.png",
+    "job_started": "2023-12-04T05:34:41.741975",
+    "job_ended": "2023-12-04T05:34:42.652841",
+    "bytes": 774949,
+    "total_bytes": 774949
+}
+
+{
+    "source": "https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/assets/missing.png",
+    "dest": "/tmp/downloads",
+    "id": 2,
+    "priority": 10,
+    "status": "error",
+    "job_started": "2023-12-04T05:34:41.742079",
+    "job_ended": "2023-12-04T05:34:42.147625",
+    "bytes": 0,
+    "total_bytes": 0,
+    "error_type": "HTTPError(Not Found)",
+    "error": "Traceback (most recent call last):\n  File \"/home/lstein/Projects/InvokeAI/invokeai/app/services/download/download_default.py\", line 182, in _download_next_item\n    self._do_download(job)\n  File \"/home/lstein/Projects/InvokeAI/invokeai/app/services/download/download_default.py\", line 206, in _do_download\n    raise HTTPError(resp.reason)\nrequests.exceptions.HTTPError: Not Found\n"
+}
+
+{
+    "source": "https://civitai.com/api/download/models/152309?type=Model&format=SafeTensor",
+    "dest": "/tmp/downloads",
+    "id": 3,
+    "priority": 10,
+    "status": "completed",
+    "download_path": "/tmp/downloads/xl_more_art-full_v1.safetensors",
+    "job_started": "2023-12-04T05:34:42.147645",
+    "job_ended": "2023-12-04T05:34:43.735990",
+    "bytes": 719020768,
+    "total_bytes": 719020768
+} 
+```
+
+##  The API
+
+The default download queue is `DownloadQueueService`, an
+implementation of ABC `DownloadQueueServiceBase`. It juggles multiple
+background download requests and provides facilities for interrogating
+and cancelling the requests. Access to a current or past download task
+is mediated via `DownloadJob` objects which report the current status
+of a job request
+
+### The Queue Object
+
+A default download queue is located in
+`ApiDependencies.invoker.services.download_queue`. However, you can
+create additional instances if you need to isolate your queue from the
+main one.
+
+```
+queue = DownloadQueueService(event_bus=events)
+```
+
+`DownloadQueueService()` takes three optional arguments:
+
+| **Argument** | **Type**          |  **Default**  | **Description** |
+|----------------|-----------------|---------------|-----------------|
+| `max_parallel_dl`  | int                         | 5    | Maximum number of simultaneous downloads allowed |
+| `event_bus` | EventServiceBase   | None | System-wide FastAPI event bus for reporting download events |
+| `requests_session` | requests.sessions.Session   | None | An alternative requests Session object to use for the download |
+
+`max_parallel_dl` specifies how many download jobs are allowed to run
+simultaneously. Each will run in a different thread of execution.
+
+`event_bus` is an EventServiceBase, typically the one created at
+InvokeAI startup. If present, download events are periodically emitted
+on this bus to allow clients to follow download progress.
+
+`requests_session` is a url library requests Session object. It is
+used for testing.
+
+### The Job object
+
+The queue operates on a series of download job objects. These objects
+specify the source and destination of the download, and keep track of
+the progress of the download.
+
+The only job type currently implemented is `DownloadJob`, a pydantic object with the
+following fields:
+
+| **Field**      | **Type**        |  **Default**  | **Description** |
+|----------------|-----------------|---------------|-----------------|
+| _Fields passed in at job creation time_                               |
+| `source`         | AnyHttpUrl      |               | Where to download from |
+| `dest`           | Path            |               | Where to download to              |
+| `access_token`   | str             |               | [optional] string containing authentication token for access |
+| `on_start`       | Callable        |               | [optional] callback when the download starts |
+| `on_progress`    | Callable        |               | [optional] callback called at intervals during download progress |
+| `on_complete`    | Callable        |               | [optional] callback called after successful download completion |
+| `on_error`       | Callable        |               | [optional] callback called after an error occurs  |
+| `id`             | int             | auto assigned | Job ID, an integer >= 0           |
+| `priority`       | int             | 10            | Job priority. Lower priorities run before higher priorities |
+|                                                                                                        |
+| _Fields updated over the course of the download task_
+| `status`         | DownloadJobStatus|              | Status code                                |
+| `download_path`  | Path |              | Path to the location of the downloaded file |
+| `job_started`    | float            |              | Timestamp for when the job started running |
+| `job_ended`      | float            |              | Timestamp for when the job completed or errored out |
+| `job_sequence`   | int              |              | A counter that is incremented each time a model is dequeued |
+| `bytes`          | int              | 0            | Bytes downloaded so far   |
+| `total_bytes`    | int              | 0            | Total size of the file at the remote site  |
+| `error_type`     | str              |              | String version of the exception that caused an error during download |
+| `error`          | str              |              | String version of the traceback associated with an error |
+| `cancelled`      | bool             | False        | Set to true if the job was cancelled by the caller|
+
+When you create a job, you can assign it a `priority`. If multiple
+jobs are queued, the job with the lowest priority runs first.
+
+Every job has a `source` and a `dest`. `source` is a pydantic.networks AnyHttpUrl object.
+The `dest` is a path on the local filesystem that specifies the
+destination for the downloaded object. Its semantics are
+described below.
+
+When the job is submitted, it is assigned a numeric `id`. The id can
+then be used to fetch the job object from the queue.
+
+The `status` field is updated by the queue to indicate where the job
+is in its lifecycle. Values are defined in the string enum
+`DownloadJobStatus`, a symbol available from
+`invokeai.app.services.download_manager`. Possible values are:
+
+| **Value**    |   **String Value**  | ** Description ** |
+|--------------|---------------------|-------------------|
+| `WAITING`      | waiting           | Job is on the queue but not yet running|
+| `RUNNING`      | running           | The download is started                |
+| `COMPLETED`    | completed         | Job has finished its work without an error |
+| `ERROR`        | error             | Job encountered an error and will not run again|
+
+`job_started` and `job_ended` indicate when the job
+was started (using a python timestamp) and when it completed.
+
+In case of an error, the job's status will be set to `DownloadJobStatus.ERROR`, the text of the
+Exception that caused the error will be placed in the `error_type`
+field and the traceback that led to the error will be in `error`.
+
+A cancelled job will have status `DownloadJobStatus.ERROR` and an
+`error_type` field of "DownloadJobCancelledException". In addition,
+the job's `cancelled` property will be set to True.
+
+### Callbacks
+
+Download jobs can be associated with a series of callbacks, each with
+the signature `Callable[["DownloadJob"], None]`. The callbacks are assigned
+using optional arguments `on_start`, `on_progress`, `on_complete` and
+`on_error`. When the corresponding event occurs, the callback wil be
+invoked and passed the job. The callback will be run in a `try:`
+context in the same thread as the download job. Any exceptions that
+occur during execution of the callback will be caught and converted
+into a log error message, thereby allowing the download to continue.
+
+#### `TqdmProgress`
+
+The `invokeai.app.services.download.download_default` module defines a
+class named `TqdmProgress` which can be used as an `on_progress`
+handler to display a completion bar in the console. Use as follows:
+
+```
+from invokeai.app.services.download import TqdmProgress
+
+download_queue.download(source='http://some.server.somewhere/some_file',
+                        dest='/tmp/downloads',
+                        on_progress=TqdmProgress().update
+                        )
+
+```
+
+### Events
+
+If the queue was initialized with the InvokeAI event bus (the case
+when using `ApiDependencies.invoker.services.download_queue`), then
+download events will also be issued on the bus. The events are:
+
+* `download_started` -- This is issued when a job is taken off the
+queue and a request is made to the remote server for the URL headers, but before any data
+has been downloaded. The event payload will contain the keys `source`
+and `download_path`. The latter contains the path that the URL will be
+downloaded to.
+
+* `download_progress -- This is issued periodically as the download
+runs. The payload contains the keys `source`, `download_path`,
+`current_bytes` and `total_bytes`. The latter two fields can be
+used to display the percent complete.
+
+* `download_complete` -- This is issued when the download completes
+successfully. The payload contains the keys `source`, `download_path`
+and `total_bytes`.
+
+* `download_error` -- This is issued when the download stops because
+of an error condition. The payload contains the fields `error_type`
+and `error`. The former is the text representation of the exception,
+and the latter is a traceback showing where the error occurred.
+
+### Job control
+
+To create a job call the queue's `download()` method. You can list all
+jobs using `list_jobs()`, fetch a single job by its with
+`id_to_job()`, cancel a running job with `cancel_job()`, cancel all
+running jobs with `cancel_all_jobs()`, and wait for all jobs to finish
+with `join()`.
+
+#### job = queue.download(source, dest, priority, access_token)
+
+Create a new download job and put it on the queue, returning the
+DownloadJob object.
+
+#### jobs = queue.list_jobs()
+
+Return a list of all active and inactive `DownloadJob`s.
+
+#### job = queue.id_to_job(id)
+
+Return the job corresponding to given ID.
+
+Return a list of all active and inactive `DownloadJob`s.
+
+#### queue.prune_jobs()
+
+Remove inactive (complete or errored) jobs from the listing returned
+by `list_jobs()`.
+
+#### queue.join()
+
+Block until all pending jobs have run to completion or errored out.
+

docs/contributing/INVOCATIONS.md

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

docs/contributing/contribution_guides/contributingToFrontend.md

@@ -1,75 +0,0 @@
-# Contributing to the Frontend
-
-# InvokeAI Web UI
-
-- [InvokeAI Web UI](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#invokeai-web-ui)
-    - [Stack](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#stack)
-    - [Contributing](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#contributing)
-        - [Dev Environment](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#dev-environment)
-        - [Production builds](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#production-builds)
-
-The UI is a fairly straightforward Typescript React app, with the Unified Canvas being more complex.
-
-Code is located in `invokeai/frontend/web/` for review.
-
-## Stack
-
-State management is Redux via [Redux Toolkit](https://github.com/reduxjs/redux-toolkit). We lean heavily on RTK:
-
-- `createAsyncThunk` for HTTP requests
-- `createEntityAdapter` for fetching images and models
-- `createListenerMiddleware` for workflows
-
-The API client and associated types are generated from the OpenAPI schema. See API_CLIENT.md.
-
-Communication with server is a mix of HTTP and [socket.io](https://github.com/socketio/socket.io-client) (with a simple socket.io redux middleware to help).
-
-[Chakra-UI](https://github.com/chakra-ui/chakra-ui) & [Mantine](https://github.com/mantinedev/mantine) for components and styling.
-
-[Konva](https://github.com/konvajs/react-konva) for the canvas, but we are pushing the limits of what is feasible with it (and HTML canvas in general). We plan to rebuild it with [PixiJS](https://github.com/pixijs/pixijs) to take advantage of WebGL's improved raster handling.
-
-[Vite](https://vitejs.dev/) for bundling.
-
-Localisation is via [i18next](https://github.com/i18next/react-i18next), but translation happens on our [Weblate](https://hosted.weblate.org/engage/invokeai/) project. Only the English source strings should be changed on this repo.
-
-## Contributing
-
-Thanks for your interest in contributing to the InvokeAI Web UI!
-
-We encourage you to ping @psychedelicious and @blessedcoolant on [Discord](https://discord.gg/ZmtBAhwWhy) if you want to contribute, just to touch base and ensure your work doesn't conflict with anything else going on. The project is very active.
-
-### Dev Environment
-
-**Setup** 
-
-1. Install [node](https://nodejs.org/en/download/). You can confirm node is installed with:
-```bash
-node --version
-```
-2. Install [yarn classic](https://classic.yarnpkg.com/lang/en/) and confirm it is installed by running this:
-```bash
-npm install --global yarn
-yarn --version
-```
-
-From `invokeai/frontend/web/` run `yarn install` to get everything set up.
-
-Start everything in dev mode:
-1. Ensure your virtual environment is running
-2. Start the dev server: `yarn dev`
-3. Start the InvokeAI Nodes backend: `python scripts/invokeai-web.py # run from the repo root`
-4. Point your browser to the dev server address e.g. [http://localhost:5173/](http://localhost:5173/)
-
-### VSCode Remote Dev
-
-We've noticed an intermittent issue with the VSCode Remote Dev port forwarding. If you use this feature of VSCode, you may intermittently click the Invoke button and then get nothing until the request times out. Suggest disabling the IDE's port forwarding feature and doing it manually via SSH:
-
-`ssh -L 9090:localhost:9090 -L 5173:localhost:5173 user@host`
-
-### Production builds
-
-For a number of technical and logistical reasons, we need to commit UI build artefacts to the repo.
-
-If you submit a PR, there is a good chance we will ask you to include a separate commit with a build of the app.
-
-To build for production, run `yarn build`.

docs/contributing/contribution_guides/development.md

@@ -12,7 +12,7 @@ To get started, take a look at our [new contributors checklist](newContributorCh
 Once you're setup, for more information, you can review the documentation specific to your area of interest:
 
 * #### [InvokeAI Architecure](../ARCHITECTURE.md)
-* #### [Frontend Documentation](./contributingToFrontend.md)
+* #### [Frontend Documentation](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web)
 * #### [Node Documentation](../INVOCATIONS.md)
 * #### [Local Development](../LOCAL_DEVELOPMENT.md)
 

docs/deprecated/2to3.md

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

docs/features/CONFIGURATION.md

@@ -154,14 +154,16 @@ groups in `invokeia.yaml`:
 
 ### Web Server
 
-| Setting  | Default Value  |  Description |
-|----------|----------------|--------------|
-| `host`     | `localhost`      | Name or IP address of the network interface that the web server will listen on  |
-| `port`     | `9090`           | Network port number that the web server will listen on  |
-| `allow_origins`  | `[]`       | A list of host names or IP addresses that are allowed to connect to the InvokeAI API in the format `['host1','host2',...]` |
-| `allow_credentials` | `true`   | Require credentials for a foreign host to access the InvokeAI API (don't change this) |
-| `allow_methods` | `*`         | List of HTTP methods ("GET", "POST") that the web server is allowed to use when accessing the API  |
-| `allow_headers` | `*`         | List of HTTP headers that the web server will accept when accessing the API  |
+| Setting             | Default Value | Description                                                                                                                |
+|---------------------|---------------|----------------------------------------------------------------------------------------------------------------------------|
+| `host`              | `localhost`   | Name or IP address of the network interface that the web server will listen on                                             |
+| `port`              | `9090`        | Network port number that the web server will listen on                                                                     |
+| `allow_origins`     | `[]`          | A list of host names or IP addresses that are allowed to connect to the InvokeAI API in the format `['host1','host2',...]` |
+| `allow_credentials` | `true`        | Require credentials for a foreign host to access the InvokeAI API (don't change this)                                      |
+| `allow_methods`     | `*`           | List of HTTP methods ("GET", "POST") that the web server is allowed to use when accessing the API                          |
+| `allow_headers`     | `*`           | List of HTTP headers that the web server will accept when accessing the API                                                |
+| `ssl_certfile`      | null          | Path to an SSL certificate file, used to enable HTTPS.                                                                     |
+| `ssl_keyfile`       | null          | Path to an SSL keyfile, if the key is not included in the certificate file.                                                |
 
 The documentation for InvokeAI's API can be accessed by browsing to the following URL: [http://localhost:9090/docs].
 

docs/features/CONTROLNET.md

@@ -94,6 +94,8 @@ A model that helps generate creative QR codes that still scan. Can also be used
 **Openpose**: 
 The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
 
+*Note:* The DWPose Processor has replaced the OpenPose processor in Invoke. Workflows and generations that relied on the OpenPose Processor will need to be updated to use the DWPose Processor instead.
+
 **Mediapipe Face**:
 
 The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.

docs/features/UNIFIED_CANVAS.md

@@ -229,29 +229,28 @@ clarity on the intent and common use cases we expect for utilizing them.
   currently being rendered by your browser into a merged copy of the image. This
   lowers the resource requirements and should improve performance.
 
-### Seam Correction
+### Compositing / Seam Correction
 
 When doing Inpainting or Outpainting, Invoke needs to merge the pixels generated
-by Stable Diffusion into your existing image. To do this, the area around the
-`seam` at the boundary between your image and the new generation is
+by Stable Diffusion into your existing image. This is achieved through compositing - the area around the the boundary between your image and the new generation is
 automatically blended to produce a seamless output. In a fully automatic
-process, a mask is generated to cover the seam, and then the area of the seam is
+process, a mask is generated to cover the boundary, and then the area of the boundary is
 Inpainted.
 
 Although the default options should work well most of the time, sometimes it can
-help to alter the parameters that control the seam Inpainting. A wider seam and
-a blur setting of about 1/3 of the seam have been noted as producing
-consistently strong results (e.g. 96 wide and 16 blur - adds up to 32 blur with
-both sides). Seam strength of 0.7 is best for reducing hard seams.
+help to alter the parameters that control the Compositing. A larger blur and
+a blur setting  have been noted as producing
+consistently strong results . Strength of 0.7 is best for reducing hard seams.
+
+- **Mode** - What part of the image will have the the Compositing applied to it.
+  - **Mask edge** will apply Compositing to the edge of the masked area
+  - **Mask** will apply Compositing to the entire masked area
+  - **Unmasked** will apply Compositing to the entire image
+- **Steps** - Number of generation steps that will occur during the Coherence Pass, similar to Denoising Steps. Higher step counts will generally have better results.
+- **Strength** - How much noise is added for the Coherence Pass, similar to Denoising Strength. A strength of 0 will result in an unchanged image, while a strength of 1 will result in an image with a completely new area as defined by the Mode setting.
+- **Blur** - Adjusts the pixel radius of the the mask. A larger blur radius will cause the mask to extend past the visibly masked area, while too small of a blur radius will result in a mask that is smaller than the visibly masked area.
+- **Blur Method** - The method of blur applied to the masked area. 
 
-- **Seam Size** - The size of the seam masked area. Set higher to make a larger
-  mask around the seam.
-- **Seam Blur** - The size of the blur that is applied on _each_ side of the
-  masked area.
-- **Seam Strength** - The Image To Image Strength parameter used for the
-  Inpainting generation that is applied to the seam area.
-- **Seam Steps** - The number of generation steps that should be used to Inpaint
-  the seam.
 
 ### Infill & Scaling
 

docs/index.md

@@ -18,7 +18,7 @@ title: Home
       width: 100%;
       max-width: 100%;
       height: 50px;
-      background-color: #448AFF;
+      background-color: #35A4DB;
       color: #fff;
       font-size: 16px;
       border: none;
@@ -43,7 +43,7 @@ title: Home
 <div align="center" markdown>
 
 
-[![project logo](assets/invoke_ai_banner.png)](https://github.com/invoke-ai/InvokeAI)
+[![project logo](https://github.com/invoke-ai/InvokeAI/assets/31807370/6e3728c7-e90e-4711-905c-3b55844ff5be)](https://github.com/invoke-ai/InvokeAI)
 
 [![discord badge]][discord link]
 
@@ -117,6 +117,11 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 
 ## :octicons-gift-24: InvokeAI Features
 
+### Installation
+  - [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
+  - [Manual Installation](installation/020_INSTALL_MANUAL.md)
+  - [Docker Installation](installation/040_INSTALL_DOCKER.md)
+
 ### The InvokeAI Web Interface
 - [WebUI overview](features/WEB.md)
 - [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
@@ -145,60 +150,6 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 - [Guide to InvokeAI Runtime Settings](features/CONFIGURATION.md)
 - [Database Maintenance and other Command Line Utilities](features/UTILITIES.md)
 
-## :octicons-log-16: Important Changes Since Version 2.3
-
-### Nodes
-
-Behind the scenes, InvokeAI has been completely rewritten to support
-"nodes," small unitary operations that can be combined into graphs to
-form arbitrary workflows. For example, there is a prompt node that
-processes the prompt string and feeds it to a text2latent node that
-generates a latent image. The latents are then fed to a latent2image
-node that translates the latent image into a PNG.
-
-The WebGUI has a node editor that allows you to graphically design and
-execute custom node graphs. The ability to save and load graphs is
-still a work in progress, but coming soon.
-
-### Command-Line Interface Retired
-
-All "invokeai" command-line interfaces have been retired as of version
-3.4.
-
-To launch the Web GUI from the command-line, use the command
-`invokeai-web` rather than the traditional `invokeai --web`.
-
-### ControlNet
-
-This version of InvokeAI features ControlNet, a system that allows you
-to achieve exact poses for human and animal figures by providing a
-model to follow. Full details are found in [ControlNet](features/CONTROLNET.md)
-
-### New Schedulers
-
-The list of schedulers has been completely revamped and brought up to date:
-
-| **Short Name** | **Scheduler**                   | **Notes**                   |
-|----------------|---------------------------------|-----------------------------|
-| **ddim**       | DDIMScheduler                   |                             |
-| **ddpm**       | DDPMScheduler                   |                             |
-| **deis**       | DEISMultistepScheduler          |                             |
-| **lms**        | LMSDiscreteScheduler            |                             |
-| **pndm**       | PNDMScheduler                   |                             |
-| **heun**       | HeunDiscreteScheduler           | original noise schedule     |
-| **heun_k**     | HeunDiscreteScheduler           | using karras noise schedule |
-| **euler**      | EulerDiscreteScheduler          | original noise schedule     |
-| **euler_k**    | EulerDiscreteScheduler          | using karras noise schedule |
-| **kdpm_2**     | KDPM2DiscreteScheduler          |                             |
-| **kdpm_2_a**   | KDPM2AncestralDiscreteScheduler |                             |
-| **dpmpp_2s**   | DPMSolverSinglestepScheduler    |                             |
-| **dpmpp_2m**   | DPMSolverMultistepScheduler     | original noise scnedule     |
-| **dpmpp_2m_k** | DPMSolverMultistepScheduler     | using karras noise schedule |
-| **unipc**      | UniPCMultistepScheduler         | CPU only                    |
-| **lcm**        | LCMScheduler                    |                             |
-
-Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details.
-
 ## :material-target: Troubleshooting
 
 Please check out our **[:material-frequently-asked-questions:

docs/installation/010_INSTALL_AUTOMATED.md

@@ -477,7 +477,7 @@ Then type the following commands:
 
 === "AMD System"
     ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.6
     ```
 
 ### Corrupted configuration file

docs/installation/020_INSTALL_MANUAL.md

@@ -154,7 +154,7 @@ manager, please follow these steps:
     === "ROCm (AMD)"
 
         ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -230,13 +230,13 @@ manager, please follow these steps:
         === "local Webserver"
 
             ```bash
-            invokeai --web
+            invokeai-web
             ```
 
         === "Public Webserver"
 
             ```bash
-            invokeai --web --host 0.0.0.0
+            invokeai-web --host 0.0.0.0
             ```
 
         === "CLI"
@@ -293,6 +293,19 @@ manager, please follow these steps:
 
 ## Developer Install
 
+!!! warning
+
+    InvokeAI uses a SQLite database. By running on `main`, you accept responsibility for your database. This
+    means making regular backups (especially before pulling) and/or fixing it yourself in the event that a
+    PR introduces a schema change.
+    
+    If you don't need persistent backend storage, you can use an ephemeral in-memory database by setting
+    `use_memory_db: true` under `Path:` in your `invokeai.yaml` file.
+
+    If this is untenable, you should run the application via the official installer or a manual install of the
+    python package from pypi. These releases will not break your database.
+
+
 If you have an interest in how InvokeAI works, or you would like to
 add features or bugfixes, you are encouraged to install the source
 code for InvokeAI. For this to work, you will need to install the
@@ -300,7 +313,7 @@ code for InvokeAI. For this to work, you will need to install the
 on your system, please see the [Git Installation
 Guide](https://github.com/git-guides/install-git)
 
-You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md).
+You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md).
 
 If you have a "normal" installation, you should create a totally separate virtual environment for the git-based installation, else the two may interfere.
 
@@ -332,7 +345,7 @@ installation protocol (important!)
 
     === "ROCm (AMD)"
         ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -348,7 +361,7 @@ installation protocol (important!)
     Be sure to pass `-e` (for an editable install) and don't forget the
     dot ("."). It is part of the command.
 
-5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md) and do a production build of the UI as described.
+5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md) and do a production build of the UI as described.
 
 6.  You can now run `invokeai` and its related commands. The code will be
     read from the repository, so that you can edit the .py source files
@@ -388,3 +401,5 @@ environment variable INVOKEAI_ROOT to point to the installation directory.
 
 Note that if you run into problems with the Conda installation, the InvokeAI
 staff will **not** be able to help you out. Caveat Emptor!
+
+[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -134,7 +134,7 @@ recipes are available
 
 When installing torch and torchvision manually with `pip`, remember to provide
 the argument `--extra-index-url
-https://download.pytorch.org/whl/rocm5.4.2` as described in the [Manual
+https://download.pytorch.org/whl/rocm5.6` as described in the [Manual
 Installation Guide](020_INSTALL_MANUAL.md).
 
 This will be done automatically for you if you use the installer

docs/installation/040_INSTALL_DOCKER.md

@@ -69,7 +69,7 @@ a token and copy it, since you will need in for the next step.
 
 ### Setup
 
-Set up your environmnent variables. In the `docker` directory, make a copy of `env.sample` and name it `.env`. Make changes as necessary.
+Set up your environmnent variables. In the `docker` directory, make a copy of `.env.sample` and name it `.env`. Make changes as necessary.
 
 Any environment variables supported by InvokeAI can be set here - please see the [CONFIGURATION](../features/CONFIGURATION.md) for further detail.
 

docs/installation/INSTALLATION.md

@@ -18,13 +18,18 @@ either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
 driver).
 
 
-## **[Automated Installer](010_INSTALL_AUTOMATED.md)**
-✅ This is the recommended installation method for first-time users. 
+## **[Automated Installer (Recommended)](010_INSTALL_AUTOMATED.md)**
+ ✅ This is the recommended installation method for first-time users. 
 
   This is a script that will install all of InvokeAI's essential
-  third party libraries and InvokeAI itself. It includes access to a
-  "developer console" which will help us debug problems with you and
-  give you to access experimental features.
+  third party libraries and InvokeAI itself.
+
+🖥️ **Download the latest installer .zip file here** : https://github.com/invoke-ai/InvokeAI/releases/latest
+  
+- *Look for the file labelled "InvokeAI-installer-v3.X.X.zip" at the bottom of the page*
+- If you experience issues, read through the full [installation instructions](010_INSTALL_AUTOMATED.md) to make sure you have met all of the installation requirements. If you need more help, join the [Discord](discord.gg/invoke-ai) or create an issue on [Github](https://github.com/invoke-ai/InvokeAI).
+
+
 
 ## **[Manual Installation](020_INSTALL_MANUAL.md)**
 This method is recommended for experienced users and developers.

docs/javascripts/init_kapa_widget.js

@@ -0,0 +1,10 @@
+document.addEventListener("DOMContentLoaded", function () {
+  var script = document.createElement("script");
+  script.src = "https://widget.kapa.ai/kapa-widget.bundle.js";
+  script.setAttribute("data-website-id", "b5973bb1-476b-451e-8cf4-98de86745a10");
+  script.setAttribute("data-project-name", "Invoke.AI");
+  script.setAttribute("data-project-color", "#11213C");
+  script.setAttribute("data-project-logo", "https://avatars.githubusercontent.com/u/113954515?s=280&v=4");
+  script.async = true;
+  document.head.appendChild(script);
+});

docs/nodes/NODES.md

@@ -6,10 +6,17 @@ If you're not familiar with Diffusion, take a look at our [Diffusion Overview.](
 
 ## Features
 
+### Workflow Library
+The Workflow Library enables you to save workflows to the Invoke database, allowing you to easily creating, modify and share workflows as needed. 
+
+A curated set of workflows are provided by default - these are designed to help explain important nodes' usage in the Workflow Editor.
+
+![workflow_library](../assets/nodes/workflow_library.png)
+
 ### Linear View
 The Workflow Editor allows you to create a UI for your workflow, to make it easier to iterate on your generations. 
 
-To add an input to the Linear UI, right click on the input label and select "Add to Linear View".
+To add an input to the Linear UI, right click on the **input label** and select "Add to Linear View".
 
 The Linear UI View will also be part of the saved workflow, allowing you share workflows and enable other to use them, regardless of complexity. 
 
@@ -30,7 +37,7 @@ Any node or input field can be renamed in the workflow editor. If the input fiel
 Nodes have a "Use Cache" option in their footer. This allows for performance improvements by using the previously cached values during the workflow processing. 
 
 
-## Important Concepts 
+## Important Nodes & Concepts 
 
 There are several node grouping concepts that can be examined with a narrow focus. These (and other) groupings can be pieced together to make up functional graph setups, and are important to understanding how groups of nodes work together as part of a whole. Note that the screenshots below aren't examples of complete functioning node graphs (see Examples).
 
@@ -56,7 +63,7 @@ The ImageToLatents node takes in a pixel image and a VAE and outputs a latents.
 
 It is common to want to use both the same seed (for continuity) and random seeds (for variety). To define a seed, simply enter it into the 'Seed' field on a noise node. Conversely, the RandomInt node generates a random integer between 'Low' and 'High', and can be used as input to the 'Seed' edge point on a noise node to randomize your seed.
 
-![groupsrandseed](../assets/nodes/groupsrandseed.png)
+![groupsrandseed](../assets/nodes/groupsnoise.png)
 
 ### ControlNet
 

docs/nodes/communityNodes.md

@@ -13,25 +13,40 @@ If you'd prefer, you can also just download the whole node folder from the linke
 To use a community workflow, download the the `.json` node graph file and load it into Invoke AI via the **Load Workflow** button in the Workflow Editor. 
 
 - Community Nodes
+    + [Adapters-Linked](#adapters-linked-nodes)
+    + [Autostereogram](#autostereogram-nodes)
     + [Average Images](#average-images)
+    + [Clean Image Artifacts After Cut](#clean-image-artifacts-after-cut)
+    + [Close Color Mask](#close-color-mask) 
+    + [Clothing Mask](#clothing-mask)
+    + [Contrast Limited Adaptive Histogram Equalization](#contrast-limited-adaptive-histogram-equalization)
     + [Depth Map from Wavefront OBJ](#depth-map-from-wavefront-obj)
     + [Film Grain](#film-grain)
     + [Generative Grammar-Based Prompt Nodes](#generative-grammar-based-prompt-nodes)
     + [GPT2RandomPromptMaker](#gpt2randompromptmaker)
     + [Grid to Gif](#grid-to-gif)
     + [Halftone](#halftone)
-    + [Ideal Size](#ideal-size)
+    + [Hand Refiner with MeshGraphormer](#hand-refiner-with-meshgraphormer)
     + [Image and Mask Composition Pack](#image-and-mask-composition-pack)
+    + [Image Dominant Color](#image-dominant-color)
     + [Image to Character Art Image Nodes](#image-to-character-art-image-nodes)
     + [Image Picker](#image-picker)
+    + [Image Resize Plus](#image-resize-plus)
     + [Load Video Frame](#load-video-frame)
     + [Make 3D](#make-3d)
+    + [Mask Operations](#mask-operations)
     + [Match Histogram](#match-histogram)
+    + [Metadata-Linked](#metadata-linked-nodes)
+    + [Negative Image](#negative-image)
+    + [Nightmare Promptgen](#nightmare-promptgen)    
     + [Oobabooga](#oobabooga)
     + [Prompt Tools](#prompt-tools)
     + [Remote Image](#remote-image)
+    + [BriaAI Background Remove](#briaai-remove-background)
+    + [Remove Background](#remove-background)    
     + [Retroize](#retroize)
     + [Size Stepper Nodes](#size-stepper-nodes)
+    + [Simple Skin Detection](#simple-skin-detection)
     + [Text font to Image](#text-font-to-image)
     + [Thresholding](#thresholding)
     + [Unsharp Mask](#unsharp-mask)
@@ -41,6 +56,30 @@ To use a community workflow, download the the `.json` node graph file and load i
 - [Help](#help)
 
 
+--------------------------------
+### Adapters Linked Nodes
+
+**Description:** A set of nodes for linked adapters (ControlNet, IP-Adaptor & T2I-Adapter). This allows multiple adapters to be chained together without using a `collect` node which means it can be used inside an `iterate` node without any collecting on every iteration issues.
+
+- `ControlNet-Linked` - Collects ControlNet info to pass to other nodes.
+- `IP-Adapter-Linked` - Collects IP-Adapter info to pass to other nodes.
+- `T2I-Adapter-Linked` - Collects T2I-Adapter info to pass to other nodes.
+
+Note: These are inherited from the core nodes so any update to the core nodes should be reflected in these. 
+
+**Node Link:** https://github.com/skunkworxdark/adapters-linked-nodes
+
+--------------------------------
+### Autostereogram Nodes
+
+**Description:** Generate autostereogram images from a depth map. This is not a very practically useful node but more a 90s nostalgic indulgence as I used to love these images as a kid.
+
+**Node Link:** https://github.com/skunkworxdark/autostereogram_nodes
+
+**Example Usage:**
+</br>
+<img src="https://github.com/skunkworxdark/autostereogram_nodes/blob/main/images/spider.png" width="200" /> -> <img src="https://github.com/skunkworxdark/autostereogram_nodes/blob/main/images/spider-depth.png" width="200" /> -> <img src="https://github.com/skunkworxdark/autostereogram_nodes/raw/main/images/spider-dots.png" width="200" /> <img src="https://github.com/skunkworxdark/autostereogram_nodes/raw/main/images/spider-pattern.png" width="200" />
+
 --------------------------------
 ### Average Images
 
@@ -48,6 +87,46 @@ To use a community workflow, download the the `.json` node graph file and load i
 
 **Node Link:** https://github.com/JPPhoto/average-images-node
 
+--------------------------------
+### Clean Image Artifacts After Cut
+
+Description: Removes residual artifacts after an image is separated from its background.
+
+Node Link: https://github.com/VeyDlin/clean-artifact-after-cut-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/clean-artifact-after-cut-node/master/.readme/node.png" width="500" />
+
+--------------------------------
+### Close Color Mask
+
+Description: Generates a mask for images based on a closely matching color, useful for color-based selections.
+
+Node Link: https://github.com/VeyDlin/close-color-mask-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/close-color-mask-node/master/.readme/node.png" width="500" />
+
+--------------------------------
+### Clothing Mask
+
+Description: Employs a U2NET neural network trained for the segmentation of clothing items in images.
+
+Node Link: https://github.com/VeyDlin/clothing-mask-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/clothing-mask-node/master/.readme/node.png" width="500" />
+
+--------------------------------
+### Contrast Limited Adaptive Histogram Equalization
+
+Description: Enhances local image contrast using adaptive histogram equalization with contrast limiting.
+
+Node Link: https://github.com/VeyDlin/clahe-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/clahe-node/master/.readme/node.png" width="500" />
+
 --------------------------------
 ### Depth Map from Wavefront OBJ
 
@@ -131,13 +210,18 @@ CMYK Halftone Output:
 <img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c59c578f-db8e-4d66-8c66-2851752d75ea" width="300" />
 
 --------------------------------
-### Ideal Size
 
-**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
+### Hand Refiner with MeshGraphormer
 
-**Node Link:** https://github.com/JPPhoto/ideal-size-node
+**Description**: Hand Refiner takes in your image and automatically generates a fixed depth map for the hands along with a mask of the hands region that will conveniently allow you to use them along with ControlNet to fix the wonky hands generated by Stable Diffusion
+
+**Node Link:** https://github.com/blessedcoolant/invoke_meshgraphormer
+
+**View**
+<img src="https://raw.githubusercontent.com/blessedcoolant/invoke_meshgraphormer/main/assets/preview.jpg" />
 
 --------------------------------
+
 ### Image and Mask Composition Pack
 
 **Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
@@ -164,6 +248,16 @@ This includes 15 Nodes:
   
 </br><img src="https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_pack_overview.jpg" width="500" />
 
+--------------------------------
+### Image Dominant Color
+
+Description: Identifies and extracts the dominant color from an image using k-means clustering.
+
+Node Link: https://github.com/VeyDlin/image-dominant-color-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/image-dominant-color-node/master/.readme/node.png" width="500" />
+
 --------------------------------
 ### Image to Character Art Image Nodes
 
@@ -185,6 +279,17 @@ This includes 15 Nodes:
 
 **Node Link:** https://github.com/JPPhoto/image-picker-node
 
+--------------------------------
+### Image Resize Plus
+
+Description: Provides various image resizing options such as fill, stretch, fit, center, and crop.
+
+Node Link: https://github.com/VeyDlin/image-resize-plus-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/image-resize-plus-node/master/.readme/node.png" width="500" />
+
+
 --------------------------------
 ### Load Video Frame
 
@@ -209,6 +314,16 @@ This includes 15 Nodes:
 <img src="https://gitlab.com/srcrr/shift3d/-/raw/main/example-1.png" width="300" />
 <img src="https://gitlab.com/srcrr/shift3d/-/raw/main/example-2.png" width="300" />
 
+--------------------------------
+### Mask Operations
+
+Description: Offers logical operations (OR, SUB, AND) for combining and manipulating image masks.
+
+Node Link: https://github.com/VeyDlin/mask-operations-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/mask-operations-node/master/.readme/node.png" width="500" />
+
 --------------------------------
 ### Match Histogram
 
@@ -226,6 +341,37 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 <img src="https://github.com/skunkworxdark/match_histogram/assets/21961335/ed12f329-a0ef-444a-9bae-129ed60d6097" width="300" />
 
+--------------------------------
+### Metadata Linked Nodes
+
+**Description:** A set of nodes for Metadata. Collect Metadata from within an `iterate` node & extract metadata from an image.
+
+- `Metadata Item Linked` - Allows collecting of metadata while within an iterate node with no need for a collect node or conversion to metadata node.
+- `Metadata From Image` - Provides Metadata from an image.
+- `Metadata To String` - Extracts a String value of a label from metadata.
+- `Metadata To Integer` - Extracts an Integer value of a label from metadata.
+- `Metadata To Float` - Extracts a Float value of a label from metadata.
+- `Metadata To Scheduler` - Extracts a Scheduler value of a label from metadata.
+
+**Node Link:** https://github.com/skunkworxdark/metadata-linked-nodes
+
+--------------------------------
+### Negative Image
+
+Description: Creates a negative version of an image, effective for visual effects and mask inversion.
+
+Node Link: https://github.com/VeyDlin/negative-image-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/negative-image-node/master/.readme/node.png" width="500" />
+
+--------------------------------
+### Nightmare Promptgen
+
+**Description:** Nightmare Prompt Generator - Uses a local text generation model to create unique imaginative (but usually nightmarish) prompts for InvokeAI. By default, it allows you to choose from some gpt-neo models I finetuned on over 2500 of my own InvokeAI prompts in Compel format, but you're able to add your own, as well. Offers support for replacing any troublesome words with a random choice from list you can also define.
+
+**Node Link:** [https://github.com/gogurtenjoyer/nightmare-promptgen](https://github.com/gogurtenjoyer/nightmare-promptgen)
+
 --------------------------------
 ### Oobabooga
 
@@ -289,6 +435,26 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 **Node Link:** https://github.com/fieldOfView/InvokeAI-remote_image
 
+--------------------------------
+
+### BriaAI Remove Background
+
+**Description**: Implements one click background removal with BriaAI's new version 1.4 model which seems to be be producing better results than any other previous background removal tool.
+
+**Node Link:** https://github.com/blessedcoolant/invoke_bria_rmbg
+
+**View**
+<img src="https://raw.githubusercontent.com/blessedcoolant/invoke_bria_rmbg/main/assets/preview.jpg" />
+
+--------------------------------
+### Remove Background
+
+Description: An integration of the rembg package to remove backgrounds from images using multiple U2NET models.
+
+Node Link: https://github.com/VeyDlin/remove-background-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/remove-background-node/master/.readme/node.png" width="500" />
 
 --------------------------------
 ### Retroize
@@ -301,6 +467,17 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 <img src="https://github.com/Ar7ific1al/InvokeAI_nodes_retroize/assets/2306586/de8b4fa6-324c-4c2d-b36c-297600c73974" width="500" />
 
+--------------------------------
+### Simple Skin Detection
+
+Description: Detects skin in images based on predefined color thresholds.
+
+Node Link: https://github.com/VeyDlin/simple-skin-detection-node
+
+View:
+</br><img src="https://raw.githubusercontent.com/VeyDlin/simple-skin-detection-node/master/.readme/node.png" width="500" />
+
+
 --------------------------------
 ### Size Stepper Nodes
 
@@ -386,6 +563,7 @@ See full docs here: https://github.com/skunkworxdark/XYGrid_nodes/edit/main/READ
 
 <img src="https://github.com/skunkworxdark/XYGrid_nodes/blob/main/images/collage.png" width="300" />
 
+
 --------------------------------
 ### Example Node Template
 

docs/nodes/defaultNodes.md

@@ -36,6 +36,7 @@ their descriptions.
 | Integer Math                                                  | Perform basic math operations on two integers                                                                                                        |
 | Convert Image Mode                                            | Converts an image to a different mode.                                                                                                               |
 | Crop Image                                                    | Crops an image to a specified box. The box can be outside of the image.                                                                              |
+| Ideal Size                                                    | Calculates an ideal image size for latents for a first pass of a multi-pass upscaling to avoid duplication and other artifacts                       |
 | Image Hue Adjustment                                          | Adjusts the Hue of an image.                                                                                                                         |
 | Inverse Lerp Image                                            | Inverse linear interpolation of all pixels of an image                                                                                               |
 | Image Primitive                                               | An image primitive value                                                                                                                             |
@@ -80,7 +81,7 @@ their descriptions.
 | ONNX Text to Latents                                          | Generates latents from conditionings.                                                                                                                |
 | ONNX Model Loader                                             | Loads a main model, outputting its submodels.                                                                                                        |
 | OpenCV Inpaint                                                | Simple inpaint using opencv.                                                                                                                         |
-| Openpose Processor                                            | Applies Openpose processing to image                                                                                                                 |
+| DW Openpose Processor                                            | Applies Openpose processing to image                                                                                                                 |
 | PIDI Processor                                                | Applies PIDI processing to image                                                                                                                     |
 | Prompts from File                                             | Loads prompts from a text file                                                                                                                       |
 | Random Integer                                                | Outputs a single random integer.                                                                                                                     |

docs/nodes/exampleWorkflows.md

@@ -1,6 +1,6 @@
 # Example Workflows
 
-We've curated some example workflows for you to get started with Workflows in InvokeAI
+We've curated some example workflows for you to get started with Workflows in InvokeAI! These can also be found in the Workflow Library, located in the Workflow Editor of Invoke.
 
 To use them, right click on your desired workflow, follow the link to GitHub and click the "⬇" button to download the raw file. You can then use the "Load Workflow" functionality in InvokeAI to load the workflow and start generating images!
 

docs/other/CONTRIBUTORS.md

@@ -13,46 +13,69 @@ We thank them for all of their time and hard work.
 
 - [Lincoln D. Stein](mailto:lincoln.stein@gmail.com)
 
-## **Current core team**
+## **Current Core Team**
 
 * @lstein (Lincoln Stein) - Co-maintainer
 * @blessedcoolant - Co-maintainer
 * @hipsterusername (Kent Keirsey) - Co-maintainer, CEO, Positive Vibes
 * @psychedelicious (Spencer Mabrito) - Web Team Leader
-* @Kyle0654 (Kyle Schouviller) - Node Architect and General Backend Wizard
-* @damian0815 - Attention Systems and Compel Maintainer
-* @ebr (Eugene Brodsky) - Cloud/DevOps/Sofware engineer; your friendly neighbourhood cluster-autoscaler
-* @genomancer (Gregg Helt) - Controlnet support
-* @StAlKeR7779 (Sergey Borisov) - Torch stack, ONNX, model management, optimization
+* @chainchompa (Jennifer Player) - Web Development & Chain-Chomping
+* @josh is toast (Josh Corbett) - Web Development
 * @cheerio (Mary Rogers) - Lead Engineer & Web App Development
+* @ebr (Eugene Brodsky) - Cloud/DevOps/Sofware engineer; your friendly neighbourhood cluster-autoscaler
+* @sunija - Standalone version
+* @genomancer (Gregg Helt) - Controlnet support
 * @brandon (Brandon Rising) - Platform, Infrastructure, Backend Systems
 * @ryanjdick (Ryan Dick) - Machine Learning & Training
-* @millu (Millun Atluri) - Community Manager, Documentation, Node-wrangler
-* @chainchompa (Jennifer Player) - Web Development & Chain-Chomping
+* @JPPhoto - Core image generation nodes
+* @dunkeroni - Image generation backend
+* @SkunkWorxDark - Image generation backend
 * @keturn (Kevin Turner) - Diffusers
+* @millu (Millun Atluri) - Community Wizard, Documentation, Node-wrangler, 
+* @glimmerleaf (Devon Hopkins) - Community Wizard
 * @gogurt enjoyer - Discord moderator and end user support
 * @whosawhatsis - Discord moderator and end user support
 * @dwinrger - Discord moderator and end user support
 * @526christian - Discord moderator and end user support
+* @harvester62 -  Discord moderator and end user support
+
+
+## **Honored Team Alumni**
+
+* @StAlKeR7779 (Sergey Borisov) - Torch stack, ONNX, model management, optimization
+* @damian0815 - Attention Systems and Compel Maintainer
+* @netsvetaev (Artur) - Localization support
+* @Kyle0654 (Kyle Schouviller) - Node Architect and General Backend Wizard
+* @tildebyte - Installation and configuration
+* @mauwii (Matthias Wilde) - Installation, release, continuous integration
+
 
 ## **Full List of Contributors by Commit Name**
 
+- 이승석
 - AbdBarho
 - ablattmann
 - AdamOStark
 - Adam Rice
 - Airton Silva
+- Aldo Hoeben
 - Alexander Eichhorn
 - Alexandre D. Roberge
+- Alexandre Macabies
+- Alfie John
 - Andreas Rozek
 - Andre LaBranche
 - Andy Bearman
 - Andy Luhrs
 - Andy Pilate
+- Anonymous
+- Anthony Monthe
 - Any-Winter-4079
 - apolinario
+- Ar7ific1al
 - ArDiouscuros
 - Armando C. Santisbon
+- Arnold Cordewiner
 - Arthur Holstvoogd
 - artmen1516
 - Artur
@@ -64,13 +87,16 @@ We thank them for all of their time and hard work.
 - blhook
 - BlueAmulet
 - Bouncyknighter
+- Brandon
 - Brandon Rising
 - Brent Ozar
 - Brian Racer
 - bsilvereagle
 - c67e708d
+- camenduru
 - CapableWeb
 - Carson Katri
+- chainchompa
 - Chloe
 - Chris Dawson
 - Chris Hayes
@@ -86,30 +112,45 @@ We thank them for all of their time and hard work.
 - cpacker
 - Cragin Godley
 - creachec
+- CrypticWit
+- d8ahazard
+- damian
+- damian0815
+- Damian at mba
 - Damian Stewart
 - Daniel Manzke
 - Danny Beer
 - Dan Sully
+- Darren Ringer
 - David Burnett
 - David Ford
 - David Regla
+- David Sisco
 - David Wager
 - Daya Adianto
 - db3000
+- DekitaRPG
 - Denis Olshin
 - Dennis
+- dependabot[bot]
+- Dmitry Parnas
+- Dobrynia100
 - Dominic Letz
 - DrGunnarMallon
+- Drun555
+- dunkeroni
 - Edward Johan
 - elliotsayes
 - Elrik
 - ElrikUnderlake
 - Eric Khun
 - Eric Wolf
+- Eugene
 - Eugene Brodsky
 - ExperimentalCyborg
 - Fabian Bahl
 - Fabio 'MrWHO' Torchetti
+- Fattire
 - fattire
 - Felipe Nogueira
 - Félix Sanz
@@ -118,8 +159,12 @@ We thank them for all of their time and hard work.
 - gabrielrotbart
 - gallegonovato
 - Gérald LONLAS
+- Gille
 - GitHub Actions Bot
+- glibesyck
 - gogurtenjoyer
+- Gohsuke Shimada
+- greatwolf
 - greentext2
 - Gregg Helt
 - H4rk
@@ -131,6 +176,7 @@ We thank them for all of their time and hard work.
 - Hosted Weblate
 - Iman Karim
 - ismail ihsan bülbül
+- ItzAttila
 - Ivan Efimov
 - jakehl
 - Jakub Kolčář
@@ -141,6 +187,7 @@ We thank them for all of their time and hard work.
 - Jason Toffaletti
 - Jaulustus
 - Jeff Mahoney
+- Jennifer Player
 - jeremy
 - Jeremy Clark
 - JigenD
@@ -148,19 +195,26 @@ We thank them for all of their time and hard work.
 - Johan Roxendal
 - Johnathon Selstad
 - Jonathan
+- Jordan Hewitt
 - Joseph Dries III
+- Josh Corbett
 - JPPhoto
 - jspraul
+- junzi
 - Justin Wong
 - Juuso V
 - Kaspar Emanuel
 - Katsuyuki-Karasawa
+- Keerigan45
 - Kent Keirsey
+- Kevin Brack
 - Kevin Coakley
 - Kevin Gibbons
 - Kevin Schaul
 - Kevin Turner
+- Kieran Klaassen
 - krummrey
+- Kyle
 - Kyle Lacy
 - Kyle Schouviller
 - Lawrence Norton
@@ -171,10 +225,15 @@ We thank them for all of their time and hard work.
 - Lynne Whitehorn
 - majick
 - Marco Labarile
+- Marta Nahorniuk
 - Martin Kristiansen
+- Mary Hipp
+- maryhipp
 - Mary Hipp Rogers
+- mastercaster
 - mastercaster9000
 - Matthias Wild
+- mauwii
 - michaelk71
 - mickr777
 - Mihai
@@ -182,11 +241,15 @@ We thank them for all of their time and hard work.
 - Mikhail Tishin
 - Millun Atluri
 - Minjune Song
+- Mitchell Allain
 - mitien
 - mofuzz
 - Muhammad Usama
 - Name
 - _nderscore
+- Neil Wang
+- nekowaiz
+- nemuruibai
 - Netzer R
 - Nicholas Koh
 - Nicholas Körfer
@@ -197,9 +260,11 @@ We thank them for all of their time and hard work.
 - ofirkris
 - Olivier Louvignes
 - owenvincent
+- pand4z31
 - Patrick Esser
 - Patrick Tien
 - Patrick von Platen
+- Paul Curry
 - Paul Sajna
 - pejotr
 - Peter Baylies
@@ -207,6 +272,7 @@ We thank them for all of their time and hard work.
 - plucked
 - prixt
 - psychedelicious
+- psychedelicious@windows
 - Rainer Bernhardt
 - Riccardo Giovanetti
 - Rich Jones
@@ -215,16 +281,22 @@ We thank them for all of their time and hard work.
 - Robert Bolender
 - Robin Rombach
 - Rohan Barar
+- Rohinish
 - rpagliuca
 - rromb
 - Rupesh Sreeraman
+- Ryan
 - Ryan Cao
+- Ryan Dick
 - Saifeddine
 - Saifeddine ALOUI
+- Sam
 - SammCheese
+- Sam McLeod
 - Sammy
 - sammyf
 - Samuel Husso
+- Saurav Maheshkar
 - Scott Lahteine
 - Sean McLellan
 - Sebastian Aigner
@@ -232,16 +304,21 @@ We thank them for all of their time and hard work.
 - Sergey Krashevich
 - Shapor Naghibzadeh
 - Shawn Zhong
+- Simona Liliac
 - Simon Vans-Colina
 - skunkworxdark
 - slashtechno
+- SoheilRezaei
+- Song, Pengcheng
 - spezialspezial
 - ssantos
 - StAlKeR7779
+- Stefan Tobler
 - Stephan Koglin-Fischer
 - SteveCaruso
 - Steve Martinelli
 - Steven Frank
+- Surisen
 - System X - Files
 - Taylor Kems
 - techicode
@@ -260,26 +337,34 @@ We thank them for all of their time and hard work.
 - tyler
 - unknown
 - user1
+- vedant-3010
 - Vedant Madane
 - veprogames
 - wa.code
 - wfng92
+- whjms
 - whosawhatsis
 - Will
 - William Becher
 - William Chong
+- Wilson E. Alvarez
+- woweenie
+- Wubbbi
 - xra
 - Yeung Yiu Hung
 - ymgenesis
 - Yorzaren
 - Yosuke Shinya
 - yun saki
+- ZachNagengast
 - Zadagu
 - zeptofine
+- Zerdoumi
+- Васянатор
 - 冯不游
 - 唐澤 克幸
 
-## **Original CompVis Authors**
+## **Original CompVis (Stable Diffusion) Authors**
 
 - [Robin Rombach](https://github.com/rromb)
 - [Patrick von Platen](https://github.com/patrickvonplaten)

docs/stylesheets/extra.css

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

docs/workflows/Text_to_Image.json

@@ -1,8 +1,8 @@
 {
-  "name": "Text to Image",
+  "name": "Text to Image - SD1.5",
   "author": "InvokeAI",
   "description": "Sample text to image workflow for Stable Diffusion 1.5/2",
-  "version": "1.0.1",
+  "version": "1.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "text2image, SD1.5, SD2, default",
   "notes": "",
@@ -18,10 +18,19 @@
     {
       "nodeId": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
       "fieldName": "prompt"
+    },
+    {
+      "nodeId": "55705012-79b9-4aac-9f26-c0b10309785b",
+      "fieldName": "width"
+    },
+    {
+      "nodeId": "55705012-79b9-4aac-9f26-c0b10309785b",
+      "fieldName": "height"
     }
   ],
   "meta": {
-    "version": "1.0.0"
+    "category": "default",
+    "version": "2.0.0"
   },
   "nodes": [
     {
@@ -30,44 +39,56 @@
       "data": {
         "id": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
         "type": "compel",
+        "label": "Negative Compel Prompt",
+        "isOpen": true,
+        "notes": "",
+        "isIntermediate": true,
+        "useCache": true,
+        "version": "1.0.0",
+        "nodePack": "invokeai",
         "inputs": {
           "prompt": {
             "id": "7739aff6-26cb-4016-8897-5a1fb2305e4e",
             "name": "prompt",
-            "type": "string",
             "fieldKind": "input",
             "label": "Negative Prompt",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "StringField"
+            },
             "value": ""
           },
           "clip": {
             "id": "48d23dce-a6ae-472a-9f8c-22a714ea5ce0",
             "name": "clip",
-            "type": "ClipField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "ClipField"
+            }
           }
         },
         "outputs": {
           "conditioning": {
             "id": "37cf3a9d-f6b7-4b64-8ff6-2558c5ecc447",
             "name": "conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "ConditioningField"
+            }
           }
-        },
-        "label": "Negative Compel Prompt",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true,
-        "useCache": true,
-        "version": "1.0.0"
+        }
       },
       "width": 320,
-      "height": 261,
+      "height": 259,
       "position": {
-        "x": 995.7263915923627,
-        "y": 239.67783573351227
+        "x": 1000,
+        "y": 350
       }
     },
     {
@@ -76,37 +97,60 @@
       "data": {
         "id": "55705012-79b9-4aac-9f26-c0b10309785b",
         "type": "noise",
+        "label": "",
+        "isOpen": true,
+        "notes": "",
+        "isIntermediate": true,
+        "useCache": true,
+        "version": "1.0.1",
+        "nodePack": "invokeai",
         "inputs": {
           "seed": {
             "id": "6431737c-918a-425d-a3b4-5d57e2f35d4d",
             "name": "seed",
-            "type": "integer",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            },
             "value": 0
           },
           "width": {
             "id": "38fc5b66-fe6e-47c8-bba9-daf58e454ed7",
             "name": "width",
-            "type": "integer",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            },
             "value": 512
           },
           "height": {
             "id": "16298330-e2bf-4872-a514-d6923df53cbb",
             "name": "height",
-            "type": "integer",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            },
             "value": 512
           },
           "use_cpu": {
             "id": "c7c436d3-7a7a-4e76-91e4-c6deb271623c",
             "name": "use_cpu",
-            "type": "boolean",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "BooleanField"
+            },
             "value": true
           }
         },
@@ -114,35 +158,40 @@
           "noise": {
             "id": "50f650dc-0184-4e23-a927-0497a96fe954",
             "name": "noise",
-            "type": "LatentsField",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "LatentsField"
+            }
           },
           "width": {
             "id": "bb8a452b-133d-42d1-ae4a-3843d7e4109a",
             "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            }
           },
           "height": {
             "id": "35cfaa12-3b8b-4b7a-a884-327ff3abddd9",
             "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            }
           }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true,
-        "useCache": true,
-        "version": "1.0.0"
+        }
       },
       "width": 320,
-      "height": 389,
+      "height": 388,
       "position": {
-        "x": 993.4442117555518,
-        "y": 605.6757415334787
+        "x": 600,
+        "y": 325
       }
     },
     {
@@ -151,13 +200,24 @@
       "data": {
         "id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
         "type": "main_model_loader",
+        "label": "",
+        "isOpen": true,
+        "notes": "",
+        "isIntermediate": true,
+        "useCache": true,
+        "version": "1.0.0",
+        "nodePack": "invokeai",
         "inputs": {
           "model": {
             "id": "993eabd2-40fd-44fe-bce7-5d0c7075ddab",
             "name": "model",
-            "type": "MainModelField",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "MainModelField"
+            },
             "value": {
               "model_name": "stable-diffusion-v1-5",
               "base_model": "sd-1",
@@ -169,35 +229,40 @@
           "unet": {
             "id": "5c18c9db-328d-46d0-8cb9-143391c410be",
             "name": "unet",
-            "type": "UNetField",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "UNetField"
+            }
           },
           "clip": {
             "id": "6effcac0-ec2f-4bf5-a49e-a2c29cf921f4",
             "name": "clip",
-            "type": "ClipField",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "ClipField"
+            }
           },
           "vae": {
             "id": "57683ba3-f5f5-4f58-b9a2-4b83dacad4a1",
             "name": "vae",
-            "type": "VaeField",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "VaeField"
+            }
           }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true,
-        "useCache": true,
-        "version": "1.0.0"
+        }
       },
       "width": 320,
       "height": 226,
       "position": {
-        "x": 163.04436745878343,
-        "y": 254.63156870373479
+        "x": 600,
+        "y": 25
       }
     },
     {
@@ -206,44 +271,56 @@
       "data": {
         "id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
         "type": "compel",
+        "label": "Positive Compel Prompt",
+        "isOpen": true,
+        "notes": "",
+        "isIntermediate": true,
+        "useCache": true,
+        "version": "1.0.0",
+        "nodePack": "invokeai",
         "inputs": {
           "prompt": {
             "id": "7739aff6-26cb-4016-8897-5a1fb2305e4e",
             "name": "prompt",
-            "type": "string",
             "fieldKind": "input",
             "label": "Positive Prompt",
-            "value": ""
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "StringField"
+            },
+            "value": "Super cute tiger cub, national geographic award-winning photograph"
           },
           "clip": {
             "id": "48d23dce-a6ae-472a-9f8c-22a714ea5ce0",
             "name": "clip",
-            "type": "ClipField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "ClipField"
+            }
           }
         },
         "outputs": {
           "conditioning": {
             "id": "37cf3a9d-f6b7-4b64-8ff6-2558c5ecc447",
             "name": "conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "ConditioningField"
+            }
           }
-        },
-        "label": "Positive Compel Prompt",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true,
-        "useCache": true,
-        "version": "1.0.0"
+        }
       },
       "width": 320,
-      "height": 261,
+      "height": 259,
       "position": {
-        "x": 595.7263915923627,
-        "y": 239.67783573351227
+        "x": 1000,
+        "y": 25
       }
     },
     {
@@ -252,21 +329,36 @@
       "data": {
         "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
         "type": "rand_int",
+        "label": "Random Seed",
+        "isOpen": false,
+        "notes": "",
+        "isIntermediate": true,
+        "useCache": false,
+        "version": "1.0.0",
+        "nodePack": "invokeai",
         "inputs": {
           "low": {
             "id": "3ec65a37-60ba-4b6c-a0b2-553dd7a84b84",
             "name": "low",
-            "type": "integer",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            },
             "value": 0
           },
           "high": {
             "id": "085f853a-1a5f-494d-8bec-e4ba29a3f2d1",
             "name": "high",
-            "type": "integer",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            },
             "value": 2147483647
           }
         },
@@ -274,23 +366,20 @@
           "value": {
             "id": "812ade4d-7699-4261-b9fc-a6c9d2ab55ee",
             "name": "value",
-            "type": "integer",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            }
           }
-        },
-        "label": "Random Seed",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true,
-        "useCache": false,
-        "version": "1.0.0"
+        }
       },
       "width": 320,
-      "height": 218,
+      "height": 32,
       "position": {
-        "x": 541.094822888628,
-        "y": 694.5704476446829
+        "x": 600,
+        "y": 275
       }
     },
     {
@@ -299,144 +388,224 @@
       "data": {
         "id": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
         "type": "denoise_latents",
+        "label": "",
+        "isOpen": true,
+        "notes": "",
+        "isIntermediate": true,
+        "useCache": true,
+        "version": "1.5.0",
+        "nodePack": "invokeai",
         "inputs": {
           "positive_conditioning": {
             "id": "90b7f4f8-ada7-4028-8100-d2e54f192052",
             "name": "positive_conditioning",
-            "type": "ConditioningField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "ConditioningField"
+            }
           },
           "negative_conditioning": {
             "id": "9393779e-796c-4f64-b740-902a1177bf53",
             "name": "negative_conditioning",
-            "type": "ConditioningField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "ConditioningField"
+            }
           },
           "noise": {
             "id": "8e17f1e5-4f98-40b1-b7f4-86aeeb4554c1",
             "name": "noise",
-            "type": "LatentsField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "LatentsField"
+            }
           },
           "steps": {
             "id": "9b63302d-6bd2-42c9-ac13-9b1afb51af88",
             "name": "steps",
-            "type": "integer",
             "fieldKind": "input",
             "label": "",
-            "value": 10
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            },
+            "value": 50
           },
           "cfg_scale": {
             "id": "87dd04d3-870e-49e1-98bf-af003a810109",
             "name": "cfg_scale",
-            "type": "FloatPolymorphic",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": true,
+              "name": "FloatField"
+            },
             "value": 7.5
           },
           "denoising_start": {
             "id": "f369d80f-4931-4740-9bcd-9f0620719fab",
             "name": "denoising_start",
-            "type": "float",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "FloatField"
+            },
             "value": 0
           },
           "denoising_end": {
             "id": "747d10e5-6f02-445c-994c-0604d814de8c",
             "name": "denoising_end",
-            "type": "float",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "FloatField"
+            },
             "value": 1
           },
           "scheduler": {
             "id": "1de84a4e-3a24-4ec8-862b-16ce49633b9b",
             "name": "scheduler",
-            "type": "Scheduler",
             "fieldKind": "input",
             "label": "",
-            "value": "euler"
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "SchedulerField"
+            },
+            "value": "unipc"
           },
           "unet": {
             "id": "ffa6fef4-3ce2-4bdb-9296-9a834849489b",
             "name": "unet",
-            "type": "UNetField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "UNetField"
+            }
           },
           "control": {
             "id": "077b64cb-34be-4fcc-83f2-e399807a02bd",
             "name": "control",
-            "type": "ControlPolymorphic",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": true,
+              "name": "ControlField"
+            }
           },
           "ip_adapter": {
             "id": "1d6948f7-3a65-4a65-a20c-768b287251aa",
             "name": "ip_adapter",
-            "type": "IPAdapterPolymorphic",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": true,
+              "name": "IPAdapterField"
+            }
           },
           "t2i_adapter": {
             "id": "75e67b09-952f-4083-aaf4-6b804d690412",
             "name": "t2i_adapter",
-            "type": "T2IAdapterPolymorphic",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": true,
+              "name": "T2IAdapterField"
+            }
+          },
+          "cfg_rescale_multiplier": {
+            "id": "9101f0a6-5fe0-4826-b7b3-47e5d506826c",
+            "name": "cfg_rescale_multiplier",
+            "fieldKind": "input",
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "FloatField"
+            },
+            "value": 0
           },
           "latents": {
             "id": "334d4ba3-5a99-4195-82c5-86fb3f4f7d43",
             "name": "latents",
-            "type": "LatentsField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "LatentsField"
+            }
           },
           "denoise_mask": {
             "id": "0d3dbdbf-b014-4e95-8b18-ff2ff9cb0bfa",
             "name": "denoise_mask",
-            "type": "DenoiseMaskField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "DenoiseMaskField"
+            }
           }
         },
         "outputs": {
           "latents": {
             "id": "70fa5bbc-0c38-41bb-861a-74d6d78d2f38",
             "name": "latents",
-            "type": "LatentsField",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "LatentsField"
+            }
           },
           "width": {
             "id": "98ee0e6c-82aa-4e8f-8be5-dc5f00ee47f0",
             "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            }
           },
           "height": {
             "id": "e8cb184a-5e1a-47c8-9695-4b8979564f5d",
             "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            }
           }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true,
-        "useCache": true,
-        "version": "1.4.0"
+        }
       },
       "width": 320,
-      "height": 646,
+      "height": 703,
       "position": {
-        "x": 1476.5794704734735,
-        "y": 256.80174342731783
+        "x": 1400,
+        "y": 25
       }
     },
     {
@@ -445,153 +614,185 @@
       "data": {
         "id": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
         "type": "l2i",
+        "label": "",
+        "isOpen": true,
+        "notes": "",
+        "isIntermediate": false,
+        "useCache": true,
+        "version": "1.2.0",
+        "nodePack": "invokeai",
         "inputs": {
           "metadata": {
             "id": "ab375f12-0042-4410-9182-29e30db82c85",
             "name": "metadata",
-            "type": "MetadataField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "MetadataField"
+            }
           },
           "latents": {
             "id": "3a7e7efd-bff5-47d7-9d48-615127afee78",
             "name": "latents",
-            "type": "LatentsField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "LatentsField"
+            }
           },
           "vae": {
             "id": "a1f5f7a1-0795-4d58-b036-7820c0b0ef2b",
             "name": "vae",
-            "type": "VaeField",
             "fieldKind": "input",
-            "label": ""
+            "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "VaeField"
+            }
           },
           "tiled": {
             "id": "da52059a-0cee-4668-942f-519aa794d739",
             "name": "tiled",
-            "type": "boolean",
             "fieldKind": "input",
             "label": "",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "BooleanField"
+            },
             "value": false
           },
           "fp32": {
             "id": "c4841df3-b24e-4140-be3b-ccd454c2522c",
             "name": "fp32",
-            "type": "boolean",
             "fieldKind": "input",
             "label": "",
-            "value": false
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "BooleanField"
+            },
+            "value": true
           }
         },
         "outputs": {
           "image": {
             "id": "72d667d0-cf85-459d-abf2-28bd8b823fe7",
             "name": "image",
-            "type": "ImageField",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "ImageField"
+            }
           },
           "width": {
             "id": "c8c907d8-1066-49d1-b9a6-83bdcd53addc",
             "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            }
           },
           "height": {
             "id": "230f359c-b4ea-436c-b372-332d7dcdca85",
             "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
+            "fieldKind": "output",
+            "type": {
+              "isCollection": false,
+              "isCollectionOrScalar": false,
+              "name": "IntegerField"
+            }
           }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": false,
-        "useCache": true,
-        "version": "1.0.0"
+        }
       },
       "width": 320,
-      "height": 267,
+      "height": 266,
       "position": {
-        "x": 2037.9648469717395,
-        "y": 426.10844427600136
+        "x": 1800,
+        "y": 25
       }
     }
   ],
   "edges": [
     {
-      "source": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
-      "sourceHandle": "value",
-      "target": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "targetHandle": "seed",
       "id": "reactflow__edge-ea94bc37-d995-4a83-aa99-4af42479f2f2value-55705012-79b9-4aac-9f26-c0b10309785bseed",
-      "type": "default"
+      "source": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
+      "target": "55705012-79b9-4aac-9f26-c0b10309785b",
+      "type": "default",
+      "sourceHandle": "value",
+      "targetHandle": "seed"
     },
     {
-      "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "sourceHandle": "clip",
-      "target": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-      "targetHandle": "clip",
       "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8clip-7d8bf987-284f-413a-b2fd-d825445a5d6cclip",
-      "type": "default"
-    },
-    {
       "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
+      "target": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
+      "type": "default",
       "sourceHandle": "clip",
-      "target": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
-      "targetHandle": "clip",
+      "targetHandle": "clip"
+    },
+    {
       "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8clip-93dc02a4-d05b-48ed-b99c-c9b616af3402clip",
-      "type": "default"
+      "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
+      "target": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
+      "type": "default",
+      "sourceHandle": "clip",
+      "targetHandle": "clip"
     },
     {
-      "source": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "sourceHandle": "noise",
-      "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
-      "targetHandle": "noise",
       "id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-eea2702a-19fb-45b5-9d75-56b4211ec03cnoise",
-      "type": "default"
+      "source": "55705012-79b9-4aac-9f26-c0b10309785b",
+      "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
+      "type": "default",
+      "sourceHandle": "noise",
+      "targetHandle": "noise"
     },
     {
-      "source": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-      "sourceHandle": "conditioning",
-      "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
-      "targetHandle": "positive_conditioning",
       "id": "reactflow__edge-7d8bf987-284f-413a-b2fd-d825445a5d6cconditioning-eea2702a-19fb-45b5-9d75-56b4211ec03cpositive_conditioning",
-      "type": "default"
-    },
-    {
-      "source": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
+      "source": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
+      "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
+      "type": "default",
       "sourceHandle": "conditioning",
-      "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
-      "targetHandle": "negative_conditioning",
+      "targetHandle": "positive_conditioning"
+    },
+    {
       "id": "reactflow__edge-93dc02a4-d05b-48ed-b99c-c9b616af3402conditioning-eea2702a-19fb-45b5-9d75-56b4211ec03cnegative_conditioning",
-      "type": "default"
-    },
-    {
-      "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "sourceHandle": "unet",
+      "source": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
       "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
-      "targetHandle": "unet",
+      "type": "default",
+      "sourceHandle": "conditioning",
+      "targetHandle": "negative_conditioning"
+    },
+    {
       "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8unet-eea2702a-19fb-45b5-9d75-56b4211ec03cunet",
-      "type": "default"
-    },
-    {
-      "source": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
-      "sourceHandle": "latents",
-      "target": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
-      "targetHandle": "latents",
-      "id": "reactflow__edge-eea2702a-19fb-45b5-9d75-56b4211ec03clatents-58c957f5-0d01-41fc-a803-b2bbf0413d4flatents",
-      "type": "default"
-    },
-    {
       "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "sourceHandle": "vae",
+      "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
+      "type": "default",
+      "sourceHandle": "unet",
+      "targetHandle": "unet"
+    },
+    {
+      "id": "reactflow__edge-eea2702a-19fb-45b5-9d75-56b4211ec03clatents-58c957f5-0d01-41fc-a803-b2bbf0413d4flatents",
+      "source": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
       "target": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
-      "targetHandle": "vae",
+      "type": "default",
+      "sourceHandle": "latents",
+      "targetHandle": "latents"
+    },
+    {
       "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8vae-58c957f5-0d01-41fc-a803-b2bbf0413d4fvae",
-      "type": "default"
+      "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
+      "target": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
+      "type": "default",
+      "sourceHandle": "vae",
+      "targetHandle": "vae"
     }
   ]
-}
+}

installer/create_installer.sh

@@ -2,56 +2,60 @@
 
 set -e
 
-cd "$(dirname "$0")"
+BCYAN="\e[1;36m"
+BYELLOW="\e[1;33m"
+BGREEN="\e[1;32m"
+BRED="\e[1;31m"
+RED="\e[31m"
+RESET="\e[0m"
+
+function is_bin_in_path {
+    builtin type -P "$1" &>/dev/null
+}
+
+function git_show {
+    git show -s --format=oneline --abbrev-commit "$1" | cat
+}
 
 if [[ -v "VIRTUAL_ENV" ]]; then
     # we can't just call 'deactivate' because this function is not exported
     # to the environment of this script from the bash process that runs the script
-    echo "A virtual environment is activated. Please deactivate it before proceeding".
+    echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
     exit -1
 fi
 
-VERSION=$(cd ..; python -c "from invokeai.version import __version__ as version; print(version)")
+cd "$(dirname "$0")"
+
+echo
+echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
+echo "The current working directory is $(pwd)"
+read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
+echo
+
+# Some machines only have `python3` in PATH, others have `python` - make an alias.
+# We can use a function to approximate an alias within a non-interactive shell.
+if ! is_bin_in_path python && is_bin_in_path python3; then
+    function python {
+        python3 "$@"
+    }
+fi
+
+VERSION=$(
+    cd ..
+    python -c "from invokeai.version import __version__ as version; print(version)"
+)
 PATCH=""
 VERSION="v${VERSION}${PATCH}"
-LATEST_TAG="v3-latest"
 
-echo Building installer for version $VERSION
-echo "Be certain that you're in the 'installer' directory before continuing."
-read -p "Press any key to continue, or CTRL-C to exit..."
-
-read -e -p "Tag this repo with '${VERSION}' and '${LATEST_TAG}'? [n]: " input
-RESPONSE=${input:='n'}
-if [ "$RESPONSE" == 'y' ]; then
-
-    git push origin :refs/tags/$VERSION
-    if ! git tag -fa $VERSION ; then
-	    echo "Existing/invalid tag"
-	    exit -1
-    fi
-
-    git push origin :refs/tags/$LATEST_TAG
-    git tag -fa $LATEST_TAG
-
-    echo "remember to push --tags!"
-fi
+echo -e "${BGREEN}HEAD${RESET}:"
+git_show HEAD
+echo
 
 # ----------------------
 
-echo Building the wheel
-
-# install the 'build' package in the user site packages, if needed
-# could be improved by using a temporary venv, but it's tiny and harmless
-if [[ $(python -c 'from importlib.util import find_spec; print(find_spec("build") is None)') == "True" ]]; then
-    pip install --user build
-fi
-
-rm -r ../build
-python -m build --wheel --outdir dist/ ../.
-
-# ----------------------
-
-echo Building installer zip fles for InvokeAI $VERSION
+echo
+echo "Building installer zip files for InvokeAI ${VERSION}..."
+echo
 
 # get rid of any old ones
 rm -f *.zip
@@ -59,12 +63,11 @@ rm -rf InvokeAI-Installer
 
 # copy content
 mkdir InvokeAI-Installer
-for f in templates lib *.txt *.reg; do
+for f in templates *.txt *.reg; do
     cp -r ${f} InvokeAI-Installer/
 done
-
-# Move the wheel
-mv dist/*.whl InvokeAI-Installer/lib/
+mkdir InvokeAI-Installer/lib
+cp lib/*.py InvokeAI-Installer/lib
 
 # Install scripts
 # Mac/Linux
@@ -72,13 +75,13 @@ cp install.sh.in InvokeAI-Installer/install.sh
 chmod a+x InvokeAI-Installer/install.sh
 
 # Windows
-perl -p -e "s/^set INVOKEAI_VERSION=.*/set INVOKEAI_VERSION=$VERSION/" install.bat.in > InvokeAI-Installer/install.bat
+cp install.bat.in InvokeAI-Installer/install.bat
 cp WinLongPathsEnabled.reg InvokeAI-Installer/
 
 # Zip everything up
 zip -r InvokeAI-installer-$VERSION.zip InvokeAI-Installer
 
 # clean up
-rm -rf InvokeAI-Installer tmp dist
+rm -rf InvokeAI-Installer tmp dist ../invokeai/frontend/web/dist/
 
 exit 0

installer/install.bat.in

@@ -15,7 +15,6 @@ if "%1" == "use-cache" (
 @rem Config
 @rem The version in the next line is replaced by an up to date release number
 @rem when create_installer.sh is run. Change the release number there.
-set INVOKEAI_VERSION=latest
 set INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
 set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
 set PYTHON_URL=https://www.python.org/downloads/windows/

installer/lib/installer.py

@@ -11,7 +11,7 @@ import sys
 import venv
 from pathlib import Path
 from tempfile import TemporaryDirectory
-from typing import Union
+from typing import Optional, Tuple
 
 SUPPORTED_PYTHON = ">=3.10.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
@@ -21,40 +21,20 @@ OS = platform.uname().system
 ARCH = platform.uname().machine
 VERSION = "latest"
 
-### Feature flags
-# Install the virtualenv into the runtime dir
-FF_VENV_IN_RUNTIME = True
-
-# Install the wheel packaged with the installer
-FF_USE_LOCAL_WHEEL = True
-
 
 class Installer:
     """
     Deploys an InvokeAI installation into a given path
     """
 
+    reqs: list[str] = INSTALLER_REQS
+
     def __init__(self) -> None:
-        self.reqs = INSTALLER_REQS
-        self.preflight()
         if os.getenv("VIRTUAL_ENV") is not None:
             print("A virtual environment is already activated. Please 'deactivate' before installation.")
             sys.exit(-1)
         self.bootstrap()
-
-    def preflight(self) -> None:
-        """
-        Preflight checks
-        """
-
-        # TODO
-        # verify python version
-        # on macOS verify XCode tools are present
-        # verify libmesa, libglx on linux
-        # check that the system arch is not i386 (?)
-        # check that the system has a GPU, and the type of GPU
-
-        pass
+        self.available_releases = get_github_releases()
 
     def mktemp_venv(self) -> TemporaryDirectory:
         """
@@ -78,12 +58,9 @@ class Installer:
 
         return venv_dir
 
-    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory:
+    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory | None:
         """
         Bootstrap the installer venv with packages required at install time
-
-        :return: path to the virtual environment directory that was bootstrapped
-        :rtype: TemporaryDirectory
         """
 
         print("Initializing the installer. This may take a minute - please wait...")
@@ -95,39 +72,27 @@ class Installer:
         cmd.extend(self.reqs)
 
         try:
-            res = subprocess.check_output(cmd).decode()
+            # upgrade pip to the latest version to avoid a confusing message
+            res = upgrade_pip(Path(venv_dir.name))
             if verbose:
                 print(res)
+
+            # run the install prerequisites installation
+            res = subprocess.check_output(cmd).decode()
+
+            if verbose:
+                print(res)
+
             return venv_dir
         except subprocess.CalledProcessError as e:
             print(e)
 
-    def app_venv(self, path: str = None):
+    def app_venv(self, venv_parent) -> Path:
         """
         Create a virtualenv for the InvokeAI installation
         """
 
-        # explicit venv location
-        # currently unused in normal operation
-        # useful for testing or special cases
-        if path is not None:
-            venv_dir = Path(path)
-
-        # experimental / testing
-        elif not FF_VENV_IN_RUNTIME:
-            if OS == "Windows":
-                venv_dir_parent = os.getenv("APPDATA", "~/AppData/Roaming")
-            elif OS == "Darwin":
-                # there is no environment variable on macOS to find this
-                # TODO: confirm this is working as expected
-                venv_dir_parent = "~/Library/Application Support"
-            elif OS == "Linux":
-                venv_dir_parent = os.getenv("XDG_DATA_DIR", "~/.local/share")
-            venv_dir = Path(venv_dir_parent).expanduser().resolve() / f"InvokeAI/{VERSION}/venv"
-
-        # stable / current
-        else:
-            venv_dir = self.dest / ".venv"
+        venv_dir = venv_parent / ".venv"
 
         # Prefer to copy python executables
         # so that updates to system python don't break InvokeAI
@@ -141,7 +106,7 @@ class Installer:
         return venv_dir
 
     def install(
-        self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None
+        self, version=None, root: str = "~/invokeai", yes_to_all=False, find_links: Optional[Path] = None
     ) -> None:
         """
         Install the InvokeAI application into the given runtime path
@@ -158,15 +123,20 @@ class Installer:
 
         import messages
 
-        messages.welcome()
+        messages.welcome(self.available_releases)
 
-        default_path = os.environ.get("INVOKEAI_ROOT") or Path(root).expanduser().resolve()
-        self.dest = default_path if yes_to_all else messages.dest_path(root)
+        version = messages.choose_version(self.available_releases)
+
+        auto_dest = Path(os.environ.get("INVOKEAI_ROOT", root)).expanduser().resolve()
+        destination = auto_dest if yes_to_all else messages.dest_path(root)
+        if destination is None:
+            print("Could not find or create the destination directory. Installation cancelled.")
+            sys.exit(0)
 
         # create the venv for the app
-        self.venv = self.app_venv()
+        self.venv = self.app_venv(venv_parent=destination)
 
-        self.instance = InvokeAiInstance(runtime=self.dest, venv=self.venv, version=version)
+        self.instance = InvokeAiInstance(runtime=destination, venv=self.venv, version=version)
 
         # install dependencies and the InvokeAI application
         (extra_index_url, optional_modules) = get_torch_source() if not yes_to_all else (None, None)
@@ -190,7 +160,7 @@ class InvokeAiInstance:
     A single runtime directory *may* be shared by multiple virtual environments, though this isn't currently tested or supported.
     """
 
-    def __init__(self, runtime: Path, venv: Path, version: str) -> None:
+    def __init__(self, runtime: Path, venv: Path, version: str = "stable") -> None:
         self.runtime = runtime
         self.venv = venv
         self.pip = get_pip_from_venv(venv)
@@ -199,6 +169,7 @@ class InvokeAiInstance:
         set_sys_path(venv)
         os.environ["INVOKEAI_ROOT"] = str(self.runtime.expanduser().resolve())
         os.environ["VIRTUAL_ENV"] = str(self.venv.expanduser().resolve())
+        upgrade_pip(venv)
 
     def get(self) -> tuple[Path, Path]:
         """
@@ -212,54 +183,7 @@ class InvokeAiInstance:
 
     def install(self, extra_index_url=None, optional_modules=None, find_links=None):
         """
-        Install this instance, including dependencies and the app itself
-
-        :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
-        :type extra_index_url: str
-        """
-
-        import messages
-
-        # install torch first to ensure the correct version gets installed.
-        # works with either source or wheel install with negligible impact on installation times.
-        messages.simple_banner("Installing PyTorch :fire:")
-        self.install_torch(extra_index_url, find_links)
-
-        messages.simple_banner("Installing the InvokeAI Application :art:")
-        self.install_app(extra_index_url, optional_modules, find_links)
-
-    def install_torch(self, extra_index_url=None, find_links=None):
-        """
-        Install PyTorch
-        """
-
-        from plumbum import FG, local
-
-        pip = local[self.pip]
-
-        (
-            pip[
-                "install",
-                "--require-virtualenv",
-                "numpy~=1.24.0",  # choose versions that won't be uninstalled during phase 2
-                "urllib3~=1.26.0",
-                "requests~=2.28.0",
-                "torch==2.1.0",
-                "torchmetrics==0.11.4",
-                "torchvision>=0.14.1",
-                "--force-reinstall",
-                "--find-links" if find_links is not None else None,
-                find_links,
-                "--extra-index-url" if extra_index_url is not None else None,
-                extra_index_url,
-            ]
-            & FG
-        )
-
-    def install_app(self, extra_index_url=None, optional_modules=None, find_links=None):
-        """
-        Install the application with pip.
-        Supports installation from PyPi or from a local source directory.
+        Install the package from PyPi.
 
         :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
         :type extra_index_url: str
@@ -271,53 +195,52 @@ class InvokeAiInstance:
         :type find_links: Path
         """
 
-        ## this only applies to pypi installs; TODO actually use this
-        if self.version == "pre":
+        import messages
+
+        # not currently used, but may be useful for "install most recent version" option
+        if self.version == "prerelease":
             version = None
-            pre = "--pre"
+            pre_flag = "--pre"
+        elif self.version == "stable":
+            version = None
+            pre_flag = None
         else:
             version = self.version
-            pre = None
+            pre_flag = None
 
-        ## TODO: only local wheel will be installed as of now; support for --version arg is TODO
-        if FF_USE_LOCAL_WHEEL:
-            # if no wheel, try to do a source install before giving up
-            try:
-                src = str(next(Path(__file__).parent.glob("InvokeAI-*.whl")))
-            except StopIteration:
-                try:
-                    src = Path(__file__).parents[1].expanduser().resolve()
-                    # if the above directory contains one of these files, we'll do a source install
-                    next(src.glob("pyproject.toml"))
-                    next(src.glob("invokeai"))
-                except StopIteration:
-                    print("Unable to find a wheel or perform a source install. Giving up.")
+        src = "invokeai"
+        if optional_modules:
+            src += optional_modules
+        if version:
+            src += f"=={version}"
 
-        elif version == "source":
-            # this makes an assumption about the location of the installer package in the source tree
-            src = Path(__file__).parents[1].expanduser().resolve()
-        else:
-            # will install from PyPi
-            src = f"invokeai=={version}" if version is not None else "invokeai"
+        messages.simple_banner("Installing the InvokeAI Application :art:")
 
-        from plumbum import FG, local
+        from plumbum import FG, ProcessExecutionError, local  # type: ignore
 
         pip = local[self.pip]
 
-        (
-            pip[
-                "install",
-                "--require-virtualenv",
-                "--use-pep517",
-                str(src) + (optional_modules if optional_modules else ""),
-                "--find-links" if find_links is not None else None,
-                find_links,
-                "--extra-index-url" if extra_index_url is not None else None,
-                extra_index_url,
-                pre,
-            ]
-            & FG
-        )
+        pipeline = pip[
+            "install",
+            "--require-virtualenv",
+            "--force-reinstall",
+            "--use-pep517",
+            str(src),
+            "--find-links" if find_links is not None else None,
+            find_links,
+            "--extra-index-url" if extra_index_url is not None else None,
+            extra_index_url,
+            pre_flag,
+        ]
+
+        try:
+            _ = pipeline & FG
+        except ProcessExecutionError as e:
+            print(f"Error: {e}")
+            print(
+                "Could not install InvokeAI. Please try downloading the latest version of the installer and install again."
+            )
+            sys.exit(1)
 
     def configure(self):
         """
@@ -373,7 +296,6 @@ class InvokeAiInstance:
 
         ext = "bat" if OS == "Windows" else "sh"
 
-        # scripts = ['invoke', 'update']
         scripts = ["invoke"]
 
         for script in scripts:
@@ -408,6 +330,23 @@ def get_pip_from_venv(venv_path: Path) -> str:
     return str(venv_path.expanduser().resolve() / pip)
 
 
+def upgrade_pip(venv_path: Path) -> str | None:
+    """
+    Upgrade the pip executable in the given virtual environment
+    """
+
+    python = "Scripts\\python.exe" if OS == "Windows" else "bin/python"
+    python = str(venv_path.expanduser().resolve() / python)
+
+    try:
+        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode()
+    except subprocess.CalledProcessError as e:
+        print(e)
+        result = None
+
+    return result
+
+
 def set_sys_path(venv_path: Path) -> None:
     """
     Given a path to a virtual environment, set the sys.path, in a cross-platform fashion,
@@ -431,7 +370,43 @@ def set_sys_path(venv_path: Path) -> None:
     sys.path.append(str(Path(venv_path, lib, "site-packages").expanduser().resolve()))
 
 
-def get_torch_source() -> (Union[str, None], str):
+def get_github_releases() -> tuple[list, list] | None:
+    """
+    Query Github for published (pre-)release versions.
+    Return a tuple where the first element is a list of stable releases and the second element is a list of pre-releases.
+    Return None if the query fails for any reason.
+    """
+
+    import requests
+
+    ## get latest releases using github api
+    url = "https://api.github.com/repos/invoke-ai/InvokeAI/releases"
+    releases, pre_releases = [], []
+    try:
+        res = requests.get(url)
+        res.raise_for_status()
+        tag_info = res.json()
+        for tag in tag_info:
+            if not tag["prerelease"]:
+                releases.append(tag["tag_name"].lstrip("v"))
+            else:
+                pre_releases.append(tag["tag_name"].lstrip("v"))
+    except requests.HTTPError as e:
+        print(f"Error: {e}")
+        print("Could not fetch version information from GitHub. Please check your network connection and try again.")
+        return
+    except Exception as e:
+        print(f"Error: {e}")
+        print("An unexpected error occurred while trying to fetch version information from GitHub. Please try again.")
+        return
+
+    releases.sort(reverse=True)
+    pre_releases.sort(reverse=True)
+
+    return releases, pre_releases
+
+
+def get_torch_source() -> Tuple[str | None, str | None]:
     """
     Determine the extra index URL for pip to use for torch installation.
     This depends on the OS and the graphics accelerator in use.
@@ -446,25 +421,26 @@ def get_torch_source() -> (Union[str, None], str):
     :rtype: list
     """
 
-    from messages import graphical_accelerator
+    from messages import select_gpu
 
-    # device can be one of: "cuda", "rocm", "cpu", "idk"
-    device = graphical_accelerator()
+    # device can be one of: "cuda", "rocm", "cpu", "cuda_and_dml, autodetect"
+    device = select_gpu()
 
     url = None
     optional_modules = "[onnx]"
     if OS == "Linux":
-        if device == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.4.2"
-        elif device == "cpu":
+        if device.value == "rocm":
+            url = "https://download.pytorch.org/whl/rocm5.6"
+        elif device.value == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 
-    if device == "cuda":
-        url = "https://download.pytorch.org/whl/cu121"
-        optional_modules = "[xformers,onnx-cuda]"
-    if device == "cuda_and_dml":
-        url = "https://download.pytorch.org/whl/cu121"
-        optional_modules = "[xformers,onnx-directml]"
+    elif OS == "Windows":
+        if device.value == "cuda":
+            url = "https://download.pytorch.org/whl/cu121"
+            optional_modules = "[xformers,onnx-cuda]"
+        if device.value == "cuda_and_dml":
+            url = "https://download.pytorch.org/whl/cu121"
+            optional_modules = "[xformers,onnx-directml]"
 
     # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
 

installer/lib/messages.py

@@ -5,10 +5,11 @@ Installer user interaction
 
 import os
 import platform
+from enum import Enum
 from pathlib import Path
 
 from prompt_toolkit import HTML, prompt
-from prompt_toolkit.completion import PathCompleter
+from prompt_toolkit.completion import FuzzyWordCompleter, PathCompleter
 from prompt_toolkit.validation import Validator
 from rich import box, print
 from rich.console import Console, Group, group
@@ -35,16 +36,26 @@ else:
     console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
 
-def welcome():
+def welcome(available_releases: tuple | None = None) -> None:
     @group()
     def text():
-        if (platform_specific := _platform_specific_help()) != "":
+        if (platform_specific := _platform_specific_help()) is not None:
             yield platform_specific
             yield ""
         yield Text.from_markup(
             "Some of the installation steps take a long time to run. Please be patient. If the script appears to hang for more than 10 minutes, please interrupt with [i]Control-C[/] and retry.",
             justify="center",
         )
+        if available_releases is not None:
+            latest_stable = available_releases[0][0]
+            last_pre = available_releases[1][0]
+            yield ""
+            yield Text.from_markup(
+                f"[red3]🠶[/] Latest stable release (recommended): [b bright_white]{latest_stable}", justify="center"
+            )
+            yield Text.from_markup(
+                f"[red3]🠶[/] Last published pre-release version: [b bright_white]{last_pre}", justify="center"
+            )
 
     console.rule()
     print(
@@ -61,19 +72,30 @@ def welcome():
     console.line()
 
 
-def confirm_install(dest: Path) -> bool:
-    if dest.exists():
-        print(f":exclamation: Directory {dest} already exists :exclamation:")
-        dest_confirmed = Confirm.ask(
-            ":stop_sign: (re)install in this location?",
-            default=False,
-        )
-    else:
-        print(f"InvokeAI will be installed in {dest}")
-        dest_confirmed = Confirm.ask("Use this location?", default=True)
+def choose_version(available_releases: tuple | None = None) -> str:
+    """
+    Prompt the user to choose an Invoke version to install
+    """
+
+    # short circuit if we couldn't get a version list
+    # still try to install the latest stable version
+    if available_releases is None:
+        return "stable"
+
+    console.print(":grey_question: [orange3]Please choose an Invoke version to install.")
+
+    choices = available_releases[0] + available_releases[1]
+
+    response = prompt(
+        message=f"   <Enter> to install the recommended release ({choices[0]}). <Tab> or type to pick a version: ",
+        complete_while_typing=True,
+        completer=FuzzyWordCompleter(choices),
+    )
+    console.print(f"   Version {choices[0] if response == '' else response} will be installed.")
+
     console.line()
 
-    return dest_confirmed
+    return "stable" if response == "" else response
 
 
 def user_wants_auto_configuration() -> bool:
@@ -109,7 +131,23 @@ def user_wants_auto_configuration() -> bool:
     return choice.lower().startswith("a")
 
 
-def dest_path(dest=None) -> Path:
+def confirm_install(dest: Path) -> bool:
+    if dest.exists():
+        print(f":stop_sign: Directory {dest} already exists!")
+        print("   Is this location correct?")
+        default = False
+    else:
+        print(f":file_folder: InvokeAI will be installed in {dest}")
+        default = True
+
+    dest_confirmed = Confirm.ask("   Please confirm:", default=default)
+
+    console.line()
+
+    return dest_confirmed
+
+
+def dest_path(dest=None) -> Path | None:
     """
     Prompt the user for the destination path and create the path
 
@@ -124,25 +162,21 @@ def dest_path(dest=None) -> Path:
     else:
         dest = Path.cwd().expanduser().resolve()
     prev_dest = init_path = dest
-
-    dest_confirmed = confirm_install(dest)
+    dest_confirmed = False
 
     while not dest_confirmed:
-        # if the given destination already exists, the starting point for browsing is its parent directory.
-        # the user may have made a typo, or otherwise wants to place the root dir next to an existing one.
-        # if the destination dir does NOT exist, then the user must have changed their mind about the selection.
-        # since we can't read their mind, start browsing at Path.cwd().
-        browse_start = (prev_dest.parent if prev_dest.exists() else Path.cwd()).expanduser().resolve()
+        browse_start = (dest or Path.cwd()).expanduser().resolve()
 
         path_completer = PathCompleter(
             only_directories=True,
             expanduser=True,
-            get_paths=lambda: [browse_start],  # noqa: B023
+            get_paths=lambda: [str(browse_start)],  # noqa: B023
             # get_paths=lambda: [".."].extend(list(browse_start.iterdir()))
         )
 
         console.line()
-        console.print(f"[orange3]Please select the destination directory for the installation:[/] \\[{browse_start}]: ")
+
+        console.print(f":grey_question: [orange3]Please select the install destination:[/] \\[{browse_start}]: ")
         selected = prompt(
             ">>> ",
             complete_in_thread=True,
@@ -155,6 +189,7 @@ def dest_path(dest=None) -> Path:
         )
         prev_dest = dest
         dest = Path(selected)
+
         console.line()
 
         dest_confirmed = confirm_install(dest.expanduser().resolve())
@@ -182,41 +217,45 @@ def dest_path(dest=None) -> Path:
         console.rule("Goodbye!")
 
 
-def graphical_accelerator():
+class GpuType(Enum):
+    CUDA = "cuda"
+    CUDA_AND_DML = "cuda_and_dml"
+    ROCM = "rocm"
+    CPU = "cpu"
+    AUTODETECT = "autodetect"
+
+
+def select_gpu() -> GpuType:
     """
-    Prompt the user to select the graphical accelerator in their system
-    This does not validate user's choices (yet), but only offers choices
-    valid for the platform.
-    CUDA is the fallback.
-    We may be able to detect the GPU driver by shelling out to `modprobe` or `lspci`,
-    but this is not yet supported or reliable. Also, some users may have exotic preferences.
+    Prompt the user to select the GPU driver
     """
 
     if ARCH == "arm64" and OS != "Darwin":
         print(f"Only CPU acceleration is available on {ARCH} architecture. Proceeding with that.")
-        return "cpu"
+        return GpuType.CPU
 
     nvidia = (
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
-        "cuda",
+        GpuType.CUDA,
     )
     nvidia_with_dml = (
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™, and DirectML™ for ONNX) -- ALPHA",
-        "cuda_and_dml",
+        GpuType.CUDA_AND_DML,
     )
     amd = (
         "an [gold1 b]AMD[/] GPU (using ROCm™)",
-        "rocm",
+        GpuType.ROCM,
     )
     cpu = (
-        "no compatible GPU, or specifically prefer to use the CPU",
-        "cpu",
+        "Do not install any GPU support, use CPU for generation (slow)",
+        GpuType.CPU,
     )
-    idk = (
+    autodetect = (
         "I'm not sure what to choose",
-        "idk",
+        GpuType.AUTODETECT,
     )
 
+    options = []
     if OS == "Windows":
         options = [nvidia, nvidia_with_dml, cpu]
     if OS == "Linux":
@@ -230,7 +269,7 @@ def graphical_accelerator():
         return options[0][1]
 
     # "I don't know" is always added the last option
-    options.append(idk)
+    options.append(autodetect)  # type: ignore
 
     options = {str(i): opt for i, opt in enumerate(options, 1)}
 
@@ -265,9 +304,9 @@ def graphical_accelerator():
         ),
     )
 
-    if options[choice][1] == "idk":
+    if options[choice][1] is GpuType.AUTODETECT:
         console.print(
-            "No problem. We will try to install a version that [i]should[/i] be compatible. :crossed_fingers:"
+            "No problem. We will install CUDA support first :crossed_fingers: If Invoke does not detect a GPU, please re-run the installer and select one of the other GPU types."
         )
 
     return options[choice][1]
@@ -291,7 +330,7 @@ def windows_long_paths_registry() -> None:
     """
 
     with open(str(Path(__file__).parent / "WinLongPathsEnabled.reg"), "r", encoding="utf-16le") as code:
-        syntax = Syntax(code.read(), line_numbers=True)
+        syntax = Syntax(code.read(), line_numbers=True, lexer="regedit")
 
     console.print(
         Panel(
@@ -301,7 +340,7 @@ def windows_long_paths_registry() -> None:
                         "We will now apply a registry fix to enable long paths on Windows. InvokeAI needs this to function correctly. We are asking your permission to modify the Windows Registry on your behalf.",
                         "",
                         "This is the change that will be applied:",
-                        syntax,
+                        str(syntax),
                     ]
                 )
             ),
@@ -340,7 +379,7 @@ def introduction() -> None:
     console.line(2)
 
 
-def _platform_specific_help() -> str:
+def _platform_specific_help() -> Text | None:
     if OS == "Darwin":
         text = Text.from_markup(
             """[b wheat1]macOS Users![/]\n\nPlease be sure you have the [b wheat1]Xcode command-line tools[/] installed before continuing.\nIf not, cancel with [i]Control-C[/] and follow the Xcode install instructions at [deep_sky_blue1]https://www.freecodecamp.org/news/install-xcode-command-line-tools/[/]."""
@@ -354,5 +393,5 @@ def _platform_specific_help() -> str:
      [deep_sky_blue1]https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170[/]"""
         )
     else:
-        text = ""
+        return
     return text

installer/tag_release.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+
+set -e
+
+BCYAN="\e[1;36m"
+BYELLOW="\e[1;33m"
+BGREEN="\e[1;32m"
+BRED="\e[1;31m"
+RED="\e[31m"
+RESET="\e[0m"
+
+function does_tag_exist {
+    git rev-parse --quiet --verify "refs/tags/$1" >/dev/null
+}
+
+function git_show_ref {
+    git show-ref --dereference $1 --abbrev 7
+}
+
+function git_show {
+    git show -s --format='%h %s' $1
+}
+
+VERSION=$(
+    cd ..
+    python -c "from invokeai.version import __version__ as version; print(version)"
+)
+PATCH=""
+MAJOR_VERSION=$(echo $VERSION | sed 's/\..*$//')
+VERSION="v${VERSION}${PATCH}"
+LATEST_TAG="v${MAJOR_VERSION}-latest"
+
+if does_tag_exist $VERSION; then
+    echo -e "${BCYAN}${VERSION}${RESET} already exists:"
+    git_show_ref tags/$VERSION
+    echo
+fi
+if does_tag_exist $LATEST_TAG; then
+    echo -e "${BCYAN}${LATEST_TAG}${RESET} already exists:"
+    git_show_ref tags/$LATEST_TAG
+    echo
+fi
+
+echo -e "${BGREEN}HEAD${RESET}:"
+git_show
+echo
+
+echo -e -n "Create tags ${BCYAN}${VERSION}${RESET} and ${BCYAN}${LATEST_TAG}${RESET} @ ${BGREEN}HEAD${RESET}, ${RED}deleting existing tags on remote${RESET}? "
+read -e -p 'y/n [n]: ' input
+RESPONSE=${input:='n'}
+if [ "$RESPONSE" == 'y' ]; then
+    echo
+    echo -e "Deleting ${BCYAN}${VERSION}${RESET} tag on remote..."
+    git push --delete origin $VERSION
+
+    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${VERSION}${RESET} locally..."
+    if ! git tag -fa $VERSION; then
+        echo "Existing/invalid tag"
+        exit -1
+    fi
+
+    echo -e "Deleting ${BCYAN}${LATEST_TAG}${RESET} tag on remote..."
+    git push --delete origin $LATEST_TAG
+
+    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${LATEST_TAG}${RESET} locally..."
+    git tag -fa $LATEST_TAG
+
+    echo -e "Pushing updated tags to remote..."
+    git push origin --tags
+fi
+exit 0

installer/templates/invoke.bat.in

@@ -15,7 +15,7 @@ echo 4. Download and install models
 echo 5. Change InvokeAI startup options
 echo 6. Re-run the configure script to fix a broken install or to complete a major upgrade
 echo 7. Open the developer console
-echo 8. Update InvokeAI
+echo 8. Update InvokeAI (DEPRECATED - please use the installer)
 echo 9. Run the InvokeAI image database maintenance script
 echo 10. Command-line help
 echo Q - Quit
@@ -52,8 +52,10 @@ IF /I "%choice%" == "1" (
     echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
     call cmd /k
 ) ELSE IF /I "%choice%" == "8" (
-   echo Running invokeai-update...
-   python -m invokeai.frontend.install.invokeai_update
+    echo UPDATING FROM WITHIN THE APP IS BEING DEPRECATED.
+    echo Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.
+    timeout 4
+    python -m invokeai.frontend.install.invokeai_update
 ) ELSE IF /I "%choice%" == "9" (
    echo Running the db maintenance script...
    python .venv\Scripts\invokeai-db-maintenance.exe
@@ -77,4 +79,3 @@ pause
 
 :ending
 exit /b
-

installer/templates/invoke.sh.in

@@ -90,7 +90,9 @@ do_choice() {
         ;;
     8)
         clear
-        printf "Update InvokeAI\n"
+        printf "UPDATING FROM WITHIN THE APP IS BEING DEPRECATED\n"
+        printf "Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.\n"
+        sleep 4
         python -m invokeai.frontend.install.invokeai_update
         ;;
     9)
@@ -122,7 +124,7 @@ do_dialog() {
         5 "Change InvokeAI startup options"
         6 "Re-run the configure script to fix a broken install or to complete a major upgrade"
         7 "Open the developer console"
-        8 "Update InvokeAI"
+        8 "Update InvokeAI (DEPRECATED - please use the installer)"
 	9 "Run the InvokeAI image database maintenance script"
 	10 "Command-line help"
     )

installer/templates/update.bat.in

@@ -1,72 +0,0 @@
-@echo off
-setlocal EnableExtensions EnableDelayedExpansion
-
-PUSHD "%~dp0"
-
-set INVOKE_AI_VERSION=latest
-set arg=%1
-if "%arg%" neq "" (
-   if "%arg:~0,2%" equ "/?" (
-       echo Usage: update.bat ^<release name or branch^>
-       echo Updates InvokeAI to use the indicated version of the code base.
-       echo Find the version or branch for the release you want, and pass it as the argument.
-       echo For example '.\update.bat v2.2.5' for release 2.2.5.
-       echo             '.\update.bat main' for the latest development version
-       echo.
-       echo If no argument provided then will install the most recent release, equivalent to
-       echo '.\update.bat latest'
-       exit /b
-   ) else (
-       set INVOKE_AI_VERSION=%arg%
-   )
-)
-
-set INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive/!INVOKE_AI_VERSION!.zip"
-set INVOKE_AI_DEP=https://raw.githubusercontent.com/invoke-ai/InvokeAI/!INVOKE_AI_VERSION!/environments-and-requirements/requirements-base.txt
-set INVOKE_AI_MODELS=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/configs/INITIAL_MODELS.yaml
-
-call curl -I "%INVOKE_AI_DEP%" -fs >.tmp.out
-if %errorlevel% neq 0 (
-    echo '!INVOKE_AI_VERSION!' is not a known branch name or tag. Please check the version and try again.
-    echo "Press any key to continue"
-    pause
-    exit /b
-)
-del .tmp.out
-
-echo This script will update InvokeAI and all its dependencies to !INVOKE_AI_SRC!.
-echo If you do not want to do this, press control-C now!
-pause
-
-call curl -L "%INVOKE_AI_DEP%" > environments-and-requirements/requirements-base.txt
-call curl -L "%INVOKE_AI_MODELS%" > configs/INITIAL_MODELS.yaml
-
-
-call .venv\Scripts\activate.bat
-call .venv\Scripts\python -mpip install -r requirements.txt
-if %errorlevel% neq 0 (
-   echo Installation of requirements failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-   pause
-   exit /b
-)
-
-call .venv\Scripts\python -mpip install !INVOKE_AI_SRC!
-if %errorlevel% neq 0 (
-   echo Installation of InvokeAI failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-   pause
-   exit /b
-)
-
-@rem call .venv\Scripts\invokeai-configure --root=.
-
-@rem if %errorlevel% neq 0 (
-@rem    echo Configuration InvokeAI failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-@rem    pause
-@rem    exit /b
-@rem )
-
-echo InvokeAI has been updated to '%INVOKE_AI_VERSION%'
-
-echo "Press any key to continue"
-pause
-endlocal

installer/templates/update.sh.in

@@ -1,58 +0,0 @@
-#!/usr/bin/env bash
-
-set -eu
-
-if [ $# -ge 1 ] && [ "${1:0:2}" == "-h" ]; then
-    echo "Usage: update.sh <release>"
-    echo "Updates InvokeAI to use the indicated version of the code base."
-    echo "Find the version or branch for the release you want, and pass it as the argument."
-    echo "For example: update.sh v2.2.5 for release 2.2.5."
-    echo "             update.sh main for the current development version."
-    echo ""
-    echo "If no argument provided then will install the version tagged with 'latest', equivalent to"
-    echo "update.sh latest"
-    exit -1
-fi
-
-INVOKE_AI_VERSION=${1:-latest}
-
-INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive/$INVOKE_AI_VERSION.zip"
-INVOKE_AI_DEP=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/environments-and-requirements/requirements-base.txt
-INVOKE_AI_MODELS=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/configs/INITIAL_MODELS.yaml
-
-# ensure we're in the correct folder in case user's CWD is somewhere else
-scriptdir=$(dirname "$0")
-cd "$scriptdir"
-
-function _err_exit {
-    if test "$1" -ne 0
-    then
-	echo "Something went wrong while installing InvokeAI and/or its requirements."
-	echo "Update cannot continue. Please report this error to https://github.com/invoke-ai/InvokeAI/issues"
-        echo -e "Error code $1; Error caught was '$2'"
-        read -p "Press any key to exit..."
-        exit
-    fi
-}
-
-if ! curl -I "$INVOKE_AI_DEP" -fs >/dev/null; then
-    echo \'$INVOKE_AI_VERSION\' is not a known branch name or tag. Please check the version and try again.
-    exit
-fi
-
-echo This script will update InvokeAI and all its dependencies to version \'$INVOKE_AI_VERSION\'.
-echo If you do not want to do this, press control-C now!
-read -p "Press any key to continue, or CTRL-C to exit..."
-
-curl -L "$INVOKE_AI_DEP" > environments-and-requirements/requirements-base.txt
-curl -L "$INVOKE_AI_MODELS" > configs/INITIAL_MODELS.yaml
-
-. .venv/bin/activate
-
-./.venv/bin/python -mpip install -r requirements.txt
-_err_exit $? "The pip program failed to install InvokeAI's requirements."
-
-./.venv/bin/python -mpip install $INVOKE_AI_SRC
-_err_exit $? "The pip program failed to install InvokeAI."
-
-echo InvokeAI updated to \'$INVOKE_AI_VERSION\'

invokeai/app/api/dependencies.py

@@ -2,6 +2,12 @@
 
 from logging import Logger
 
+import torch
+
+from invokeai.app.services.object_serializer.object_serializer_disk import ObjectSerializerDisk
+from invokeai.app.services.object_serializer.object_serializer_forward_cache import ObjectSerializerForwardCache
+from invokeai.app.services.shared.sqlite.sqlite_util import init_db
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
 
@@ -9,27 +15,22 @@ from ..services.board_image_records.board_image_records_sqlite import SqliteBoar
 from ..services.board_images.board_images_default import BoardImagesService
 from ..services.board_records.board_records_sqlite import SqliteBoardRecordStorage
 from ..services.boards.boards_default import BoardService
+from ..services.bulk_download.bulk_download_default import BulkDownloadService
 from ..services.config import InvokeAIAppConfig
+from ..services.download import DownloadQueueService
 from ..services.image_files.image_files_disk import DiskImageFileStorage
 from ..services.image_records.image_records_sqlite import SqliteImageRecordStorage
 from ..services.images.images_default import ImageService
 from ..services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
-from ..services.invocation_processor.invocation_processor_default import DefaultInvocationProcessor
-from ..services.invocation_queue.invocation_queue_memory import MemoryInvocationQueue
 from ..services.invocation_services import InvocationServices
 from ..services.invocation_stats.invocation_stats_default import InvocationStatsService
 from ..services.invoker import Invoker
-from ..services.item_storage.item_storage_sqlite import SqliteItemStorage
-from ..services.latents_storage.latents_storage_disk import DiskLatentsStorage
-from ..services.latents_storage.latents_storage_forward_cache import ForwardCacheLatentsStorage
 from ..services.model_manager.model_manager_default import ModelManagerService
+from ..services.model_metadata import ModelMetadataStoreSQL
 from ..services.model_records import ModelRecordServiceSQL
 from ..services.names.names_default import SimpleNameService
 from ..services.session_processor.session_processor_default import DefaultSessionProcessor
 from ..services.session_queue.session_queue_sqlite import SqliteSessionQueue
-from ..services.shared.default_graphs import create_system_graphs
-from ..services.shared.graph import GraphExecutionState, LibraryGraph
-from ..services.shared.sqlite.sqlite_database import SqliteDatabase
 from ..services.urls.urls_default import LocalUrlService
 from ..services.workflow_records.workflow_records_sqlite import SqliteWorkflowRecordsStorage
 from .events import FastAPIEventService
@@ -60,14 +61,18 @@ class ApiDependencies:
     invoker: Invoker
 
     @staticmethod
-    def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger):
+    def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger) -> None:
         logger.info(f"InvokeAI version {__version__}")
         logger.info(f"Root directory = {str(config.root_path)}")
         logger.debug(f"Internet connectivity is {config.internet_available}")
 
         output_folder = config.output_path
+        if output_folder is None:
+            raise ValueError("Output folder is not set")
 
-        db = SqliteDatabase(config, logger)
+        image_files = DiskImageFileStorage(f"{output_folder}/images")
+
+        db = init_db(config=config, logger=logger, image_files=image_files)
 
         configuration = config
         logger = logger
@@ -77,19 +82,26 @@ class ApiDependencies:
         board_records = SqliteBoardRecordStorage(db=db)
         boards = BoardService()
         events = FastAPIEventService(event_handler_id)
-        graph_execution_manager = SqliteItemStorage[GraphExecutionState](db=db, table_name="graph_executions")
-        graph_library = SqliteItemStorage[LibraryGraph](db=db, table_name="graphs")
-        image_files = DiskImageFileStorage(f"{output_folder}/images")
+        bulk_download = BulkDownloadService()
         image_records = SqliteImageRecordStorage(db=db)
         images = ImageService()
         invocation_cache = MemoryInvocationCache(max_cache_size=config.node_cache_size)
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
-        model_manager = ModelManagerService(config, logger)
-        model_record_service = ModelRecordServiceSQL(db=db)
+        tensors = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[torch.Tensor](output_folder / "tensors", ephemeral=True)
+        )
+        conditioning = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[ConditioningFieldData](output_folder / "conditioning", ephemeral=True)
+        )
+        download_queue_service = DownloadQueueService(event_bus=events)
+        model_metadata_service = ModelMetadataStoreSQL(db=db)
+        model_manager = ModelManagerService.build_model_manager(
+            app_config=configuration,
+            model_record_service=ModelRecordServiceSQL(db=db, metadata_store=model_metadata_service),
+            download_queue=download_queue_service,
+            events=events,
+        )
         names = SimpleNameService()
         performance_statistics = InvocationStatsService()
-        processor = DefaultInvocationProcessor()
-        queue = MemoryInvocationQueue()
         session_processor = DefaultSessionProcessor()
         session_queue = SqliteSessionQueue(db=db)
         urls = LocalUrlService()
@@ -100,34 +112,30 @@ class ApiDependencies:
             board_images=board_images,
             board_records=board_records,
             boards=boards,
+            bulk_download=bulk_download,
             configuration=configuration,
             events=events,
-            graph_execution_manager=graph_execution_manager,
-            graph_library=graph_library,
             image_files=image_files,
             image_records=image_records,
             images=images,
             invocation_cache=invocation_cache,
-            latents=latents,
             logger=logger,
             model_manager=model_manager,
-            model_records=model_record_service,
+            download_queue=download_queue_service,
             names=names,
             performance_statistics=performance_statistics,
-            processor=processor,
-            queue=queue,
             session_processor=session_processor,
             session_queue=session_queue,
             urls=urls,
             workflow_records=workflow_records,
+            tensors=tensors,
+            conditioning=conditioning,
         )
 
-        create_system_graphs(services.graph_library)
-
         ApiDependencies.invoker = Invoker(services)
         db.clean()
 
     @staticmethod
-    def shutdown():
+    def shutdown() -> None:
         if ApiDependencies.invoker:
             ApiDependencies.invoker.stop()

invokeai/app/api/no_cache_staticfiles.py

@@ -0,0 +1,28 @@
+from typing import Any
+
+from starlette.responses import Response
+from starlette.staticfiles import StaticFiles
+
+
+class NoCacheStaticFiles(StaticFiles):
+    """
+    This class is used to override the default caching behavior of starlette for static files,
+    ensuring we *never* cache static files. It modifies the file response headers to strictly
+    never cache the files.
+
+    Static files include the javascript bundles, fonts, locales, and some images. Generated
+    images are not included, as they are served by a router.
+    """
+
+    def __init__(self, *args: Any, **kwargs: Any):
+        self.cachecontrol = "max-age=0, no-cache, no-store, , must-revalidate"
+        self.pragma = "no-cache"
+        self.expires = "0"
+        super().__init__(*args, **kwargs)
+
+    def file_response(self, *args: Any, **kwargs: Any) -> Response:
+        resp = super().file_response(*args, **kwargs)
+        resp.headers.setdefault("Cache-Control", self.cachecontrol)
+        resp.headers.setdefault("Pragma", self.pragma)
+        resp.headers.setdefault("Expires", self.expires)
+        return resp

invokeai/app/api/routers/download_queue.py

@@ -0,0 +1,111 @@
+# Copyright (c) 2023 Lincoln D. Stein
+"""FastAPI route for the download queue."""
+
+from typing import List, Optional
+
+from fastapi import Body, Path, Response
+from fastapi.routing import APIRouter
+from pydantic.networks import AnyHttpUrl
+from starlette.exceptions import HTTPException
+
+from invokeai.app.services.download import (
+    DownloadJob,
+    UnknownJobIDException,
+)
+
+from ..dependencies import ApiDependencies
+
+download_queue_router = APIRouter(prefix="/v1/download_queue", tags=["download_queue"])
+
+
+@download_queue_router.get(
+    "/",
+    operation_id="list_downloads",
+)
+async def list_downloads() -> List[DownloadJob]:
+    """Get a list of active and inactive jobs."""
+    queue = ApiDependencies.invoker.services.download_queue
+    return queue.list_jobs()
+
+
+@download_queue_router.patch(
+    "/",
+    operation_id="prune_downloads",
+    responses={
+        204: {"description": "All completed jobs have been pruned"},
+        400: {"description": "Bad request"},
+    },
+)
+async def prune_downloads() -> Response:
+    """Prune completed and errored jobs."""
+    queue = ApiDependencies.invoker.services.download_queue
+    queue.prune_jobs()
+    return Response(status_code=204)
+
+
+@download_queue_router.post(
+    "/i/",
+    operation_id="download",
+)
+async def download(
+    source: AnyHttpUrl = Body(description="download source"),
+    dest: str = Body(description="download destination"),
+    priority: int = Body(default=10, description="queue priority"),
+    access_token: Optional[str] = Body(default=None, description="token for authorization to download"),
+) -> DownloadJob:
+    """Download the source URL to the file or directory indicted in dest."""
+    queue = ApiDependencies.invoker.services.download_queue
+    return queue.download(source, Path(dest), priority, access_token)
+
+
+@download_queue_router.get(
+    "/i/{id}",
+    operation_id="get_download_job",
+    responses={
+        200: {"description": "Success"},
+        404: {"description": "The requested download JobID could not be found"},
+    },
+)
+async def get_download_job(
+    id: int = Path(description="ID of the download job to fetch."),
+) -> DownloadJob:
+    """Get a download job using its ID."""
+    try:
+        job = ApiDependencies.invoker.services.download_queue.id_to_job(id)
+        return job
+    except UnknownJobIDException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@download_queue_router.delete(
+    "/i/{id}",
+    operation_id="cancel_download_job",
+    responses={
+        204: {"description": "Job has been cancelled"},
+        404: {"description": "The requested download JobID could not be found"},
+    },
+)
+async def cancel_download_job(
+    id: int = Path(description="ID of the download job to cancel."),
+) -> Response:
+    """Cancel a download job using its ID."""
+    try:
+        queue = ApiDependencies.invoker.services.download_queue
+        job = queue.id_to_job(id)
+        queue.cancel_job(job)
+        return Response(status_code=204)
+    except UnknownJobIDException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@download_queue_router.delete(
+    "/i",
+    operation_id="cancel_all_download_jobs",
+    responses={
+        204: {"description": "Download jobs have been cancelled"},
+    },
+)
+async def cancel_all_download_jobs() -> Response:
+    """Cancel all download jobs."""
+    ApiDependencies.invoker.services.download_queue.cancel_all_jobs()
+    return Response(status_code=204)

invokeai/app/api/routers/images.py

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

invokeai/app/api/routers/model_manager.py

@@ -0,0 +1,751 @@
+# Copyright (c) 2023 Lincoln D. Stein
+"""FastAPI route for model configuration records."""
+
+import pathlib
+import shutil
+from hashlib import sha1
+from random import randbytes
+from typing import Any, Dict, List, Optional, Set
+
+from fastapi import Body, Path, Query, Response
+from fastapi.routing import APIRouter
+from pydantic import BaseModel, ConfigDict, Field
+from starlette.exceptions import HTTPException
+from typing_extensions import Annotated
+
+from invokeai.app.services.model_install import ModelInstallJob
+from invokeai.app.services.model_records import (
+    DuplicateModelException,
+    InvalidModelException,
+    ModelRecordOrderBy,
+    ModelSummary,
+    UnknownModelException,
+)
+from invokeai.app.services.shared.pagination import PaginatedResults
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    MainCheckpointConfig,
+    ModelFormat,
+    ModelType,
+    SubModelType,
+)
+from invokeai.backend.model_manager.merge import MergeInterpolationMethod, ModelMerger
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
+from invokeai.backend.model_manager.search import ModelSearch
+
+from ..dependencies import ApiDependencies
+
+model_manager_router = APIRouter(prefix="/v2/models", tags=["model_manager"])
+
+
+class ModelsList(BaseModel):
+    """Return list of configs."""
+
+    models: List[AnyModelConfig]
+
+    model_config = ConfigDict(use_enum_values=True)
+
+
+class ModelTagSet(BaseModel):
+    """Return tags for a set of models."""
+
+    key: str
+    name: str
+    author: str
+    tags: Set[str]
+
+
+##############################################################################
+# These are example inputs and outputs that are used in places where Swagger
+# is unable to generate a correct example.
+##############################################################################
+example_model_config = {
+    "path": "string",
+    "name": "string",
+    "base": "sd-1",
+    "type": "main",
+    "format": "checkpoint",
+    "config": "string",
+    "key": "string",
+    "original_hash": "string",
+    "current_hash": "string",
+    "description": "string",
+    "source": "string",
+    "last_modified": 0,
+    "vae": "string",
+    "variant": "normal",
+    "prediction_type": "epsilon",
+    "repo_variant": "fp16",
+    "upcast_attention": False,
+    "ztsnr_training": False,
+}
+
+example_model_input = {
+    "path": "/path/to/model",
+    "name": "model_name",
+    "base": "sd-1",
+    "type": "main",
+    "format": "checkpoint",
+    "config": "configs/stable-diffusion/v1-inference.yaml",
+    "description": "Model description",
+    "vae": None,
+    "variant": "normal",
+}
+
+example_model_metadata = {
+    "name": "ip_adapter_sd_image_encoder",
+    "author": "InvokeAI",
+    "tags": [
+        "transformers",
+        "safetensors",
+        "clip_vision_model",
+        "endpoints_compatible",
+        "region:us",
+        "has_space",
+        "license:apache-2.0",
+    ],
+    "files": [
+        {
+            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/README.md",
+            "path": "ip_adapter_sd_image_encoder/README.md",
+            "size": 628,
+            "sha256": None,
+        },
+        {
+            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/config.json",
+            "path": "ip_adapter_sd_image_encoder/config.json",
+            "size": 560,
+            "sha256": None,
+        },
+        {
+            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/model.safetensors",
+            "path": "ip_adapter_sd_image_encoder/model.safetensors",
+            "size": 2528373448,
+            "sha256": "6ca9667da1ca9e0b0f75e46bb030f7e011f44f86cbfb8d5a36590fcd7507b030",
+        },
+    ],
+    "type": "huggingface",
+    "id": "InvokeAI/ip_adapter_sd_image_encoder",
+    "tag_dict": {"license": "apache-2.0"},
+    "last_modified": "2023-09-23T17:33:25Z",
+}
+
+##############################################################################
+# ROUTES
+##############################################################################
+
+
+@model_manager_router.get(
+    "/",
+    operation_id="list_model_records",
+)
+async def list_model_records(
+    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
+    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
+    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
+    model_format: Optional[ModelFormat] = Query(
+        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
+    ),
+) -> ModelsList:
+    """Get a list of models."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    found_models: list[AnyModelConfig] = []
+    if base_models:
+        for base_model in base_models:
+            found_models.extend(
+                record_store.search_by_attr(
+                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
+                )
+            )
+    else:
+        found_models.extend(
+            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
+        )
+    return ModelsList(models=found_models)
+
+
+@model_manager_router.get(
+    "/get_by_attrs",
+    operation_id="get_model_records_by_attrs",
+    response_model=AnyModelConfig,
+)
+async def get_model_records_by_attrs(
+    name: str = Query(description="The name of the model"),
+    type: ModelType = Query(description="The type of the model"),
+    base: BaseModelType = Query(description="The base model of the model"),
+) -> AnyModelConfig:
+    """Gets a model by its attributes. The main use of this route is to provide backwards compatibility with the old
+    model manager, which identified models by a combination of name, base and type."""
+    configs = ApiDependencies.invoker.services.model_manager.store.search_by_attr(
+        base_model=base, model_type=type, model_name=name
+    )
+    if not configs:
+        raise HTTPException(status_code=404, detail="No model found with these attributes")
+
+    return configs[0]
+
+
+@model_manager_router.get(
+    "/i/{key}",
+    operation_id="get_model_record",
+    responses={
+        200: {
+            "description": "The model configuration was retrieved successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+    },
+)
+async def get_model_record(
+    key: str = Path(description="Key of the model record to fetch."),
+) -> AnyModelConfig:
+    """Get a model record"""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    try:
+        config: AnyModelConfig = record_store.get_model(key)
+        return config
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.get("/summary", operation_id="list_model_summary")
+async def list_model_summary(
+    page: int = Query(default=0, description="The page to get"),
+    per_page: int = Query(default=10, description="The number of models per page"),
+    order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
+) -> PaginatedResults[ModelSummary]:
+    """Gets a page of model summary data."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    results: PaginatedResults[ModelSummary] = record_store.list_models(page=page, per_page=per_page, order_by=order_by)
+    return results
+
+
+@model_manager_router.get(
+    "/i/{key}/metadata",
+    operation_id="get_model_metadata",
+    responses={
+        200: {
+            "description": "The model metadata was retrieved successfully",
+            "content": {"application/json": {"example": example_model_metadata}},
+        },
+        400: {"description": "Bad request"},
+    },
+)
+async def get_model_metadata(
+    key: str = Path(description="Key of the model repo metadata to fetch."),
+) -> Optional[AnyModelRepoMetadata]:
+    """Get a model metadata object."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    result: Optional[AnyModelRepoMetadata] = record_store.get_metadata(key)
+
+    return result
+
+
+@model_manager_router.get(
+    "/tags",
+    operation_id="list_tags",
+)
+async def list_tags() -> Set[str]:
+    """Get a unique set of all the model tags."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    result: Set[str] = record_store.list_tags()
+    return result
+
+
+class FoundModel(BaseModel):
+    path: str = Field(description="Path to the model")
+    is_installed: bool = Field(description="Whether or not the model is already installed")
+
+
+@model_manager_router.get(
+    "/scan_folder",
+    operation_id="scan_for_models",
+    responses={
+        200: {"description": "Directory scanned successfully"},
+        400: {"description": "Invalid directory path"},
+    },
+    status_code=200,
+    response_model=List[FoundModel],
+)
+async def scan_for_models(
+    scan_path: str = Query(description="Directory path to search for models", default=None),
+) -> List[FoundModel]:
+    path = pathlib.Path(scan_path)
+    if not scan_path or not path.is_dir():
+        raise HTTPException(
+            status_code=400,
+            detail=f"The search path '{scan_path}' does not exist or is not directory",
+        )
+
+    search = ModelSearch()
+    try:
+        found_model_paths = search.search(path)
+        models_path = ApiDependencies.invoker.services.configuration.models_path
+
+        # If the search path includes the main models directory, we need to exclude core models from the list.
+        # TODO(MM2): Core models should be handled by the model manager so we can determine if they are installed
+        # without needing to crawl the filesystem.
+        core_models_path = pathlib.Path(models_path, "core").resolve()
+        non_core_model_paths = [p for p in found_model_paths if not p.is_relative_to(core_models_path)]
+
+        installed_models = ApiDependencies.invoker.services.model_manager.store.search_by_attr()
+        resolved_installed_model_paths: list[str] = []
+        installed_model_sources: list[str] = []
+
+        # This call lists all installed models.
+        for model in installed_models:
+            path = pathlib.Path(model.path)
+            # If the model has a source, we need to add it to the list of installed sources.
+            if model.source:
+                installed_model_sources.append(model.source)
+            # If the path is not absolute, that means it is in the app models directory, and we need to join it with
+            # the models path before resolving.
+            if not path.is_absolute():
+                resolved_installed_model_paths.append(str(pathlib.Path(models_path, path).resolve()))
+                continue
+            resolved_installed_model_paths.append(str(path.resolve()))
+
+        scan_results: list[FoundModel] = []
+
+        # Check if the model is installed by comparing the resolved paths, appending to the scan result.
+        for p in non_core_model_paths:
+            path = str(p)
+            is_installed = path in resolved_installed_model_paths or path in installed_model_sources
+            found_model = FoundModel(path=path, is_installed=is_installed)
+            scan_results.append(found_model)
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"An error occurred while searching the directory: {e}",
+        )
+    return scan_results
+
+
+@model_manager_router.get(
+    "/tags/search",
+    operation_id="search_by_metadata_tags",
+)
+async def search_by_metadata_tags(
+    tags: Set[str] = Query(default=None, description="Tags to search for"),
+) -> ModelsList:
+    """Get a list of models."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    results = record_store.search_by_metadata_tag(tags)
+    return ModelsList(models=results)
+
+
+@model_manager_router.patch(
+    "/i/{key}",
+    operation_id="update_model_record",
+    responses={
+        200: {
+            "description": "The model was updated successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+        409: {"description": "There is already a model corresponding to the new name"},
+    },
+    status_code=200,
+)
+async def update_model_record(
+    key: Annotated[str, Path(description="Unique key of model")],
+    info: Annotated[
+        AnyModelConfig, Body(description="Model config", discriminator="type", example=example_model_input)
+    ],
+) -> AnyModelConfig:
+    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
+    logger = ApiDependencies.invoker.services.logger
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    try:
+        model_response: AnyModelConfig = record_store.update_model(key, config=info)
+        logger.info(f"Updated model: {key}")
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return model_response
+
+
+@model_manager_router.delete(
+    "/i/{key}",
+    operation_id="del_model_record",
+    responses={
+        204: {"description": "Model deleted successfully"},
+        404: {"description": "Model not found"},
+    },
+    status_code=204,
+)
+async def del_model_record(
+    key: str = Path(description="Unique key of model to remove from model registry."),
+) -> Response:
+    """
+    Delete model record from database.
+
+    The configuration record will be removed. The corresponding weights files will be
+    deleted as well if they reside within the InvokeAI "models" directory.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        installer.delete(key)
+        logger.info(f"Deleted model: {key}")
+        return Response(status_code=204)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.post(
+    "/i/",
+    operation_id="add_model_record",
+    responses={
+        201: {
+            "description": "The model added successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+        415: {"description": "Unrecognized file/folder format"},
+    },
+    status_code=201,
+)
+async def add_model_record(
+    config: Annotated[
+        AnyModelConfig, Body(description="Model config", discriminator="type", example=example_model_input)
+    ],
+) -> AnyModelConfig:
+    """Add a model using the configuration information appropriate for its type."""
+    logger = ApiDependencies.invoker.services.logger
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    if config.key == "<NOKEY>":
+        config.key = sha1(randbytes(100)).hexdigest()
+        logger.info(f"Created model {config.key} for {config.name}")
+    try:
+        record_store.add_model(config.key, config)
+    except DuplicateModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+
+    # now fetch it out
+    result: AnyModelConfig = record_store.get_model(config.key)
+    return result
+
+
+@model_manager_router.post(
+    "/install",
+    operation_id="install_model",
+    responses={
+        201: {"description": "The model imported successfully"},
+        415: {"description": "Unrecognized file/folder format"},
+        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+    },
+    status_code=201,
+)
+async def install_model(
+    source: str = Query(description="Model source to install, can be a local path, repo_id, or remote URL"),
+    # TODO(MM2): Can we type this?
+    config: Optional[Dict[str, Any]] = Body(
+        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
+        default=None,
+        example={"name": "string", "description": "string"},
+    ),
+    access_token: Optional[str] = None,
+) -> ModelInstallJob:
+    """Install a model using a string identifier.
+
+    `source` can be any of the following.
+
+    1. A path on the local filesystem ('C:\\users\\fred\\model.safetensors')
+    2. A Url pointing to a single downloadable model file
+    3. A HuggingFace repo_id with any of the following formats:
+       - model/name
+       - model/name:fp16:vae
+       - model/name::vae          -- use default precision
+       - model/name:fp16:path/to/model.safetensors
+       - model/name::path/to/model.safetensors
+
+    `config` is an optional dict containing model configuration values that will override
+    the ones that are probed automatically.
+
+    `access_token` is an optional access token for use with Urls that require
+    authentication.
+
+    Models will be downloaded, probed, configured and installed in a
+    series of background threads. The return object has `status` attribute
+    that can be used to monitor progress.
+
+    See the documentation for `import_model_record` for more information on
+    interpreting the job information returned by this route.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        result: ModelInstallJob = installer.heuristic_import(
+            source=source,
+            config=config,
+            access_token=access_token,
+        )
+        logger.info(f"Started installation of {source}")
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return result
+
+
+@model_manager_router.get(
+    "/import",
+    operation_id="list_model_install_jobs",
+)
+async def list_model_install_jobs() -> List[ModelInstallJob]:
+    """Return the list of model install jobs.
+
+    Install jobs have a numeric `id`, a `status`, and other fields that provide information on
+    the nature of the job and its progress. The `status` is one of:
+
+    * "waiting" -- Job is waiting in the queue to run
+    * "downloading" -- Model file(s) are downloading
+    * "running" -- Model has downloaded and the model probing and registration process is running
+    * "completed" -- Installation completed successfully
+    * "error" -- An error occurred. Details will be in the "error_type" and "error" fields.
+    * "cancelled" -- Job was cancelled before completion.
+
+    Once completed, information about the model such as its size, base
+    model, type, and metadata can be retrieved from the `config_out`
+    field. For multi-file models such as diffusers, information on individual files
+    can be retrieved from `download_parts`.
+
+    See the example and schema below for more information.
+    """
+    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_manager.install.list_jobs()
+    return jobs
+
+
+@model_manager_router.get(
+    "/import/{id}",
+    operation_id="get_model_install_job",
+    responses={
+        200: {"description": "Success"},
+        404: {"description": "No such job"},
+    },
+)
+async def get_model_install_job(id: int = Path(description="Model install id")) -> ModelInstallJob:
+    """
+    Return model install job corresponding to the given source. See the documentation for 'List Model Install Jobs'
+    for information on the format of the return value.
+    """
+    try:
+        result: ModelInstallJob = ApiDependencies.invoker.services.model_manager.install.get_job_by_id(id)
+        return result
+    except ValueError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.delete(
+    "/import/{id}",
+    operation_id="cancel_model_install_job",
+    responses={
+        201: {"description": "The job was cancelled successfully"},
+        415: {"description": "No such job"},
+    },
+    status_code=201,
+)
+async def cancel_model_install_job(id: int = Path(description="Model install job ID")) -> None:
+    """Cancel the model install job(s) corresponding to the given job ID."""
+    installer = ApiDependencies.invoker.services.model_manager.install
+    try:
+        job = installer.get_job_by_id(id)
+    except ValueError as e:
+        raise HTTPException(status_code=415, detail=str(e))
+    installer.cancel_job(job)
+
+
+@model_manager_router.patch(
+    "/import",
+    operation_id="prune_model_install_jobs",
+    responses={
+        204: {"description": "All completed and errored jobs have been pruned"},
+        400: {"description": "Bad request"},
+    },
+)
+async def prune_model_install_jobs() -> Response:
+    """Prune all completed and errored jobs from the install job list."""
+    ApiDependencies.invoker.services.model_manager.install.prune_jobs()
+    return Response(status_code=204)
+
+
+@model_manager_router.patch(
+    "/sync",
+    operation_id="sync_models_to_config",
+    responses={
+        204: {"description": "Model config record database resynced with files on disk"},
+        400: {"description": "Bad request"},
+    },
+)
+async def sync_models_to_config() -> Response:
+    """
+    Traverse the models and autoimport directories.
+
+    Model files without a corresponding
+    record in the database are added. Orphan records without a models file are deleted.
+    """
+    ApiDependencies.invoker.services.model_manager.install.sync_to_config()
+    return Response(status_code=204)
+
+
+@model_manager_router.put(
+    "/convert/{key}",
+    operation_id="convert_model",
+    responses={
+        200: {
+            "description": "Model converted successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "Model not found"},
+        409: {"description": "There is already a model registered at this location"},
+    },
+)
+async def convert_model(
+    key: str = Path(description="Unique key of the safetensors main model to convert to diffusers format."),
+) -> AnyModelConfig:
+    """
+    Permanently convert a model into diffusers format, replacing the safetensors version.
+    Note that during the conversion process the key and model hash will change.
+    The return value is the model configuration for the converted model.
+    """
+    model_manager = ApiDependencies.invoker.services.model_manager
+    logger = ApiDependencies.invoker.services.logger
+    loader = ApiDependencies.invoker.services.model_manager.load
+    store = ApiDependencies.invoker.services.model_manager.store
+    installer = ApiDependencies.invoker.services.model_manager.install
+
+    try:
+        model_config = store.get_model(key)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+
+    if not isinstance(model_config, MainCheckpointConfig):
+        logger.error(f"The model with key {key} is not a main checkpoint model.")
+        raise HTTPException(400, f"The model with key {key} is not a main checkpoint model.")
+
+    # loading the model will convert it into a cached diffusers file
+    model_manager.load_model_by_config(model_config, submodel_type=SubModelType.Scheduler)
+
+    # Get the path of the converted model from the loader
+    cache_path = loader.convert_cache.cache_path(key)
+    assert cache_path.exists()
+
+    # temporarily rename the original safetensors file so that there is no naming conflict
+    original_name = model_config.name
+    model_config.name = f"{original_name}.DELETE"
+    store.update_model(key, config=model_config)
+
+    # install the diffusers
+    try:
+        new_key = installer.install_path(
+            cache_path,
+            config={
+                "name": original_name,
+                "description": model_config.description,
+                "original_hash": model_config.original_hash,
+                "source": model_config.source,
+            },
+        )
+    except DuplicateModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+
+    # get the original metadata
+    if orig_metadata := store.get_metadata(key):
+        store.metadata_store.add_metadata(new_key, orig_metadata)
+
+    # delete the original safetensors file
+    installer.delete(key)
+
+    # delete the cached version
+    shutil.rmtree(cache_path)
+
+    # return the config record for the new diffusers directory
+    new_config: AnyModelConfig = store.get_model(new_key)
+    return new_config
+
+
+@model_manager_router.put(
+    "/merge",
+    operation_id="merge",
+    responses={
+        200: {
+            "description": "Model converted successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "Model not found"},
+        409: {"description": "There is already a model registered at this location"},
+    },
+)
+async def merge(
+    keys: List[str] = Body(description="Keys for two to three models to merge", min_length=2, max_length=3),
+    merged_model_name: Optional[str] = Body(description="Name of destination model", default=None),
+    alpha: float = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
+    force: bool = Body(
+        description="Force merging of models created with different versions of diffusers",
+        default=False,
+    ),
+    interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method", default=None),
+    merge_dest_directory: Optional[str] = Body(
+        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
+        default=None,
+    ),
+) -> AnyModelConfig:
+    """
+    Merge diffusers models. The process is controlled by a set parameters provided in the body of the request.
+    ```
+    Argument                Description [default]
+    --------               ----------------------
+    keys                   List of 2-3 model keys to merge together. All models must use the same base type.
+    merged_model_name      Name for the merged model [Concat model names]
+    alpha                  Alpha value (0.0-1.0). Higher values give more weight to the second model [0.5]
+    force                  If true, force the merge even if the models were generated by different versions of the diffusers library [False]
+    interp                 Interpolation method. One of "weighted_sum", "sigmoid", "inv_sigmoid" or "add_difference" [weighted_sum]
+    merge_dest_directory   Specify a directory to store the merged model in [models directory]
+    ```
+    """
+    logger = ApiDependencies.invoker.services.logger
+    try:
+        logger.info(f"Merging models: {keys} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
+        dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
+        installer = ApiDependencies.invoker.services.model_manager.install
+        merger = ModelMerger(installer)
+        model_names = [installer.record_store.get_model(x).name for x in keys]
+        response = merger.merge_diffusion_models_and_save(
+            model_keys=keys,
+            merged_model_name=merged_model_name or "+".join(model_names),
+            alpha=alpha,
+            interp=interp,
+            force=force,
+            merge_dest_directory=dest,
+        )
+    except UnknownModelException:
+        raise HTTPException(
+            status_code=404,
+            detail=f"One or more of the models '{keys}' not found",
+        )
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    return response

invokeai/app/api/routers/model_records.py

@@ -1,164 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein
-"""FastAPI route for model configuration records."""
-
-
-from hashlib import sha1
-from random import randbytes
-from typing import List, Optional
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, ConfigDict
-from starlette.exceptions import HTTPException
-from typing_extensions import Annotated
-
-from invokeai.app.services.model_records import (
-    DuplicateModelException,
-    InvalidModelException,
-    UnknownModelException,
-)
-from invokeai.backend.model_manager.config import (
-    AnyModelConfig,
-    BaseModelType,
-    ModelType,
-)
-
-from ..dependencies import ApiDependencies
-
-model_records_router = APIRouter(prefix="/v1/model/record", tags=["models"])
-
-
-class ModelsList(BaseModel):
-    """Return list of configs."""
-
-    models: list[AnyModelConfig]
-
-    model_config = ConfigDict(use_enum_values=True)
-
-
-@model_records_router.get(
-    "/",
-    operation_id="list_model_records",
-)
-async def list_model_records(
-    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_records
-    found_models: list[AnyModelConfig] = []
-    if base_models:
-        for base_model in base_models:
-            found_models.extend(record_store.search_by_attr(base_model=base_model, model_type=model_type))
-    else:
-        found_models.extend(record_store.search_by_attr(model_type=model_type))
-    return ModelsList(models=found_models)
-
-
-@model_records_router.get(
-    "/i/{key}",
-    operation_id="get_model_record",
-    responses={
-        200: {"description": "Success"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-    },
-)
-async def get_model_record(
-    key: str = Path(description="Key of the model record to fetch."),
-) -> AnyModelConfig:
-    """Get a model record"""
-    record_store = ApiDependencies.invoker.services.model_records
-    try:
-        return record_store.get_model(key)
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.patch(
-    "/i/{key}",
-    operation_id="update_model_record",
-    responses={
-        200: {"description": "The model was updated successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-        409: {"description": "There is already a model corresponding to the new name"},
-    },
-    status_code=200,
-    response_model=AnyModelConfig,
-)
-async def update_model_record(
-    key: Annotated[str, Path(description="Unique key of model")],
-    info: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
-) -> AnyModelConfig:
-    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_records
-    try:
-        model_response = record_store.update_model(key, config=info)
-        logger.info(f"Updated model: {key}")
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return model_response
-
-
-@model_records_router.delete(
-    "/i/{key}",
-    operation_id="del_model_record",
-    responses={
-        204: {"description": "Model deleted successfully"},
-        404: {"description": "Model not found"},
-    },
-    status_code=204,
-)
-async def del_model_record(
-    key: str = Path(description="Unique key of model to remove from model registry."),
-) -> Response:
-    """Delete Model"""
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        record_store = ApiDependencies.invoker.services.model_records
-        record_store.del_model(key)
-        logger.info(f"Deleted model: {key}")
-        return Response(status_code=204)
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.post(
-    "/i/",
-    operation_id="add_model_record",
-    responses={
-        201: {"description": "The model added successfully"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-        415: {"description": "Unrecognized file/folder format"},
-    },
-    status_code=201,
-)
-async def add_model_record(
-    config: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
-) -> AnyModelConfig:
-    """
-    Add a model using the configuration information appropriate for its type.
-    """
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_records
-    if config.key == "<NOKEY>":
-        config.key = sha1(randbytes(100)).hexdigest()
-        logger.info(f"Created model {config.key} for {config.name}")
-    try:
-        record_store.add_model(config.key, config)
-    except DuplicateModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-
-    # now fetch it out
-    return record_store.get_model(config.key)

invokeai/app/api/routers/models.py

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

invokeai/app/api/routers/sessions.py

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

invokeai/app/api/routers/utilities.py

@@ -23,10 +23,11 @@ class DynamicPromptsResponse(BaseModel):
 )
 async def parse_dynamicprompts(
     prompt: str = Body(description="The prompt to parse with dynamicprompts"),
-    max_prompts: int = Body(default=1000, description="The max number of prompts to generate"),
+    max_prompts: int = Body(ge=1, le=10000, default=1000, description="The max number of prompts to generate"),
     combinatorial: bool = Body(default=True, description="Whether to use the combinatorial generator"),
 ) -> DynamicPromptsResponse:
     """Creates a batch process"""
+    max_prompts = min(max_prompts, 10000)
     generator: Union[RandomPromptGenerator, CombinatorialPromptGenerator]
     try:
         error: Optional[str] = None

invokeai/app/api/sockets.py

@@ -12,14 +12,25 @@ class SocketIO:
     __sio: AsyncServer
     __app: ASGIApp
 
+    __sub_queue: str = "subscribe_queue"
+    __unsub_queue: str = "unsubscribe_queue"
+
+    __sub_bulk_download: str = "subscribe_bulk_download"
+    __unsub_bulk_download: str = "unsubscribe_bulk_download"
+
     def __init__(self, app: FastAPI):
         self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
-        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="socket.io")
+        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="/ws/socket.io")
         app.mount("/ws", self.__app)
 
-        self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)
-        self.__sio.on("unsubscribe_queue", handler=self._handle_unsub_queue)
+        self.__sio.on(self.__sub_queue, handler=self._handle_sub_queue)
+        self.__sio.on(self.__unsub_queue, handler=self._handle_unsub_queue)
         local_handler.register(event_name=EventServiceBase.queue_event, _func=self._handle_queue_event)
+        local_handler.register(event_name=EventServiceBase.model_event, _func=self._handle_model_event)
+
+        self.__sio.on(self.__sub_bulk_download, handler=self._handle_sub_bulk_download)
+        self.__sio.on(self.__unsub_bulk_download, handler=self._handle_unsub_bulk_download)
+        local_handler.register(event_name=EventServiceBase.bulk_download_event, _func=self._handle_bulk_download_event)
 
     async def _handle_queue_event(self, event: Event):
         await self.__sio.emit(
@@ -28,10 +39,28 @@ class SocketIO:
             room=event[1]["data"]["queue_id"],
         )
 
-    async def _handle_sub_queue(self, sid, data, *args, **kwargs):
+    async def _handle_sub_queue(self, sid, data, *args, **kwargs) -> None:
         if "queue_id" in data:
             await self.__sio.enter_room(sid, data["queue_id"])
 
-    async def _handle_unsub_queue(self, sid, data, *args, **kwargs):
+    async def _handle_unsub_queue(self, sid, data, *args, **kwargs) -> None:
         if "queue_id" in data:
             await self.__sio.leave_room(sid, data["queue_id"])
+
+    async def _handle_model_event(self, event: Event) -> None:
+        await self.__sio.emit(event=event[1]["event"], data=event[1]["data"])
+
+    async def _handle_bulk_download_event(self, event: Event):
+        await self.__sio.emit(
+            event=event[1]["event"],
+            data=event[1]["data"],
+            room=event[1]["data"]["bulk_download_id"],
+        )
+
+    async def _handle_sub_bulk_download(self, sid, data, *args, **kwargs):
+        if "bulk_download_id" in data:
+            await self.__sio.enter_room(sid, data["bulk_download_id"])
+
+    async def _handle_unsub_bulk_download(self, sid, data, *args, **kwargs):
+        if "bulk_download_id" in data:
+            await self.__sio.leave_room(sid, data["bulk_download_id"])

invokeai/app/api_app.py

@@ -3,8 +3,10 @@
 # values from the command line or config file.
 import sys
 
+from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
 from invokeai.version.invokeai_version import __version__
 
+from .invocations.fields import InputFieldJSONSchemaExtra, OutputFieldJSONSchemaExtra
 from .services.config import InvokeAIAppConfig
 
 app_config = InvokeAIAppConfig.get_config()
@@ -27,8 +29,7 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
     from fastapi.middleware.gzip import GZipMiddleware
     from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
     from fastapi.openapi.utils import get_openapi
-    from fastapi.responses import FileResponse, HTMLResponse
-    from fastapi.staticfiles import StaticFiles
+    from fastapi.responses import HTMLResponse
     from fastapi_events.handlers.local import local_handler
     from fastapi_events.middleware import EventHandlerASGIMiddleware
     from pydantic.json_schema import models_json_schema
@@ -45,19 +46,16 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
         app_info,
         board_images,
         boards,
+        download_queue,
         images,
-        model_records,
-        models,
+        model_manager,
         session_queue,
-        sessions,
         utilities,
         workflows,
     )
     from .api.sockets import SocketIO
     from .invocations.baseinvocation import (
         BaseInvocation,
-        InputFieldJSONSchemaExtra,
-        OutputFieldJSONSchemaExtra,
         UIConfigBase,
     )
 
@@ -75,7 +73,7 @@ mimetypes.add_type("text/css", ".css")
 
 # 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, separate_input_output_schemas=False)
+app = FastAPI(title="Invoke - Community Edition", docs_url=None, redoc_url=None, separate_input_output_schemas=False)
 
 # Add event handler
 event_handler_id: int = id(app)
@@ -111,11 +109,9 @@ async def shutdown_event() -> None:
 
 
 # Include all routers
-app.include_router(sessions.session_router, prefix="/api")
-
 app.include_router(utilities.utilities_router, prefix="/api")
-app.include_router(models.models_router, prefix="/api")
-app.include_router(model_records.model_records_router, prefix="/api")
+app.include_router(model_manager.model_manager_router, prefix="/api")
+app.include_router(download_queue.download_queue_router, prefix="/api")
 app.include_router(images.images_router, prefix="/api")
 app.include_router(boards.boards_router, prefix="/api")
 app.include_router(board_images.board_images_router, prefix="/api")
@@ -152,6 +148,8 @@ def custom_openapi() -> dict[str, Any]:
         # TODO: note that we assume the schema_key here is the TYPE.__name__
         # This could break in some cases, figure out a better way to do it
         output_type_titles[schema_key] = output_schema["title"]
+        openapi_schema["components"]["schemas"][schema_key] = output_schema
+        openapi_schema["components"]["schemas"][schema_key]["class"] = "output"
 
     # Add Node Editor UI helper schemas
     ui_config_schemas = models_json_schema(
@@ -174,23 +172,24 @@ def custom_openapi() -> dict[str, Any]:
         outputs_ref = {"$ref": f"#/components/schemas/{output_type_title}"}
         invoker_schema["output"] = outputs_ref
         invoker_schema["class"] = "invocation"
-        openapi_schema["components"]["schemas"][f"{output_type_title}"]["class"] = "output"
 
-    from invokeai.backend.model_management.models import get_model_config_enums
+    # This code no longer seems to be necessary?
+    # Leave it here just in case
+    #
+    # from invokeai.backend.model_manager import get_model_config_formats
+    # formats = get_model_config_formats()
+    # for model_config_name, enum_set in formats.items():
 
-    for model_config_format_enum in set(get_model_config_enums()):
-        name = model_config_format_enum.__qualname__
+    #     if model_config_name in openapi_schema["components"]["schemas"]:
+    #         # print(f"Config with name {name} already defined")
+    #         continue
 
-        if name in openapi_schema["components"]["schemas"]:
-            # print(f"Config with name {name} already defined")
-            continue
-
-        openapi_schema["components"]["schemas"][name] = {
-            "title": name,
-            "description": "An enumeration.",
-            "type": "string",
-            "enum": [v.value for v in model_config_format_enum],
-        }
+    #     openapi_schema["components"]["schemas"][model_config_name] = {
+    #         "title": model_config_name,
+    #         "description": "An enumeration.",
+    #         "type": "string",
+    #         "enum": [v.value for v in enum_set],
+    #     }
 
     app.openapi_schema = openapi_schema
     return app.openapi_schema
@@ -203,8 +202,8 @@ app.openapi = custom_openapi  # type: ignore [method-assign] # this is a valid a
 def overridden_swagger() -> HTMLResponse:
     return get_swagger_ui_html(
         openapi_url=app.openapi_url,  # type: ignore [arg-type] # this is always a string
-        title=app.title,
-        swagger_favicon_url="/static/docs/favicon.ico",
+        title=f"{app.title} - Swagger UI",
+        swagger_favicon_url="static/docs/invoke-favicon-docs.svg",
     )
 
 
@@ -212,25 +211,20 @@ def overridden_swagger() -> HTMLResponse:
 def overridden_redoc() -> HTMLResponse:
     return get_redoc_html(
         openapi_url=app.openapi_url,  # type: ignore [arg-type] # this is always a string
-        title=app.title,
-        redoc_favicon_url="/static/docs/favicon.ico",
+        title=f"{app.title} - Redoc",
+        redoc_favicon_url="static/docs/invoke-favicon-docs.svg",
     )
 
 
 web_root_path = Path(list(web_dir.__path__)[0])
 
-
-# Cannot add headers to StaticFiles, so we must serve index.html with a custom route
-# Add cache-control: no-store header to prevent caching of index.html, which leads to broken UIs at release
-@app.get("/", include_in_schema=False, name="ui_root")
-def get_index() -> FileResponse:
-    return FileResponse(Path(web_root_path, "dist/index.html"), headers={"Cache-Control": "no-store"})
-
-
-# # Must mount *after* the other routes else it borks em
-app.mount("/static", StaticFiles(directory=Path(web_root_path, "static/")), name="static")  # docs favicon is in here
-app.mount("/assets", StaticFiles(directory=Path(web_root_path, "dist/assets/")), name="assets")
-app.mount("/locales", StaticFiles(directory=Path(web_root_path, "dist/locales/")), name="locales")
+try:
+    app.mount("/", NoCacheStaticFiles(directory=Path(web_root_path, "dist"), html=True), name="ui")
+except RuntimeError:
+    logger.warn(f"No UI found at {web_root_path}/dist, skipping UI mount")
+app.mount(
+    "/static", NoCacheStaticFiles(directory=Path(web_root_path, "static/")), name="static"
+)  # docs favicon is in here
 
 
 def invoke_api() -> None:
@@ -271,6 +265,8 @@ def invoke_api() -> None:
         port=port,
         loop="asyncio",
         log_level=app_config.log_level,
+        ssl_certfile=app_config.ssl_certfile,
+        ssl_keyfile=app_config.ssl_keyfile,
     )
     server = uvicorn.Server(config)
 

invokeai/app/invocations/baseinvocation.py

@@ -4,20 +4,37 @@ from __future__ import annotations
 
 import inspect
 import re
+import warnings
 from abc import ABC, abstractmethod
 from enum import Enum
 from inspect import signature
-from types import UnionType
-from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union, cast
+from typing import (
+    TYPE_CHECKING,
+    Annotated,
+    Any,
+    Callable,
+    ClassVar,
+    Iterable,
+    Literal,
+    Optional,
+    Type,
+    TypeVar,
+    Union,
+    cast,
+)
 
 import semver
-from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter, create_model
-from pydantic.fields import FieldInfo, _Unset
+from pydantic import BaseModel, ConfigDict, Field, TypeAdapter, create_model
+from pydantic.fields import FieldInfo
 from pydantic_core import PydanticUndefined
+from typing_extensions import TypeAliasType
 
+from invokeai.app.invocations.fields import (
+    FieldKind,
+    Input,
+)
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.metaenum import MetaEnum
 from invokeai.app.util.misc import uuid_string
 from invokeai.backend.util.logging import InvokeAILogger
@@ -38,391 +55,17 @@ class InvalidFieldError(TypeError):
     pass
 
 
-class Input(str, Enum, metaclass=MetaEnum):
+class Classification(str, Enum, metaclass=MetaEnum):
     """
-    The type of input a field accepts.
-    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
-      are instantiated.
-    - `Input.Connection`: The field must have its value provided by a connection.
-    - `Input.Any`: The field may have its value provided either directly or by a connection.
+    The classification of an Invocation.
+    - `Stable`: The invocation, including its inputs/outputs and internal logic, is stable. You may build workflows with it, having confidence that they will not break because of a change in this invocation.
+    - `Beta`: The invocation is not yet stable, but is planned to be stable in the future. Workflows built around this invocation may break, but we are committed to supporting this invocation long-term.
+    - `Prototype`: The invocation is not yet stable and may be removed from the application at any time. Workflows built around this invocation may break, and we are *not* committed to supporting this invocation.
     """
 
-    Connection = "connection"
-    Direct = "direct"
-    Any = "any"
-
-
-class FieldKind(str, Enum, metaclass=MetaEnum):
-    """
-    The kind of field.
-    - `Input`: An input field on a node.
-    - `Output`: An output field on a node.
-    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
-    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
-    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
-    allowing "metadata" for that field.
-    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
-    but which are used to store information about the node. For example, the `id` and `type` fields are node
-    attributes.
-
-    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
-    startup, and when generating the OpenAPI schema for the workflow editor.
-    """
-
-    Input = "input"
-    Output = "output"
-    Internal = "internal"
-    NodeAttribute = "node_attribute"
-
-
-class UIType(str, Enum, metaclass=MetaEnum):
-    """
-    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
-
-    - Model Fields
-    The most common node-author-facing use will be for model fields. Internally, there is no difference
-    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
-    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
-    the field is an SDXL main model field.
-
-    - Any Field
-    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
-    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
-
-    - Scheduler Field
-    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
-
-    - Internal Fields
-    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
-    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
-    should not be used by node authors.
-
-    - DEPRECATED Fields
-    These types are deprecated and should not be used by node authors. A warning will be logged if one is
-    used, and the type will be ignored. They are included here for backwards compatibility.
-    """
-
-    # region Model Field Types
-    SDXLMainModel = "SDXLMainModelField"
-    SDXLRefinerModel = "SDXLRefinerModelField"
-    ONNXModel = "ONNXModelField"
-    VaeModel = "VAEModelField"
-    LoRAModel = "LoRAModelField"
-    ControlNetModel = "ControlNetModelField"
-    IPAdapterModel = "IPAdapterModelField"
-    # endregion
-
-    # region Misc Field Types
-    Scheduler = "SchedulerField"
-    Any = "AnyField"
-    # endregion
-
-    # region Internal Field Types
-    _Collection = "CollectionField"
-    _CollectionItem = "CollectionItemField"
-    # endregion
-
-    # region DEPRECATED
-    Boolean = "DEPRECATED_Boolean"
-    Color = "DEPRECATED_Color"
-    Conditioning = "DEPRECATED_Conditioning"
-    Control = "DEPRECATED_Control"
-    Float = "DEPRECATED_Float"
-    Image = "DEPRECATED_Image"
-    Integer = "DEPRECATED_Integer"
-    Latents = "DEPRECATED_Latents"
-    String = "DEPRECATED_String"
-    BooleanCollection = "DEPRECATED_BooleanCollection"
-    ColorCollection = "DEPRECATED_ColorCollection"
-    ConditioningCollection = "DEPRECATED_ConditioningCollection"
-    ControlCollection = "DEPRECATED_ControlCollection"
-    FloatCollection = "DEPRECATED_FloatCollection"
-    ImageCollection = "DEPRECATED_ImageCollection"
-    IntegerCollection = "DEPRECATED_IntegerCollection"
-    LatentsCollection = "DEPRECATED_LatentsCollection"
-    StringCollection = "DEPRECATED_StringCollection"
-    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
-    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
-    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
-    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
-    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
-    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
-    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
-    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
-    StringPolymorphic = "DEPRECATED_StringPolymorphic"
-    MainModel = "DEPRECATED_MainModel"
-    UNet = "DEPRECATED_UNet"
-    Vae = "DEPRECATED_Vae"
-    CLIP = "DEPRECATED_CLIP"
-    Collection = "DEPRECATED_Collection"
-    CollectionItem = "DEPRECATED_CollectionItem"
-    Enum = "DEPRECATED_Enum"
-    WorkflowField = "DEPRECATED_WorkflowField"
-    IsIntermediate = "DEPRECATED_IsIntermediate"
-    BoardField = "DEPRECATED_BoardField"
-    MetadataItem = "DEPRECATED_MetadataItem"
-    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
-    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
-    MetadataDict = "DEPRECATED_MetadataDict"
-    # endregion
-
-
-class UIComponent(str, Enum, metaclass=MetaEnum):
-    """
-    The type of UI component to use for a field, used to override the default components, which are
-    inferred from the field type.
-    """
-
-    None_ = "none"
-    Textarea = "textarea"
-    Slider = "slider"
-
-
-class InputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
-    and by the workflow editor during schema parsing and UI rendering.
-    """
-
-    input: Input
-    orig_required: bool
-    field_kind: FieldKind
-    default: Optional[Any] = None
-    orig_default: Optional[Any] = None
-    ui_hidden: bool = False
-    ui_type: Optional[UIType] = None
-    ui_component: Optional[UIComponent] = None
-    ui_order: Optional[int] = None
-    ui_choice_labels: Optional[dict[str, str]] = None
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-class OutputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
-    during schema parsing and UI rendering.
-    """
-
-    field_kind: FieldKind
-    ui_hidden: bool
-    ui_type: Optional[UIType]
-    ui_order: Optional[int]
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-def InputField(
-    # copied from pydantic's Field
-    # TODO: Can we support default_factory?
-    default: Any = _Unset,
-    default_factory: Callable[[], Any] | None = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    input: Input = Input.Any,
-    ui_type: Optional[UIType] = None,
-    ui_component: Optional[UIComponent] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-    ui_choice_labels: Optional[dict[str, str]] = None,
-) -> Any:
-    """
-    Creates an input field for an invocation.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param Input input: [Input.Any] The kind of input this field requires. \
-      `Input.Direct` means a value must be provided on instantiation. \
-      `Input.Connection` means the value must be provided by a connection. \
-      `Input.Any` means either will do.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
-      The UI will always render a suitable component, but sometimes you want something different than the default. \
-      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
-      For this case, you could provide `UIComponent.Textarea`.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
-
-    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
-    """
-
-    json_schema_extra_ = InputFieldJSONSchemaExtra(
-        input=input,
-        ui_type=ui_type,
-        ui_component=ui_component,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        ui_choice_labels=ui_choice_labels,
-        field_kind=FieldKind.Input,
-        orig_required=True,
-    )
-
-    """
-    There is a conflict between the typing of invocation definitions and the typing of an invocation's
-    `invoke()` function.
-
-    On instantiation of a node, the invocation definition is used to create the python class. At this time,
-    any number of fields may be optional, because they may be provided by connections.
-
-    On calling of `invoke()`, however, those fields may be required.
-
-    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
-
-    `image` is required during the call to `invoke()`, but when the python class is instantiated,
-    the field may not be present. This is fine, because that image field will be provided by a
-    connection from an ancestor node, which outputs an image.
-
-    This means we want to type the `image` field as optional for the node class definition, but required
-    for the `invoke()` function.
-
-    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
-    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
-    any static type analysis tools will complain.
-
-    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
-    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
-    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
-    """
-
-    if default_factory is not _Unset and default_factory is not None:
-        default = default_factory()
-        logger.warn('"default_factory" is not supported, calling it now to set "default"')
-
-    # These are the args we may wish pass to the pydantic `Field()` function
-    field_args = {
-        "default": default,
-        "title": title,
-        "description": description,
-        "pattern": pattern,
-        "strict": strict,
-        "gt": gt,
-        "ge": ge,
-        "lt": lt,
-        "le": le,
-        "multiple_of": multiple_of,
-        "allow_inf_nan": allow_inf_nan,
-        "max_digits": max_digits,
-        "decimal_places": decimal_places,
-        "min_length": min_length,
-        "max_length": max_length,
-    }
-
-    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
-    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
-
-    # Because we are manually making fields optional, we need to store the original required bool for reference later
-    json_schema_extra_.orig_required = default is PydanticUndefined
-
-    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
-    if input is Input.Any or input is Input.Connection:
-        default_ = None if default is PydanticUndefined else default
-        provided_args.update({"default": default_})
-        if default is not PydanticUndefined:
-            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
-            json_schema_extra_.default = default
-            json_schema_extra_.orig_default = default
-    elif default is not PydanticUndefined:
-        default_ = default
-        provided_args.update({"default": default_})
-        json_schema_extra_.orig_default = default_
-
-    return Field(
-        **provided_args,
-        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
-    )
-
-
-def OutputField(
-    # copied from pydantic's Field
-    default: Any = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    ui_type: Optional[UIType] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-) -> Any:
-    """
-    Creates an output field for an invocation output.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
-    """
-    return Field(
-        default=default,
-        title=title,
-        description=description,
-        pattern=pattern,
-        strict=strict,
-        gt=gt,
-        ge=ge,
-        lt=lt,
-        le=le,
-        multiple_of=multiple_of,
-        allow_inf_nan=allow_inf_nan,
-        max_digits=max_digits,
-        decimal_places=decimal_places,
-        min_length=min_length,
-        max_length=max_length,
-        json_schema_extra=OutputFieldJSONSchemaExtra(
-            ui_type=ui_type,
-            ui_hidden=ui_hidden,
-            ui_order=ui_order,
-            field_kind=FieldKind.Output,
-        ).model_dump(exclude_none=True),
-    )
+    Stable = "stable"
+    Beta = "beta"
+    Prototype = "prototype"
 
 
 class UIConfigBase(BaseModel):
@@ -438,6 +81,7 @@ class UIConfigBase(BaseModel):
         description='The node\'s version. Should be a valid semver string e.g. "1.0.0" or "3.8.13".',
     )
     node_pack: Optional[str] = Field(default=None, description="Whether or not this is a custom node")
+    classification: Classification = Field(default=Classification.Stable, description="The node's classification")
 
     model_config = ConfigDict(
         validate_assignment=True,
@@ -445,33 +89,6 @@ class UIConfigBase(BaseModel):
     )
 
 
-class InvocationContext:
-    """Initialized and provided to on execution of invocations."""
-
-    services: InvocationServices
-    graph_execution_state_id: str
-    queue_id: str
-    queue_item_id: int
-    queue_batch_id: str
-    workflow: Optional[WorkflowWithoutID]
-
-    def __init__(
-        self,
-        services: InvocationServices,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        workflow: Optional[WorkflowWithoutID],
-    ):
-        self.services = services
-        self.graph_execution_state_id = graph_execution_state_id
-        self.queue_id = queue_id
-        self.queue_item_id = queue_item_id
-        self.queue_batch_id = queue_batch_id
-        self.workflow = workflow
-
-
 class BaseInvocationOutput(BaseModel):
     """
     Base class for all invocation outputs.
@@ -480,6 +97,7 @@ class BaseInvocationOutput(BaseModel):
     """
 
     _output_classes: ClassVar[set[BaseInvocationOutput]] = set()
+    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def register_output(cls, output: BaseInvocationOutput) -> None:
@@ -492,10 +110,14 @@ class BaseInvocationOutput(BaseModel):
         return cls._output_classes
 
     @classmethod
-    def get_outputs_union(cls) -> UnionType:
-        """Gets a union of all invocation outputs."""
-        outputs_union = Union[tuple(cls._output_classes)]  # type: ignore [valid-type]
-        return outputs_union  # type: ignore [return-value]
+    def get_typeadapter(cls) -> TypeAdapter[Any]:
+        """Gets a pydantc TypeAdapter for the union of all invocation output types."""
+        if not cls._typeadapter:
+            InvocationOutputsUnion = TypeAliasType(
+                "InvocationOutputsUnion", Annotated[Union[tuple(cls._output_classes)], Field(discriminator="type")]
+            )
+            cls._typeadapter = TypeAdapter(InvocationOutputsUnion)
+        return cls._typeadapter
 
     @classmethod
     def get_output_types(cls) -> Iterable[str]:
@@ -544,6 +166,7 @@ class BaseInvocation(ABC, BaseModel):
     """
 
     _invocation_classes: ClassVar[set[BaseInvocation]] = set()
+    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def get_type(cls) -> str:
@@ -556,10 +179,14 @@ class BaseInvocation(ABC, BaseModel):
         cls._invocation_classes.add(invocation)
 
     @classmethod
-    def get_invocations_union(cls) -> UnionType:
-        """Gets a union of all invocation types."""
-        invocations_union = Union[tuple(cls._invocation_classes)]  # type: ignore [valid-type]
-        return invocations_union  # type: ignore [return-value]
+    def get_typeadapter(cls) -> TypeAdapter[Any]:
+        """Gets a pydantc TypeAdapter for the union of all invocation types."""
+        if not cls._typeadapter:
+            InvocationsUnion = TypeAliasType(
+                "InvocationsUnion", Annotated[Union[tuple(cls._invocation_classes)], Field(discriminator="type")]
+            )
+            cls._typeadapter = TypeAdapter(InvocationsUnion)
+        return cls._typeadapter
 
     @classmethod
     def get_invocations(cls) -> Iterable[BaseInvocation]:
@@ -606,6 +233,7 @@ class BaseInvocation(ABC, BaseModel):
                 schema["category"] = uiconfig.category
             if uiconfig.node_pack is not None:
                 schema["node_pack"] = uiconfig.node_pack
+            schema["classification"] = uiconfig.classification
             schema["version"] = uiconfig.version
         if "required" not in schema or not isinstance(schema["required"], list):
             schema["required"] = []
@@ -616,7 +244,7 @@ class BaseInvocation(ABC, BaseModel):
         """Invoke with provided context and return outputs."""
         pass
 
-    def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
+    def invoke_internal(self, context: InvocationContext, services: "InvocationServices") -> BaseInvocationOutput:
         """
         Internal invoke method, calls `invoke()` after some prep.
         Handles optional fields that are required to call `invoke()` and invocation cache.
@@ -641,23 +269,23 @@ class BaseInvocation(ABC, BaseModel):
                     raise MissingInputException(self.model_fields["type"].default, field_name)
 
         # skip node cache codepath if it's disabled
-        if context.services.configuration.node_cache_size == 0:
+        if services.configuration.node_cache_size == 0:
             return self.invoke(context)
 
         output: BaseInvocationOutput
         if self.use_cache:
-            key = context.services.invocation_cache.create_key(self)
-            cached_value = context.services.invocation_cache.get(key)
+            key = services.invocation_cache.create_key(self)
+            cached_value = services.invocation_cache.get(key)
             if cached_value is None:
-                context.services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
                 output = self.invoke(context)
-                context.services.invocation_cache.save(key, output)
+                services.invocation_cache.save(key, output)
                 return output
             else:
-                context.services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
                 return cached_value
         else:
-            context.services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
+            services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
             return self.invoke(context)
 
     id: str = Field(
@@ -698,9 +326,7 @@ RESERVED_NODE_ATTRIBUTE_FIELD_NAMES = {
     "workflow",
 }
 
-RESERVED_INPUT_FIELD_NAMES = {
-    "metadata",
-}
+RESERVED_INPUT_FIELD_NAMES = {"metadata", "board"}
 
 RESERVED_OUTPUT_FIELD_NAMES = {"type"}
 
@@ -709,8 +335,10 @@ class _Model(BaseModel):
     pass
 
 
-# Get all pydantic model attrs, methods, etc
-RESERVED_PYDANTIC_FIELD_NAMES = {m[0] for m in inspect.getmembers(_Model())}
+with warnings.catch_warnings():
+    warnings.simplefilter("ignore", category=DeprecationWarning)
+    # Get all pydantic model attrs, methods, etc
+    RESERVED_PYDANTIC_FIELD_NAMES = {m[0] for m in inspect.getmembers(_Model())}
 
 
 def validate_fields(model_fields: dict[str, FieldInfo], model_type: str) -> None:
@@ -779,6 +407,7 @@ def invocation(
     category: Optional[str] = None,
     version: Optional[str] = None,
     use_cache: Optional[bool] = True,
+    classification: Classification = Classification.Stable,
 ) -> Callable[[Type[TBaseInvocation]], Type[TBaseInvocation]]:
     """
     Registers an invocation.
@@ -789,6 +418,7 @@ def invocation(
     :param Optional[str] category: Adds a category to the invocation. Used to group the invocations in the UI. Defaults to None.
     :param Optional[str] version: Adds a version to the invocation. Must be a valid semver string. Defaults to None.
     :param Optional[bool] use_cache: Whether or not to use the invocation cache. Defaults to True. The user may override this in the workflow editor.
+    :param Classification classification: The classification of the invocation. Defaults to FeatureClassification.Stable. Use Beta or Prototype if the invocation is unstable.
     """
 
     def wrapper(cls: Type[TBaseInvocation]) -> Type[TBaseInvocation]:
@@ -809,6 +439,7 @@ def invocation(
         cls.UIConfig.title = title
         cls.UIConfig.tags = tags
         cls.UIConfig.category = category
+        cls.UIConfig.classification = classification
 
         # Grab the node pack's name from the module name, if it's a custom node
         is_custom_node = cls.__module__.rsplit(".", 1)[0] == "invokeai.app.invocations"
@@ -905,37 +536,3 @@ def invocation_output(
         return cls
 
     return wrapper
-
-
-class MetadataField(RootModel):
-    """
-    Pydantic model for metadata with custom root of type dict[str, Any].
-    Metadata is stored without a strict schema.
-    """
-
-    root: dict[str, Any] = Field(description="The metadata")
-
-
-MetadataFieldValidator = TypeAdapter(MetadataField)
-
-
-class WithMetadata(BaseModel):
-    metadata: Optional[MetadataField] = Field(
-        default=None,
-        description=FieldDescriptions.metadata,
-        json_schema_extra=InputFieldJSONSchemaExtra(
-            field_kind=FieldKind.Internal,
-            input=Input.Connection,
-            orig_required=False,
-        ).model_dump(exclude_none=True),
-    )
-
-
-class WithWorkflow:
-    workflow = None
-
-    def __init_subclass__(cls) -> None:
-        logger.warn(
-            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
-        )
-        super().__init_subclass__()

invokeai/app/invocations/collections.py

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

invokeai/app/invocations/compel.py

@@ -1,40 +1,39 @@
-import re
-from dataclasses import dataclass
-from typing import List, Optional, Union
+from typing import Iterator, List, Optional, Tuple, Union
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
+from transformers import CLIPTextModel, CLIPTokenizer
 
-from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    Input,
+    InputField,
+    OutputField,
+    UIComponent,
+)
+from invokeai.app.invocations.primitives import ConditioningOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.ti_utils import generate_ti_list
+from invokeai.backend.lora import LoRAModelRaw
+from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
+    ConditioningFieldData,
     ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
+from invokeai.backend.util.devices import torch_dtype
 
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import ModelNotFoundException, ModelType
-from ...backend.util.devices import torch_dtype
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
 from .model import ClipField
 
-
-@dataclass
-class ConditioningFieldData:
-    conditionings: List[BasicConditioningInfo]
-    # unconditioned: Optional[torch.Tensor]
+# unconditioned: Optional[torch.Tensor]
 
 
 # class ConditioningAlgo(str, Enum):
@@ -48,7 +47,7 @@ class ConditioningFieldData:
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -66,49 +65,27 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-            context=context,
-        )
+        tokenizer_info = context.models.load(**self.clip.tokenizer.model_dump())
+        tokenizer_model = tokenizer_info.model
+        assert isinstance(tokenizer_model, CLIPTokenizer)
+        text_encoder_info = context.models.load(**self.clip.text_encoder.model_dump())
+        text_encoder_model = text_encoder_info.model
+        assert isinstance(text_encoder_model, CLIPTextModel)
 
-        def _lora_loader():
+        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in self.clip.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
-                yield (lora_info.context.model, lora.weight)
+                lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
+                assert isinstance(lora_info.model, LoRAModelRaw)
+                yield (lora_info.model, lora.weight)
                 del lora_info
             return
 
-        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        ti_list = []
-        for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
-            name = trigger[1:-1]
-            try:
-                ti_list.append(
-                    (
-                        name,
-                        context.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=self.clip.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                            context=context,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
-                # print(e)
-                # import traceback
-                # print(traceback.format_exc())
-                print(f'Warn: trigger: "{trigger}" not found')
+        ti_list = generate_ti_list(self.prompt, text_encoder_info.config.base, context)
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -116,8 +93,9 @@ class CompelInvocation(BaseInvocation):
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_model, self.clip.skipped_layers),
         ):
+            assert isinstance(text_encoder, CLIPTextModel)
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -128,7 +106,7 @@ class CompelInvocation(BaseInvocation):
 
             conjunction = Compel.parse_prompt_string(self.prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
             c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
@@ -149,17 +127,14 @@ class CompelInvocation(BaseInvocation):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 class SDXLPromptInvocationBase:
+    """Prompt processor for SDXL models."""
+
     def run_clip_compel(
         self,
         context: InvocationContext,
@@ -168,26 +143,25 @@ class SDXLPromptInvocationBase:
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ):
-        tokenizer_info = context.services.model_manager.get_model(
-            **clip_field.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.model_dump(),
-            context=context,
-        )
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[ExtraConditioningInfo]]:
+        tokenizer_info = context.models.load(**clip_field.tokenizer.model_dump())
+        tokenizer_model = tokenizer_info.model
+        assert isinstance(tokenizer_model, CLIPTokenizer)
+        text_encoder_info = context.models.load(**clip_field.text_encoder.model_dump())
+        text_encoder_model = text_encoder_info.model
+        assert isinstance(text_encoder_model, CLIPTextModel)
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
-            cpu_text_encoder = text_encoder_info.context.model
+            cpu_text_encoder = text_encoder_info.model
+            assert isinstance(cpu_text_encoder, torch.nn.Module)
             c = torch.zeros(
                 (
                     1,
                     cpu_text_encoder.config.max_position_embeddings,
                     cpu_text_encoder.config.hidden_size,
                 ),
-                dtype=text_encoder_info.context.cache.precision,
+                dtype=cpu_text_encoder.dtype,
             )
             if get_pooled:
                 c_pooled = torch.zeros(
@@ -198,40 +172,21 @@ class SDXLPromptInvocationBase:
                 c_pooled = None
             return c, c_pooled, None
 
-        def _lora_loader():
+        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in clip_field.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
-                yield (lora_info.context.model, lora.weight)
+                lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
+                lora_model = lora_info.model
+                assert isinstance(lora_model, LoRAModelRaw)
+                yield (lora_model, lora.weight)
                 del lora_info
             return
 
-        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        ti_list = []
-        for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", prompt):
-            name = trigger[1:-1]
-            try:
-                ti_list.append(
-                    (
-                        name,
-                        context.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=clip_field.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                            context=context,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
-                # print(e)
-                # import traceback
-                # print(traceback.format_exc())
-                print(f'Warn: trigger: "{trigger}" not found')
+        ti_list = generate_ti_list(prompt, text_encoder_info.config.base, context)
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -239,8 +194,9 @@ class SDXLPromptInvocationBase:
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_model, clip_field.skipped_layers),
         ):
+            assert isinstance(text_encoder, CLIPTextModel)
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -253,7 +209,7 @@ class SDXLPromptInvocationBase:
 
             conjunction = Compel.parse_prompt_string(prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 # TODO: better logging for and syntax
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
@@ -286,7 +242,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -357,6 +313,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 dim=1,
             )
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -368,14 +325,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation(
@@ -383,7 +335,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     title="SDXL Refiner Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -410,6 +362,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         add_time_ids = torch.tensor([original_size + crop_coords + (self.aesthetic_score,)])
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -421,14 +374,9 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation_output("clip_skip_output")
@@ -449,7 +397,7 @@ class ClipSkipInvocation(BaseInvocation):
     """Skip layers in clip text_encoder model."""
 
     clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
-    skipped_layers: int = InputField(default=0, description=FieldDescriptions.skipped_layers)
+    skipped_layers: int = InputField(default=0, ge=0, description=FieldDescriptions.skipped_layers)
 
     def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
         self.clip.skipped_layers += self.skipped_layers
@@ -459,9 +407,9 @@ class ClipSkipInvocation(BaseInvocation):
 
 
 def get_max_token_count(
-    tokenizer,
+    tokenizer: CLIPTokenizer,
     prompt: Union[FlattenedPrompt, Blend, Conjunction],
-    truncate_if_too_long=False,
+    truncate_if_too_long: bool = False,
 ) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt
@@ -473,7 +421,9 @@ def get_max_token_count(
         return len(get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long))
 
 
-def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True) -> List[str]:
+def get_tokens_for_prompt_object(
+    tokenizer: CLIPTokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long: bool = True
+) -> List[str]:
     if type(parsed_prompt) is Blend:
         raise ValueError("Blend is not supported here - you need to get tokens for each of its .children")
 
@@ -486,24 +436,29 @@ def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, trun
         for x in parsed_prompt.children
     ]
     text = " ".join(text_fragments)
-    tokens = tokenizer.tokenize(text)
+    tokens: List[str] = tokenizer.tokenize(text)
     if truncate_if_too_long:
         max_tokens_length = tokenizer.model_max_length - 2  # typically 75
         tokens = tokens[0:max_tokens_length]
     return tokens
 
 
-def log_tokenization_for_conjunction(c: Conjunction, tokenizer, display_label_prefix=None):
+def log_tokenization_for_conjunction(
+    c: Conjunction, tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
+) -> None:
     display_label_prefix = display_label_prefix or ""
     for i, p in enumerate(c.prompts):
         if len(c.prompts) > 1:
             this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
         else:
+            assert display_label_prefix is not None
             this_display_label_prefix = display_label_prefix
         log_tokenization_for_prompt_object(p, tokenizer, display_label_prefix=this_display_label_prefix)
 
 
-def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None):
+def log_tokenization_for_prompt_object(
+    p: Union[Blend, FlattenedPrompt], tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
+) -> None:
     display_label_prefix = display_label_prefix or ""
     if type(p) is Blend:
         blend: Blend = p
@@ -543,7 +498,12 @@ def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokeniz
             log_tokenization_for_text(text, tokenizer, display_label=display_label_prefix)
 
 
-def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
+def log_tokenization_for_text(
+    text: str,
+    tokenizer: CLIPTokenizer,
+    display_label: Optional[str] = None,
+    truncate_if_too_long: Optional[bool] = False,
+) -> None:
     """shows how the prompt is tokenized
     # usually tokens have '</w>' to indicate end-of-word,
     # but for readability it has been replaced with ' '

invokeai/app/invocations/constants.py

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

invokeai/app/invocations/controlnet_image_processors.py

@@ -17,31 +17,30 @@ from controlnet_aux import (
     MidasDetector,
     MLSDdetector,
     NormalBaeDetector,
-    OpenposeDetector,
     PidiNetDetector,
     SamDetector,
     ZoeDetector,
 )
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
-from pydantic import BaseModel, ConfigDict, Field, field_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
-
-from ...backend.model_management import BaseModelType
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
     Input,
     InputField,
-    InvocationContext,
     OutputField,
+    WithBoard,
     WithMetadata,
-    invocation,
-    invocation_output,
 )
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
+from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
+
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 
 CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
 CONTROLNET_RESIZE_VALUES = Literal[
@@ -55,10 +54,7 @@ CONTROLNET_RESIZE_VALUES = Literal[
 class ControlNetModelField(BaseModel):
     """ControlNet model field"""
 
-    model_name: str = Field(description="Name of the ControlNet model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Model config record key for the ControlNet model")
 
 
 class ControlField(BaseModel):
@@ -75,17 +71,16 @@ class ControlField(BaseModel):
     resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
 
     @field_validator("control_weight")
+    @classmethod
     def validate_control_weight(cls, v):
-        """Validate that all control weights in the valid range"""
-        if isinstance(v, list):
-            for i in v:
-                if i < -1 or i > 2:
-                    raise ValueError("Control weights must be within -1 to 2 range")
-        else:
-            if v < -1 or v > 2:
-                raise ValueError("Control weights must be within -1 to 2 range")
+        validate_weights(v)
         return v
 
+    @model_validator(mode="after")
+    def validate_begin_end_step_percent(self):
+        validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
+        return self
+
 
 @invocation_output("control_output")
 class ControlOutput(BaseInvocationOutput):
@@ -95,17 +90,17 @@ class ControlOutput(BaseInvocationOutput):
     control: ControlField = OutputField(description=FieldDescriptions.control)
 
 
-@invocation("controlnet", title="ControlNet", tags=["controlnet"], category="controlnet", version="1.1.0")
+@invocation("controlnet", title="ControlNet", tags=["controlnet"], category="controlnet", version="1.1.1")
 class ControlNetInvocation(BaseInvocation):
     """Collects ControlNet info to pass to other nodes"""
 
     image: ImageField = InputField(description="The control image")
     control_model: ControlNetModelField = InputField(description=FieldDescriptions.controlnet_model, input=Input.Direct)
     control_weight: Union[float, List[float]] = InputField(
-        default=1.0, description="The weight given to the ControlNet"
+        default=1.0, ge=-1, le=2, description="The weight given to the ControlNet"
     )
     begin_step_percent: float = InputField(
-        default=0, ge=-1, le=2, description="When the ControlNet is first applied (% of total steps)"
+        default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
     )
     end_step_percent: float = InputField(
         default=1, ge=0, le=1, description="When the ControlNet is last applied (% of total steps)"
@@ -113,6 +108,17 @@ class ControlNetInvocation(BaseInvocation):
     control_mode: CONTROLNET_MODE_VALUES = InputField(default="balanced", description="The control mode used")
     resize_mode: CONTROLNET_RESIZE_VALUES = InputField(default="just_resize", description="The resize mode used")
 
+    @field_validator("control_weight")
+    @classmethod
+    def validate_control_weight(cls, v):
+        validate_weights(v)
+        return v
+
+    @model_validator(mode="after")
+    def validate_begin_end_step_percent(self) -> "ControlNetInvocation":
+        validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
+        return self
+
     def invoke(self, context: InvocationContext) -> ControlOutput:
         return ControlOutput(
             control=ControlField(
@@ -128,7 +134,7 @@ class ControlNetInvocation(BaseInvocation):
 
 
 # This invocation exists for other invocations to subclass it - do not register with @invocation!
-class ImageProcessorInvocation(BaseInvocation, WithMetadata):
+class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Base class for invocations that preprocess images for ControlNet"""
 
     image: ImageField = InputField(description="The image to process")
@@ -137,23 +143,18 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
         # superclass just passes through image without processing
         return image
 
+    def load_image(self, context: InvocationContext) -> Image.Image:
+        # allows override for any special formatting specific to the preprocessor
+        return context.images.get_pil(self.image.image_name, "RGB")
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        raw_image = context.services.images.get_pil_image(self.image.image_name)
+        raw_image = self.load_image(context)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
         # currently can't see processed image in node UI without a showImage node,
         #    so for now setting image_type to RESULT instead of INTERMEDIATE so will get saved in gallery
-        image_dto = context.services.images.create(
-            image=processed_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.CONTROL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=processed_image)
 
         """Builds an ImageOutput and its ImageField"""
         processed_image_field = ImageField(image_name=image_dto.image_name)
@@ -172,7 +173,7 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
     title="Canny Processor",
     tags=["controlnet", "canny"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class CannyImageProcessorInvocation(ImageProcessorInvocation):
     """Canny edge detection for ControlNet"""
@@ -184,6 +185,10 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
         default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)"
     )
 
+    def load_image(self, context: InvocationContext) -> Image.Image:
+        # Keep alpha channel for Canny processing to detect edges of transparent areas
+        return context.images.get_pil(self.image.image_name, "RGBA")
+
     def run_processor(self, image):
         canny_processor = CannyDetector()
         processed_image = canny_processor(image, self.low_threshold, self.high_threshold)
@@ -195,7 +200,7 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
     title="HED (softedge) Processor",
     tags=["controlnet", "hed", "softedge"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class HedImageProcessorInvocation(ImageProcessorInvocation):
     """Applies HED edge detection to image"""
@@ -224,7 +229,7 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Processor",
     tags=["controlnet", "lineart"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LineartImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art processing to image"""
@@ -246,7 +251,7 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Anime Processor",
     tags=["controlnet", "lineart", "anime"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art anime processing to image"""
@@ -264,37 +269,12 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "openpose_image_processor",
-    title="Openpose Processor",
-    tags=["controlnet", "openpose", "pose"],
-    category="controlnet",
-    version="1.2.0",
-)
-class OpenposeImageProcessorInvocation(ImageProcessorInvocation):
-    """Applies Openpose processing to image"""
-
-    hand_and_face: bool = InputField(default=False, description="Whether to use hands and face mode")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-
-    def run_processor(self, image):
-        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
-
-
 @invocation(
     "midas_depth_image_processor",
     title="Midas Depth Processor",
     tags=["controlnet", "midas"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Midas depth processing to image"""
@@ -321,7 +301,7 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Normal BAE Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies NormalBae processing to image"""
@@ -338,7 +318,7 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.0"
+    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.1"
 )
 class MlsdImageProcessorInvocation(ImageProcessorInvocation):
     """Applies MLSD processing to image"""
@@ -361,7 +341,7 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.0"
+    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.1"
 )
 class PidiImageProcessorInvocation(ImageProcessorInvocation):
     """Applies PIDI processing to image"""
@@ -388,7 +368,7 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
     title="Content Shuffle Processor",
     tags=["controlnet", "contentshuffle"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     """Applies content shuffle processing to image"""
@@ -418,7 +398,7 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     title="Zoe (Depth) Processor",
     tags=["controlnet", "zoe", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Zoe depth processing to image"""
@@ -434,7 +414,7 @@ class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Mediapipe Face Processor",
     tags=["controlnet", "mediapipe", "face"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     """Applies mediapipe face processing to image"""
@@ -443,10 +423,6 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     min_confidence: float = InputField(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
 
     def run_processor(self, image):
-        # MediaPipeFaceDetector throws an error if image has alpha channel
-        #     so convert to RGB if needed
-        if image.mode == "RGBA":
-            image = image.convert("RGB")
         mediapipe_face_processor = MediapipeFaceDetector()
         processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence)
         return processed_image
@@ -457,7 +433,7 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     title="Leres (Depth) Processor",
     tags=["controlnet", "leres", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LeresImageProcessorInvocation(ImageProcessorInvocation):
     """Applies leres processing to image"""
@@ -486,7 +462,7 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
     title="Tile Resample Processor",
     tags=["controlnet", "tile"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     """Tile resampler processor"""
@@ -526,7 +502,7 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     title="Segment Anything Processor",
     tags=["controlnet", "segmentanything"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     """Applies segment anything processing to image"""
@@ -568,7 +544,7 @@ class SamDetectorReproducibleColors(SamDetector):
     title="Color Map Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a color map from the provided image"""
@@ -576,7 +552,6 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     color_map_tile_size: int = InputField(default=64, ge=0, description=FieldDescriptions.tile_size)
 
     def run_processor(self, image: Image.Image):
-        image = image.convert("RGB")
         np_image = np.array(image, dtype=np.uint8)
         height, width = np_image.shape[:2]
 
@@ -591,3 +566,57 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
         color_map = cv2.resize(color_map, (width, height), interpolation=cv2.INTER_NEAREST)
         color_map = Image.fromarray(color_map)
         return color_map
+
+
+DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
+
+
+@invocation(
+    "depth_anything_image_processor",
+    title="Depth Anything Processor",
+    tags=["controlnet", "depth", "depth anything"],
+    category="controlnet",
+    version="1.0.0",
+)
+class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
+    """Generates a depth map based on the Depth Anything algorithm"""
+
+    model_size: DEPTH_ANYTHING_MODEL_SIZES = InputField(
+        default="small", description="The size of the depth model to use"
+    )
+    resolution: int = InputField(default=512, ge=64, multiple_of=64, description=FieldDescriptions.image_res)
+    offload: bool = InputField(default=False)
+
+    def run_processor(self, image: Image.Image):
+        depth_anything_detector = DepthAnythingDetector()
+        depth_anything_detector.load_model(model_size=self.model_size)
+
+        processed_image = depth_anything_detector(image=image, resolution=self.resolution, offload=self.offload)
+        return processed_image
+
+
+@invocation(
+    "dw_openpose_image_processor",
+    title="DW Openpose Image Processor",
+    tags=["controlnet", "dwpose", "openpose"],
+    category="controlnet",
+    version="1.0.0",
+)
+class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
+    """Generates an openpose pose from an image using DWPose"""
+
+    draw_body: bool = InputField(default=True)
+    draw_face: bool = InputField(default=False)
+    draw_hands: bool = InputField(default=False)
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+
+    def run_processor(self, image: Image.Image):
+        dw_openpose = DWOpenposeDetector()
+        processed_image = dw_openpose(
+            image,
+            draw_face=self.draw_face,
+            draw_hands=self.draw_hands,
+            draw_body=self.draw_body,
+            resolution=self.image_resolution,
+        )
+        return processed_image

invokeai/app/invocations/cv.py

@@ -5,22 +5,24 @@ import cv2 as cv
 import numpy
 from PIL import Image, ImageOps
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 
 
-@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.0")
-class CvInpaintInvocation(BaseInvocation, WithMetadata):
+@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.1")
+class CvInpaintInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Simple inpaint using opencv."""
 
     image: ImageField = InputField(description="The image to inpaint")
     mask: ImageField = InputField(description="The mask to use when inpainting")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        mask = context.services.images.get_pil_image(self.mask.image_name)
+        image = context.images.get_pil(self.image.image_name)
+        mask = context.images.get_pil(self.mask.image_name)
 
         # Convert to cv image/mask
         # TODO: consider making these utility functions
@@ -34,18 +36,6 @@ class CvInpaintInvocation(BaseInvocation, WithMetadata):
         # TODO: consider making a utility function
         image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
 
-        image_dto = context.services.images.create(
-            image=image_inpainted,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=image_inpainted)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/facetools.py

@@ -13,15 +13,13 @@ from pydantic import field_validator
 import invokeai.assets.fonts as font_assets
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 
 @invocation_output("face_mask_output")
@@ -306,37 +304,37 @@ def extract_face(
 
     # Adjust the crop boundaries to stay within the original image's dimensions
     if x_min < 0:
-        context.services.logger.warning("FaceTools --> -X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -X-axis padding reached image edge.")
         x_max -= x_min
         x_min = 0
     elif x_max > mask.width:
-        context.services.logger.warning("FaceTools --> +X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +X-axis padding reached image edge.")
         x_min -= x_max - mask.width
         x_max = mask.width
 
     if y_min < 0:
-        context.services.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
         y_max -= y_min
         y_min = 0
     elif y_max > mask.height:
-        context.services.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
         y_min -= y_max - mask.height
         y_max = mask.height
 
     # Ensure the crop is square and adjust the boundaries if needed
     if x_max - x_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
         diff = crop_size - (x_max - x_min)
         x_min -= diff // 2
         x_max += diff - diff // 2
 
     if y_max - y_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
         diff = crop_size - (y_max - y_min)
         y_min -= diff // 2
         y_max += diff - diff // 2
 
-    context.services.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
+    context.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
 
     # Crop the output image to the specified size with the center of the face mesh as the center.
     mask = mask.crop((x_min, y_min, x_max, y_max))
@@ -368,7 +366,7 @@ def get_faces_list(
 
     # Generate the face box mask and get the center of the face.
     if not should_chunk:
-        context.services.logger.info("FaceTools --> Attempting full image face detection.")
+        context.logger.info("FaceTools --> Attempting full image face detection.")
         result = generate_face_box_mask(
             context=context,
             minimum_confidence=minimum_confidence,
@@ -380,7 +378,7 @@ def get_faces_list(
             draw_mesh=draw_mesh,
         )
     if should_chunk or len(result) == 0:
-        context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
+        context.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
         width, height = image.size
         image_chunks = []
         x_offsets = []
@@ -399,7 +397,7 @@ def get_faces_list(
                 x_offsets.append(x)
                 y_offsets.append(0)
                 fx += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
+                context.logger.info(f"FaceTools --> Chunk starting at x = {x}")
         elif height > width:
             # Portrait - slice the image vertically
             fy = 0.0
@@ -411,10 +409,10 @@ def get_faces_list(
                 x_offsets.append(0)
                 y_offsets.append(y)
                 fy += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
+                context.logger.info(f"FaceTools --> Chunk starting at y = {y}")
 
         for idx in range(len(image_chunks)):
-            context.services.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
+            context.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
             result = result + generate_face_box_mask(
                 context=context,
                 minimum_confidence=minimum_confidence,
@@ -428,7 +426,7 @@ def get_faces_list(
 
         if len(result) == 0:
             # Give up
-            context.services.logger.warning(
+            context.logger.warning(
                 "FaceTools --> No face detected in chunked input image. Passing through original image."
             )
 
@@ -437,7 +435,7 @@ def get_faces_list(
     return all_faces
 
 
-@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.1")
 class FaceOffInvocation(BaseInvocation, WithMetadata):
     """Bound, extract, and mask a face from an image using MediaPipe detection"""
 
@@ -470,11 +468,11 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         )
 
         if len(all_faces) == 0:
-            context.services.logger.warning("FaceOff --> No faces detected. Passing through original image.")
+            context.logger.warning("FaceOff --> No faces detected. Passing through original image.")
             return None
 
         if self.face_id > len(all_faces) - 1:
-            context.services.logger.warning(
+            context.logger.warning(
                 f"FaceOff --> Face ID {self.face_id} is outside of the number of faces detected ({len(all_faces)}). Passing through original image."
             )
             return None
@@ -486,7 +484,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return face_data
 
     def invoke(self, context: InvocationContext) -> FaceOffOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.faceoff(context=context, image=image)
 
         if result is None:
@@ -500,24 +498,9 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
             x = result["x_min"]
             y = result["y_min"]
 
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        mask_dto = context.services.images.create(
-            image=result_mask,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result_mask, image_category=ImageCategory.MASK)
 
         output = FaceOffOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -531,7 +514,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return output
 
 
-@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.1")
 class FaceMaskInvocation(BaseInvocation, WithMetadata):
     """Face mask creation using mediapipe face detection"""
 
@@ -580,7 +563,7 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
             if len(intersected_face_ids) == 0:
                 id_range_str = ",".join([str(id) for id in id_range])
-                context.services.logger.warning(
+                context.logger.warning(
                     f"Face IDs must be in range of detected faces - requested {self.face_ids}, detected {id_range_str}. Passing through original image."
                 )
                 return FaceMaskResult(
@@ -616,27 +599,12 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
         )
 
     def invoke(self, context: InvocationContext) -> FaceMaskOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.facemask(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result["image"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result["image"])
 
-        mask_dto = context.services.images.create(
-            image=result["mask"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result["mask"], image_category=ImageCategory.MASK)
 
         output = FaceMaskOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -649,9 +617,9 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
 
 @invocation(
-    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.0"
+    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.1"
 )
-class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
+class FaceIdentifierInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
 
     image: ImageField = InputField(description="Image to face detect")
@@ -705,21 +673,9 @@ class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
         return image
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result_image = self.faceidentifier(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/fields.py

@@ -0,0 +1,566 @@
+from enum import Enum
+from typing import Any, Callable, Optional, Tuple
+
+from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter
+from pydantic.fields import _Unset
+from pydantic_core import PydanticUndefined
+
+from invokeai.app.util.metaenum import MetaEnum
+from invokeai.backend.util.logging import InvokeAILogger
+
+logger = InvokeAILogger.get_logger()
+
+
+class UIType(str, Enum, metaclass=MetaEnum):
+    """
+    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
+
+    - Model Fields
+    The most common node-author-facing use will be for model fields. Internally, there is no difference
+    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
+    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
+    the field is an SDXL main model field.
+
+    - Any Field
+    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
+    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
+
+    - Scheduler Field
+    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
+
+    - Internal Fields
+    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
+    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
+    should not be used by node authors.
+
+    - DEPRECATED Fields
+    These types are deprecated and should not be used by node authors. A warning will be logged if one is
+    used, and the type will be ignored. They are included here for backwards compatibility.
+    """
+
+    # region Model Field Types
+    SDXLMainModel = "SDXLMainModelField"
+    SDXLRefinerModel = "SDXLRefinerModelField"
+    ONNXModel = "ONNXModelField"
+    VaeModel = "VAEModelField"
+    LoRAModel = "LoRAModelField"
+    ControlNetModel = "ControlNetModelField"
+    IPAdapterModel = "IPAdapterModelField"
+    # endregion
+
+    # region Misc Field Types
+    Scheduler = "SchedulerField"
+    Any = "AnyField"
+    # endregion
+
+    # region Internal Field Types
+    _Collection = "CollectionField"
+    _CollectionItem = "CollectionItemField"
+    # endregion
+
+    # region DEPRECATED
+    Boolean = "DEPRECATED_Boolean"
+    Color = "DEPRECATED_Color"
+    Conditioning = "DEPRECATED_Conditioning"
+    Control = "DEPRECATED_Control"
+    Float = "DEPRECATED_Float"
+    Image = "DEPRECATED_Image"
+    Integer = "DEPRECATED_Integer"
+    Latents = "DEPRECATED_Latents"
+    String = "DEPRECATED_String"
+    BooleanCollection = "DEPRECATED_BooleanCollection"
+    ColorCollection = "DEPRECATED_ColorCollection"
+    ConditioningCollection = "DEPRECATED_ConditioningCollection"
+    ControlCollection = "DEPRECATED_ControlCollection"
+    FloatCollection = "DEPRECATED_FloatCollection"
+    ImageCollection = "DEPRECATED_ImageCollection"
+    IntegerCollection = "DEPRECATED_IntegerCollection"
+    LatentsCollection = "DEPRECATED_LatentsCollection"
+    StringCollection = "DEPRECATED_StringCollection"
+    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
+    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
+    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
+    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
+    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
+    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
+    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
+    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
+    StringPolymorphic = "DEPRECATED_StringPolymorphic"
+    MainModel = "DEPRECATED_MainModel"
+    UNet = "DEPRECATED_UNet"
+    Vae = "DEPRECATED_Vae"
+    CLIP = "DEPRECATED_CLIP"
+    Collection = "DEPRECATED_Collection"
+    CollectionItem = "DEPRECATED_CollectionItem"
+    Enum = "DEPRECATED_Enum"
+    WorkflowField = "DEPRECATED_WorkflowField"
+    IsIntermediate = "DEPRECATED_IsIntermediate"
+    BoardField = "DEPRECATED_BoardField"
+    MetadataItem = "DEPRECATED_MetadataItem"
+    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
+    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
+    MetadataDict = "DEPRECATED_MetadataDict"
+
+
+class UIComponent(str, Enum, metaclass=MetaEnum):
+    """
+    The type of UI component to use for a field, used to override the default components, which are
+    inferred from the field type.
+    """
+
+    None_ = "none"
+    Textarea = "textarea"
+    Slider = "slider"
+
+
+class FieldDescriptions:
+    denoising_start = "When to start denoising, expressed a percentage of total steps"
+    denoising_end = "When to stop denoising, expressed a percentage of total steps"
+    cfg_scale = "Classifier-Free Guidance scale"
+    cfg_rescale_multiplier = "Rescale multiplier for CFG guidance, used for models trained with zero-terminal SNR"
+    scheduler = "Scheduler to use during inference"
+    positive_cond = "Positive conditioning tensor"
+    negative_cond = "Negative conditioning tensor"
+    noise = "Noise tensor"
+    clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
+    unet = "UNet (scheduler, LoRAs)"
+    vae = "VAE"
+    cond = "Conditioning tensor"
+    controlnet_model = "ControlNet model to load"
+    vae_model = "VAE model to load"
+    lora_model = "LoRA model to load"
+    main_model = "Main model (UNet, VAE, CLIP) to load"
+    sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
+    sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
+    onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
+    lora_weight = "The weight at which the LoRA is applied to each model"
+    compel_prompt = "Prompt to be parsed by Compel to create a conditioning tensor"
+    raw_prompt = "Raw prompt text (no parsing)"
+    sdxl_aesthetic = "The aesthetic score to apply to the conditioning tensor"
+    skipped_layers = "Number of layers to skip in text encoder"
+    seed = "Seed for random number generation"
+    steps = "Number of steps to run"
+    width = "Width of output (px)"
+    height = "Height of output (px)"
+    control = "ControlNet(s) to apply"
+    ip_adapter = "IP-Adapter to apply"
+    t2i_adapter = "T2I-Adapter(s) to apply"
+    denoised_latents = "Denoised latents tensor"
+    latents = "Latents tensor"
+    strength = "Strength of denoising (proportional to steps)"
+    metadata = "Optional metadata to be saved with the image"
+    metadata_collection = "Collection of Metadata"
+    metadata_item_polymorphic = "A single metadata item or collection of metadata items"
+    metadata_item_label = "Label for this metadata item"
+    metadata_item_value = "The value for this metadata item (may be any type)"
+    workflow = "Optional workflow to be saved with the image"
+    interp_mode = "Interpolation mode"
+    torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
+    fp32 = "Whether or not to use full float32 precision"
+    precision = "Precision to use"
+    tiled = "Processing using overlapping tiles (reduce memory consumption)"
+    detect_res = "Pixel resolution for detection"
+    image_res = "Pixel resolution for output image"
+    safe_mode = "Whether or not to use safe mode"
+    scribble_mode = "Whether or not to use scribble mode"
+    scale_factor = "The factor by which to scale"
+    blend_alpha = (
+        "Blending factor. 0.0 = use input A only, 1.0 = use input B only, 0.5 = 50% mix of input A and input B."
+    )
+    num_1 = "The first number"
+    num_2 = "The second number"
+    mask = "The mask to use for the operation"
+    board = "The board to save the image to"
+    image = "The image to process"
+    tile_size = "Tile size"
+    inclusive_low = "The inclusive low value"
+    exclusive_high = "The exclusive high value"
+    decimal_places = "The number of decimal places to round to"
+    freeu_s1 = 'Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
+    freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."
+
+
+class ImageField(BaseModel):
+    """An image primitive field"""
+
+    image_name: str = Field(description="The name of the image")
+
+
+class BoardField(BaseModel):
+    """A board primitive field"""
+
+    board_id: str = Field(description="The id of the board")
+
+
+class DenoiseMaskField(BaseModel):
+    """An inpaint mask field"""
+
+    mask_name: str = Field(description="The name of the mask image")
+    masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
+    gradient: bool = Field(default=False, description="Used for gradient inpainting")
+
+
+class LatentsField(BaseModel):
+    """A latents tensor primitive field"""
+
+    latents_name: str = Field(description="The name of the latents")
+    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
+
+
+class ColorField(BaseModel):
+    """A color primitive field"""
+
+    r: int = Field(ge=0, le=255, description="The red component")
+    g: int = Field(ge=0, le=255, description="The green component")
+    b: int = Field(ge=0, le=255, description="The blue component")
+    a: int = Field(ge=0, le=255, description="The alpha component")
+
+    def tuple(self) -> Tuple[int, int, int, int]:
+        return (self.r, self.g, self.b, self.a)
+
+
+class ConditioningField(BaseModel):
+    """A conditioning tensor primitive value"""
+
+    conditioning_name: str = Field(description="The name of conditioning tensor")
+    # endregion
+
+
+class MetadataField(RootModel):
+    """
+    Pydantic model for metadata with custom root of type dict[str, Any].
+    Metadata is stored without a strict schema.
+    """
+
+    root: dict[str, Any] = Field(description="The metadata")
+
+
+MetadataFieldValidator = TypeAdapter(MetadataField)
+
+
+class Input(str, Enum, metaclass=MetaEnum):
+    """
+    The type of input a field accepts.
+    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
+      are instantiated.
+    - `Input.Connection`: The field must have its value provided by a connection.
+    - `Input.Any`: The field may have its value provided either directly or by a connection.
+    """
+
+    Connection = "connection"
+    Direct = "direct"
+    Any = "any"
+
+
+class FieldKind(str, Enum, metaclass=MetaEnum):
+    """
+    The kind of field.
+    - `Input`: An input field on a node.
+    - `Output`: An output field on a node.
+    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
+    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
+    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
+    allowing "metadata" for that field.
+    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
+    but which are used to store information about the node. For example, the `id` and `type` fields are node
+    attributes.
+
+    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
+    startup, and when generating the OpenAPI schema for the workflow editor.
+    """
+
+    Input = "input"
+    Output = "output"
+    Internal = "internal"
+    NodeAttribute = "node_attribute"
+
+
+class InputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
+    and by the workflow editor during schema parsing and UI rendering.
+    """
+
+    input: Input
+    orig_required: bool
+    field_kind: FieldKind
+    default: Optional[Any] = None
+    orig_default: Optional[Any] = None
+    ui_hidden: bool = False
+    ui_type: Optional[UIType] = None
+    ui_component: Optional[UIComponent] = None
+    ui_order: Optional[int] = None
+    ui_choice_labels: Optional[dict[str, str]] = None
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+class WithMetadata(BaseModel):
+    """
+    Inherit from this class if your node needs a metadata input field.
+    """
+
+    metadata: Optional[MetadataField] = Field(
+        default=None,
+        description=FieldDescriptions.metadata,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Connection,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class WithWorkflow:
+    workflow = None
+
+    def __init_subclass__(cls) -> None:
+        logger.warn(
+            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
+        )
+        super().__init_subclass__()
+
+
+class WithBoard(BaseModel):
+    """
+    Inherit from this class if your node needs a board input field.
+    """
+
+    board: Optional[BoardField] = Field(
+        default=None,
+        description=FieldDescriptions.board,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Direct,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class OutputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
+    during schema parsing and UI rendering.
+    """
+
+    field_kind: FieldKind
+    ui_hidden: bool
+    ui_type: Optional[UIType]
+    ui_order: Optional[int]
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+def InputField(
+    # copied from pydantic's Field
+    # TODO: Can we support default_factory?
+    default: Any = _Unset,
+    default_factory: Callable[[], Any] | None = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    input: Input = Input.Any,
+    ui_type: Optional[UIType] = None,
+    ui_component: Optional[UIComponent] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+    ui_choice_labels: Optional[dict[str, str]] = None,
+) -> Any:
+    """
+    Creates an input field for an invocation.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param Input input: [Input.Any] The kind of input this field requires. \
+      `Input.Direct` means a value must be provided on instantiation. \
+      `Input.Connection` means the value must be provided by a connection. \
+      `Input.Any` means either will do.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
+      The UI will always render a suitable component, but sometimes you want something different than the default. \
+      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
+      For this case, you could provide `UIComponent.Textarea`.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
+
+    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
+    """
+
+    json_schema_extra_ = InputFieldJSONSchemaExtra(
+        input=input,
+        ui_type=ui_type,
+        ui_component=ui_component,
+        ui_hidden=ui_hidden,
+        ui_order=ui_order,
+        ui_choice_labels=ui_choice_labels,
+        field_kind=FieldKind.Input,
+        orig_required=True,
+    )
+
+    """
+    There is a conflict between the typing of invocation definitions and the typing of an invocation's
+    `invoke()` function.
+
+    On instantiation of a node, the invocation definition is used to create the python class. At this time,
+    any number of fields may be optional, because they may be provided by connections.
+
+    On calling of `invoke()`, however, those fields may be required.
+
+    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
+
+    `image` is required during the call to `invoke()`, but when the python class is instantiated,
+    the field may not be present. This is fine, because that image field will be provided by a
+    connection from an ancestor node, which outputs an image.
+
+    This means we want to type the `image` field as optional for the node class definition, but required
+    for the `invoke()` function.
+
+    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
+    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
+    any static type analysis tools will complain.
+
+    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
+    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
+    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
+    """
+
+    if default_factory is not _Unset and default_factory is not None:
+        default = default_factory()
+        logger.warn('"default_factory" is not supported, calling it now to set "default"')
+
+    # These are the args we may wish pass to the pydantic `Field()` function
+    field_args = {
+        "default": default,
+        "title": title,
+        "description": description,
+        "pattern": pattern,
+        "strict": strict,
+        "gt": gt,
+        "ge": ge,
+        "lt": lt,
+        "le": le,
+        "multiple_of": multiple_of,
+        "allow_inf_nan": allow_inf_nan,
+        "max_digits": max_digits,
+        "decimal_places": decimal_places,
+        "min_length": min_length,
+        "max_length": max_length,
+    }
+
+    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
+    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
+
+    # Because we are manually making fields optional, we need to store the original required bool for reference later
+    json_schema_extra_.orig_required = default is PydanticUndefined
+
+    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
+    if input is Input.Any or input is Input.Connection:
+        default_ = None if default is PydanticUndefined else default
+        provided_args.update({"default": default_})
+        if default is not PydanticUndefined:
+            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
+            json_schema_extra_.default = default
+            json_schema_extra_.orig_default = default
+    elif default is not PydanticUndefined:
+        default_ = default
+        provided_args.update({"default": default_})
+        json_schema_extra_.orig_default = default_
+
+    return Field(
+        **provided_args,
+        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
+    )
+
+
+def OutputField(
+    # copied from pydantic's Field
+    default: Any = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    ui_type: Optional[UIType] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+) -> Any:
+    """
+    Creates an output field for an invocation output.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
+    """
+    return Field(
+        default=default,
+        title=title,
+        description=description,
+        pattern=pattern,
+        strict=strict,
+        gt=gt,
+        ge=ge,
+        lt=lt,
+        le=le,
+        multiple_of=multiple_of,
+        allow_inf_nan=allow_inf_nan,
+        max_digits=max_digits,
+        decimal_places=decimal_places,
+        min_length=min_length,
+        max_length=max_length,
+        json_schema_extra=OutputFieldJSONSchemaExtra(
+            ui_type=ui_type,
+            ui_hidden=ui_hidden,
+            ui_order=ui_order,
+            field_kind=FieldKind.Output,
+        ).model_dump(exclude_none=True),
+    )

invokeai/app/invocations/infill.py

@@ -6,14 +6,16 @@ from typing import Literal, Optional, get_args
 import numpy as np
 from PIL import Image, ImageOps
 
-from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ColorField, ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
 from invokeai.backend.image_util.lama import LaMA
 from invokeai.backend.image_util.patchmatch import PatchMatch
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
 
 
@@ -118,8 +120,8 @@ def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int]
     return si
 
 
-@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class InfillColorInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class InfillColorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image with a solid color"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -129,33 +131,20 @@ class InfillColorInvocation(BaseInvocation, WithMetadata):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         solid_bg = Image.new("RGBA", image.size, self.color.tuple())
         infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
 
         infilled.paste(image, (0, 0), image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
-class InfillTileInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
+class InfillTileInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image with tiles of the image"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -168,33 +157,20 @@ class InfillTileInvocation(BaseInvocation, WithMetadata):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = tile_fill_missing(image.copy(), seed=self.seed, tile_size=self.tile_size)
         infilled.paste(image, (0, 0), image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
 @invocation(
-    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0"
+    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1"
 )
-class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
+class InfillPatchMatchInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -202,7 +178,7 @@ class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name).convert("RGBA")
+        image = context.images.get_pil(self.image.image_name).convert("RGBA")
 
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
@@ -227,77 +203,38 @@ class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
         infilled.paste(image, (0, 0), mask=image.split()[-1])
         # image.paste(infilled, (0, 0), mask=image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class LaMaInfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class LaMaInfillInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using the LaMa model"""
 
     image: ImageField = InputField(description="The image to infill")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = infill_lama(image.copy())
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class CV2InfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class CV2InfillInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
     image: ImageField = InputField(description="The image to infill")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = infill_cv2(image.copy())
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/ip_adapter.py

@@ -1,37 +1,29 @@
-import os
 from builtins import float
 from typing import List, Union
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, Field, field_validator, model_validator
+from typing_extensions import Self
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
 from invokeai.app.invocations.primitives import ImageField
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.model_management.models.base import BaseModelType, ModelType
-from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
+from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager.config import BaseModelType, ModelType
 
 
+# LS: Consider moving these two classes into model.py
 class IPAdapterModelField(BaseModel):
-    model_name: str = Field(description="Name of the IP-Adapter model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Key to the IP-Adapter model")
 
 
 class CLIPVisionModelField(BaseModel):
-    model_name: str = Field(description="Name of the CLIP Vision image encoder model")
-    base_model: BaseModelType = Field(description="Base model (usually 'Any')")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Key to the CLIP Vision image encoder model")
 
 
 class IPAdapterField(BaseModel):
@@ -39,7 +31,6 @@ class IPAdapterField(BaseModel):
     ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
     image_encoder_model: CLIPVisionModelField = Field(description="The name of the CLIP image encoder model.")
     weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
-    # weight: float = Field(default=1.0, ge=0, description="The weight of the IP-Adapter.")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
     )
@@ -47,6 +38,17 @@ class IPAdapterField(BaseModel):
         default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
 
+    @field_validator("weight")
+    @classmethod
+    def validate_ip_adapter_weight(cls, v: float) -> float:
+        validate_weights(v)
+        return v
+
+    @model_validator(mode="after")
+    def validate_begin_end_step_percent(self) -> Self:
+        validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
+        return self
+
 
 @invocation_output("ip_adapter_output")
 class IPAdapterOutput(BaseInvocationOutput):
@@ -54,7 +56,7 @@ class IPAdapterOutput(BaseInvocationOutput):
     ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.0")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.2")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
@@ -64,36 +66,37 @@ class IPAdapterInvocation(BaseInvocation):
         description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
     )
 
-    # weight: float = InputField(default=1.0, description="The weight of the IP-Adapter.", ui_type=UIType.Float)
     weight: Union[float, List[float]] = InputField(
-        default=1, ge=-1, description="The weight given to the IP-Adapter", title="Weight"
+        default=1, description="The weight given to the IP-Adapter", title="Weight"
     )
-
     begin_step_percent: float = InputField(
-        default=0, ge=-1, le=2, description="When the IP-Adapter is first applied (% of total steps)"
+        default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
     )
     end_step_percent: float = InputField(
         default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
 
+    @field_validator("weight")
+    @classmethod
+    def validate_ip_adapter_weight(cls, v: float) -> float:
+        validate_weights(v)
+        return v
+
+    @model_validator(mode="after")
+    def validate_begin_end_step_percent(self) -> Self:
+        validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
+        return self
+
     def invoke(self, context: InvocationContext) -> IPAdapterOutput:
         # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
-        ip_adapter_info = context.services.model_manager.model_info(
-            self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
-        )
-        # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
-        # directly, and 2) we are reading from disk every time this invocation is called without caching the result.
-        # A better solution would be to store the image encoder model reference in the IP-Adapter model info, but this
-        # is currently messy due to differences between how the model info is generated when installing a model from
-        # disk vs. downloading the model.
-        image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
-            os.path.join(context.services.configuration.get_config().models_path, ip_adapter_info["path"])
-        )
+        ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
+        image_encoder_model_id = ip_adapter_info.image_encoder_model_id
         image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
-        image_encoder_model = CLIPVisionModelField(
-            model_name=image_encoder_model_name,
-            base_model=BaseModelType.Any,
+        image_encoder_models = context.models.search_by_attrs(
+            model_name=image_encoder_model_name, base_model=BaseModelType.Any, model_type=ModelType.CLIPVision
         )
+        assert len(image_encoder_models) == 1
+        image_encoder_model = CLIPVisionModelField(key=image_encoder_models[0].key)
         return IPAdapterOutput(
             ip_adapter=IPAdapterField(
                 image=self.image,

invokeai/app/invocations/latent.py

@@ -1,14 +1,17 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
+import math
 from contextlib import ExitStack
 from functools import singledispatchmethod
-from typing import List, Literal, Optional, Union
+from typing import Any, Iterator, List, Literal, Optional, Tuple, Union
 
 import einops
 import numpy as np
+import numpy.typing as npt
 import torch
 import torchvision.transforms as T
 from diffusers import AutoencoderKL, AutoencoderTiny
+from diffusers.configuration_utils import ConfigMixin
 from diffusers.image_processor import VaeImageProcessor
 from diffusers.models.adapter import T2IAdapter
 from diffusers.models.attention_processor import (
@@ -17,34 +20,44 @@ from diffusers.models.attention_processor import (
     LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
+from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
 from diffusers.schedulers import DPMSolverSDEScheduler
 from diffusers.schedulers import SchedulerMixin as Scheduler
+from PIL import Image, ImageFilter
 from pydantic import field_validator
 from torchvision.transforms.functional import resize as tv_resize
 
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR, SCHEDULER_NAME_VALUES
+from invokeai.app.invocations.fields import (
+    ConditioningField,
+    DenoiseMaskField,
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    LatentsField,
+    OutputField,
+    UIType,
+    WithBoard,
+    WithMetadata,
+)
 from invokeai.app.invocations.ip_adapter import IPAdapterField
 from invokeai.app.invocations.primitives import (
-    DenoiseMaskField,
     DenoiseMaskOutput,
-    ImageField,
     ImageOutput,
-    LatentsField,
     LatentsOutput,
-    build_latents_output,
 )
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
-from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
-from invokeai.backend.model_management.models import ModelType, SilenceWarnings
+from invokeai.backend.lora import LoRAModelRaw
+from invokeai.backend.model_manager import BaseModelType, LoadedModel
+from invokeai.backend.model_patcher import ModelPatcher
+from invokeai.backend.stable_diffusion import PipelineIntermediateState, set_seamless
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
+from invokeai.backend.util.silence_warnings import SilenceWarnings
 
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import BaseModelType
-from ...backend.model_management.seamless import set_seamless
-from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.stable_diffusion.diffusers_pipeline import (
     ControlNetData,
     IPAdapterData,
@@ -58,16 +71,9 @@ from ...backend.util.devices import choose_precision, choose_torch_device
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from .compel import ConditioningField
 from .controlnet_image_processors import ControlField
 from .model import ModelInfo, UNetField, VaeField
 
@@ -76,18 +82,10 @@ if choose_torch_device() == torch.device("mps"):
 
 DEFAULT_PRECISION = choose_precision(choose_torch_device())
 
-SAMPLER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
-
-# HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
-# be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
-# factor is hard-coded to a literal '8' rather than using this constant.
-# The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
-LATENT_SCALE_FACTOR = 8
-
 
 @invocation_output("scheduler_output")
 class SchedulerOutput(BaseInvocationOutput):
-    scheduler: SAMPLER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
+    scheduler: SCHEDULER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
 
 
 @invocation(
@@ -100,7 +98,7 @@ class SchedulerOutput(BaseInvocationOutput):
 class SchedulerInvocation(BaseInvocation):
     """Selects a scheduler."""
 
-    scheduler: SAMPLER_NAME_VALUES = InputField(
+    scheduler: SCHEDULER_NAME_VALUES = InputField(
         default="euler",
         description=FieldDescriptions.scheduler,
         ui_type=UIType.Scheduler,
@@ -115,7 +113,7 @@ class SchedulerInvocation(BaseInvocation):
     title="Create Denoise Mask",
     tags=["mask", "denoise"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class CreateDenoiseMaskInvocation(BaseInvocation):
     """Creates mask for denoising model run."""
@@ -130,10 +128,10 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
         ui_order=4,
     )
 
-    def prep_mask_tensor(self, mask_image):
+    def prep_mask_tensor(self, mask_image: Image.Image) -> torch.Tensor:
         if mask_image.mode != "L":
             mask_image = mask_image.convert("L")
-        mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        mask_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
         if mask_tensor.dim() == 3:
             mask_tensor = mask_tensor.unsqueeze(0)
         # if shape is not None:
@@ -143,41 +141,90 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
         if self.image is not None:
-            image = context.services.images.get_pil_image(self.image.image_name)
-            image = image_resized_to_grid_as_tensor(image.convert("RGB"))
-            if image.dim() == 3:
-                image = image.unsqueeze(0)
+            image = context.images.get_pil(self.image.image_name)
+            image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+            if image_tensor.dim() == 3:
+                image_tensor = image_tensor.unsqueeze(0)
         else:
-            image = None
+            image_tensor = None
 
         mask = self.prep_mask_tensor(
-            context.services.images.get_pil_image(self.mask.image_name),
+            context.images.get_pil(self.mask.image_name),
         )
 
-        if image is not None:
-            vae_info = context.services.model_manager.get_model(
-                **self.vae.vae.model_dump(),
-                context=context,
-            )
+        if image_tensor is not None:
+            vae_info = context.models.load(**self.vae.vae.model_dump())
 
-            img_mask = tv_resize(mask, image.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
-            masked_image = image * torch.where(img_mask < 0.5, 0.0, 1.0)
+            img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
+            masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
             # TODO:
             masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
 
-            masked_latents_name = f"{context.graph_execution_state_id}__{self.id}_masked_latents"
-            context.services.latents.save(masked_latents_name, masked_latents)
+            masked_latents_name = context.tensors.save(tensor=masked_latents)
         else:
             masked_latents_name = None
 
-        mask_name = f"{context.graph_execution_state_id}__{self.id}_mask"
-        context.services.latents.save(mask_name, mask)
+        mask_name = context.tensors.save(tensor=mask)
 
-        return DenoiseMaskOutput(
-            denoise_mask=DenoiseMaskField(
-                mask_name=mask_name,
-                masked_latents_name=masked_latents_name,
-            ),
+        return DenoiseMaskOutput.build(
+            mask_name=mask_name,
+            masked_latents_name=masked_latents_name,
+            gradient=False,
+        )
+
+
+@invocation(
+    "create_gradient_mask",
+    title="Create Gradient Mask",
+    tags=["mask", "denoise"],
+    category="latents",
+    version="1.0.0",
+)
+class CreateGradientMaskInvocation(BaseInvocation):
+    """Creates mask for denoising model run."""
+
+    mask: ImageField = InputField(default=None, description="Image which will be masked", ui_order=1)
+    edge_radius: int = InputField(
+        default=16, ge=0, description="How far to blur/expand the edges of the mask", ui_order=2
+    )
+    coherence_mode: Literal["Gaussian Blur", "Box Blur", "Staged"] = InputField(default="Gaussian Blur", ui_order=3)
+    minimum_denoise: float = InputField(
+        default=0.0, ge=0, le=1, description="Minimum denoise level for the coherence region", ui_order=4
+    )
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
+        mask_image = context.images.get_pil(self.mask.image_name, mode="L")
+        if self.coherence_mode == "Box Blur":
+            blur_mask = mask_image.filter(ImageFilter.BoxBlur(self.edge_radius))
+        else:  # Gaussian Blur OR Staged
+            # Gaussian Blur uses standard deviation. 1/2 radius is a good approximation
+            blur_mask = mask_image.filter(ImageFilter.GaussianBlur(self.edge_radius / 2))
+
+        mask_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        blur_tensor: torch.Tensor = image_resized_to_grid_as_tensor(blur_mask, normalize=False)
+
+        # redistribute blur so that the edges are 0 and blur out to 1
+        blur_tensor = (blur_tensor - 0.5) * 2
+
+        threshold = 1 - self.minimum_denoise
+
+        if self.coherence_mode == "Staged":
+            # wherever the blur_tensor is masked to any degree, convert it to threshold
+            blur_tensor = torch.where((blur_tensor < 1), threshold, blur_tensor)
+        else:
+            # wherever the blur_tensor is above threshold but less than 1, drop it to threshold
+            blur_tensor = torch.where((blur_tensor > threshold) & (blur_tensor < 1), threshold, blur_tensor)
+
+        # multiply original mask to force actually masked regions to 0
+        blur_tensor = mask_tensor * blur_tensor
+
+        mask_name = context.tensors.save(tensor=blur_tensor.unsqueeze(1))
+
+        return DenoiseMaskOutput.build(
+            mask_name=mask_name,
+            masked_latents_name=None,
+            gradient=True,
         )
 
 
@@ -188,10 +235,7 @@ def get_scheduler(
     seed: int,
 ) -> Scheduler:
     scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
-    orig_scheduler_info = context.services.model_manager.get_model(
-        **scheduler_info.model_dump(),
-        context=context,
-    )
+    orig_scheduler_info = context.models.load(**scheduler_info.model_dump())
     with orig_scheduler_info as orig_scheduler:
         scheduler_config = orig_scheduler.config
 
@@ -199,7 +243,7 @@ def get_scheduler(
         scheduler_config = scheduler_config["_backup"]
     scheduler_config = {
         **scheduler_config,
-        **scheduler_extra_config,
+        **scheduler_extra_config,  # FIXME
         "_backup": scheduler_config,
     }
 
@@ -212,6 +256,7 @@ def get_scheduler(
     # hack copied over from generate.py
     if not hasattr(scheduler, "uses_inpainting_model"):
         scheduler.uses_inpainting_model = lambda: False
+    assert isinstance(scheduler, Scheduler)
     return scheduler
 
 
@@ -220,7 +265,7 @@ def get_scheduler(
     title="Denoise Latents",
     tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
     category="latents",
-    version="1.5.0",
+    version="1.5.2",
 )
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
@@ -248,7 +293,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         description=FieldDescriptions.denoising_start,
     )
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
-    scheduler: SAMPLER_NAME_VALUES = InputField(
+    scheduler: SCHEDULER_NAME_VALUES = InputField(
         default="euler",
         description=FieldDescriptions.scheduler,
         ui_type=UIType.Scheduler,
@@ -279,7 +324,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         ui_order=7,
     )
     cfg_rescale_multiplier: float = InputField(
-        default=0, ge=0, lt=1, description=FieldDescriptions.cfg_rescale_multiplier
+        title="CFG Rescale Multiplier", default=0, ge=0, lt=1, description=FieldDescriptions.cfg_rescale_multiplier
     )
     latents: Optional[LatentsField] = InputField(
         default=None,
@@ -295,7 +340,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     )
 
     @field_validator("cfg_scale")
-    def ge_one(cls, v):
+    def ge_one(cls, v: Union[List[float], float]) -> Union[List[float], float]:
         """validate that all cfg_scale values are >= 1"""
         if isinstance(v, list):
             for i in v:
@@ -306,34 +351,18 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 raise ValueError("cfg_scale must be greater than 1")
         return v
 
-    # 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,
-        base_model: BaseModelType,
-    ) -> None:
-        stable_diffusion_step_callback(
-            context=context,
-            intermediate_state=intermediate_state,
-            node=self.model_dump(),
-            source_node_id=source_node_id,
-            base_model=base_model,
-        )
-
     def get_conditioning_data(
         self,
         context: InvocationContext,
-        scheduler,
-        unet,
-        seed,
+        scheduler: Scheduler,
+        unet: UNet2DConditionModel,
+        seed: int,
     ) -> ConditioningData:
-        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        positive_cond_data = context.conditioning.load(self.positive_conditioning.conditioning_name)
         c = positive_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
         extra_conditioning_info = c.extra_conditioning
 
-        negative_cond_data = context.services.latents.get(self.negative_conditioning.conditioning_name)
+        negative_cond_data = context.conditioning.load(self.negative_conditioning.conditioning_name)
         uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
 
         conditioning_data = ConditioningData(
@@ -350,7 +379,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             ),
         )
 
-        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(
+        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(  # FIXME
             scheduler,
             # for ddim scheduler
             eta=0.0,  # ddim_eta
@@ -362,8 +391,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     def create_pipeline(
         self,
-        unet,
-        scheduler,
+        unet: UNet2DConditionModel,
+        scheduler: Scheduler,
     ) -> StableDiffusionGeneratorPipeline:
         # TODO:
         # configure_model_padding(
@@ -374,10 +403,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         class FakeVae:
             class FakeVaeConfig:
-                def __init__(self):
+                def __init__(self) -> None:
                     self.block_out_channels = [0]
 
-            def __init__(self):
+            def __init__(self) -> None:
                 self.config = FakeVae.FakeVaeConfig()
 
         return StableDiffusionGeneratorPipeline(
@@ -394,11 +423,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def prep_control_data(
         self,
         context: InvocationContext,
-        control_input: Union[ControlField, List[ControlField]],
+        control_input: Optional[Union[ControlField, List[ControlField]]],
         latents_shape: List[int],
         exit_stack: ExitStack,
         do_classifier_free_guidance: bool = True,
-    ) -> List[ControlNetData]:
+    ) -> Optional[List[ControlNetData]]:
         # Assuming fixed dimensional scaling of LATENT_SCALE_FACTOR.
         control_height_resize = latents_shape[2] * LATENT_SCALE_FACTOR
         control_width_resize = latents_shape[3] * LATENT_SCALE_FACTOR
@@ -420,18 +449,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         #        and if weight is None, populate with default 1.0?
         controlnet_data = []
         for control_info in control_list:
-            control_model = exit_stack.enter_context(
-                context.services.model_manager.get_model(
-                    model_name=control_info.control_model.model_name,
-                    model_type=ModelType.ControlNet,
-                    base_model=control_info.control_model.base_model,
-                    context=context,
-                )
-            )
+            control_model = exit_stack.enter_context(context.models.load(key=control_info.control_model.key))
 
             # control_models.append(control_model)
             control_image_field = control_info.image
-            input_image = context.services.images.get_pil_image(control_image_field.image_name)
+            input_image = context.images.get_pil(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?
@@ -489,27 +511,17 @@ class DenoiseLatentsInvocation(BaseInvocation):
         conditioning_data.ip_adapter_conditioning = []
         for single_ip_adapter in ip_adapter:
             ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
-                context.services.model_manager.get_model(
-                    model_name=single_ip_adapter.ip_adapter_model.model_name,
-                    model_type=ModelType.IPAdapter,
-                    base_model=single_ip_adapter.ip_adapter_model.base_model,
-                    context=context,
-                )
+                context.models.load(key=single_ip_adapter.ip_adapter_model.key)
             )
 
-            image_encoder_model_info = context.services.model_manager.get_model(
-                model_name=single_ip_adapter.image_encoder_model.model_name,
-                model_type=ModelType.CLIPVision,
-                base_model=single_ip_adapter.image_encoder_model.base_model,
-                context=context,
-            )
+            image_encoder_model_info = context.models.load(key=single_ip_adapter.image_encoder_model.key)
 
             # `single_ip_adapter.image` could be a list or a single ImageField. Normalize to a list here.
-            single_ipa_images = single_ip_adapter.image
-            if not isinstance(single_ipa_images, list):
-                single_ipa_images = [single_ipa_images]
+            single_ipa_image_fields = single_ip_adapter.image
+            if not isinstance(single_ipa_image_fields, list):
+                single_ipa_image_fields = [single_ipa_image_fields]
 
-            single_ipa_images = [context.services.images.get_pil_image(image.image_name) for image in single_ipa_images]
+            single_ipa_images = [context.images.get_pil(image.image_name) for image in single_ipa_image_fields]
 
             # TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
             # models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
@@ -553,26 +565,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
-            t2i_adapter_model_info = context.services.model_manager.get_model(
-                model_name=t2i_adapter_field.t2i_adapter_model.model_name,
-                model_type=ModelType.T2IAdapter,
-                base_model=t2i_adapter_field.t2i_adapter_model.base_model,
-                context=context,
-            )
-            image = context.services.images.get_pil_image(t2i_adapter_field.image.image_name)
+            t2i_adapter_model_config = context.models.get_config(key=t2i_adapter_field.t2i_adapter_model.key)
+            t2i_adapter_loaded_model = context.models.load(key=t2i_adapter_field.t2i_adapter_model.key)
+            image = context.images.get_pil(t2i_adapter_field.image.image_name)
 
             # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
-            if t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusion1:
+            if t2i_adapter_model_config.base == BaseModelType.StableDiffusion1:
                 max_unet_downscale = 8
-            elif t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusionXL:
+            elif t2i_adapter_model_config.base == BaseModelType.StableDiffusionXL:
                 max_unet_downscale = 4
             else:
-                raise ValueError(
-                    f"Unexpected T2I-Adapter base model type: '{t2i_adapter_field.t2i_adapter_model.base_model}'."
-                )
+                raise ValueError(f"Unexpected T2I-Adapter base model type: '{t2i_adapter_model_config.base}'.")
 
             t2i_adapter_model: T2IAdapter
-            with t2i_adapter_model_info as t2i_adapter_model:
+            with t2i_adapter_loaded_model as t2i_adapter_model:
                 total_downscale_factor = t2i_adapter_model.total_downscale_factor
 
                 # Resize the T2I-Adapter input image.
@@ -592,7 +598,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     do_classifier_free_guidance=False,
                     width=t2i_input_width,
                     height=t2i_input_height,
-                    num_channels=t2i_adapter_model.config.in_channels,
+                    num_channels=t2i_adapter_model.config["in_channels"],  # mypy treats this as a FrozenDict
                     device=t2i_adapter_model.device,
                     dtype=t2i_adapter_model.dtype,
                     resize_mode=t2i_adapter_field.resize_mode,
@@ -617,7 +623,15 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     # original idea by https://github.com/AmericanPresidentJimmyCarter
     # TODO: research more for second order schedulers timesteps
-    def init_scheduler(self, scheduler, device, steps, denoising_start, denoising_end):
+    def init_scheduler(
+        self,
+        scheduler: Union[Scheduler, ConfigMixin],
+        device: torch.device,
+        steps: int,
+        denoising_start: float,
+        denoising_end: float,
+    ) -> Tuple[int, List[int], int]:
+        assert isinstance(scheduler, ConfigMixin)
         if scheduler.config.get("cpu_only", False):
             scheduler.set_timesteps(steps, device="cpu")
             timesteps = scheduler.timesteps.to(device=device)
@@ -629,11 +643,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         _timesteps = timesteps[:: scheduler.order]
 
         # get start timestep index
-        t_start_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_start)))
+        t_start_val = int(round(scheduler.config["num_train_timesteps"] * (1 - denoising_start)))
         t_start_idx = len(list(filter(lambda ts: ts >= t_start_val, _timesteps)))
 
         # get end timestep index
-        t_end_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_end)))
+        t_end_val = int(round(scheduler.config["num_train_timesteps"] * (1 - denoising_end)))
         t_end_idx = len(list(filter(lambda ts: ts >= t_end_val, _timesteps[t_start_idx:])))
 
         # apply order to indexes
@@ -646,18 +660,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         return num_inference_steps, timesteps, init_timestep
 
-    def prep_inpaint_mask(self, context, latents):
+    def prep_inpaint_mask(
+        self, context: InvocationContext, latents: torch.Tensor
+    ) -> Tuple[Optional[torch.Tensor], Optional[torch.Tensor], bool]:
         if self.denoise_mask is None:
-            return None, None
+            return None, None, False
 
-        mask = context.services.latents.get(self.denoise_mask.mask_name)
+        mask = context.tensors.load(self.denoise_mask.mask_name)
         mask = tv_resize(mask, latents.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
         if self.denoise_mask.masked_latents_name is not None:
-            masked_latents = context.services.latents.get(self.denoise_mask.masked_latents_name)
+            masked_latents = context.tensors.load(self.denoise_mask.masked_latents_name)
         else:
             masked_latents = None
 
-        return 1 - mask, masked_latents
+        return 1 - mask, masked_latents, self.denoise_mask.gradient
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
@@ -665,11 +681,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
             seed = None
             noise = None
             if self.noise is not None:
-                noise = context.services.latents.get(self.noise.latents_name)
+                noise = context.tensors.load(self.noise.latents_name)
                 seed = self.noise.seed
 
             if self.latents is not None:
-                latents = context.services.latents.get(self.latents.latents_name)
+                latents = context.tensors.load(self.latents.latents_name)
                 if seed is None:
                     seed = self.latents.seed
 
@@ -684,7 +700,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             if seed is None:
                 seed = 0
 
-            mask, masked_latents = self.prep_inpaint_mask(context, latents)
+            mask, masked_latents, gradient_mask = self.prep_inpaint_mask(context, latents)
 
             # TODO(ryand): I have hard-coded `do_classifier_free_guidance=True` to mirror the behaviour of ControlNets,
             # below. Investigate whether this is appropriate.
@@ -695,35 +711,30 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 do_classifier_free_guidance=True,
             )
 
-            # 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]
+            # get the unet's config so that we can pass the base to dispatch_progress()
+            unet_config = context.models.get_config(self.unet.unet.key)
 
-            def step_callback(state: PipelineIntermediateState):
-                self.dispatch_progress(context, source_node_id, state, self.unet.unet.base_model)
+            def step_callback(state: PipelineIntermediateState) -> None:
+                context.util.sd_step_callback(state, unet_config.base)
 
-            def _lora_loader():
+            def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
                 for lora in self.unet.loras:
-                    lora_info = context.services.model_manager.get_model(
-                        **lora.model_dump(exclude={"weight"}),
-                        context=context,
-                    )
-                    yield (lora_info.context.model, lora.weight)
+                    lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
+                    yield (lora_info.model, lora.weight)
                     del lora_info
                 return
 
-            unet_info = context.services.model_manager.get_model(
-                **self.unet.unet.model_dump(),
-                context=context,
-            )
+            unet_info = context.models.load(**self.unet.unet.model_dump())
+            assert isinstance(unet_info.model, UNet2DConditionModel)
             with (
                 ExitStack() as exit_stack,
-                ModelPatcher.apply_freeu(unet_info.context.model, self.unet.freeu_config),
-                set_seamless(unet_info.context.model, self.unet.seamless_axes),
+                ModelPatcher.apply_freeu(unet_info.model, self.unet.freeu_config),
+                set_seamless(unet_info.model, self.unet.seamless_axes),  # FIXME
                 unet_info as unet,
                 # Apply the LoRA after unet has been moved to its target device for faster patching.
                 ModelPatcher.apply_lora_unet(unet, _lora_loader()),
             ):
+                assert isinstance(unet, UNet2DConditionModel)
                 latents = latents.to(device=unet.device, dtype=unet.dtype)
                 if noise is not None:
                     noise = noise.to(device=unet.device, dtype=unet.dtype)
@@ -777,6 +788,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     seed=seed,
                     mask=mask,
                     masked_latents=masked_latents,
+                    gradient_mask=gradient_mask,
                     num_inference_steps=num_inference_steps,
                     conditioning_data=conditioning_data,
                     control_data=controlnet_data,
@@ -791,9 +803,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
             if choose_torch_device() == torch.device("mps"):
                 mps.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, seed=seed)
+            name = context.tensors.save(tensor=result_latents)
+        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=seed)
 
 
 @invocation(
@@ -801,9 +812,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
     title="Latents to Image",
     tags=["latents", "image", "vae", "l2i"],
     category="latents",
-    version="1.2.0",
+    version="1.2.1",
 )
-class LatentsToImageInvocation(BaseInvocation, WithMetadata):
+class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Generates an image from latents."""
 
     latents: LatentsField = InputField(
@@ -819,14 +830,12 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-            context=context,
-        )
+        vae_info = context.models.load(**self.vae.vae.model_dump())
 
-        with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
+        with set_seamless(vae_info.model, self.vae.seamless_axes), vae_info as vae:
+            assert isinstance(vae, torch.nn.Module)
             latents = latents.to(vae.device)
             if self.fp32:
                 vae.to(dtype=torch.float32)
@@ -853,7 +862,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
                 vae.to(dtype=torch.float16)
                 latents = latents.half()
 
-            if self.tiled or context.services.configuration.tiled_decode:
+            if self.tiled or context.config.get().tiled_decode:
                 vae.enable_tiling()
             else:
                 vae.disable_tiling()
@@ -877,22 +886,9 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
         if choose_torch_device() == torch.device("mps"):
             mps.empty_cache()
 
-        image_dto = context.services.images.create(
-            image=image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
 LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
@@ -903,7 +899,7 @@ LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic",
     title="Resize Latents",
     tags=["latents", "resize"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ResizeLatentsInvocation(BaseInvocation):
     """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
@@ -926,7 +922,7 @@ class ResizeLatentsInvocation(BaseInvocation):
     antialias: bool = InputField(default=False, description=FieldDescriptions.torch_antialias)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         # TODO:
         device = choose_torch_device()
@@ -944,10 +940,8 @@ class ResizeLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.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, seed=self.latents.seed)
+        name = context.tensors.save(tensor=resized_latents)
+        return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
 @invocation(
@@ -955,7 +949,7 @@ class ResizeLatentsInvocation(BaseInvocation):
     title="Scale Latents",
     tags=["latents", "resize"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ScaleLatentsInvocation(BaseInvocation):
     """Scales latents by a given factor."""
@@ -969,7 +963,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     antialias: bool = InputField(default=False, description=FieldDescriptions.torch_antialias)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         # TODO:
         device = choose_torch_device()
@@ -988,10 +982,8 @@ class ScaleLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.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, seed=self.latents.seed)
+        name = context.tensors.save(tensor=resized_latents)
+        return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
 @invocation(
@@ -999,7 +991,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     title="Image to Latents",
     tags=["latents", "image", "vae", "i2l"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ImageToLatentsInvocation(BaseInvocation):
     """Encodes an image into latents."""
@@ -1015,8 +1007,9 @@ class ImageToLatentsInvocation(BaseInvocation):
     fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
 
     @staticmethod
-    def vae_encode(vae_info, upcast, tiled, image_tensor):
+    def vae_encode(vae_info: LoadedModel, upcast: bool, tiled: bool, image_tensor: torch.Tensor) -> torch.Tensor:
         with vae_info as vae:
+            assert isinstance(vae, torch.nn.Module)
             orig_dtype = vae.dtype
             if upcast:
                 vae.to(dtype=torch.float32)
@@ -1060,12 +1053,9 @@ class ImageToLatentsInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-            context=context,
-        )
+        vae_info = context.models.load(**self.vae.vae.model_dump())
 
         image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
         if image_tensor.dim() == 3:
@@ -1073,22 +1063,26 @@ class ImageToLatentsInvocation(BaseInvocation):
 
         latents = self.vae_encode(vae_info, self.fp32, self.tiled, image_tensor)
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
         latents = latents.to("cpu")
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=latents, seed=None)
+        name = context.tensors.save(tensor=latents)
+        return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
 
     @singledispatchmethod
     @staticmethod
     def _encode_to_tensor(vae: AutoencoderKL, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
+        assert isinstance(vae, torch.nn.Module)
         image_tensor_dist = vae.encode(image_tensor).latent_dist
-        latents = image_tensor_dist.sample().to(dtype=vae.dtype)  # FIXME: uses torch.randn. make reproducible!
+        latents: torch.Tensor = image_tensor_dist.sample().to(
+            dtype=vae.dtype
+        )  # FIXME: uses torch.randn. make reproducible!
         return latents
 
     @_encode_to_tensor.register
     @staticmethod
     def _(vae: AutoencoderTiny, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
-        return vae.encode(image_tensor).latents
+        assert isinstance(vae, torch.nn.Module)
+        latents: torch.FloatTensor = vae.encode(image_tensor).latents
+        return latents
 
 
 @invocation(
@@ -1096,7 +1090,7 @@ class ImageToLatentsInvocation(BaseInvocation):
     title="Blend Latents",
     tags=["latents", "blend"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class BlendLatentsInvocation(BaseInvocation):
     """Blend two latents using a given alpha. Latents must have same size."""
@@ -1112,8 +1106,8 @@ class BlendLatentsInvocation(BaseInvocation):
     alpha: float = InputField(default=0.5, description=FieldDescriptions.blend_alpha)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents_a = context.services.latents.get(self.latents_a.latents_name)
-        latents_b = context.services.latents.get(self.latents_b.latents_name)
+        latents_a = context.tensors.load(self.latents_a.latents_name)
+        latents_b = context.tensors.load(self.latents_b.latents_name)
 
         if latents_a.shape != latents_b.shape:
             raise Exception("Latents to blend must be the same size.")
@@ -1121,7 +1115,12 @@ class BlendLatentsInvocation(BaseInvocation):
         # TODO:
         device = choose_torch_device()
 
-        def slerp(t, v0, v1, DOT_THRESHOLD=0.9995):
+        def slerp(
+            t: Union[float, npt.NDArray[Any]],  # FIXME: maybe use np.float32 here?
+            v0: Union[torch.Tensor, npt.NDArray[Any]],
+            v1: Union[torch.Tensor, npt.NDArray[Any]],
+            DOT_THRESHOLD: float = 0.9995,
+        ) -> Union[torch.Tensor, npt.NDArray[Any]]:
             """
             Spherical linear interpolation
             Args:
@@ -1154,12 +1153,16 @@ class BlendLatentsInvocation(BaseInvocation):
                 v2 = s0 * v0 + s1 * v1
 
             if inputs_are_torch:
-                v2 = torch.from_numpy(v2).to(device)
-
-            return v2
+                v2_torch: torch.Tensor = torch.from_numpy(v2).to(device)
+                return v2_torch
+            else:
+                assert isinstance(v2, np.ndarray)
+                return v2
 
         # blend
-        blended_latents = slerp(self.alpha, latents_a, latents_b)
+        bl = slerp(self.alpha, latents_a, latents_b)
+        assert isinstance(bl, torch.Tensor)
+        blended_latents: torch.Tensor = bl  # for type checking convenience
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         blended_latents = blended_latents.to("cpu")
@@ -1167,10 +1170,8 @@ class BlendLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, blended_latents)
-        return build_latents_output(latents_name=name, latents=blended_latents)
+        name = context.tensors.save(tensor=blended_latents)
+        return LatentsOutput.build(latents_name=name, latents=blended_latents)
 
 
 # The Crop Latents node was copied from @skunkworxdark's implementation here:
@@ -1180,7 +1181,7 @@ class BlendLatentsInvocation(BaseInvocation):
     title="Crop Latents",
     tags=["latents", "crop"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 # TODO(ryand): Named `CropLatentsCoreInvocation` to prevent a conflict with custom node `CropLatentsInvocation`.
 # Currently, if the class names conflict then 'GET /openapi.json' fails.
@@ -1215,7 +1216,7 @@ class CropLatentsCoreInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         x1 = self.x // LATENT_SCALE_FACTOR
         y1 = self.y // LATENT_SCALE_FACTOR
@@ -1224,7 +1225,61 @@ class CropLatentsCoreInvocation(BaseInvocation):
 
         cropped_latents = latents[..., y1:y2, x1:x2]
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, cropped_latents)
+        name = context.tensors.save(tensor=cropped_latents)
 
-        return build_latents_output(latents_name=name, latents=cropped_latents)
+        return LatentsOutput.build(latents_name=name, latents=cropped_latents)
+
+
+@invocation_output("ideal_size_output")
+class IdealSizeOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    width: int = OutputField(description="The ideal width of the image (in pixels)")
+    height: int = OutputField(description="The ideal height of the image (in pixels)")
+
+
+@invocation(
+    "ideal_size",
+    title="Ideal Size",
+    tags=["latents", "math", "ideal_size"],
+    version="1.0.2",
+)
+class IdealSizeInvocation(BaseInvocation):
+    """Calculates the ideal size for generation to avoid duplication"""
+
+    width: int = InputField(default=1024, description="Final image width")
+    height: int = InputField(default=576, description="Final image height")
+    unet: UNetField = InputField(default=None, description=FieldDescriptions.unet)
+    multiplier: float = InputField(
+        default=1.0,
+        description="Amount to multiply the model's dimensions by when calculating the ideal size (may result in initial generation artifacts if too large)",
+    )
+
+    def trim_to_multiple_of(self, *args: int, multiple_of: int = LATENT_SCALE_FACTOR) -> Tuple[int, ...]:
+        return tuple((x - x % multiple_of) for x in args)
+
+    def invoke(self, context: InvocationContext) -> IdealSizeOutput:
+        unet_config = context.models.get_config(**self.unet.unet.model_dump())
+        aspect = self.width / self.height
+        dimension: float = 512
+        if unet_config.base == BaseModelType.StableDiffusion2:
+            dimension = 768
+        elif unet_config.base == BaseModelType.StableDiffusionXL:
+            dimension = 1024
+        dimension = dimension * self.multiplier
+        min_dimension = math.floor(dimension * 0.5)
+        model_area = dimension * dimension  # hardcoded for now since all models are trained on square images
+
+        if aspect > 1.0:
+            init_height = max(min_dimension, math.sqrt(model_area / aspect))
+            init_width = init_height * aspect
+        else:
+            init_width = max(min_dimension, math.sqrt(model_area * aspect))
+            init_height = init_width / aspect
+
+        scaled_width, scaled_height = self.trim_to_multiple_of(
+            math.floor(init_width),
+            math.floor(init_height),
+        )
+
+        return IdealSizeOutput(width=scaled_width, height=scaled_height)

invokeai/app/invocations/math.py

@@ -5,10 +5,11 @@ from typing import Literal
 import numpy as np
 from pydantic import ValidationInfo, field_validator
 
+from invokeai.app.invocations.fields import FieldDescriptions, InputField
 from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
 
 
 @invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.0")

invokeai/app/invocations/metadata.py

@@ -5,20 +5,22 @@ from pydantic import BaseModel, ConfigDict, Field
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    MetadataField,
-    OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import ControlField
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
+    InputField,
+    MetadataField,
+    OutputField,
+    UIType,
+)
 from invokeai.app.invocations.ip_adapter import IPAdapterModelField
 from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
-from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from ...version import __version__
 
@@ -31,7 +33,7 @@ class MetadataItemField(BaseModel):
 class LoRAMetadataField(BaseModel):
     """LoRA Metadata Field"""
 
-    lora: LoRAModelField = Field(description=FieldDescriptions.lora_model)
+    model: LoRAModelField = Field(description=FieldDescriptions.lora_model)
     weight: float = Field(description=FieldDescriptions.lora_weight)
 
 
@@ -112,7 +114,7 @@ GENERATION_MODES = Literal[
 ]
 
 
-@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.0.1")
+@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.1.1")
 class CoreMetadataInvocation(BaseInvocation):
     """Collects core generation metadata into a MetadataField"""
 

invokeai/app/invocations/model.py

@@ -1,31 +1,24 @@
 import copy
 from typing import List, Optional
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.shared.models import FreeUConfig
 
-from ...backend.model_management import BaseModelType, ModelType, SubModelType
+from ...backend.model_manager import SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
 
 
 class ModelInfo(BaseModel):
-    model_name: str = Field(description="Info to load submodel")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Info to load submodel")
-    submodel: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Key of model as returned by ModelRecordServiceBase.get_model()")
+    submodel_type: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
 
 
 class LoraInfo(ModelInfo):
@@ -55,7 +48,7 @@ class VaeField(BaseModel):
 
 @invocation_output("unet_output")
 class UNetOutput(BaseInvocationOutput):
-    """Base class for invocations that output a UNet field"""
+    """Base class for invocations that output a UNet field."""
 
     unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
 
@@ -84,20 +77,13 @@ class ModelLoaderOutput(UNetOutput, CLIPOutput, VAEOutput):
 class MainModelField(BaseModel):
     """Main model field"""
 
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Model Type")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Model key")
 
 
 class LoRAModelField(BaseModel):
     """LoRA model field"""
 
-    model_name: str = Field(description="Name of the LoRA model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="LoRA model key")
 
 
 @invocation(
@@ -105,7 +91,7 @@ class LoRAModelField(BaseModel):
     title="Main Model",
     tags=["model"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
@@ -114,85 +100,40 @@ class MainModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.Main
+        key = self.model.key
 
         # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
-
-        """
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.Tokenizer,
-        ):
-            raise Exception(
-                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.TextEncoder,
-        ):
-            raise Exception(
-                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.UNet,
-        ):
-            raise Exception(
-                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
-            )
-        """
+        if not context.models.exists(key):
+            raise Exception(f"Unknown model {key}")
 
         return ModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
+                    key=key,
+                    submodel_type=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
+                    key=key,
+                    submodel_type=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip=ClipField(
                 tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
+                    key=key,
+                    submodel_type=SubModelType.Tokenizer,
                 ),
                 text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
+                    key=key,
+                    submodel_type=SubModelType.TextEncoder,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Vae,
+                    key=key,
+                    submodel_type=SubModelType.Vae,
                 ),
             ),
         )
@@ -206,7 +147,7 @@ class LoraLoaderOutput(BaseInvocationOutput):
     clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
-@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.0")
+@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.1")
 class LoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
@@ -229,21 +170,16 @@ class LoraLoaderInvocation(BaseInvocation):
         if self.lora is None:
             raise Exception("No LoRA provided")
 
-        base_model = self.lora.base_model
-        lora_name = self.lora.model_name
+        lora_key = self.lora.key
 
-        if not context.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unkown lora name: {lora_name}!")
+        if not context.models.exists(lora_key):
+            raise Exception(f"Unkown lora: {lora_key}!")
 
-        if self.unet is not None and any(lora.model_name == lora_name for lora in self.unet.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to unet')
+        if self.unet is not None and any(lora.key == lora_key for lora in self.unet.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to unet')
 
-        if self.clip is not None and any(lora.model_name == lora_name for lora in self.clip.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip')
+        if self.clip is not None and any(lora.key == lora_key for lora in self.clip.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to clip')
 
         output = LoraLoaderOutput()
 
@@ -251,10 +187,8 @@ class LoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -263,10 +197,8 @@ class LoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -288,7 +220,7 @@ class SDXLLoraLoaderOutput(BaseInvocationOutput):
     title="SDXL LoRA",
     tags=["lora", "model"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLLoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
@@ -318,24 +250,19 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
         if self.lora is None:
             raise Exception("No LoRA provided")
 
-        base_model = self.lora.base_model
-        lora_name = self.lora.model_name
+        lora_key = self.lora.key
 
-        if not context.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unknown lora name: {lora_name}!")
+        if not context.models.exists(lora_key):
+            raise Exception(f"Unknown lora: {lora_key}!")
 
-        if self.unet is not None and any(lora.model_name == lora_name for lora in self.unet.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to unet')
+        if self.unet is not None and any(lora.key == lora_key for lora in self.unet.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to unet')
 
-        if self.clip is not None and any(lora.model_name == lora_name for lora in self.clip.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip')
+        if self.clip is not None and any(lora.key == lora_key for lora in self.clip.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to clip')
 
-        if self.clip2 is not None and any(lora.model_name == lora_name for lora in self.clip2.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip2')
+        if self.clip2 is not None and any(lora.key == lora_key for lora in self.clip2.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to clip2')
 
         output = SDXLLoraLoaderOutput()
 
@@ -343,10 +270,8 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -355,10 +280,8 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -367,10 +290,8 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.clip2 = copy.deepcopy(self.clip2)
             output.clip2.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -381,13 +302,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
 class VAEModelField(BaseModel):
     """Vae model field"""
 
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Model's key")
 
 
-@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.0")
+@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.1")
 class VaeLoaderInvocation(BaseInvocation):
     """Loads a VAE model, outputting a VaeLoaderOutput"""
 
@@ -398,25 +316,12 @@ class VaeLoaderInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> VAEOutput:
-        base_model = self.vae_model.base_model
-        model_name = self.vae_model.model_name
-        model_type = ModelType.Vae
+        key = self.vae_model.key
 
-        if not context.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=model_name,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unkown vae name: {model_name}!")
-        return VAEOutput(
-            vae=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                )
-            )
-        )
+        if not context.models.exists(key):
+            raise Exception(f"Unkown vae: {key}!")
+
+        return VAEOutput(vae=VaeField(vae=ModelInfo(key=key)))
 
 
 @invocation_output("seamless_output")

invokeai/app/invocations/noise.py

@@ -4,17 +4,15 @@
 import torch
 from pydantic import field_validator
 
-from invokeai.app.invocations.latent import LatentsField
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import FieldDescriptions, InputField, LatentsField, OutputField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
 from ...backend.util.devices import choose_torch_device, torch_dtype
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
@@ -69,13 +67,13 @@ class NoiseOutput(BaseInvocationOutput):
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
-
-def build_noise_output(latents_name: str, latents: torch.Tensor, seed: int):
-    return NoiseOutput(
-        noise=LatentsField(latents_name=latents_name, seed=seed),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
+    @classmethod
+    def build(cls, latents_name: str, latents: torch.Tensor, seed: int) -> "NoiseOutput":
+        return cls(
+            noise=LatentsField(latents_name=latents_name, seed=seed),
+            width=latents.size()[3] * LATENT_SCALE_FACTOR,
+            height=latents.size()[2] * LATENT_SCALE_FACTOR,
+        )
 
 
 @invocation(
@@ -96,13 +94,13 @@ class NoiseInvocation(BaseInvocation):
     )
     width: int = InputField(
         default=512,
-        multiple_of=8,
+        multiple_of=LATENT_SCALE_FACTOR,
         gt=0,
         description=FieldDescriptions.width,
     )
     height: int = InputField(
         default=512,
-        multiple_of=8,
+        multiple_of=LATENT_SCALE_FACTOR,
         gt=0,
         description=FieldDescriptions.height,
     )
@@ -124,6 +122,5 @@ class NoiseInvocation(BaseInvocation):
             seed=self.seed,
             use_cpu=self.use_cpu,
         )
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, noise)
-        return build_noise_output(latents_name=name, latents=noise, seed=self.seed)
+        name = context.tensors.save(tensor=noise)
+        return NoiseOutput.build(latents_name=name, latents=noise, seed=self.seed)

invokeai/app/invocations/onnx.py

@@ -1,508 +0,0 @@
-# Copyright (c) 2023 Borisov Sergey (https://github.com/StAlKeR7779)
-
-import inspect
-import re
-
-# from contextlib import ExitStack
-from typing import List, Literal, Union
-
-import numpy as np
-import torch
-from diffusers.image_processor import VaeImageProcessor
-from pydantic import BaseModel, ConfigDict, Field, field_validator
-from tqdm import tqdm
-
-from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput, ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.app.util.step_callback import stable_diffusion_step_callback
-from invokeai.backend import BaseModelType, ModelType, SubModelType
-
-from ...backend.model_management import ONNXModelPatcher
-from ...backend.stable_diffusion import PipelineIntermediateState
-from ...backend.util import choose_torch_device
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
-    UIType,
-    WithMetadata,
-    invocation,
-    invocation_output,
-)
-from .controlnet_image_processors import ControlField
-from .latent import SAMPLER_NAME_VALUES, LatentsField, LatentsOutput, build_latents_output, get_scheduler
-from .model import ClipField, ModelInfo, UNetField, VaeField
-
-ORT_TO_NP_TYPE = {
-    "tensor(bool)": np.bool_,
-    "tensor(int8)": np.int8,
-    "tensor(uint8)": np.uint8,
-    "tensor(int16)": np.int16,
-    "tensor(uint16)": np.uint16,
-    "tensor(int32)": np.int32,
-    "tensor(uint32)": np.uint32,
-    "tensor(int64)": np.int64,
-    "tensor(uint64)": np.uint64,
-    "tensor(float16)": np.float16,
-    "tensor(float)": np.float32,
-    "tensor(double)": np.float64,
-}
-
-PRECISION_VALUES = Literal[tuple(ORT_TO_NP_TYPE.keys())]
-
-
-@invocation("prompt_onnx", title="ONNX Prompt (Raw)", tags=["prompt", "onnx"], category="conditioning", version="1.0.0")
-class ONNXPromptInvocation(BaseInvocation):
-    prompt: str = InputField(default="", description=FieldDescriptions.raw_prompt, ui_component=UIComponent.Textarea)
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
-
-    def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-        )
-        with tokenizer_info as orig_tokenizer, text_encoder_info as text_encoder:  # , ExitStack() as stack:
-            loras = [
-                (
-                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
-                    lora.weight,
-                )
-                for lora in self.clip.loras
-            ]
-
-            ti_list = []
-            for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
-                name = trigger[1:-1]
-                try:
-                    ti_list.append(
-                        (
-                            name,
-                            context.services.model_manager.get_model(
-                                model_name=name,
-                                base_model=self.clip.text_encoder.base_model,
-                                model_type=ModelType.TextualInversion,
-                            ).context.model,
-                        )
-                    )
-                except Exception:
-                    # print(e)
-                    # import traceback
-                    # print(traceback.format_exc())
-                    print(f'Warn: trigger: "{trigger}" not found')
-            if loras or ti_list:
-                text_encoder.release_session()
-            with (
-                ONNXModelPatcher.apply_lora_text_encoder(text_encoder, loras),
-                ONNXModelPatcher.apply_ti(orig_tokenizer, text_encoder, ti_list) as (tokenizer, ti_manager),
-            ):
-                text_encoder.create_session()
-
-                # copy from
-                # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L153
-                text_inputs = tokenizer(
-                    self.prompt,
-                    padding="max_length",
-                    max_length=tokenizer.model_max_length,
-                    truncation=True,
-                    return_tensors="np",
-                )
-                text_input_ids = text_inputs.input_ids
-                """
-                untruncated_ids = tokenizer(prompt, padding="max_length", return_tensors="np").input_ids
-
-                if not np.array_equal(text_input_ids, untruncated_ids):
-                    removed_text = self.tokenizer.batch_decode(
-                        untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
-                    )
-                    logger.warning(
-                        "The following part of your input was truncated because CLIP can only handle sequences up to"
-                        f" {self.tokenizer.model_max_length} tokens: {removed_text}"
-                    )
-                """
-
-                prompt_embeds = text_encoder(input_ids=text_input_ids.astype(np.int32))[0]
-
-        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, (prompt_embeds, None))
-
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
-
-
-# Text to image
-@invocation(
-    "t2l_onnx",
-    title="ONNX Text to Latents",
-    tags=["latents", "inference", "txt2img", "onnx"],
-    category="latents",
-    version="1.0.0",
-)
-class ONNXTextToLatentsInvocation(BaseInvocation):
-    """Generates latents from conditionings."""
-
-    positive_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.positive_cond,
-        input=Input.Connection,
-    )
-    negative_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.negative_cond,
-        input=Input.Connection,
-    )
-    noise: LatentsField = InputField(
-        description=FieldDescriptions.noise,
-        input=Input.Connection,
-    )
-    steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
-    cfg_scale: Union[float, List[float]] = InputField(
-        default=7.5,
-        ge=1,
-        description=FieldDescriptions.cfg_scale,
-    )
-    scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, input=Input.Direct, ui_type=UIType.Scheduler
-    )
-    precision: PRECISION_VALUES = InputField(default="tensor(float16)", description=FieldDescriptions.precision)
-    unet: UNetField = InputField(
-        description=FieldDescriptions.unet,
-        input=Input.Connection,
-    )
-    control: Union[ControlField, list[ControlField]] = InputField(
-        default=None,
-        description=FieldDescriptions.control,
-    )
-    # seamless:   bool = InputField(default=False, description="Whether or not to generate an image that can tile without seams", )
-    # seamless_axes: str = InputField(default="", description="The axes to tile the image on, 'x' and/or 'y'")
-
-    @field_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
-
-    # based on
-    # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L375
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        c, _ = context.services.latents.get(self.positive_conditioning.conditioning_name)
-        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
-        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]
-        if isinstance(c, torch.Tensor):
-            c = c.cpu().numpy()
-        if isinstance(uc, torch.Tensor):
-            uc = uc.cpu().numpy()
-        device = torch.device(choose_torch_device())
-        prompt_embeds = np.concatenate([uc, c])
-
-        latents = context.services.latents.get(self.noise.latents_name)
-        if isinstance(latents, torch.Tensor):
-            latents = latents.cpu().numpy()
-
-        # TODO: better execution device handling
-        latents = latents.astype(ORT_TO_NP_TYPE[self.precision])
-
-        # get the initial random noise unless the user supplied it
-        do_classifier_free_guidance = True
-        # latents_dtype = prompt_embeds.dtype
-        # latents_shape = (batch_size * num_images_per_prompt, 4, height // 8, width // 8)
-        # if latents.shape != latents_shape:
-        #    raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {latents_shape}")
-
-        scheduler = get_scheduler(
-            context=context,
-            scheduler_info=self.unet.scheduler,
-            scheduler_name=self.scheduler,
-            seed=0,  # TODO: refactor this node
-        )
-
-        def torch2numpy(latent: torch.Tensor):
-            return latent.cpu().numpy()
-
-        def numpy2torch(latent, device):
-            return torch.from_numpy(latent).to(device)
-
-        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.model_dump(),
-                source_node_id=source_node_id,
-            )
-
-        scheduler.set_timesteps(self.steps)
-        latents = latents * np.float64(scheduler.init_noise_sigma)
-
-        extra_step_kwargs = {}
-        if "eta" in set(inspect.signature(scheduler.step).parameters.keys()):
-            extra_step_kwargs.update(
-                eta=0.0,
-            )
-
-        unet_info = context.services.model_manager.get_model(**self.unet.unet.model_dump())
-
-        with unet_info as unet:  # , ExitStack() as stack:
-            # loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
-            loras = [
-                (
-                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
-                    lora.weight,
-                )
-                for lora in self.unet.loras
-            ]
-
-            if loras:
-                unet.release_session()
-            with ONNXModelPatcher.apply_lora_unet(unet, loras):
-                # TODO:
-                _, _, h, w = latents.shape
-                unet.create_session(h, w)
-
-                timestep_dtype = next(
-                    (input.type for input in unet.session.get_inputs() if input.name == "timestep"), "tensor(float16)"
-                )
-                timestep_dtype = ORT_TO_NP_TYPE[timestep_dtype]
-                for i in tqdm(range(len(scheduler.timesteps))):
-                    t = scheduler.timesteps[i]
-                    # expand the latents if we are doing classifier free guidance
-                    latent_model_input = np.concatenate([latents] * 2) if do_classifier_free_guidance else latents
-                    latent_model_input = scheduler.scale_model_input(numpy2torch(latent_model_input, device), t)
-                    latent_model_input = latent_model_input.cpu().numpy()
-
-                    # predict the noise residual
-                    timestep = np.array([t], dtype=timestep_dtype)
-                    noise_pred = unet(sample=latent_model_input, timestep=timestep, encoder_hidden_states=prompt_embeds)
-                    noise_pred = noise_pred[0]
-
-                    # perform guidance
-                    if do_classifier_free_guidance:
-                        noise_pred_uncond, noise_pred_text = np.split(noise_pred, 2)
-                        noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
-
-                    # compute the previous noisy sample x_t -> x_t-1
-                    scheduler_output = scheduler.step(
-                        numpy2torch(noise_pred, device), t, numpy2torch(latents, device), **extra_step_kwargs
-                    )
-                    latents = torch2numpy(scheduler_output.prev_sample)
-
-                    state = PipelineIntermediateState(
-                        run_id="test", step=i, timestep=timestep, latents=scheduler_output.prev_sample
-                    )
-                    dispatch_progress(self, context=context, source_node_id=source_node_id, intermediate_state=state)
-
-                    # call the callback, if provided
-                    # if callback is not None and i % callback_steps == 0:
-                    #    callback(i, t, latents)
-
-        torch.cuda.empty_cache()
-
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=torch.from_numpy(latents))
-
-
-# Latent to image
-@invocation(
-    "l2i_onnx",
-    title="ONNX Latents to Image",
-    tags=["latents", "image", "vae", "onnx"],
-    category="image",
-    version="1.2.0",
-)
-class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata):
-    """Generates an image from latents."""
-
-    latents: LatentsField = InputField(
-        description=FieldDescriptions.denoised_latents,
-        input=Input.Connection,
-    )
-    vae: VaeField = InputField(
-        description=FieldDescriptions.vae,
-        input=Input.Connection,
-    )
-    # tiled: bool = InputField(default=False, description="Decode latents by overlaping tiles(less memory consumption)")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
-
-        if self.vae.vae.submodel != SubModelType.VaeDecoder:
-            raise Exception(f"Expected vae_decoder, found: {self.vae.vae.model_type}")
-
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-        )
-
-        # clear memory as vae decode can request a lot
-        torch.cuda.empty_cache()
-
-        with vae_info as vae:
-            vae.create_session()
-
-            # copied from
-            # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L427
-            latents = 1 / 0.18215 * latents
-            # image = self.vae_decoder(latent_sample=latents)[0]
-            # it seems likes there is a strange result for using half-precision vae decoder if batchsize>1
-            image = np.concatenate([vae(latent_sample=latents[i : i + 1])[0] for i in range(latents.shape[0])])
-
-            image = np.clip(image / 2 + 0.5, 0, 1)
-            image = image.transpose((0, 2, 3, 1))
-            image = VaeImageProcessor.numpy_to_pil(image)[0]
-
-        torch.cuda.empty_cache()
-
-        image_dto = context.services.images.create(
-            image=image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation_output("model_loader_output_onnx")
-class ONNXModelLoaderOutput(BaseInvocationOutput):
-    """Model loader output"""
-
-    unet: UNetField = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
-    vae_decoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Decoder")
-    vae_encoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Encoder")
-
-
-class OnnxModelField(BaseModel):
-    """Onnx model field"""
-
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Model Type")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@invocation("onnx_model_loader", title="ONNX Main Model", tags=["onnx", "model"], category="model", version="1.0.0")
-class OnnxModelLoaderInvocation(BaseInvocation):
-    """Loads a main model, outputting its submodels."""
-
-    model: OnnxModelField = InputField(
-        description=FieldDescriptions.onnx_main_model, input=Input.Direct, ui_type=UIType.ONNXModel
-    )
-
-    def invoke(self, context: InvocationContext) -> ONNXModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.ONNX
-
-        # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
-
-        """
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.Tokenizer,
-        ):
-            raise Exception(
-                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.TextEncoder,
-        ):
-            raise Exception(
-                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.UNet,
-        ):
-            raise Exception(
-                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
-            )
-        """
-
-        return ONNXModelLoaderOutput(
-            unet=UNetField(
-                unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
-                ),
-                scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
-                ),
-                loras=[],
-            ),
-            clip=ClipField(
-                tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
-                ),
-                text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
-                ),
-                loras=[],
-                skipped_layers=0,
-            ),
-            vae_decoder=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.VaeDecoder,
-                ),
-            ),
-            vae_encoder=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.VaeEncoder,
-                ),
-            ),
-        )

invokeai/app/invocations/param_easing.py

@@ -40,8 +40,10 @@ from easing_functions import (
 from matplotlib.ticker import MaxNLocator
 
 from invokeai.app.invocations.primitives import FloatCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField
 
 
 @invocation(
@@ -109,7 +111,7 @@ EASING_FUNCTION_KEYS = Literal[tuple(EASING_FUNCTIONS_MAP.keys())]
     title="Step Param Easing",
     tags=["step", "easing"],
     category="step",
-    version="1.0.0",
+    version="1.0.1",
 )
 class StepParamEasingInvocation(BaseInvocation):
     """Experimental per-step parameter easing for denoising steps"""
@@ -148,19 +150,19 @@ class StepParamEasingInvocation(BaseInvocation):
         postlist = list(num_poststeps * [self.post_end_value])
 
         if log_diagnostics:
-            context.services.logger.debug("start_step: " + str(start_step))
-            context.services.logger.debug("end_step: " + str(end_step))
-            context.services.logger.debug("num_easing_steps: " + str(num_easing_steps))
-            context.services.logger.debug("num_presteps: " + str(num_presteps))
-            context.services.logger.debug("num_poststeps: " + str(num_poststeps))
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
-            context.services.logger.debug("prelist: " + str(prelist))
-            context.services.logger.debug("postlist: " + str(postlist))
+            context.logger.debug("start_step: " + str(start_step))
+            context.logger.debug("end_step: " + str(end_step))
+            context.logger.debug("num_easing_steps: " + str(num_easing_steps))
+            context.logger.debug("num_presteps: " + str(num_presteps))
+            context.logger.debug("num_poststeps: " + str(num_poststeps))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist: " + str(prelist))
+            context.logger.debug("postlist: " + str(postlist))
 
         easing_class = EASING_FUNCTIONS_MAP[self.easing]
         if log_diagnostics:
-            context.services.logger.debug("easing class: " + str(easing_class))
+            context.logger.debug("easing class: " + str(easing_class))
         easing_list = []
         if self.mirror:  # "expected" mirroring
             # if number of steps is even, squeeze duration down to (number_of_steps)/2
@@ -171,7 +173,7 @@ class StepParamEasingInvocation(BaseInvocation):
 
             base_easing_duration = int(np.ceil(num_easing_steps / 2.0))
             if log_diagnostics:
-                context.services.logger.debug("base easing duration: " + str(base_easing_duration))
+                context.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,
@@ -183,14 +185,14 @@ class StepParamEasingInvocation(BaseInvocation):
                 easing_val = easing_function.ease(step_index)
                 base_easing_vals.append(easing_val)
                 if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
+                    context.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:
-                context.services.logger.debug("base easing vals: " + str(base_easing_vals))
-                context.services.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
+                context.logger.debug("base easing vals: " + str(base_easing_vals))
+                context.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
@@ -225,12 +227,12 @@ class StepParamEasingInvocation(BaseInvocation):
                 step_val = easing_function.ease(step_index)
                 easing_list.append(step_val)
                 if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
 
         if log_diagnostics:
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("easing_list size: " + str(len(easing_list)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("easing_list size: " + str(len(easing_list)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
 
         param_list = prelist + easing_list + postlist
 

invokeai/app/invocations/primitives.py

@@ -1,20 +1,28 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Optional, Tuple
+from typing import Optional
 
 import torch
-from pydantic import BaseModel, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import (
+    ColorField,
+    ConditioningField,
+    DenoiseMaskField,
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    LatentsField,
+    OutputField,
+    UIComponent,
+)
+from invokeai.app.services.images.images_common import ImageDTO
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
@@ -221,18 +229,6 @@ class StringCollectionInvocation(BaseInvocation):
 # region Image
 
 
-class ImageField(BaseModel):
-    """An image primitive field"""
-
-    image_name: str = Field(description="The name of the image")
-
-
-class BoardField(BaseModel):
-    """A board primitive field"""
-
-    board_id: str = Field(description="The id of the board")
-
-
 @invocation_output("image_output")
 class ImageOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
@@ -241,6 +237,14 @@ class ImageOutput(BaseInvocationOutput):
     width: int = OutputField(description="The width of the image in pixels")
     height: int = OutputField(description="The height of the image in pixels")
 
+    @classmethod
+    def build(cls, image_dto: ImageDTO) -> "ImageOutput":
+        return cls(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
 
 @invocation_output("image_collection_output")
 class ImageCollectionOutput(BaseInvocationOutput):
@@ -251,16 +255,14 @@ class ImageCollectionOutput(BaseInvocationOutput):
     )
 
 
-@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.0")
-class ImageInvocation(
-    BaseInvocation,
-):
+@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.1")
+class ImageInvocation(BaseInvocation):
     """An image primitive value"""
 
     image: ImageField = InputField(description="The image to load")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         return ImageOutput(
             image=ImageField(image_name=self.image.image_name),
@@ -290,42 +292,44 @@ class ImageCollectionInvocation(BaseInvocation):
 # region DenoiseMask
 
 
-class DenoiseMaskField(BaseModel):
-    """An inpaint mask field"""
-
-    mask_name: str = Field(description="The name of the mask image")
-    masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
-
-
 @invocation_output("denoise_mask_output")
 class DenoiseMaskOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
 
     denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
 
+    @classmethod
+    def build(
+        cls, mask_name: str, masked_latents_name: Optional[str] = None, gradient: bool = False
+    ) -> "DenoiseMaskOutput":
+        return cls(
+            denoise_mask=DenoiseMaskField(
+                mask_name=mask_name, masked_latents_name=masked_latents_name, gradient=gradient
+            ),
+        )
+
 
 # endregion
 
 # region Latents
 
 
-class LatentsField(BaseModel):
-    """A latents tensor primitive field"""
-
-    latents_name: str = Field(description="The name of the latents")
-    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
-
-
 @invocation_output("latents_output")
 class LatentsOutput(BaseInvocationOutput):
     """Base class for nodes that output a single latents tensor"""
 
-    latents: LatentsField = OutputField(
-        description=FieldDescriptions.latents,
-    )
+    latents: LatentsField = OutputField(description=FieldDescriptions.latents)
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
+    @classmethod
+    def build(cls, latents_name: str, latents: torch.Tensor, seed: Optional[int] = None) -> "LatentsOutput":
+        return cls(
+            latents=LatentsField(latents_name=latents_name, seed=seed),
+            width=latents.size()[3] * LATENT_SCALE_FACTOR,
+            height=latents.size()[2] * LATENT_SCALE_FACTOR,
+        )
+
 
 @invocation_output("latents_collection_output")
 class LatentsCollectionOutput(BaseInvocationOutput):
@@ -337,7 +341,7 @@ class LatentsCollectionOutput(BaseInvocationOutput):
 
 
 @invocation(
-    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.0"
+    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.1"
 )
 class LatentsInvocation(BaseInvocation):
     """A latents tensor primitive value"""
@@ -345,9 +349,9 @@ class LatentsInvocation(BaseInvocation):
     latents: LatentsField = InputField(description="The latents tensor", input=Input.Connection)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
-        return build_latents_output(self.latents.latents_name, latents)
+        return LatentsOutput.build(self.latents.latents_name, latents)
 
 
 @invocation(
@@ -368,31 +372,11 @@ class LatentsCollectionInvocation(BaseInvocation):
         return LatentsCollectionOutput(collection=self.collection)
 
 
-def build_latents_output(latents_name: str, latents: torch.Tensor, seed: Optional[int] = None):
-    return LatentsOutput(
-        latents=LatentsField(latents_name=latents_name, seed=seed),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
-
-
 # endregion
 
 # region Color
 
 
-class ColorField(BaseModel):
-    """A color primitive field"""
-
-    r: int = Field(ge=0, le=255, description="The red component")
-    g: int = Field(ge=0, le=255, description="The green component")
-    b: int = Field(ge=0, le=255, description="The blue component")
-    a: int = Field(ge=0, le=255, description="The alpha component")
-
-    def tuple(self) -> Tuple[int, int, int, int]:
-        return (self.r, self.g, self.b, self.a)
-
-
 @invocation_output("color_output")
 class ColorOutput(BaseInvocationOutput):
     """Base class for nodes that output a single color"""
@@ -424,18 +408,16 @@ class ColorInvocation(BaseInvocation):
 # region Conditioning
 
 
-class ConditioningField(BaseModel):
-    """A conditioning tensor primitive value"""
-
-    conditioning_name: str = Field(description="The name of conditioning tensor")
-
-
 @invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""
 
     conditioning: ConditioningField = OutputField(description=FieldDescriptions.cond)
 
+    @classmethod
+    def build(cls, conditioning_name: str) -> "ConditioningOutput":
+        return cls(conditioning=ConditioningField(conditioning_name=conditioning_name))
+
 
 @invocation_output("conditioning_collection_output")
 class ConditioningCollectionOutput(BaseInvocationOutput):