chore(ui): regen types

Crawled through a few custom nodes to figure out what I had missed.

.github/actions/install-frontend-deps/action.yml

@@ -1,33 +0,0 @@
-name: install frontend dependencies
-description: Installs frontend dependencies with pnpm, with caching
-runs:
-  using: 'composite'
-  steps:
-    - name: setup node 18
-      uses: actions/setup-node@v4
-      with:
-        node-version: '18'
-
-    - name: setup pnpm
-      uses: pnpm/action-setup@v2
-      with:
-        version: 8
-        run_install: false
-
-    - name: get pnpm store directory
-      shell: bash
-      run: |
-        echo "STORE_PATH=$(pnpm store path --silent)" >> $GITHUB_ENV
-
-    - name: setup cache
-      uses: actions/cache@v4
-      with:
-        path: ${{ env.STORE_PATH }}
-        key: ${{ runner.os }}-pnpm-store-${{ hashFiles('**/pnpm-lock.yaml') }}
-        restore-keys: |
-          ${{ runner.os }}-pnpm-store-
-
-    - name: install frontend dependencies
-      run: pnpm install --prefer-frozen-lockfile
-      shell: bash
-      working-directory: invokeai/frontend/web

.github/pr_labels.yml

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

.github/workflows/build-container.yml

@@ -11,7 +11,7 @@ on:
       - 'docker/docker-entrypoint.sh'
       - 'workflows/build-container.yml'
     tags:
-      - 'v*.*.*'
+      - 'v*'
   workflow_dispatch:
 
 permissions:

.github/workflows/build-installer.yml

@@ -1,45 +0,0 @@
-# Builds and uploads the installer and python build artifacts.
-
-name: build installer
-
-on:
-  workflow_dispatch:
-  workflow_call:
-
-jobs:
-  build-installer:
-    runs-on: ubuntu-latest
-    timeout-minutes: 5 # expected run time: <2 min
-    steps:
-      - name: checkout
-        uses: actions/checkout@v4
-
-      - name: setup python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.10'
-          cache: pip
-          cache-dependency-path: pyproject.toml
-
-      - name: install pypa/build
-        run: pip install --upgrade build
-
-      - name: setup frontend
-        uses: ./.github/actions/install-frontend-deps
-
-      - name: create installer
-        id: create_installer
-        run: ./create_installer.sh
-        working-directory: installer
-
-      - name: upload python distribution artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: dist
-          path: ${{ steps.create_installer.outputs.DIST_PATH }}
-
-      - name: upload installer artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ${{ steps.create_installer.outputs.INSTALLER_FILENAME }}
-          path: ${{ steps.create_installer.outputs.INSTALLER_PATH }}

.github/workflows/frontend-checks.yml

@@ -1,68 +0,0 @@
-# Runs frontend code quality checks.
-#
-# Checks for changes to frontend files before running the checks.
-# When manually triggered or when called from another workflow, always runs the checks.
-
-name: 'frontend checks'
-
-on:
-  push:
-    branches:
-      - 'main'
-  pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  merge_group:
-  workflow_dispatch:
-  workflow_call:
-
-defaults:
-  run:
-    working-directory: invokeai/frontend/web
-
-jobs:
-  frontend-checks:
-    runs-on: ubuntu-latest
-    timeout-minutes: 10 # expected run time: <2 min
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: check for changed frontend files
-        if: ${{ github.event_name != 'workflow_dispatch' && github.event_name != 'workflow_call' }}
-        id: changed-files
-        uses: tj-actions/changed-files@v42
-        with:
-          files_yaml: |
-            frontend:
-              - 'invokeai/frontend/web/**'
-
-      - name: install dependencies
-        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        uses: ./.github/actions/install-frontend-deps
-
-      - name: tsc
-        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: 'pnpm lint:tsc'
-        shell: bash
-
-      - name: dpdm
-        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: 'pnpm lint:dpdm'
-        shell: bash
-
-      - name: eslint
-        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: 'pnpm lint:eslint'
-        shell: bash
-
-      - name: prettier
-        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: 'pnpm lint:prettier'
-        shell: bash
-
-      - name: knip
-        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: 'pnpm lint:knip'
-        shell: bash

.github/workflows/frontend-tests.yml

@@ -1,48 +0,0 @@
-# Runs frontend tests.
-#
-# Checks for changes to frontend files before running the tests.
-# When manually triggered or called from another workflow, always runs the tests.
-
-name: 'frontend tests'
-
-on:
-  push:
-    branches:
-      - 'main'
-  pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  merge_group:
-  workflow_dispatch:
-  workflow_call:
-
-defaults:
-  run:
-    working-directory: invokeai/frontend/web
-
-jobs:
-  frontend-tests:
-    runs-on: ubuntu-latest
-    timeout-minutes: 10 # expected run time: <2 min
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: check for changed frontend files
-        if: ${{ github.event_name != 'workflow_dispatch' && github.event_name != 'workflow_call' }}
-        id: changed-files
-        uses: tj-actions/changed-files@v42
-        with:
-          files_yaml: |
-            frontend:
-              - 'invokeai/frontend/web/**'
-
-      - name: install dependencies
-        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        uses: ./.github/actions/install-frontend-deps
-
-      - name: vitest
-        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: 'pnpm test:no-watch'
-        shell: bash

.github/workflows/label-pr.yml

@@ -1,6 +1,6 @@
-name: 'label PRs'
+name: "Pull Request Labeler"
 on:
-  - pull_request_target
+- pull_request_target
 
 jobs:
   labeler:
@@ -9,10 +9,8 @@ jobs:
       pull-requests: write
     runs-on: ubuntu-latest
     steps:
-      - name: checkout
+      - name: Checkout
         uses: actions/checkout@v4
-
-      - name: label PRs
-        uses: actions/labeler@v5
+      - uses: actions/labeler@v5
         with:
-          configuration-path: .github/pr_labels.yml
+          configuration-path: .github/pr_labels.yml

.github/workflows/lint-frontend.yml

@@ -0,0 +1,43 @@
+name: Lint frontend
+
+on:
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  push:
+    branches:
+      - 'main'
+  merge_group:
+  workflow_dispatch:
+
+defaults:
+  run:
+    working-directory: invokeai/frontend/web
+
+jobs:
+  lint-frontend:
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Setup Node 18
+        uses: actions/setup-node@v4
+        with:
+          node-version: '18'
+      - 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:madge'
+      - name: ESLint
+        run: 'pnpm run lint:eslint'
+      - name: Prettier
+        run: 'pnpm run lint:prettier'

.github/workflows/mkdocs-material.yml

@@ -1,49 +1,51 @@
-# This is a mostly a copy-paste from https://github.com/squidfunk/mkdocs-material/blob/master/docs/publishing-your-site.md
-
-name: mkdocs
-
+name: mkdocs-material
 on:
   push:
     branches:
-      - main
-  workflow_dispatch:
+      - 'refs/heads/main'
 
 permissions:
-  contents: write
+    contents: write
 
 jobs:
-  deploy:
+  mkdocs-material:
     if: github.event.pull_request.draft == false
     runs-on: ubuntu-latest
     env:
       REPO_URL: '${{ github.server_url }}/${{ github.repository }}'
       REPO_NAME: '${{ github.repository }}'
       SITE_URL: 'https://${{ github.repository_owner }}.github.io/InvokeAI'
-
     steps:
-      - name: checkout
-        uses: actions/checkout@v4
+      - name: checkout sources
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
 
       - name: setup python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v4
         with:
           python-version: '3.10'
           cache: pip
           cache-dependency-path: pyproject.toml
 
-      - name: set cache id
-        run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
+      - name: install requirements
+        env:
+          PIP_USE_PEP517: 1
+        run: |
+          python -m \
+            pip install ".[docs]"
 
-      - name: use cache
-        uses: actions/cache@v4
-        with:
-          key: mkdocs-material-${{ env.cache_id }}
-          path: .cache
-          restore-keys: |
-            mkdocs-material-
+      - name: confirm buildability
+        run: |
+          python -m \
+            mkdocs build \
+            --clean \
+            --verbose
 
-      - name: install dependencies
-        run: python -m pip install ".[docs]"
-
-      - name: build & deploy
-        run: mkdocs gh-deploy --force
+      - name: deploy to gh-pages
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: |
+          python -m \
+            mkdocs gh-deploy \
+            --clean \
+            --force

.github/workflows/pypi-release.yml

@@ -0,0 +1,67 @@
+name: PyPI Release
+
+on:
+  workflow_dispatch:
+    inputs:
+      publish_package:
+        description: 'Publish build on PyPi? [true/false]'
+        required: true
+        default: 'false'
+
+jobs:
+  build-and-release:
+    if: github.repository == 'invoke-ai/InvokeAI'
+    runs-on: ubuntu-22.04
+    env:
+      TWINE_USERNAME: __token__
+      TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+      TWINE_NON_INTERACTIVE: 1
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - 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 python package
+        run: python3 -m build
+
+      - 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
+        if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
+        run: |
+          pip install --upgrade requests
+          python -c "\
+          import scripts.pypi_helper; \
+          EXISTS=scripts.pypi_helper.local_on_pypi(); \
+          print(f'PACKAGE_EXISTS={EXISTS}')" >> $GITHUB_ENV
+
+      - name: Publish build on PyPi
+        if: env.PACKAGE_EXISTS == 'False' && env.TWINE_PASSWORD != '' && github.event.inputs.publish_package == 'true'
+        run: twine upload dist/*

.github/workflows/python-checks.yml

@@ -1,64 +0,0 @@
-# Runs python code quality checks.
-#
-# Checks for changes to python files before running the checks.
-# When manually triggered or called from another workflow, always runs the tests.
-#
-# TODO: Add mypy or pyright to the checks.
-
-name: 'python checks'
-
-on:
-  push:
-    branches:
-      - 'main'
-  pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  merge_group:
-  workflow_dispatch:
-  workflow_call:
-
-jobs:
-  python-checks:
-    runs-on: ubuntu-latest
-    timeout-minutes: 5 # expected run time: <1 min
-    steps:
-      - name: checkout
-        uses: actions/checkout@v4
-
-      - name: check for changed python files
-        if: ${{ github.event_name != 'workflow_dispatch' && github.event_name != 'workflow_call' }}
-        id: changed-files
-        uses: tj-actions/changed-files@v42
-        with:
-          files_yaml: |
-            python:
-              - 'pyproject.toml'
-              - 'invokeai/**'
-              - '!invokeai/frontend/web/**'
-              - 'tests/**'
-
-      - name: setup python
-        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.10'
-          cache: pip
-          cache-dependency-path: pyproject.toml
-
-      - name: install ruff
-        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: pip install ruff
-        shell: bash
-
-      - name: ruff check
-        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: ruff check --output-format=github .
-        shell: bash
-
-      - name: ruff format
-        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: ruff format --check .
-        shell: bash

.github/workflows/python-tests.yml

@@ -1,94 +0,0 @@
-# Runs python tests on a matrix of python versions and platforms.
-#
-# Checks for changes to python files before running the tests.
-# When manually triggered or called from another workflow, always runs the tests.
-
-name: 'python tests'
-
-on:
-  push:
-    branches:
-      - 'main'
-  pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  merge_group:
-  workflow_dispatch:
-  workflow_call:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  matrix:
-    strategy:
-      matrix:
-        python-version:
-          - '3.10'
-          - '3.11'
-        platform:
-          - linux-cuda-11_7
-          - linux-rocm-5_2
-          - linux-cpu
-          - macos-default
-          - windows-cpu
-        include:
-          - platform: linux-cuda-11_7
-            os: ubuntu-22.04
-            github-env: $GITHUB_ENV
-          - platform: linux-rocm-5_2
-            os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
-            github-env: $GITHUB_ENV
-          - platform: linux-cpu
-            os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/cpu'
-            github-env: $GITHUB_ENV
-          - platform: macos-default
-            os: macOS-12
-            github-env: $GITHUB_ENV
-          - platform: windows-cpu
-            os: windows-2022
-            github-env: $env:GITHUB_ENV
-    name: 'py${{ matrix.python-version }}: ${{ matrix.platform }}'
-    runs-on: ${{ matrix.os }}
-    timeout-minutes: 15 # expected run time: 2-6 min, depending on platform
-    env:
-      PIP_USE_PEP517: '1'
-    steps:
-      - name: checkout
-        uses: actions/checkout@v4
-
-      - name: check for changed python files
-        if: ${{ github.event_name != 'workflow_dispatch' && github.event_name != 'workflow_call' }}
-        id: changed-files
-        uses: tj-actions/changed-files@v42
-        with:
-          files_yaml: |
-            python:
-              - 'pyproject.toml'
-              - 'invokeai/**'
-              - '!invokeai/frontend/web/**'
-              - 'tests/**'
-
-      - name: setup python
-        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: pip
-          cache-dependency-path: pyproject.toml
-
-      - name: install dependencies
-        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        env:
-          PIP_EXTRA_INDEX_URL: ${{ matrix.extra-index-url }}
-        run: >
-          pip3 install --editable=".[test]"
-
-      - name: run pytest
-        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_call' }}
-        run: pytest

.github/workflows/release.yml

@@ -1,96 +0,0 @@
-# Main release workflow. Triggered on tag push or manual trigger.
-#
-# - Runs all code checks and tests
-# - Verifies the app version matches the tag version.
-# - Builds the installer and build, uploading them as artifacts.
-# - Publishes to TestPyPI and PyPI. Both are conditional on the previous steps passing and require a manual approval.
-#
-# See docs/RELEASE.md for more information on the release process.
-
-name: release
-
-on:
-  push:
-    tags:
-      - 'v*'
-  workflow_dispatch:
-
-jobs:
-  check-version:
-    runs-on: ubuntu-latest
-    steps:
-      - name: checkout
-        uses: actions/checkout@v4
-
-      - name: check python version
-        uses: samuelcolvin/check-python-version@v4
-        id: check-python-version
-        with:
-          version_file_path: invokeai/version/invokeai_version.py
-
-  frontend-checks:
-    uses: ./.github/workflows/frontend-checks.yml
-
-  frontend-tests:
-    uses: ./.github/workflows/frontend-tests.yml
-
-  python-checks:
-    uses: ./.github/workflows/python-checks.yml
-
-  python-tests:
-    uses: ./.github/workflows/python-tests.yml
-
-  build:
-    uses: ./.github/workflows/build-installer.yml
-
-  publish-testpypi:
-    runs-on: ubuntu-latest
-    timeout-minutes: 5 # expected run time: <1 min
-    needs:
-      [
-        check-version,
-        frontend-checks,
-        frontend-tests,
-        python-checks,
-        python-tests,
-        build,
-      ]
-    environment:
-      name: testpypi
-      url: https://test.pypi.org/p/invokeai
-    steps:
-      - name: download distribution from build job
-        uses: actions/download-artifact@v4
-        with:
-          name: dist
-          path: dist/
-
-      - name: publish distribution to TestPyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          repository-url: https://test.pypi.org/legacy/
-
-  publish-pypi:
-    runs-on: ubuntu-latest
-    timeout-minutes: 5 # expected run time: <1 min
-    needs:
-      [
-        check-version,
-        frontend-checks,
-        frontend-tests,
-        python-checks,
-        python-tests,
-        build,
-      ]
-    environment:
-      name: pypi
-      url: https://pypi.org/p/invokeai
-    steps:
-      - name: download distribution from build job
-        uses: actions/download-artifact@v4
-        with:
-          name: dist
-          path: dist/
-
-      - name: publish distribution to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/style-checks.yml

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

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

@@ -0,0 +1,129 @@
+name: Test invoke.py pip
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  matrix:
+    if: github.event.pull_request.draft == false
+    strategy:
+      matrix:
+        python-version:
+          # - '3.9'
+          - '3.10'
+        pytorch:
+          - linux-cuda-11_7
+          - linux-rocm-5_2
+          - linux-cpu
+          - macos-default
+          - windows-cpu
+        include:
+          - pytorch: linux-cuda-11_7
+            os: ubuntu-22.04
+            github-env: $GITHUB_ENV
+          - pytorch: linux-rocm-5_2
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
+            github-env: $GITHUB_ENV
+          - pytorch: linux-cpu
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/cpu'
+            github-env: $GITHUB_ENV
+          - pytorch: macos-default
+            os: macOS-12
+            github-env: $GITHUB_ENV
+          - pytorch: windows-cpu
+            os: windows-2022
+            github-env: $env:GITHUB_ENV
+    name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
+    runs-on: ${{ matrix.os }}
+    env:
+      PIP_USE_PEP517: '1'
+    steps:
+      - name: Checkout sources
+        id: checkout-sources
+        uses: actions/checkout@v3
+
+      - name: Check for changed python files
+        id: changed-files
+        uses: tj-actions/changed-files@v41
+        with:
+          files_yaml: |
+            python:
+              - 'pyproject.toml'
+              - 'invokeai/**'
+              - '!invokeai/frontend/web/**'
+              - 'tests/**'
+
+      - name: set test prompt to main branch validation
+        if: steps.changed-files.outputs.python_any_changed == 'true'
+        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
+
+      - name: setup python
+        if: steps.changed-files.outputs.python_any_changed == 'true'
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+          cache-dependency-path: pyproject.toml
+
+      - name: install invokeai
+        if: steps.changed-files.outputs.python_any_changed == 'true'
+        env:
+          PIP_EXTRA_INDEX_URL: ${{ matrix.extra-index-url }}
+        run: >
+          pip3 install
+          --editable=".[test]"
+
+      - name: run pytest
+        if: steps.changed-files.outputs.python_any_changed == 'true'
+        id: run-pytest
+        run: pytest
+
+      # - name: run invokeai-configure
+      #   env:
+      #     HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
+      #   run: >
+      #     invokeai-configure
+      #     --yes
+      #     --default_only
+      #     --full-precision
+      #   # can't use fp16 weights without a GPU
+
+      # - name: run invokeai
+      #   id: run-invokeai
+      #   env:
+      #     # Set offline mode to make sure configure preloaded successfully.
+      #     HF_HUB_OFFLINE: 1
+      #     HF_DATASETS_OFFLINE: 1
+      #     TRANSFORMERS_OFFLINE: 1
+      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
+      #   run: >
+      #     invokeai
+      #     --no-patchmatch
+      #     --no-nsfw_checker
+      #     --precision=float32
+      #     --always_use_cpu
+      #     --use_memory_db
+      #     --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+      #     --from_file ${{ env.TEST_PROMPTS }}
+
+      # - name: Archive results
+      #   env:
+      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
+      #   uses: actions/upload-artifact@v3
+      #   with:
+      #     name: results
+      #     path: ${{ env.INVOKEAI_OUTDIR }}

.prettierrc.yaml

@@ -7,7 +7,7 @@ embeddedLanguageFormatting: auto
 overrides:
   - files: '*.md'
     options:
-      proseWrap: preserve
+      proseWrap: always
       printWidth: 80
       parser: markdown
       cursorOffset: -1

Makefile

@@ -6,44 +6,33 @@ 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!)"
+	@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 "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
-
-# 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
+		mypy scripts/invokeai-web.py --config-file= --ignore-missing-imports
 
 # Build the frontend
 frontend-build:

docs/RELEASE.md

@@ -1,142 +0,0 @@
-# Release Process
-
-The app is published in twice, in different build formats.
-
-- A [PyPI] distribution. This includes both a source distribution and built distribution (a wheel). Users install with `pip install invokeai`. The updater uses this build.
-- An installer on the [InvokeAI Releases Page]. This is a zip file with install scripts and a wheel. This is only used for new installs.
-
-## General Prep
-
-Make a developer call-out for PRs to merge. Merge and test things out.
-
-While the release workflow does not include end-to-end tests, it does pause before publishing so you can download and test the final build.
-
-## Release Workflow
-
-The `release.yml` workflow runs a number of jobs to handle code checks, tests, build and publish on PyPI.
-
-It is triggered on **tag push**, when the tag matches `v*`. It doesn't matter if you've prepped a release branch like `release/v3.5.0` or are releasing from `main` - it works the same.
-
-> Because commits are reference-counted, it is safe to create a release branch, tag it, let the workflow run, then delete the branch. So long as the tag exists, that commit will exist.
-
-### Triggering the Workflow
-
-Run `make tag-release` to tag the current commit and kick off the workflow.
-
-The release may also be dispatched [manually].
-
-### Workflow Jobs and Process
-
-The workflow consists of a number of concurrently-run jobs, and two final publish jobs.
-
-The publish jobs require manual approval and are only run if the other jobs succeed.
-
-#### `check-version` Job
-
-This job checks that the git ref matches the app version. It matches the ref against the `__version__` variable in `invokeai/version/invokeai_version.py`.
-
-When the workflow is triggered by tag push, the ref is the tag. If the workflow is run manually, the ref is the target selected from the **Use workflow from** dropdown.
-
-This job uses [samuelcolvin/check-python-version].
-
-> Any valid [version specifier] works, so long as the tag matches the version. The release workflow works exactly the same for `RC`, `post`, `dev`, etc.
-
-#### Check and Test Jobs
-
-- **`python-tests`**: runs `pytest` on matrix of platforms
-- **`python-checks`**: runs `ruff` (format and lint)
-- **`frontend-tests`**: runs `vitest`
-- **`frontend-checks`**: runs `prettier` (format), `eslint` (lint), `dpdm` (circular refs), `tsc` (static type check) and `knip` (unused imports)
-
-> **TODO** We should add `mypy` or `pyright` to the **`check-python`** job.
-
-> **TODO** We should add an end-to-end test job that generates an image.
-
-#### `build-installer` Job
-
-This sets up both python and frontend dependencies and builds the python package. Internally, this runs `installer/create_installer.sh` and uploads two artifacts:
-
-- **`dist`**: the python distribution, to be published on PyPI
-- **`InvokeAI-installer-${VERSION}.zip`**: the installer to be included in the GitHub release
-
-#### Sanity Check & Smoke Test
-
-At this point, the release workflow pauses as the remaining publish jobs require approval.
-
-A maintainer should go to the **Summary** tab of the workflow, download the installer and test it. Ensure the app loads and generates.
-
-> The same wheel file is bundled in the installer and in the `dist` artifact, which is uploaded to PyPI. You should end up with the exactly the same installation of the `invokeai` package from any of these methods.
-
-#### PyPI Publish Jobs
-
-The publish jobs will run if any of the previous jobs fail.
-
-They use [GitHub environments], which are configured as [trusted publishers] on PyPI.
-
-Both jobs require a maintainer to approve them from the workflow's **Summary** tab.
-
-- Click the **Review deployments** button
-- Select the environment (either `testpypi` or `pypi`)
-- Click **Approve and deploy**
-
-> **If the version already exists on PyPI, the publish jobs will fail.** PyPI only allows a given version to be published once - you cannot change it. If version published on PyPI has a problem, you'll need to "fail forward" by bumping the app version and publishing a followup release.
-
-#### `publish-testpypi` Job
-
-Publishes the distribution on the [Test PyPI] index, using the `testpypi` GitHub environment.
-
-This job is not required for the production PyPI publish, but included just in case you want to test the PyPI release.
-
-If approved and successful, you could try out the test release like this:
-
-```sh
-# Create a new virtual environment
-python -m venv ~/.test-invokeai-dist --prompt test-invokeai-dist
-# Install the distribution from Test PyPI
-pip install --index-url https://test.pypi.org/simple/ invokeai
-# Run and test the app
-invokeai-web
-# Cleanup
-deactivate
-rm -rf ~/.test-invokeai-dist
-```
-
-#### `publish-pypi` Job
-
-Publishes the distribution on the production PyPI index, using the `pypi` GitHub environment.
-
-## Publish the GitHub Release with installer
-
-Once the release is published to PyPI, it's time to publish the GitHub release.
-
-1. [Draft a new release] on GitHub, choosing the tag that triggered the release.
-2. Write the release notes, describing important changes. The **Generate release notes** button automatically inserts the changelog and new contributors, and you can copy/paste the intro from previous releases.
-3. Upload the zip file created in **`build`** job into the Assets section of the release notes. You can also upload the zip into the body of the release notes, since it can be hard for users to find the Assets section.
-4. Check the **Set as a pre-release** and **Create a discussion for this release** checkboxes at the bottom of the release page.
-5. Publish the pre-release.
-6. Announce the pre-release in Discord.
-
-> **TODO** Workflows can create a GitHub release from a template and upload release assets. One popular action to handle this is [ncipollo/release-action]. A future enhancement to the release process could set this up.
-
-## Manual Build
-
-The `build installer` workflow can be dispatched manually. This is useful to test the installer for a given branch or tag.
-
-No checks are run, it just builds.
-
-## Manual Release
-
-The `release` workflow can be dispatched manually. You must dispatch the workflow from the right tag, else it will fail the version check.
-
-This functionality is available as a fallback in case something goes wonky. Typically, releases should be triggered via tag push as described above.
-
-[InvokeAI Releases Page]: https://github.com/invoke-ai/InvokeAI/releases
-[PyPI]: https://pypi.org/
-[Draft a new release]: https://github.com/invoke-ai/InvokeAI/releases/new
-[Test PyPI]: https://test.pypi.org/
-[version specifier]: https://packaging.python.org/en/latest/specifications/version-specifiers/
-[ncipollo/release-action]: https://github.com/ncipollo/release-action
-[GitHub environments]: https://docs.github.com/en/actions/deployment/targeting-different-environments/using-environments-for-deployment
-[trusted publishers]: https://docs.pypi.org/trusted-publishers/
-[samuelcolvin/check-python-version]: https://github.com/samuelcolvin/check-python-version
-[manually]: #manual-release

docs/contributing/MODEL_MANAGER.md

@@ -28,7 +28,7 @@ model. These are the:
   Hugging Face, as well as discriminating among model versions in
   Civitai, but can be used for arbitrary content.
   
-  * _ModelLoadServiceBase_
+  * _ModelLoadServiceBase_ (**CURRENTLY UNDER DEVELOPMENT - NOT IMPLEMENTED**)
   Responsible for loading a model from disk
   into RAM and VRAM and getting it ready for inference.
 
@@ -41,10 +41,10 @@ The four main services can be found in
 * `invokeai/app/services/model_records/`
 * `invokeai/app/services/model_install/`
 * `invokeai/app/services/downloads/`
-* `invokeai/app/services/model_load/`
+* `invokeai/app/services/model_loader/` (**under development**)
 
 Code related to the FastAPI web API can be found in
-`invokeai/app/api/routers/model_manager_v2.py`.
+`invokeai/app/api/routers/model_records.py`.
 
 ***
 
@@ -84,10 +84,10 @@ diffusers model. When this happens, `original_hash` is unchanged, but
 `ModelType`, `ModelFormat` and `BaseModelType` are string enums that
 are defined in `invokeai.backend.model_manager.config`. They are also
 imported by, and can be reexported from,
-`invokeai.app.services.model_manager.model_records`:
+`invokeai.app.services.model_record_service`:
 
 ```
-from invokeai.app.services.model_records import ModelType, ModelFormat, BaseModelType
+from invokeai.app.services.model_record_service import ModelType, ModelFormat, BaseModelType
 ```
 
 The `path` field can be absolute or relative. If relative, it is taken
@@ -123,7 +123,7 @@ taken to be the `models_dir` directory.
 
 `variant` is an enumerated string class with values `normal`,
 `inpaint` and `depth`. If needed, it can be imported if needed from
-either `invokeai.app.services.model_records` or
+either `invokeai.app.services.model_record_service` or
 `invokeai.backend.model_manager.config`.
 
 ### ONNXSD2Config
@@ -134,7 +134,7 @@ either `invokeai.app.services.model_records` or
 | `upcast_attention`  | bool | Model requires its attention module to be upcast |
 
 The `SchedulerPredictionType` enum can be imported from either
-`invokeai.app.services.model_records` or
+`invokeai.app.services.model_record_service` or
 `invokeai.backend.model_manager.config`.
 
 ### Other config classes
@@ -157,6 +157,15 @@ indicates that the model is compatible with any of the base
 models. This works OK for some models, such as the IP Adapter image
 encoders, but is an all-or-nothing proposition.
 
+Another issue is that the config class hierarchy is paralleled to some
+extent by a `ModelBase` class hierarchy defined in
+`invokeai.backend.model_manager.models.base` and its subclasses. These
+are classes representing the models after they are loaded into RAM and
+include runtime information such as load status and bytes used. Some
+of the fields, including `name`, `model_type` and `base_model`, are
+shared between `ModelConfigBase` and `ModelBase`, and this is a
+potential source of confusion.
+
 ## Reading and Writing Model Configuration Records
 
 The `ModelRecordService` provides the ability to retrieve model
@@ -168,11 +177,11 @@ initialization and can be retrieved within an invocation from the
 `InvocationContext` object:
 
 ```
-store = context.services.model_manager.store
+store = context.services.model_record_store
 ```
 
 or from elsewhere in the code by accessing
-`ApiDependencies.invoker.services.model_manager.store`.
+`ApiDependencies.invoker.services.model_record_store`.
 
 ### Creating a `ModelRecordService` 
 
@@ -181,7 +190,7 @@ you can directly create either a `ModelRecordServiceSQL` or a
 `ModelRecordServiceFile` object:
 
 ```
-from invokeai.app.services.model_records import ModelRecordServiceSQL, ModelRecordServiceFile
+from invokeai.app.services.model_record_service import ModelRecordServiceSQL, ModelRecordServiceFile
 
 store = ModelRecordServiceSQL.from_connection(connection, lock)
 store = ModelRecordServiceSQL.from_db_file('/path/to/sqlite_database.db')
@@ -243,7 +252,7 @@ So a typical startup pattern would be:
 ```
 import sqlite3
 from invokeai.app.services.thread import lock
-from invokeai.app.services.model_records import ModelRecordServiceBase
+from invokeai.app.services.model_record_service import ModelRecordServiceBase
 from invokeai.app.services.config import InvokeAIAppConfig
 
 config = InvokeAIAppConfig.get_config()
@@ -251,6 +260,19 @@ db_conn = sqlite3.connect(config.db_path.as_posix(), check_same_thread=False)
 store = ModelRecordServiceBase.open(config, db_conn, lock)
 ```
 
+_A note on simultaneous access to `invokeai.db`_: The current InvokeAI
+service architecture for the image and graph databases is careful to
+use a shared sqlite3 connection and a thread lock to ensure that two
+threads don't attempt to access the database simultaneously. However,
+the default `sqlite3` library used by Python reports using
+**Serialized** mode, which allows multiple threads to access the
+database simultaneously using multiple database connections (see
+https://www.sqlite.org/threadsafe.html and
+https://ricardoanderegg.com/posts/python-sqlite-thread-safety/). Therefore
+it should be safe to allow the record service to open its own SQLite
+database connection. Opening a model record service should then be as
+simple as `ModelRecordServiceBase.open(config)`.
+
 ### Fetching a Model's Configuration from `ModelRecordServiceBase`
 
 Configurations can be retrieved in several ways.
@@ -446,44 +468,6 @@ required parameters:
 
 Once initialized, the installer will provide the following methods:
 
-#### install_job = installer.heuristic_import(source, [config], [access_token])
-
-This is a simplified interface to the installer which takes a source
-string, an optional model configuration dictionary and an optional
-access token.
-
-The `source` is a string that can be any of these forms
-
-1. A path on the local filesystem (`C:\\users\\fred\\model.safetensors`)
-2. A Url pointing to a single downloadable model file (`https://civitai.com/models/58390/detail-tweaker-lora-lora`)
-3. A HuggingFace repo_id with any of the following formats:
-   - `model/name` -- entire model
-   - `model/name:fp32` -- entire model, using the fp32 variant
-   - `model/name:fp16:vae` -- vae submodel, using the fp16 variant
-   - `model/name::vae` -- vae submodel, using default precision
-   - `model/name:fp16:path/to/model.safetensors` -- an individual model file, fp16 variant
-   - `model/name::path/to/model.safetensors` -- an individual model file, default variant
-
-Note that by specifying a relative path to the top of the HuggingFace
-repo, you can download and install arbitrary models files. 
-
-The variant, if not provided, will be automatically filled in with
-`fp32` if the user has requested full precision, and `fp16`
-otherwise. If a variant that does not exist is requested, then the
-method will install whatever HuggingFace returns as its default
-revision.
-
-`config` is an optional dict of values that will override the
-autoprobed values for model type, base, scheduler prediction type, and
-so forth. See [Model configuration and
-probing](#Model-configuration-and-probing) for details.
-
-`access_token` is an optional access token for accessing resources
-that need authentication.
-
-The method will return a `ModelInstallJob`. This object is discussed
-at length in the following section.
-
 #### install_job = installer.import_model()
 
 The `import_model()` method is the core of the installer. The
@@ -502,10 +486,9 @@ source2 = LocalModelSource(path='/opt/models/sushi_diffusers')     # a local dif
 source3 = HFModelSource(repo_id='runwayml/stable-diffusion-v1-5')  # a repo_id
 source4 = HFModelSource(repo_id='runwayml/stable-diffusion-v1-5', subfolder='vae')  # a subfolder within a repo_id
 source5 = HFModelSource(repo_id='runwayml/stable-diffusion-v1-5', variant='fp16')   # a named variant of a HF model
-source6 = HFModelSource(repo_id='runwayml/stable-diffusion-v1-5', subfolder='OrangeMix/OrangeMix1.ckpt')   # path to an individual model file
 
-source7 = URLModelSource(url='https://civitai.com/api/download/models/63006')       # model located at a URL
-source8 = URLModelSource(url='https://civitai.com/api/download/models/63006', access_token='letmein') # with an access token
+source6 = URLModelSource(url='https://civitai.com/api/download/models/63006')       # model located at a URL
+source7 = URLModelSource(url='https://civitai.com/api/download/models/63006', access_token='letmein') # with an access token
 
 for source in [source1, source2, source3, source4, source5, source6, source7]:
    install_job = installer.install_model(source)
@@ -561,6 +544,7 @@ can be passed to `import_model()`.
 attributes returned by the model prober. See the section below for
 details.
 
+
 #### LocalModelSource
 
 This is used for a model that is located on a locally-accessible Posix
@@ -753,7 +737,7 @@ and `cancelled`, as well as `in_terminal_state`. The last will return
 True if the job is in the complete, errored or cancelled states.
 
 
-#### Model configuration and probing
+#### Model confguration and probing
 
 The install service uses the `invokeai.backend.model_manager.probe`
 module during import to determine the model's type, base type, and
@@ -792,14 +776,6 @@ returns a list of completed jobs. The optional `timeout` argument will
 return from the call if jobs aren't completed in the specified
 time. An argument of 0 (the default) will block indefinitely.
 
-#### jobs = installer.wait_for_job(job, [timeout])
-
-Like `wait_for_installs()`, but block until a specific job has
-completed or errored, and then return the job.  The optional `timeout`
-argument will return from the call if the job doesn't complete in the
-specified time. An argument of 0 (the default) will block
-indefinitely.
-
 #### jobs = installer.list_jobs()
 
 Return a list of all active and complete `ModelInstallJobs`.
@@ -862,31 +838,6 @@ This method is similar to `unregister()`, but also unconditionally
 deletes the corresponding model weights file(s), regardless of whether
 they are inside or outside the InvokeAI models hierarchy.
 
-
-#### path = installer.download_and_cache(remote_source, [access_token], [timeout])
-
-This utility routine will download the model file located at source,
-cache it, and return the path to the cached file. It does not attempt
-to determine the model type, probe its configuration values, or
-register it with the models database.
-
-You may provide an access token if the remote source requires
-authorization. The call will block indefinitely until the file is
-completely downloaded, cancelled or raises an error of some sort. If
-you provide a timeout (in seconds), the call will raise a
-`TimeoutError` exception if the download hasn't completed in the
-specified period.
-
-You may use this mechanism to request any type of file, not just a
-model. The file will be stored in a subdirectory of
-`INVOKEAI_ROOT/models/.cache`. If the requested file is found in the
-cache, its path will be returned without redownloading it.
-
-Be aware that the models cache is cleared of infrequently-used files
-and directories at regular intervals when the size of the cache
-exceeds the value specified in Invoke's `convert_cache` configuration
-variable.
-
 #### List[str]=installer.scan_directory(scan_dir: Path, install: bool)
 
 This method will recursively scan the directory indicated in
@@ -1177,7 +1128,7 @@ job = queue.create_download_job(
 		 event_handlers=[my_handler1, my_handler2], # if desired
 		 start=True,
 	)
-```
+ ```
  
 The `filename` argument forces the downloader to use the specified
 name for the file rather than the name provided by the remote source,
@@ -1220,13 +1171,6 @@ queue or was not created by this queue.
 This method will block until all the active jobs in the queue have
 reached a terminal state (completed, errored or cancelled).
 
-#### queue.wait_for_job(job, [timeout])
-
-This method will block until the indicated job has reached a terminal
-state (completed, errored or cancelled). If the optional timeout is
-provided, the call will block for at most timeout seconds, and raise a
-TimeoutError otherwise.
-
 #### jobs = queue.list_jobs()
 
 This will return a list of all jobs, including ones that have not yet
@@ -1505,9 +1449,9 @@ set of keys to the corresponding model config objects.
 Find all model metadata records that have the given author and return
 a set of keys to the corresponding model config objects.
 
-***
+# The remainder of this documentation is provisional, pending implementation of the Load service
 
-## The Lowdown on the ModelLoadService
+## Let's get loaded, the lowdown on ModelLoadService
 
 The `ModelLoadService` is responsible for loading a named model into
 memory so that it can be used for inference. Despite the fact that it
@@ -1521,7 +1465,7 @@ create alternative instances if you wish.
 ### Creating a ModelLoadService object
 
 The class is defined in
-`invokeai.app.services.model_load`. It is initialized with
+`invokeai.app.services.model_loader_service`. It is initialized with
 an InvokeAIAppConfig object, from which it gets configuration
 information such as the user's desired GPU and precision, and with a
 previously-created `ModelRecordServiceBase` object, from which it
@@ -1531,29 +1475,26 @@ Here is a typical initialization pattern:
 
 ```
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.model_load import ModelLoadService, ModelLoaderRegistry
+from invokeai.app.services.model_record_service import ModelRecordServiceBase
+from invokeai.app.services.model_loader_service import ModelLoadService
 
 config = InvokeAIAppConfig.get_config()
-ram_cache = ModelCache(
-	max_cache_size=config.ram_cache_size, max_vram_cache_size=config.vram_cache_size, logger=logger
-)
-convert_cache = ModelConvertCache(
-	cache_path=config.models_convert_cache_path, max_size=config.convert_cache_size
-)
-loader = ModelLoadService(
-	app_config=config,
-	ram_cache=ram_cache,
-	convert_cache=convert_cache,
-	registry=ModelLoaderRegistry
-)
+store = ModelRecordServiceBase.open(config)
+loader = ModelLoadService(config, store)
 ```
 
-### load_model(model_config, [submodel_type], [context]) -> LoadedModel
+Note that we are relying on the contents of the application
+configuration to choose the implementation of
+`ModelRecordServiceBase`.
 
-The `load_model()` method takes an `AnyModelConfig` returned by
-`ModelRecordService.get_model()` and returns the corresponding loaded
+### get_model(key, [submodel_type], [context]) -> ModelInfo:
+
+*** TO DO: change to get_model(key, context=None, **kwargs)
+
+The `get_model()` method, like its similarly-named cousin in
+`ModelRecordService`, receives the unique key that identifies the
 model.  It loads the model into memory, gets the model ready for use,
-and returns a `LoadedModel` object.
+and returns a `ModelInfo` object. 
 
 The optional second argument, `subtype` is a `SubModelType` string
 enum, such as "vae". It is mandatory when used with a main model, and
@@ -1563,45 +1504,46 @@ The optional third argument, `context` can be provided by
 an invocation to trigger model load event reporting. See below for
 details.
 
-The returned `LoadedModel` object contains a copy of the configuration
-record returned by the model record `get_model()` method, as well as
-the in-memory loaded model:
+The returned `ModelInfo` object shares some fields in common with
+`ModelConfigBase`, but is otherwise a completely different beast:
 
-
-| **Attribute Name** | **Type**        |  **Description** |
+| **Field Name** | **Type**        |  **Description** |
 |----------------|-----------------|------------------|
-| `config`       | AnyModelConfig         | A copy of the model's configuration record for retrieving base type, etc. |
-| `model`        | AnyModel               | The instantiated model (details below) |
-| `locker`       | ModelLockerBase        | A context manager that mediates the movement of the model into VRAM |
+| `key`          | str                    | The model key derived from the ModelRecordService database |
+| `name`         | str                    | Name of this model |
+| `base_model`   | BaseModelType          | Base model for this model |
+| `type`         | ModelType or SubModelType   | Either the model type (non-main) or the submodel type (main models)|
+| `location`     | Path or str            | Location of the model on the filesystem |
+| `precision`    | torch.dtype            | The torch.precision to use for inference |
+| `context`      | ModelCache.ModelLocker | A context class used to lock the model in VRAM while in use |
 
-Because the loader can return multiple model types, it is typed to
-return `AnyModel`, a Union `ModelMixin`, `torch.nn.Module`,
-`IAIOnnxRuntimeModel`, `IPAdapter`, `IPAdapterPlus`, and
-`EmbeddingModelRaw`. `ModelMixin` is the base class of all diffusers
-models, `EmbeddingModelRaw` is used for LoRA and TextualInversion
-models. The others are obvious.
+The types for `ModelInfo` and `SubModelType` can be imported from
+`invokeai.app.services.model_loader_service`.
 
-
-`LoadedModel` acts as a context manager. The context loads the model
-into the execution device (e.g. VRAM on CUDA systems), locks the model
-in the execution device for the duration of the context, and returns
-the model. Use it like this:
+To use the model, you use the `ModelInfo` as a context manager using
+the following pattern:
 
 ```
-model_info = loader.get_model_by_key('f13dd932c0c35c22dcb8d6cda4203764', SubModelType('vae'))
+model_info = loader.get_model('f13dd932c0c35c22dcb8d6cda4203764', SubModelType('vae'))
 with model_info as vae:
 	image = vae.decode(latents)[0]
 ```
 
-`get_model_by_key()` may raise any of the following exceptions:
+The `vae` model will stay locked in the GPU during the period of time
+it is in the context manager's scope.
 
-- `UnknownModelException`   -- key not in database
-- `ModelNotFoundException`  -- key in database but model not found at path
-- `NotImplementedException` -- the loader doesn't know how to load this type of model
+`get_model()` may raise any of the following exceptions:
+
+- `UnknownModelException`  -- key not in database
+- `ModelNotFoundException` -- key in database but model not found at path
+- `InvalidModelException`  -- the model is guilty of a variety of sins
   
+** TO DO: ** Resolve discrepancy between ModelInfo.location and
+ModelConfig.path.
+
 ### Emitting model loading events
 
-When the `context` argument is passed to `load_model_*()`, it will
+When the `context` argument is passed to `get_model()`, it will
 retrieve the invocation event bus from the passed `InvocationContext`
 object to emit events on the invocation bus. The two events are
 "model_load_started" and "model_load_completed". Both carry the
@@ -1614,174 +1556,10 @@ payload=dict(
 	queue_batch_id=queue_batch_id,
 	graph_execution_state_id=graph_execution_state_id,
 	model_key=model_key,
-	submodel_type=submodel,
+	submodel=submodel,
 	hash=model_info.hash,
 	location=str(model_info.location),
 	precision=str(model_info.precision),
 )
 ```
 
-### Adding Model Loaders
-
-Model loaders are small classes that inherit from the `ModelLoader`
-base class. They typically implement one method `_load_model()` whose
-signature is:
-
-```
-def _load_model(
-    self,
-    model_path: Path,
-    model_variant: Optional[ModelRepoVariant] = None,
-    submodel_type: Optional[SubModelType] = None,
-) -> AnyModel:
-```
-
-`_load_model()` will be passed the path to the model on disk, an
-optional repository variant (used by the diffusers loaders to select,
-e.g.  the `fp16` variant, and an optional submodel_type for main and
-onnx models.
-
-To install a new loader, place it in
-`invokeai/backend/model_manager/load/model_loaders`. Inherit from
-`ModelLoader` and use the `@ModelLoaderRegistry.register()` decorator to
-indicate what type of models the loader can handle.
-
-Here is a complete example from `generic_diffusers.py`, which is able
-to load several different diffusers types:
-
-```
-from pathlib import Path
-from typing import Optional
-
-from invokeai.backend.model_manager import (
-    AnyModel,
-    BaseModelType,
-    ModelFormat,
-    ModelRepoVariant,
-    ModelType,
-    SubModelType,
-)
-from .. import ModelLoader, ModelLoaderRegistry
-
-
-@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.CLIPVision, format=ModelFormat.Diffusers)
-@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.T2IAdapter, format=ModelFormat.Diffusers)
-class GenericDiffusersLoader(ModelLoader):
-    """Class to load simple diffusers models."""
-
-    def _load_model(
-        self,
-        model_path: Path,
-        model_variant: Optional[ModelRepoVariant] = None,
-        submodel_type: Optional[SubModelType] = None,
-    ) -> AnyModel:
-        model_class = self._get_hf_load_class(model_path)
-        if submodel_type is not None:
-            raise Exception(f"There are no submodels in models of type {model_class}")
-        variant = model_variant.value if model_variant else None
-        result: AnyModel = model_class.from_pretrained(model_path, torch_dtype=self._torch_dtype, variant=variant)  # type: ignore
-        return result
-```
-
-Note that a loader can register itself to handle several different
-model types. An exception will be raised if more than one loader tries
-to register the same model type.
-
-#### Conversion
-
-Some models require conversion to diffusers format before they can be
-loaded. These loaders should override two additional methods:
-
-```
-_needs_conversion(self, config: AnyModelConfig, model_path: Path, dest_path: Path) -> bool
-_convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Path) -> Path:
-```
-
-The first method accepts the model configuration, the path to where
-the unmodified model is currently installed, and a proposed
-destination for the converted model. This method returns True if the
-model needs to be converted. It typically does this by comparing the
-last modification time of the original model file to the modification
-time of the converted model. In some cases you will also want to check
-the modification date of the configuration record, in the event that
-the user has changed something like the scheduler prediction type that
-will require the model to be re-converted. See `controlnet.py` for an
-example of this logic.
-
-The second method accepts the model configuration, the path to the
-original model on disk, and the desired output path for the converted
-model. It does whatever it needs to do to get the model into diffusers
-format, and returns the Path of the resulting model. (The path should
-ordinarily be the same as `output_path`.)
-
-## The ModelManagerService object
-
-For convenience, the API provides a `ModelManagerService` object which
-gives a single point of access to the major model manager
-services. This object is created at initialization time and can be
-found in the global `ApiDependencies.invoker.services.model_manager`
-object, or in `context.services.model_manager` from within an
-invocation.
-
-In the examples below, we have retrieved the manager using:
-```
-mm = ApiDependencies.invoker.services.model_manager
-```
-
-The following properties and methods will be available:
-
-### mm.store
-
-This retrieves the `ModelRecordService` associated with the
-manager. Example:
-
-```
-configs = mm.store.get_model_by_attr(name='stable-diffusion-v1-5')
-```
-
-### mm.install
-
-This retrieves the `ModelInstallService` associated with the manager.
-Example:
-
-```
-job = mm.install.heuristic_import(`https://civitai.com/models/58390/detail-tweaker-lora-lora`)
-```
-
-### mm.load
-
-This retrieves the `ModelLoaderService` associated with the manager. Example:
-
-```
-configs = mm.store.get_model_by_attr(name='stable-diffusion-v1-5')
-assert len(configs) > 0
-
-loaded_model = mm.load.load_model(configs[0])
-```
-
-The model manager also offers a few convenience shortcuts for loading
-models:
-
-### mm.load_model_by_config(model_config, [submodel], [context]) -> LoadedModel
-
-Same as `mm.load.load_model()`.
-
-### mm.load_model_by_attr(model_name, base_model, model_type, [submodel], [context]) -> LoadedModel
-
-This accepts the combination of the model's name, type and base, which
-it passes to the model record config store for retrieval. If a unique
-model config is found, this method returns a `LoadedModel`. It can
-raise the following exceptions:
-
-```
-UnknownModelException -- model with these attributes not known
-NotImplementedException -- the loader doesn't know how to load this type of model
-ValueError -- more than one model matches this combination of base/type/name
-```
-
-### mm.load_model_by_key(key, [submodel], [context]) -> LoadedModel
-
-This method takes a model key, looks it up using the
-`ModelRecordServiceBase` object in `mm.store`, and passes the returned
-model configuration to `load_model_by_config()`.  It may raise a
-`NotImplementedException`.

docs/nodes/INVOCATION_API.md

@@ -1,45 +0,0 @@
-# Invocation API
-
-Each invocation's `invoke` method is provided a single arg - the Invocation
-Context.
-
-This object provides access to various methods, used to interact with the
-application. Loading and saving images, logging messages, etc.
-
-!!! warning ""
-
-    This API may shift slightly until the release of v4.0.0 as we work through a few final updates to the Model Manager.
-
-```py
-class MyInvocation(BaseInvocation):
-  ...
-  def invoke(self, context: InvocationContext) -> ImageOutput:
-      image_pil = context.images.get_pil(image_name)
-      # Do something to the image
-      image_dto = context.images.save(image_pil)
-      # Log a message
-      context.logger.info(f"Did something cool, image saved!")
-      ...
-```
-
-<!-- prettier-ignore-start -->
-::: invokeai.app.services.shared.invocation_context.InvocationContext
-    options:
-        members: false
-
-::: invokeai.app.services.shared.invocation_context.ImagesInterface
-
-::: invokeai.app.services.shared.invocation_context.TensorsInterface
-
-::: invokeai.app.services.shared.invocation_context.ConditioningInterface
-
-::: invokeai.app.services.shared.invocation_context.ModelsInterface
-
-::: invokeai.app.services.shared.invocation_context.LoggerInterface
-
-::: invokeai.app.services.shared.invocation_context.ConfigInterface
-
-::: invokeai.app.services.shared.invocation_context.UtilInterface
-
-::: invokeai.app.services.shared.invocation_context.BoardsInterface
-<!-- prettier-ignore-end -->

docs/nodes/NODES_MIGRATION_V3_V4.md

@@ -1,148 +0,0 @@
-# Invoke v4.0.0 Nodes API Migration guide
-
-Invoke v4.0.0 is versioned as such due to breaking changes to the API utilized
-by nodes, both core and custom.
-
-## Motivation
-
-Prior to v4.0.0, the `invokeai` python package has not be set up to be utilized
-as a library. That is to say, it didn't have any explicitly public API, and node
-authors had to work with the unstable internal application API.
-
-v4.0.0 introduces a stable public API for nodes.
-
-## Changes
-
-There are two node-author-facing changes:
-
-1. Import Paths
-1. Invocation Context API
-
-### Import Paths
-
-All public objects are now exported from `invokeai.invocation_api`:
-
-```py
-# Old
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    InputField,
-    InvocationContext,
-    invocation,
-)
-from invokeai.app.invocations.primitives import ImageField
-
-# New
-from invokeai.invocation_api import (
-    BaseInvocation,
-    ImageField,
-    InputField,
-    InvocationContext,
-    invocation,
-)
-```
-
-It's possible that we've missed some classes you need in your node. Please let
-us know if that's the case.
-
-### Invocation Context API
-
-Most nodes utilize the Invocation Context, an object that is passed to the
-`invoke` that provides access to data and services a node may need.
-
-Until now, that object and the services it exposed were internal. Exposing them
-to nodes means that changes to our internal implementation could break nodes.
-The methods on the services are also often fairly complicated and allowed nodes
-to footgun.
-
-In v4.0.0, this object has been refactored to be much simpler.
-
-See [INVOCATION_API](./INVOCATION_API.md) for full details of the API.
-
-!!! warning ""
-
-    This API may shift slightly until the release of v4.0.0 as we work through a few final updates to the Model Manager.
-
-#### Improved Service Methods
-
-The biggest offender was the image save method:
-
-```py
-# Old
-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,
-)
-
-# New
-image_dto = context.images.save(image=image)
-```
-
-Other methods are simplified, or enhanced with additional functionality:
-
-```py
-# Old
-image = context.services.images.get_pil_image(image_name)
-
-# New
-image = context.images.get_pil(image_name)
-image_cmyk = context.images.get_pil(image_name, "CMYK")
-```
-
-We also had some typing issues around tensors:
-
-```py
-# Old
-# `latents` typed as `torch.Tensor`, but could be `ConditioningFieldData`
-latents = context.services.latents.get(self.latents.latents_name)
-# `data` typed as `torch.Tenssor,` but could be `ConditioningFieldData`
-context.services.latents.save(latents_name, data)
-
-# New - separate methods for tensors and conditioning data w/ correct typing
-# Also, the service generates the names
-tensor_name = context.tensors.save(tensor)
-tensor = context.tensors.load(tensor_name)
-# For conditioning
-cond_name = context.conditioning.save(cond_data)
-cond_data = context.conditioning.load(cond_name)
-```
-
-#### Output Construction
-
-Core Outputs have builder functions right on them - no need to manually
-construct these objects, or use an extra utility:
-
-```py
-# Old
-image_output = ImageOutput(
-    image=ImageField(image_name=image_dto.image_name),
-    width=image_dto.width,
-    height=image_dto.height,
-)
-latents_output = build_latents_output(latents_name=name, latents=latents, seed=None)
-noise_output = NoiseOutput(
-    noise=LatentsField(latents_name=latents_name, seed=seed),
-    width=latents.size()[3] * 8,
-    height=latents.size()[2] * 8,
-)
-cond_output = ConditioningOutput(
-    conditioning=ConditioningField(
-        conditioning_name=conditioning_name,
-    ),
-)
-
-# New
-image_output = ImageOutput.build(image_dto)
-latents_output = LatentsOutput.build(latents_name=name, latents=noise, seed=self.seed)
-noise_output = NoiseOutput.build(latents_name=name, latents=noise, seed=self.seed)
-cond_output = ConditioningOutput.build(conditioning_name)
-```
-
-You can still create the objects using constructors if you want, but we suggest
-using the builder methods.

docs/nodes/communityNodes.md

@@ -32,7 +32,6 @@ To use a community workflow, download the the `.json` node graph file and load i
     + [Image to Character Art Image Nodes](#image-to-character-art-image-nodes)
     + [Image Picker](#image-picker)
     + [Image Resize Plus](#image-resize-plus)
-    + [Latent Upscale](#latent-upscale)
     + [Load Video Frame](#load-video-frame)
     + [Make 3D](#make-3d)
     + [Mask Operations](#mask-operations)
@@ -291,13 +290,6 @@ View:
 </br><img src="https://raw.githubusercontent.com/VeyDlin/image-resize-plus-node/master/.readme/node.png" width="500" />
 
 
---------------------------------
-### Latent Upscale
-
-**Description:** This node uses a small (~2.4mb) model to upscale the latents used in a Stable Diffusion 1.5 or Stable Diffusion XL image generation, rather than the typical interpolation method, avoiding the traditional downsides of the latent upscale technique.
-
-**Node Link:** [https://github.com/gogurtenjoyer/latent-upscale](https://github.com/gogurtenjoyer/latent-upscale)
-
 --------------------------------
 ### Load Video Frame
 
@@ -354,21 +346,12 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 **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
-- `Metadata To Bool` - Extracts Bool types from metadata
-- `Metadata To Model` - Extracts model types from metadata
-- `Metadata To SDXL Model` - Extracts SDXL model types from metadata
-- `Metadata To LoRAs` - Extracts Loras from metadata. 
-- `Metadata To SDXL LoRAs` - Extracts SDXL Loras from metadata
-- `Metadata To ControlNets` - Extracts ControNets from metadata
-- `Metadata To IP-Adapters` - Extracts IP-Adapters from metadata
-- `Metadata To T2I-Adapters` - Extracts T2I-Adapters from metadata
-- `Denoise Latents + Metadata` - This is an inherited version of the existing `Denoise Latents` node but with a metadata input and output. 
+- `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
 

docs/nodes/defaultNodes.md

@@ -19,8 +19,6 @@ their descriptions.
 | Conditioning Primitive                                        | A conditioning tensor primitive value                                                                                                                |
 | Content Shuffle Processor                                     | Applies content shuffle processing to image                                                                                                          |
 | ControlNet                                                    | Collects ControlNet info to pass to other nodes                                                                                                      |
-| Create Denoise Mask                                           | Converts a greyscale or transparency image into a mask for denoising.                                                                                |
-| Create Gradient Mask                                          | Creates a mask for Gradient ("soft", "differential") inpainting that gradually expands during denoising. Improves edge coherence.                    |
 | Denoise Latents                                               | Denoises noisy latents to decodable images                                                                                                           |
 | Divide Integers                                               | Divides two numbers                                                                                                                                  |
 | Dynamic Prompt                                                | Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator                                                                      |

docs/requirements-mkdocs.txt

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

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;
+  }

installer/create_installer.sh

@@ -2,18 +2,22 @@
 
 set -e
 
-BCYAN="\033[1;36m"
-BYELLOW="\033[1;33m"
-BGREEN="\033[1;32m"
-BRED="\033[1;31m"
-RED="\033[31m"
-RESET="\033[0m"
+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 [[ ! -z "${VIRTUAL_ENV}" ]]; then
+if [[ -v "VIRTUAL_ENV" ]]; then
     # we can't just call 'deactivate' because this function is not exported
     # to the environment of this script from the bash process that runs the script
     echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
@@ -22,63 +26,31 @@ fi
 
 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=$(
     cd ..
-    python3 -c "from invokeai.version import __version__ as version; print(version)"
+    python -c "from invokeai.version import __version__ as version; print(version)"
 )
-VERSION="v${VERSION}"
-
-if [[ ! -z ${CI} ]]; then
-    echo
-    echo -e "${BCYAN}CI environment detected${RESET}"
-    echo
-else
-    echo
-    echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
-    echo "The current working directory is $(pwd)"
-    read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
-    echo
-fi
+PATCH=""
+VERSION="v${VERSION}${PATCH}"
 
 echo -e "${BGREEN}HEAD${RESET}:"
 git_show HEAD
 echo
 
-# ---------------------- FRONTEND ----------------------
-
-pushd ../invokeai/frontend/web >/dev/null
-echo "Installing frontend dependencies..."
-echo
-pnpm i --frozen-lockfile
-echo
-if [[ ! -z ${CI} ]]; then
-    echo "Building frontend without checks..."
-    # In CI, we have already done the frontend checks and can just build
-    pnpm vite build
-else
-    echo "Running checks and building frontend..."
-    # This runs all the frontend checks and builds
-    pnpm build
-fi
-echo
-popd
-
-# ---------------------- BACKEND ----------------------
-
-echo
-echo "Building wheel..."
-echo
-
-# 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 [[ $(python3 -c 'from importlib.util import find_spec; print(find_spec("build") is None)') == "True" ]]; then
-    pip install --user build
-fi
-
-rm -rf ../build
-
-python3 -m build --outdir dist/ ../.
-
 # ----------------------
 
 echo
@@ -106,28 +78,10 @@ chmod a+x InvokeAI-Installer/install.sh
 cp install.bat.in InvokeAI-Installer/install.bat
 cp WinLongPathsEnabled.reg InvokeAI-Installer/
 
-FILENAME=InvokeAI-installer-$VERSION.zip
-
 # Zip everything up
-zip -r ${FILENAME} InvokeAI-Installer
+zip -r InvokeAI-installer-$VERSION.zip InvokeAI-Installer
 
-echo
-echo -e "${BGREEN}Built installer: ./${FILENAME}${RESET}"
-echo -e "${BGREEN}Built PyPi distribution: ./dist${RESET}"
-
-# clean up, but only if we are not in a github action
-if [[ -z ${CI} ]]; then
-    echo
-    echo "Cleaning up intermediate build files..."
-    rm -rf InvokeAI-Installer tmp ../invokeai/frontend/web/dist/
-fi
-
-if [[ ! -z ${CI} ]]; then
-    echo
-    echo "Setting GitHub action outputs..."
-    echo "INSTALLER_FILENAME=${FILENAME}" >>$GITHUB_OUTPUT
-    echo "INSTALLER_PATH=installer/${FILENAME}" >>$GITHUB_OUTPUT
-    echo "DIST_PATH=installer/dist/" >>$GITHUB_OUTPUT
-fi
+# clean up
+rm -rf InvokeAI-Installer tmp dist ../invokeai/frontend/web/dist/
 
 exit 0

installer/tag_release.sh

@@ -2,12 +2,12 @@
 
 set -e
 
-BCYAN="\033[1;36m"
-BYELLOW="\033[1;33m"
-BGREEN="\033[1;32m"
-BRED="\033[1;31m"
-RED="\033[31m"
-RESET="\033[0m"
+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
@@ -23,40 +23,49 @@ function git_show {
 
 VERSION=$(
     cd ..
-    python3 -c "from invokeai.version import __version__ as version; print(version)"
+    python -c "from invokeai.version import __version__ as version; print(version)"
 )
 PATCH=""
+MAJOR_VERSION=$(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 "${BGREEN}git remote -v${RESET}:"
-git remote -v
-echo
-
-echo -e -n "Create tags ${BCYAN}${VERSION}${RESET} @ ${BGREEN}HEAD${RESET}, ${RED}deleting existing tags on origin remote${RESET}? "
+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}${RESET} tag on origin remote..."
-    git push origin :refs/tags/$VERSION
+    echo -e "Deleting ${BCYAN}${VERSION}${RESET} tag on remote..."
+    git push --delete origin $VERSION
 
-    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${VERSION}${RESET} on locally..."
+    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 "Pushing updated tags to origin remote..."
+    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

invokeai/app/api/dependencies.py

@@ -4,9 +4,11 @@ from logging import Logger
 
 import torch
 
+from invokeai.app.services.item_storage.item_storage_memory import ItemStorageMemory
 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.model_manager.metadata import ModelMetadataStore
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
@@ -15,22 +17,24 @@ 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.model_install import ModelInstallService
 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.graph import GraphExecutionState
 from ..services.urls.urls_default import LocalUrlService
 from ..services.workflow_records.workflow_records_sqlite import SqliteWorkflowRecordsStorage
 from .events import FastAPIEventService
@@ -82,7 +86,7 @@ class ApiDependencies:
         board_records = SqliteBoardRecordStorage(db=db)
         boards = BoardService()
         events = FastAPIEventService(event_handler_id)
-        bulk_download = BulkDownloadService()
+        graph_execution_manager = ItemStorageMemory[GraphExecutionState]()
         image_records = SqliteImageRecordStorage(db=db)
         images = ImageService()
         invocation_cache = MemoryInvocationCache(max_cache_size=config.node_cache_size)
@@ -92,16 +96,21 @@ class ApiDependencies:
         conditioning = ObjectSerializerForwardCache(
             ObjectSerializerDisk[ConditioningFieldData](output_folder / "conditioning", ephemeral=True)
         )
+        model_manager = ModelManagerService(config, logger)
+        model_record_service = ModelRecordServiceSQL(db=db)
         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),
+        metadata_store = ModelMetadataStore(db=db)
+        model_install_service = ModelInstallService(
+            app_config=config,
+            record_store=model_record_service,
             download_queue=download_queue_service,
-            events=events,
+            metadata_store=metadata_store,
+            event_bus=events,
         )
         names = SimpleNameService()
         performance_statistics = InvocationStatsService()
+        processor = DefaultInvocationProcessor()
+        queue = MemoryInvocationQueue()
         session_processor = DefaultSessionProcessor()
         session_queue = SqliteSessionQueue(db=db)
         urls = LocalUrlService()
@@ -112,18 +121,22 @@ 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,
             image_files=image_files,
             image_records=image_records,
             images=images,
             invocation_cache=invocation_cache,
             logger=logger,
             model_manager=model_manager,
+            model_records=model_record_service,
             download_queue=download_queue_service,
+            model_install=model_install_service,
             names=names,
             performance_statistics=performance_statistics,
+            processor=processor,
+            queue=queue,
             session_processor=session_processor,
             session_queue=session_queue,
             urls=urls,

invokeai/app/api/routers/download_queue.py

@@ -36,7 +36,7 @@ async def list_downloads() -> List[DownloadJob]:
         400: {"description": "Bad request"},
     },
 )
-async def prune_downloads() -> Response:
+async def prune_downloads():
     """Prune completed and errored jobs."""
     queue = ApiDependencies.invoker.services.download_queue
     queue.prune_jobs()
@@ -55,7 +55,7 @@ async def 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)
+    return queue.download(source, dest, priority, access_token)
 
 
 @download_queue_router.get(
@@ -87,7 +87,7 @@ async def get_download_job(
 )
 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
@@ -105,7 +105,7 @@ async def cancel_download_job(
         204: {"description": "Download jobs have been cancelled"},
     },
 )
-async def cancel_all_download_jobs() -> Response:
+async def cancel_all_download_jobs():
     """Cancel all download jobs."""
     ApiDependencies.invoker.services.download_queue.cancel_all_jobs()
     return Response(status_code=204)

invokeai/app/api/routers/images.py

@@ -2,7 +2,7 @@ import io
 import traceback
 from typing import Optional
 
-from fastapi import BackgroundTasks, Body, HTTPException, Path, Query, Request, Response, UploadFile
+from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
 from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
 from PIL import Image
@@ -375,67 +375,16 @@ async def unstar_images_in_list(
 
 class ImagesDownloaded(BaseModel):
     response: Optional[str] = Field(
-        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"
+        description="If defined, the message to display to the user when images begin downloading"
     )
 
 
-@images_router.post(
-    "/download", operation_id="download_images_from_list", response_model=ImagesDownloaded, status_code=202
-)
+@images_router.post("/download", operation_id="download_images_from_list", response_model=ImagesDownloaded)
 async def download_images_from_list(
-    background_tasks: BackgroundTasks,
-    image_names: Optional[list[str]] = Body(
-        default=None, description="The list of names of images to download", embed=True
-    ),
+    image_names: list[str] = Body(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", embed=True
+        default=None, description="The board from which image should be downloaded from", embed=True
     ),
 ) -> ImagesDownloaded:
-    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)
+    # return ImagesDownloaded(response="Your images are downloading")
+    raise HTTPException(status_code=501, detail="Endpoint is not yet implemented")

invokeai/app/api/routers/model_manager.py

@@ -1,796 +0,0 @@
-# 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_metadata.metadata_store_base import ModelMetadataChanges
-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.metadata.metadata_base import BaseMetadata
-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.patch(
-    "/i/{key}/metadata",
-    operation_id="update_model_metadata",
-    responses={
-        201: {
-            "description": "The model metadata was updated successfully",
-            "content": {"application/json": {"example": example_model_metadata}},
-        },
-        400: {"description": "Bad request"},
-    },
-)
-async def update_model_metadata(
-    key: str = Path(description="Key of the model repo metadata to fetch."),
-    changes: ModelMetadataChanges = Body(description="The changes"),
-) -> Optional[AnyModelRepoMetadata]:
-    """Updates or creates a model metadata object."""
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    metadata_store = ApiDependencies.invoker.services.model_manager.store.metadata_store
-
-    try:
-        original_metadata = record_store.get_metadata(key)
-        if original_metadata:
-            if changes.default_settings:
-                original_metadata.default_settings = changes.default_settings
-
-            metadata_store.update_metadata(key, original_metadata)
-        else:
-            metadata_store.add_metadata(
-                key, BaseMetadata(name="", author="", default_settings=changes.default_settings)
-            )
-    except Exception as e:
-        raise HTTPException(
-            status_code=500,
-            detail=f"An error occurred while updating the model metadata: {e}",
-        )
-
-    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"),
-    inplace: Optional[bool] = Query(description="Whether or not to install a local model in place", default=False),
-    # 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,
-            inplace=bool(inplace),
-        )
-        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

@@ -0,0 +1,472 @@
+# Copyright (c) 2023 Lincoln D. Stein
+"""FastAPI route for model configuration records."""
+
+import pathlib
+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
+from starlette.exceptions import HTTPException
+from typing_extensions import Annotated
+
+from invokeai.app.services.model_install import ModelInstallJob, ModelSource
+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,
+    ModelFormat,
+    ModelType,
+)
+from invokeai.backend.model_manager.merge import MergeInterpolationMethod, ModelMerger
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
+
+from ..dependencies import ApiDependencies
+
+model_records_router = APIRouter(prefix="/v1/model/record", tags=["model_manager_v2_unstable"])
+
+
+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]
+
+
+@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"),
+    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_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, 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_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.get("/meta", 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."""
+    return ApiDependencies.invoker.services.model_records.list_models(page=page, per_page=per_page, order_by=order_by)
+
+
+@model_records_router.get(
+    "/meta/i/{key}",
+    operation_id="get_model_metadata",
+    responses={
+        200: {"description": "Success"},
+        400: {"description": "Bad request"},
+        404: {"description": "No metadata available"},
+    },
+)
+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_records
+    result = record_store.get_metadata(key)
+    if not result:
+        raise HTTPException(status_code=404, detail="No metadata for a model with this key")
+    return result
+
+
+@model_records_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_records
+    return record_store.list_tags()
+
+
+@model_records_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_records
+    results = record_store.search_by_metadata_tag(tags)
+    return ModelsList(models=results)
+
+
+@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 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_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_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)
+
+
+@model_records_router.post(
+    "/import",
+    operation_id="import_model_record",
+    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 import_model(
+    source: ModelSource,
+    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,
+    ),
+) -> ModelInstallJob:
+    """Add a model using its local path, repo_id, or remote URL.
+
+    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.
+
+    The source object is a discriminated Union of LocalModelSource,
+    HFModelSource and URLModelSource. Set the "type" field to the
+    appropriate value:
+
+    * To install a local path using LocalModelSource, pass a source of form:
+      `{
+        "type": "local",
+        "path": "/path/to/model",
+        "inplace": false
+      }`
+       The "inplace" flag, if true, will register the model in place in its
+       current filesystem location. Otherwise, the model will be copied
+       into the InvokeAI models directory.
+
+    * To install a HuggingFace repo_id using HFModelSource, pass a source of form:
+      `{
+        "type": "hf",
+        "repo_id": "stabilityai/stable-diffusion-2.0",
+        "variant": "fp16",
+        "subfolder": "vae",
+        "access_token": "f5820a918aaf01"
+      }`
+     The `variant`, `subfolder` and `access_token` fields are optional.
+
+    * To install a remote model using an arbitrary URL, pass:
+      `{
+        "type": "url",
+        "url": "http://www.civitai.com/models/123456",
+        "access_token": "f5820a918aaf01"
+      }`
+    The `access_token` field is optonal
+
+    The model's configuration record will be probed and filled in
+    automatically.  To override the default guesses, pass "metadata"
+    with a Dict containing the attributes you wish to override.
+
+    Installation occurs in the background. Either use list_model_install_jobs()
+    to poll for completion, or listen on the event bus for the following events:
+
+      "model_install_running"
+      "model_install_completed"
+      "model_install_error"
+
+    On successful completion, the event's payload will contain the field "key"
+    containing the installed ID of the model. On an error, the event's payload
+    will contain the fields "error_type" and "error" describing the nature of the
+    error and its traceback, respectively.
+
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_install
+        result: ModelInstallJob = installer.import_model(
+            source=source,
+            config=config,
+        )
+        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_records_router.get(
+    "/import",
+    operation_id="list_model_install_jobs",
+)
+async def list_model_install_jobs() -> List[ModelInstallJob]:
+    """Return list of model install jobs."""
+    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_install.list_jobs()
+    return jobs
+
+
+@model_records_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."""
+    try:
+        return ApiDependencies.invoker.services.model_install.get_job_by_id(id)
+    except ValueError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_records_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_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_records_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_install.prune_jobs()
+    return Response(status_code=204)
+
+
+@model_records_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_install.sync_to_config()
+    return Response(status_code=204)
+
+
+@model_records_router.put(
+    "/merge",
+    operation_id="merge",
+)
+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.
+
+        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]
+    """
+    print(f"here i am, keys={keys}")
+    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_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/models.py

@@ -0,0 +1,427 @@
+# 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

@@ -0,0 +1,276 @@
+# 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/sockets.py

@@ -12,26 +12,16 @@ 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="/ws/socket.io")
         app.mount("/ws", self.__app)
 
-        self.__sio.on(self.__sub_queue, handler=self._handle_sub_queue)
-        self.__sio.on(self.__unsub_queue, handler=self._handle_unsub_queue)
+        self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)
+        self.__sio.on("unsubscribe_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(
             event=event[1]["event"],
@@ -49,18 +39,3 @@ class SocketIO:
 
     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

@@ -2,7 +2,6 @@
 # which are imported/used before parse_args() is called will get the default config values instead of the
 # values from the command line or config file.
 import sys
-from contextlib import asynccontextmanager
 
 from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
 from invokeai.version.invokeai_version import __version__
@@ -49,8 +48,10 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
         boards,
         download_queue,
         images,
-        model_manager,
+        model_records,
+        models,
         session_queue,
+        sessions,
         utilities,
         workflows,
     )
@@ -72,25 +73,9 @@ logger = InvokeAILogger.get_logger(config=app_config)
 mimetypes.add_type("application/javascript", ".js")
 mimetypes.add_type("text/css", ".css")
 
-
-@asynccontextmanager
-async def lifespan(app: FastAPI):
-    # Add startup event to load dependencies
-    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
-    yield
-    # Shut down threads
-    ApiDependencies.shutdown()
-
-
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
-app = FastAPI(
-    title="Invoke - Community Edition",
-    docs_url=None,
-    redoc_url=None,
-    separate_input_output_schemas=False,
-    lifespan=lifespan,
-)
+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)
@@ -113,9 +98,24 @@ app.add_middleware(
 app.add_middleware(GZipMiddleware, minimum_size=1000)
 
 
+# Add startup event to load dependencies
+@app.on_event("startup")
+async def startup_event() -> None:
+    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
+
+
+# Shut down threads
+@app.on_event("shutdown")
+async def shutdown_event() -> None:
+    ApiDependencies.shutdown()
+
+
 # Include all routers
+app.include_router(sessions.session_router, prefix="/api")
+
 app.include_router(utilities.utilities_router, prefix="/api")
-app.include_router(model_manager.model_manager_router, prefix="/api")
+app.include_router(models.models_router, prefix="/api")
+app.include_router(model_records.model_records_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")
@@ -153,8 +153,6 @@ 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(
@@ -177,24 +175,23 @@ 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"
 
-    # 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():
+    from invokeai.backend.model_management.models import get_model_config_enums
 
-    #     if model_config_name in openapi_schema["components"]["schemas"]:
-    #         # print(f"Config with name {name} already defined")
-    #         continue
+    for model_config_format_enum in set(get_model_config_enums()):
+        name = model_config_format_enum.__qualname__
 
-    #     openapi_schema["components"]["schemas"][model_config_name] = {
-    #         "title": model_config_name,
-    #         "description": "An enumeration.",
-    #         "type": "string",
-    #         "enum": [v.value for v in enum_set],
-    #     }
+        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],
+        }
 
     app.openapi_schema = openapi_schema
     return app.openapi_schema

invokeai/app/invocations/baseinvocation.py

@@ -8,26 +8,13 @@ import warnings
 from abc import ABC, abstractmethod
 from enum import Enum
 from inspect import signature
-from typing import (
-    TYPE_CHECKING,
-    Annotated,
-    Any,
-    Callable,
-    ClassVar,
-    Iterable,
-    Literal,
-    Optional,
-    Type,
-    TypeVar,
-    Union,
-    cast,
-)
+from types import UnionType
+from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union, cast
 
 import semver
-from pydantic import BaseModel, ConfigDict, Field, TypeAdapter, create_model
+from pydantic import BaseModel, ConfigDict, Field, create_model
 from pydantic.fields import FieldInfo
 from pydantic_core import PydanticUndefined
-from typing_extensions import TypeAliasType
 
 from invokeai.app.invocations.fields import (
     FieldKind,
@@ -97,7 +84,6 @@ class BaseInvocationOutput(BaseModel):
     """
 
     _output_classes: ClassVar[set[BaseInvocationOutput]] = set()
-    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def register_output(cls, output: BaseInvocationOutput) -> None:
@@ -110,14 +96,10 @@ class BaseInvocationOutput(BaseModel):
         return cls._output_classes
 
     @classmethod
-    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
+    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]
 
     @classmethod
     def get_output_types(cls) -> Iterable[str]:
@@ -166,7 +148,6 @@ class BaseInvocation(ABC, BaseModel):
     """
 
     _invocation_classes: ClassVar[set[BaseInvocation]] = set()
-    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def get_type(cls) -> str:
@@ -179,14 +160,10 @@ class BaseInvocation(ABC, BaseModel):
         cls._invocation_classes.add(invocation)
 
     @classmethod
-    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
+    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]
 
     @classmethod
     def get_invocations(cls) -> Iterable[BaseInvocation]:

invokeai/app/invocations/compel.py

@@ -1,33 +1,35 @@
-from typing import Iterator, List, Optional, Tuple, Union, cast
+from typing import List, Optional, Union
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
-from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
 
 from invokeai.app.invocations.fields import (
-    ConditioningField,
     FieldDescriptions,
     Input,
     InputField,
-    MaskField,
     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 .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.model_management.models import ModelNotFoundException, ModelType
+from ...backend.util.devices import torch_dtype
+from ..util.ti_utils import extract_ti_triggers_from_prompt
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    invocation,
+    invocation_output,
+)
 from .model import ClipField
 
 # unconditioned: Optional[torch.Tensor]
@@ -44,7 +46,7 @@ from .model import ClipField
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.2.0",
+    version="1.0.1",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -59,34 +61,43 @@ class CompelInvocation(BaseInvocation):
         description=FieldDescriptions.clip,
         input=Input.Connection,
     )
-    mask: Optional[MaskField] = InputField(
-        default=None, description="A mask defining the region that this conditioning prompt applies to."
-    )
-    mask_weight: float = InputField(default=1.0, description="")
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         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() -> Iterator[Tuple[LoRAModelRaw, float]]:
+        def _lora_loader():
             for lora in self.clip.loras:
                 lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
-                assert isinstance(lora_info.model, LoRAModelRaw)
-                yield (lora_info.model, lora.weight)
+                yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
         # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        ti_list = generate_ti_list(self.prompt, text_encoder_info.config.base, context)
+        ti_list = []
+        for trigger in extract_ti_triggers_from_prompt(self.prompt):
+            name = trigger[1:-1]
+            try:
+                ti_list.append(
+                    (
+                        name,
+                        context.models.load(
+                            model_name=name,
+                            base_model=self.clip.text_encoder.base_model,
+                            model_type=ModelType.TextualInversion,
+                        ).context.model,
+                    )
+                )
+            except ModelNotFoundException:
+                # print(e)
+                # import traceback
+                # print(traceback.format_exc())
+                print(f'Warn: trigger: "{trigger}" not found')
 
         with (
-            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -94,9 +105,8 @@ 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_model, self.clip.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
         ):
-            assert isinstance(text_encoder, CLIPTextModel)
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -130,18 +140,10 @@ class CompelInvocation(BaseInvocation):
 
         conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-                mask=self.mask,
-                mask_weight=self.mask_weight,
-            )
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 class SDXLPromptInvocationBase:
-    """Prompt processor for SDXL models."""
-
     def run_clip_compel(
         self,
         context: InvocationContext,
@@ -150,25 +152,20 @@ class SDXLPromptInvocationBase:
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ) -> 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, CLIPTextModelWithProjection))
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
-            cpu_text_encoder = text_encoder_info.model
-            assert isinstance(cpu_text_encoder, torch.nn.Module)
+            cpu_text_encoder = text_encoder_info.context.model
             c = torch.zeros(
                 (
                     1,
                     cpu_text_encoder.config.max_position_embeddings,
                     cpu_text_encoder.config.hidden_size,
                 ),
-                dtype=cpu_text_encoder.dtype,
+                dtype=text_encoder_info.context.cache.precision,
             )
             if get_pooled:
                 c_pooled = torch.zeros(
@@ -179,21 +176,37 @@ class SDXLPromptInvocationBase:
                 c_pooled = None
             return c, c_pooled, None
 
-        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
+        def _lora_loader():
             for lora in clip_field.loras:
                 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)
+                yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
         # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        ti_list = generate_ti_list(prompt, text_encoder_info.config.base, context)
+        ti_list = []
+        for trigger in extract_ti_triggers_from_prompt(prompt):
+            name = trigger[1:-1]
+            try:
+                ti_list.append(
+                    (
+                        name,
+                        context.models.load(
+                            model_name=name,
+                            base_model=clip_field.text_encoder.base_model,
+                            model_type=ModelType.TextualInversion,
+                        ).context.model,
+                    )
+                )
+            except ModelNotFoundException:
+                # print(e)
+                # import traceback
+                # print(traceback.format_exc())
+                print(f'Warn: trigger: "{trigger}" not found')
 
         with (
-            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -201,10 +214,8 @@ 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_model, clip_field.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
         ):
-            assert isinstance(text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
-            text_encoder = cast(CLIPTextModel, text_encoder)
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -250,7 +261,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.2.0",
+    version="1.0.1",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -274,11 +285,6 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
     clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
 
-    mask: Optional[MaskField] = InputField(
-        default=None, description="A mask defining the region that this conditioning prompt applies to."
-    )
-    mask_weight: float = InputField(default=1.0, description="")
-
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         c1, c1_pooled, ec1 = self.run_clip_compel(
@@ -326,7 +332,6 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 dim=1,
             )
 
-        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -340,13 +345,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
 
         conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-                mask=self.mask,
-                mask_weight=self.mask_weight,
-            )
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation(
@@ -381,7 +380,6 @@ 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(
@@ -395,7 +393,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(conditioning=ConditioningField(conditioning_name=conditioning_name, mask_weight=1.0))
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation_output("clip_skip_output")
@@ -416,7 +414,7 @@ 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, ge=0, description=FieldDescriptions.skipped_layers)
+    skipped_layers: int = InputField(default=0, description=FieldDescriptions.skipped_layers)
 
     def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
         self.clip.skipped_layers += self.skipped_layers
@@ -426,9 +424,9 @@ class ClipSkipInvocation(BaseInvocation):
 
 
 def get_max_token_count(
-    tokenizer: CLIPTokenizer,
+    tokenizer,
     prompt: Union[FlattenedPrompt, Blend, Conjunction],
-    truncate_if_too_long: bool = False,
+    truncate_if_too_long=False,
 ) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt
@@ -440,9 +438,7 @@ 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: CLIPTokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long: bool = True
-) -> List[str]:
+def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=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")
 
@@ -455,29 +451,24 @@ def get_tokens_for_prompt_object(
         for x in parsed_prompt.children
     ]
     text = " ".join(text_fragments)
-    tokens: List[str] = tokenizer.tokenize(text)
+    tokens = tokenizer.tokenize(text)
     if truncate_if_too_long:
         max_tokens_length = tokenizer.model_max_length - 2  # typically 75
         tokens = tokens[0:max_tokens_length]
     return tokens
 
 
-def log_tokenization_for_conjunction(
-    c: Conjunction, tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
-) -> None:
+def log_tokenization_for_conjunction(c: Conjunction, tokenizer, display_label_prefix=None):
     display_label_prefix = display_label_prefix or ""
     for i, p in enumerate(c.prompts):
         if len(c.prompts) > 1:
             this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
         else:
-            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: CLIPTokenizer, display_label_prefix: Optional[str] = None
-) -> None:
+def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None):
     display_label_prefix = display_label_prefix or ""
     if type(p) is Blend:
         blend: Blend = p
@@ -517,12 +508,7 @@ def log_tokenization_for_prompt_object(
             log_tokenization_for_text(text, tokenizer, display_label=display_label_prefix)
 
 
-def log_tokenization_for_text(
-    text: str,
-    tokenizer: CLIPTokenizer,
-    display_label: Optional[str] = None,
-    truncate_if_too_long: Optional[bool] = False,
-) -> None:
+def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
     """shows how the prompt is tokenized
     # usually tokens have '</w>' to indicate end-of-word,
     # but for readability it has been replaced with ' '

invokeai/app/invocations/conditioning.py

@@ -1,40 +0,0 @@
-import torch
-
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    InvocationContext,
-    invocation,
-)
-from invokeai.app.invocations.fields import InputField, WithMetadata
-from invokeai.app.invocations.primitives import MaskField, MaskOutput
-
-
-@invocation(
-    "rectangle_mask",
-    title="Create Rectangle Mask",
-    tags=["conditioning"],
-    category="conditioning",
-    version="1.0.0",
-)
-class RectangleMaskInvocation(BaseInvocation, WithMetadata):
-    """Create a rectangular mask."""
-
-    height: int = InputField(description="The height of the entire mask.")
-    width: int = InputField(description="The width of the entire mask.")
-    y_top: int = InputField(description="The top y-coordinate of the rectangular masked region (inclusive).")
-    x_left: int = InputField(description="The left x-coordinate of the rectangular masked region (inclusive).")
-    rectangle_height: int = InputField(description="The height of the rectangular masked region.")
-    rectangle_width: int = InputField(description="The width of the rectangular masked region.")
-
-    def invoke(self, context: InvocationContext) -> MaskOutput:
-        mask = torch.zeros((1, self.height, self.width), dtype=torch.bool)
-        mask[
-            :, self.y_top : self.y_top + self.rectangle_height, self.x_left : self.x_left + self.rectangle_width
-        ] = True
-
-        mask_name = context.tensors.save(mask)
-        return MaskOutput(
-            mask=MaskField(mask_name=mask_name),
-            width=self.width,
-            height=self.height,
-        )

invokeai/app/invocations/constants.py

@@ -12,6 +12,3 @@ 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

@@ -23,7 +23,7 @@ from controlnet_aux import (
 )
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
-from pydantic import BaseModel, Field, field_validator, model_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
 from invokeai.app.invocations.fields import (
     FieldDescriptions,
@@ -39,8 +39,14 @@ from invokeai.app.invocations.util import validate_begin_end_step, validate_weig
 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 invokeai.backend.model_management.models.base import BaseModelType
 
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    invocation,
+    invocation_output,
+)
 
 CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
 CONTROLNET_RESIZE_VALUES = Literal[
@@ -54,7 +60,10 @@ CONTROLNET_RESIZE_VALUES = Literal[
 class ControlNetModelField(BaseModel):
     """ControlNet model field"""
 
-    key: str = Field(description="Model config record key for the ControlNet model")
+    model_name: str = Field(description="Name of the ControlNet model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class ControlField(BaseModel):
@@ -143,12 +152,8 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
         # 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 = self.load_image(context)
+        raw_image = context.images.get_pil(self.image.image_name)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
@@ -185,10 +190,6 @@ 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)
@@ -423,6 +424,10 @@ 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
@@ -552,6 +557,7 @@ 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]
 
@@ -591,6 +597,9 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
         depth_anything_detector = DepthAnythingDetector()
         depth_anything_detector.load_model(model_size=self.model_size)
 
+        if image.mode == "RGBA":
+            image = image.convert("RGB")
+
         processed_image = depth_anything_detector(image=image, resolution=self.resolution, offload=self.offload)
         return processed_image
 
@@ -610,7 +619,7 @@ class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
     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):
+    def run_processor(self, image):
         dw_openpose = DWOpenposeDetector()
         processed_image = dw_openpose(
             image,

invokeai/app/invocations/fields.py

@@ -194,18 +194,11 @@ class BoardField(BaseModel):
     board_id: str = Field(description="The id of the board")
 
 
-class MaskField(BaseModel):
-    """A mask primitive field."""
-
-    mask_name: str = Field(description="The name of the mask.")
-
-
 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):
@@ -231,12 +224,7 @@ class ConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 
     conditioning_name: str = Field(description="The name of conditioning tensor")
-    mask: Optional[MaskField] = Field(
-        default=None,
-        description="The bool mask associated with this conditioning tensor. Excluded regions should be set to False, "
-        "included regions should be set to True.",
-    )
-    mask_weight: float = Field(description="")
+    # endregion
 
 
 class MetadataField(RootModel):

invokeai/app/invocations/image.py

@@ -7,7 +7,6 @@ import cv2
 import numpy
 from PIL import Image, ImageChops, ImageFilter, ImageOps
 
-from invokeai.app.invocations.constants import IMAGE_MODES
 from invokeai.app.invocations.fields import (
     ColorField,
     FieldDescriptions,
@@ -22,7 +21,11 @@ from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 
-from .baseinvocation import BaseInvocation, Classification, invocation
+from .baseinvocation import (
+    BaseInvocation,
+    Classification,
+    invocation,
+)
 
 
 @invocation("show_image", title="Show Image", tags=["image"], category="image", version="1.0.1")
@@ -260,6 +263,9 @@ class ImageChannelInvocation(BaseInvocation, WithMetadata, WithBoard):
         return ImageOutput.build(image_dto)
 
 
+IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
+
+
 @invocation(
     "img_conv",
     title="Convert Image Mode",
@@ -930,40 +936,3 @@ class SaveImageInvocation(BaseInvocation, WithMetadata, WithBoard):
         image_dto = context.images.save(image=image)
 
         return ImageOutput.build(image_dto)
-
-
-@invocation(
-    "canvas_paste_back",
-    title="Canvas Paste Back",
-    tags=["image", "combine"],
-    category="image",
-    version="1.0.0",
-)
-class CanvasPasteBackInvocation(BaseInvocation, WithMetadata, WithBoard):
-    """Combines two images by using the mask provided. Intended for use on the Unified Canvas."""
-
-    source_image: ImageField = InputField(description="The source image")
-    target_image: ImageField = InputField(default=None, description="The target image")
-    mask: ImageField = InputField(
-        description="The mask to use when pasting",
-    )
-    mask_blur: int = InputField(default=0, ge=0, description="The amount to blur the mask by")
-
-    def _prepare_mask(self, mask: Image.Image) -> Image.Image:
-        mask_array = numpy.array(mask)
-        kernel = numpy.ones((self.mask_blur, self.mask_blur), numpy.uint8)
-        dilated_mask_array = cv2.erode(mask_array, kernel, iterations=3)
-        dilated_mask = Image.fromarray(dilated_mask_array)
-        if self.mask_blur > 0:
-            mask = dilated_mask.filter(ImageFilter.GaussianBlur(self.mask_blur))
-        return ImageOps.invert(mask.convert("L"))
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        source_image = context.images.get_pil(self.source_image.image_name)
-        target_image = context.images.get_pil(self.target_image.image_name)
-        mask = self._prepare_mask(context.images.get_pil(self.mask.image_name))
-
-        source_image.paste(target_image, (0, 0), mask)
-
-        image_dto = context.images.save(image=source_image)
-        return ImageOutput.build(image_dto)

invokeai/app/invocations/ip_adapter.py

@@ -1,8 +1,8 @@
+import os
 from builtins import float
 from typing import List, Union
 
-from pydantic import BaseModel, Field, field_validator, model_validator
-from typing_extensions import Self
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -14,16 +14,22 @@ from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField
 from invokeai.app.invocations.primitives import ImageField
 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
+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
 
 
-# LS: Consider moving these two classes into model.py
 class IPAdapterModelField(BaseModel):
-    key: str = Field(description="Key to the IP-Adapter model")
+    model_name: str = Field(description="Name of the IP-Adapter model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class CLIPVisionModelField(BaseModel):
-    key: str = Field(description="Key to the CLIP Vision image encoder model")
+    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=())
 
 
 class IPAdapterField(BaseModel):
@@ -40,12 +46,12 @@ class IPAdapterField(BaseModel):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v: float) -> float:
+    def validate_ip_adapter_weight(cls, v):
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self) -> Self:
+    def validate_begin_end_step_percent(self):
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
@@ -78,25 +84,33 @@ class IPAdapterInvocation(BaseInvocation):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v: float) -> float:
+    def validate_ip_adapter_weight(cls, v):
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self) -> Self:
+    def validate_begin_end_step_percent(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.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_models = context.models.search_by_attrs(
-            name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
+        ip_adapter_info = context.models.get_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.config.get().models_path, ip_adapter_info["path"])
+        )
+        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,
         )
-        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

@@ -1,18 +1,15 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-import inspect
+
 import math
 from contextlib import ExitStack
 from functools import singledispatchmethod
-from typing import Any, Iterator, List, Literal, Optional, Tuple, Union
+from typing import List, Literal, Optional, Union
 
 import einops
 import numpy as np
-import numpy.typing as npt
 import torch
-import torchvision
 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 (
@@ -21,10 +18,8 @@ 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
 
@@ -52,20 +47,13 @@ from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
-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 (
-    BasicConditioningInfo,
-    IPAdapterConditioningInfo,
-    Range,
-    SDXLConditioningInfo,
-    TextConditioningData,
-    TextConditioningRegions,
-)
-from invokeai.backend.util.silence_warnings import SilenceWarnings
+from invokeai.backend.model_management.models import ModelType, SilenceWarnings
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
 
+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,
@@ -73,6 +61,7 @@ from ...backend.stable_diffusion.diffusers_pipeline import (
     T2IAdapterData,
     image_resized_to_grid_as_tensor,
 )
+from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
 from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
 from ...backend.util.devices import choose_precision, choose_torch_device
 from .baseinvocation import (
@@ -135,10 +124,10 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
         ui_order=4,
     )
 
-    def prep_mask_tensor(self, mask_image: Image.Image) -> torch.Tensor:
+    def prep_mask_tensor(self, mask_image):
         if mask_image.mode != "L":
             mask_image = mask_image.convert("L")
-        mask_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        mask_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:
@@ -149,21 +138,21 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
         if self.image is not None:
             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)
+            image = image_resized_to_grid_as_tensor(image.convert("RGB"))
+            if image.dim() == 3:
+                image = image.unsqueeze(0)
         else:
-            image_tensor = None
+            image = None
 
         mask = self.prep_mask_tensor(
             context.images.get_pil(self.mask.image_name),
         )
 
-        if image_tensor is not None:
+        if image is not None:
             vae_info = context.models.load(**self.vae.vae.model_dump())
 
-            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)
+            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)
             # TODO:
             masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
 
@@ -176,76 +165,6 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
         return DenoiseMaskOutput.build(
             mask_name=mask_name,
             masked_latents_name=masked_latents_name,
-            gradient=False,
-        )
-
-
-@invocation_output("gradient_mask_output")
-class GradientMaskOutput(BaseInvocationOutput):
-    """Outputs a denoise mask and an image representing the total gradient of the mask."""
-
-    denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
-    expanded_mask_area: ImageField = OutputField(
-        description="Image representing the total gradient area of the mask. For paste-back purposes."
-    )
-
-
-@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) -> GradientMaskOutput:
-        mask_image = context.images.get_pil(self.mask.image_name, mode="L")
-        if self.edge_radius > 0:
-            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))
-
-            blur_tensor: torch.Tensor = image_resized_to_grid_as_tensor(blur_mask, normalize=False)
-
-            # redistribute blur so that the original edges are 0 and blur outwards to 1
-            blur_tensor = (blur_tensor - 0.5) * 2
-
-            threshold = 1 - self.minimum_denoise
-
-            if self.coherence_mode == "Staged":
-                # wherever the blur_tensor is less than fully masked, convert it to threshold
-                blur_tensor = torch.where((blur_tensor < 1) & (blur_tensor > 0), 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)
-
-        else:
-            blur_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
-
-        mask_name = context.tensors.save(tensor=blur_tensor.unsqueeze(1))
-
-        # compute a [0, 1] mask from the blur_tensor
-        expanded_mask = torch.where((blur_tensor < 1), 0, 1)
-        expanded_mask_image = Image.fromarray((expanded_mask.squeeze(0).numpy() * 255).astype(np.uint8), mode="L")
-        expanded_image_dto = context.images.save(expanded_mask_image)
-
-        return GradientMaskOutput(
-            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=None, gradient=True),
-            expanded_mask_area=ImageField(image_name=expanded_image_dto.image_name),
         )
 
 
@@ -264,7 +183,7 @@ def get_scheduler(
         scheduler_config = scheduler_config["_backup"]
     scheduler_config = {
         **scheduler_config,
-        **scheduler_extra_config,  # FIXME
+        **scheduler_extra_config,
         "_backup": scheduler_config,
     }
 
@@ -277,7 +196,6 @@ 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
 
 
@@ -291,11 +209,11 @@ def get_scheduler(
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
 
-    positive_conditioning: Union[ConditioningField, list[ConditioningField]] = InputField(
+    positive_conditioning: ConditioningField = InputField(
         description=FieldDescriptions.positive_cond, input=Input.Connection, ui_order=0
     )
-    negative_conditioning: Union[ConditioningField, list[ConditioningField]] = InputField(
-        description=FieldDescriptions.negative_cond, input=Input.Connection, ui_order=0
+    negative_conditioning: ConditioningField = InputField(
+        description=FieldDescriptions.negative_cond, input=Input.Connection, ui_order=1
     )
     noise: Optional[LatentsField] = InputField(
         default=None,
@@ -361,7 +279,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     )
 
     @field_validator("cfg_scale")
-    def ge_one(cls, v: Union[List[float], float]) -> Union[List[float], float]:
+    def ge_one(cls, v):
         """validate that all cfg_scale values are >= 1"""
         if isinstance(v, list):
             for i in v:
@@ -372,197 +290,48 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 raise ValueError("cfg_scale must be greater than 1")
         return v
 
-    def _get_text_embeddings_and_masks(
-        self,
-        cond_list: list[ConditioningField],
-        context: InvocationContext,
-        device: torch.device,
-        dtype: torch.dtype,
-    ) -> tuple[Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]], list[Optional[torch.Tensor]]]:
-        """Get the text embeddings and masks from the input conditioning fields."""
-        text_embeddings: Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]] = []
-        text_embeddings_masks: list[Optional[torch.Tensor]] = []
-        for cond in cond_list:
-            cond_data = context.conditioning.load(cond.conditioning_name)
-            text_embeddings.append(cond_data.conditionings[0].to(device=device, dtype=dtype))
-
-            mask = cond.mask
-            if mask is not None:
-                mask = context.tensors.load(mask.mask_name)
-            text_embeddings_masks.append(mask)
-
-        return text_embeddings, text_embeddings_masks
-
-    def _preprocess_regional_prompt_mask(
-        self, mask: Optional[torch.Tensor], target_height: int, target_width: int
-    ) -> torch.Tensor:
-        """Preprocess a regional prompt mask to match the target height and width.
-
-        If mask is None, returns a mask of all ones with the target height and width.
-        If mask is not None, resizes the mask to the target height and width using nearest neighbor interpolation.
-
-        Returns:
-            torch.Tensor: The processed mask. dtype: torch.bool, shape: (1, 1, target_height, target_width).
-        """
-        if mask is None:
-            return torch.ones((1, 1, target_height, target_width), dtype=torch.bool)
-
-        tf = torchvision.transforms.Resize(
-            (target_height, target_width), interpolation=torchvision.transforms.InterpolationMode.NEAREST
-        )
-        mask = mask.unsqueeze(0)  # Shape: (1, h, w) -> (1, 1, h, w)
-        mask = tf(mask)
-
-        return mask
-
-    def concat_regional_text_embeddings(
-        self,
-        text_conditionings: Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]],
-        masks: Optional[list[Optional[torch.Tensor]]],
-        conditioning_fields: list[ConditioningField],
-        latent_height: int,
-        latent_width: int,
-    ) -> tuple[Union[BasicConditioningInfo, SDXLConditioningInfo], Optional[TextConditioningRegions]]:
-        """Concatenate regional text embeddings into a single embedding and track the region masks accordingly."""
-        if masks is None:
-            masks = [None] * len(text_conditionings)
-        assert len(text_conditionings) == len(masks)
-
-        is_sdxl = type(text_conditionings[0]) is SDXLConditioningInfo
-
-        all_masks_are_none = all(mask is None for mask in masks)
-
-        text_embedding = []
-        pooled_embedding = None
-        add_time_ids = None
-        cur_text_embedding_len = 0
-        processed_masks = []
-        embedding_ranges = []
-        extra_conditioning = None
-
-        for prompt_idx, text_embedding_info in enumerate(text_conditionings):
-            mask = masks[prompt_idx]
-            if (
-                text_embedding_info.extra_conditioning is not None
-                and text_embedding_info.extra_conditioning.wants_cross_attention_control
-            ):
-                extra_conditioning = text_embedding_info.extra_conditioning
-
-            if is_sdxl:
-                # We choose a random SDXLConditioningInfo's pooled_embeds and add_time_ids here, with a preference for
-                # prompts without a mask. We prefer prompts without a mask, because they are more likely to contain
-                # global prompt information.  In an ideal case, there should be exactly one global prompt without a
-                # mask, but we don't enforce this.
-
-                # HACK(ryand): The fact that we have to choose a single pooled_embedding and add_time_ids here is a
-                # fundamental interface issue. The SDXL Compel nodes are not designed to be used in the way that we use
-                # them for regional prompting. Ideally, the DenoiseLatents invocation should accept a single
-                # pooled_embeds tensor and a list of standard text embeds with region masks. This change would be a
-                # pretty major breaking change to a popular node, so for now we use this hack.
-                if pooled_embedding is None or mask is None:
-                    pooled_embedding = text_embedding_info.pooled_embeds
-                if add_time_ids is None or mask is None:
-                    add_time_ids = text_embedding_info.add_time_ids
-
-            text_embedding.append(text_embedding_info.embeds)
-            if not all_masks_are_none:
-                # embedding_ranges.append(
-                #     Range(
-                #         start=cur_text_embedding_len, end=cur_text_embedding_len + text_embedding_info.embeds.shape[1]
-                #     )
-                # )
-                # HACK(ryand): Contrary to its name, tokens_count_including_eos_bos does not seem to include eos and bos
-                # in the count.
-                embedding_ranges.append(
-                    Range(
-                        start=cur_text_embedding_len + 1,
-                        end=cur_text_embedding_len
-                        + text_embedding_info.extra_conditioning.tokens_count_including_eos_bos,
-                    )
-                )
-                processed_masks.append(self._preprocess_regional_prompt_mask(mask, latent_height, latent_width))
-
-            cur_text_embedding_len += text_embedding_info.embeds.shape[1]
-
-        text_embedding = torch.cat(text_embedding, dim=1)
-        assert len(text_embedding.shape) == 3  # batch_size, seq_len, token_len
-
-        regions = None
-        if not all_masks_are_none:
-            regions = TextConditioningRegions(
-                masks=torch.cat(processed_masks, dim=1),
-                ranges=embedding_ranges,
-                mask_weights=[x.mask_weight for x in conditioning_fields],
-            )
-
-        if extra_conditioning is not None and len(text_conditionings) > 1:
-            raise ValueError(
-                "Prompt-to-prompt cross-attention control (a.k.a. `swap()`) is not supported when using multiple "
-                "prompts."
-            )
-
-        if is_sdxl:
-            return SDXLConditioningInfo(
-                embeds=text_embedding,
-                extra_conditioning=extra_conditioning,
-                pooled_embeds=pooled_embedding,
-                add_time_ids=add_time_ids,
-            ), regions
-        return BasicConditioningInfo(
-            embeds=text_embedding,
-            extra_conditioning=extra_conditioning,
-        ), regions
-
     def get_conditioning_data(
         self,
         context: InvocationContext,
-        unet: UNet2DConditionModel,
-        latent_height: int,
-        latent_width: int,
-    ) -> TextConditioningData:
-        # Normalize self.positive_conditioning and self.negative_conditioning to lists.
-        cond_list = self.positive_conditioning
-        if not isinstance(cond_list, list):
-            cond_list = [cond_list]
-        uncond_list = self.negative_conditioning
-        if not isinstance(uncond_list, list):
-            uncond_list = [uncond_list]
+        scheduler,
+        unet,
+        seed,
+    ) -> ConditioningData:
+        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
 
-        cond_text_embeddings, cond_text_embedding_masks = self._get_text_embeddings_and_masks(
-            cond_list, context, unet.device, unet.dtype
-        )
+        negative_cond_data = context.conditioning.load(self.negative_conditioning.conditioning_name)
+        uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
 
-        uncond_text_embeddings, uncond_text_embedding_masks = self._get_text_embeddings_and_masks(
-            uncond_list, context, unet.device, unet.dtype
-        )
-        cond_text_embedding, cond_regions = self.concat_regional_text_embeddings(
-            text_conditionings=cond_text_embeddings,
-            masks=cond_text_embedding_masks,
-            conditioning_fields=cond_list,
-            latent_height=latent_height,
-            latent_width=latent_width,
-        )
-        uncond_text_embedding, uncond_regions = self.concat_regional_text_embeddings(
-            text_conditionings=uncond_text_embeddings,
-            masks=uncond_text_embedding_masks,
-            conditioning_fields=uncond_list,
-            latent_height=latent_height,
-            latent_width=latent_width,
-        )
-        conditioning_data = TextConditioningData(
-            uncond_text=uncond_text_embedding,
-            cond_text=cond_text_embedding,
-            uncond_regions=uncond_regions,
-            cond_regions=cond_regions,
+        conditioning_data = ConditioningData(
+            unconditioned_embeddings=uc,
+            text_embeddings=c,
             guidance_scale=self.cfg_scale,
             guidance_rescale_multiplier=self.cfg_rescale_multiplier,
+            extra=extra_conditioning_info,
+            postprocessing_settings=PostprocessingSettings(
+                threshold=0.0,  # threshold,
+                warmup=0.2,  # warmup,
+                h_symmetry_time_pct=None,  # h_symmetry_time_pct,
+                v_symmetry_time_pct=None,  # v_symmetry_time_pct,
+            ),
+        )
+
+        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(
+            scheduler,
+            # for ddim scheduler
+            eta=0.0,  # ddim_eta
+            # for ancestral and sde schedulers
+            # flip all bits to have noise different from initial
+            generator=torch.Generator(device=unet.device).manual_seed(seed ^ 0xFFFFFFFF),
         )
         return conditioning_data
 
     def create_pipeline(
         self,
-        unet: UNet2DConditionModel,
-        scheduler: Scheduler,
+        unet,
+        scheduler,
     ) -> StableDiffusionGeneratorPipeline:
         # TODO:
         # configure_model_padding(
@@ -573,10 +342,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         class FakeVae:
             class FakeVaeConfig:
-                def __init__(self) -> None:
+                def __init__(self):
                     self.block_out_channels = [0]
 
-            def __init__(self) -> None:
+            def __init__(self):
                 self.config = FakeVae.FakeVaeConfig()
 
         return StableDiffusionGeneratorPipeline(
@@ -593,11 +362,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def prep_control_data(
         self,
         context: InvocationContext,
-        control_input: Optional[Union[ControlField, List[ControlField]]],
+        control_input: Union[ControlField, List[ControlField]],
         latents_shape: List[int],
         exit_stack: ExitStack,
         do_classifier_free_guidance: bool = True,
-    ) -> Optional[List[ControlNetData]]:
+    ) -> 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
@@ -619,7 +388,13 @@ 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.models.load(key=control_info.control_model.key))
+            control_model = exit_stack.enter_context(
+                context.models.load(
+                    model_name=control_info.control_model.model_name,
+                    model_type=ModelType.ControlNet,
+                    base_model=control_info.control_model.base_model,
+                )
+            )
 
             # control_models.append(control_model)
             control_image_field = control_info.image
@@ -661,6 +436,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         self,
         context: InvocationContext,
         ip_adapter: Optional[Union[IPAdapterField, list[IPAdapterField]]],
+        conditioning_data: ConditioningData,
         exit_stack: ExitStack,
     ) -> Optional[list[IPAdapterData]]:
         """If IP-Adapter is enabled, then this function loads the requisite models, and adds the image prompt embeddings
@@ -677,19 +453,28 @@ class DenoiseLatentsInvocation(BaseInvocation):
             return None
 
         ip_adapter_data_list = []
+        conditioning_data.ip_adapter_conditioning = []
         for single_ip_adapter in ip_adapter:
             ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
-                context.models.load(key=single_ip_adapter.ip_adapter_model.key)
+                context.models.load(
+                    model_name=single_ip_adapter.ip_adapter_model.model_name,
+                    model_type=ModelType.IPAdapter,
+                    base_model=single_ip_adapter.ip_adapter_model.base_model,
+                )
             )
 
-            image_encoder_model_info = context.models.load(key=single_ip_adapter.image_encoder_model.key)
+            image_encoder_model_info = context.models.load(
+                model_name=single_ip_adapter.image_encoder_model.model_name,
+                model_type=ModelType.CLIPVision,
+                base_model=single_ip_adapter.image_encoder_model.base_model,
+            )
 
             # `single_ip_adapter.image` could be a list or a single ImageField. Normalize to a list here.
-            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 = single_ip_adapter.image
+            if not isinstance(single_ipa_images, list):
+                single_ipa_images = [single_ipa_images]
 
-            single_ipa_images = [context.images.get_pil(image.image_name) for image in single_ipa_image_fields]
+            single_ipa_images = [context.images.get_pil(image.image_name) for image in single_ipa_images]
 
             # 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.
@@ -699,13 +484,16 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     single_ipa_images, image_encoder_model
                 )
 
+                conditioning_data.ip_adapter_conditioning.append(
+                    IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds)
+                )
+
             ip_adapter_data_list.append(
                 IPAdapterData(
                     ip_adapter_model=ip_adapter_model,
                     weight=single_ip_adapter.weight,
                     begin_step_percent=single_ip_adapter.begin_step_percent,
                     end_step_percent=single_ip_adapter.end_step_percent,
-                    ip_adapter_conditioning=IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds),
                 )
             )
 
@@ -730,20 +518,25 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
-            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)
+            t2i_adapter_model_info = context.models.load(
+                model_name=t2i_adapter_field.t2i_adapter_model.model_name,
+                model_type=ModelType.T2IAdapter,
+                base_model=t2i_adapter_field.t2i_adapter_model.base_model,
+            )
             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_model_config.base == BaseModelType.StableDiffusion1:
+            if t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusion1:
                 max_unet_downscale = 8
-            elif t2i_adapter_model_config.base == BaseModelType.StableDiffusionXL:
+            elif t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusionXL:
                 max_unet_downscale = 4
             else:
-                raise ValueError(f"Unexpected T2I-Adapter base model type: '{t2i_adapter_model_config.base}'.")
+                raise ValueError(
+                    f"Unexpected T2I-Adapter base model type: '{t2i_adapter_field.t2i_adapter_model.base_model}'."
+                )
 
             t2i_adapter_model: T2IAdapter
-            with t2i_adapter_loaded_model as t2i_adapter_model:
+            with t2i_adapter_model_info as t2i_adapter_model:
                 total_downscale_factor = t2i_adapter_model.total_downscale_factor
 
                 # Resize the T2I-Adapter input image.
@@ -763,7 +556,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     do_classifier_free_guidance=False,
                     width=t2i_input_width,
                     height=t2i_input_height,
-                    num_channels=t2i_adapter_model.config["in_channels"],  # mypy treats this as a FrozenDict
+                    num_channels=t2i_adapter_model.config.in_channels,
                     device=t2i_adapter_model.device,
                     dtype=t2i_adapter_model.dtype,
                     resize_mode=t2i_adapter_field.resize_mode,
@@ -788,16 +581,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     # original idea by https://github.com/AmericanPresidentJimmyCarter
     # TODO: research more for second order schedulers timesteps
-    def init_scheduler(
-        self,
-        scheduler: Union[Scheduler, ConfigMixin],
-        device: torch.device,
-        steps: int,
-        denoising_start: float,
-        denoising_end: float,
-        seed: int,
-    ) -> Tuple[int, List[int], int]:
-        assert isinstance(scheduler, ConfigMixin)
+    def init_scheduler(self, scheduler, device, steps, denoising_start, denoising_end):
         if scheduler.config.get("cpu_only", False):
             scheduler.set_timesteps(steps, device="cpu")
             timesteps = scheduler.timesteps.to(device=device)
@@ -809,11 +593,11 @@ 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
@@ -824,21 +608,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         timesteps = timesteps[t_start_idx : t_start_idx + t_end_idx]
         num_inference_steps = len(timesteps) // scheduler.order
 
-        scheduler_step_kwargs = {}
-        scheduler_step_signature = inspect.signature(scheduler.step)
-        if "generator" in scheduler_step_signature.parameters:
-            # At some point, someone decided that schedulers that accept a generator should use the original seed with
-            # all bits flipped. I don't know the original rationale for this, but now we must keep it like this for
-            # reproducibility.
-            scheduler_step_kwargs = {"generator": torch.Generator(device=device).manual_seed(seed ^ 0xFFFFFFFF)}
+        return num_inference_steps, timesteps, init_timestep
 
-        return num_inference_steps, timesteps, init_timestep, scheduler_step_kwargs
-
-    def prep_inpaint_mask(
-        self, context: InvocationContext, latents: torch.Tensor
-    ) -> Tuple[Optional[torch.Tensor], Optional[torch.Tensor], bool]:
+    def prep_inpaint_mask(self, context: InvocationContext, latents):
         if self.denoise_mask is None:
-            return None, None, False
+            return None, None
 
         mask = context.tensors.load(self.denoise_mask.mask_name)
         mask = tv_resize(mask, latents.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
@@ -847,7 +621,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         else:
             masked_latents = None
 
-        return 1 - mask, masked_latents, self.denoise_mask.gradient
+        return 1 - mask, masked_latents
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
@@ -874,7 +648,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             if seed is None:
                 seed = 0
 
-            mask, masked_latents, gradient_mask = self.prep_inpaint_mask(context, latents)
+            mask, masked_latents = 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.
@@ -885,30 +659,25 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 do_classifier_free_guidance=True,
             )
 
-            # 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):
+                context.util.sd_step_callback(state, self.unet.unet.base_model)
 
-            def step_callback(state: PipelineIntermediateState) -> None:
-                context.util.sd_step_callback(state, unet_config.base)
-
-            def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
+            def _lora_loader():
                 for lora in self.unet.loras:
                     lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
-                    yield (lora_info.model, lora.weight)
+                    yield (lora_info.context.model, lora.weight)
                     del lora_info
                 return
 
             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.model, self.unet.freeu_config),
-                set_seamless(unet_info.model, self.unet.seamless_axes),  # FIXME
+                ModelPatcher.apply_freeu(unet_info.context.model, self.unet.freeu_config),
+                set_seamless(unet_info.context.model, self.unet.seamless_axes),
                 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)
@@ -925,10 +694,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 )
 
                 pipeline = self.create_pipeline(unet, scheduler)
-                _, _, latent_height, latent_width = latents.shape
-                conditioning_data = self.get_conditioning_data(
-                    context=context, unet=unet, latent_height=latent_height, latent_width=latent_width
-                )
+                conditioning_data = self.get_conditioning_data(context, scheduler, unet, seed)
 
                 controlnet_data = self.prep_control_data(
                     context=context,
@@ -942,19 +708,22 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 ip_adapter_data = self.prep_ip_adapter_data(
                     context=context,
                     ip_adapter=self.ip_adapter,
+                    conditioning_data=conditioning_data,
                     exit_stack=exit_stack,
                 )
 
-                num_inference_steps, timesteps, init_timestep, scheduler_step_kwargs = self.init_scheduler(
+                num_inference_steps, timesteps, init_timestep = self.init_scheduler(
                     scheduler,
                     device=unet.device,
                     steps=self.steps,
                     denoising_start=self.denoising_start,
                     denoising_end=self.denoising_end,
-                    seed=seed,
                 )
 
-                result_latents = pipeline.latents_from_embeddings(
+                (
+                    result_latents,
+                    result_attention_map_saver,
+                ) = pipeline.latents_from_embeddings(
                     latents=latents,
                     timesteps=timesteps,
                     init_timestep=init_timestep,
@@ -962,9 +731,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     seed=seed,
                     mask=mask,
                     masked_latents=masked_latents,
-                    gradient_mask=gradient_mask,
                     num_inference_steps=num_inference_steps,
-                    scheduler_step_kwargs=scheduler_step_kwargs,
                     conditioning_data=conditioning_data,
                     control_data=controlnet_data,
                     ip_adapter_data=ip_adapter_data,
@@ -1009,8 +776,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
 
         vae_info = context.models.load(**self.vae.vae.model_dump())
 
-        with set_seamless(vae_info.model, self.vae.seamless_axes), vae_info as vae:
-            assert isinstance(vae, torch.nn.Module)
+        with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
             latents = latents.to(vae.device)
             if self.fp32:
                 vae.to(dtype=torch.float32)
@@ -1182,9 +948,8 @@ class ImageToLatentsInvocation(BaseInvocation):
     fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
 
     @staticmethod
-    def vae_encode(vae_info: LoadedModel, upcast: bool, tiled: bool, image_tensor: torch.Tensor) -> torch.Tensor:
+    def vae_encode(vae_info, upcast, tiled, image_tensor):
         with vae_info as vae:
-            assert isinstance(vae, torch.nn.Module)
             orig_dtype = vae.dtype
             if upcast:
                 vae.to(dtype=torch.float32)
@@ -1245,19 +1010,14 @@ class ImageToLatentsInvocation(BaseInvocation):
     @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: torch.Tensor = image_tensor_dist.sample().to(
-            dtype=vae.dtype
-        )  # FIXME: uses torch.randn. make reproducible!
+        latents = 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:
-        assert isinstance(vae, torch.nn.Module)
-        latents: torch.FloatTensor = vae.encode(image_tensor).latents
-        return latents
+        return vae.encode(image_tensor).latents
 
 
 @invocation(
@@ -1290,12 +1050,7 @@ class BlendLatentsInvocation(BaseInvocation):
         # TODO:
         device = choose_torch_device()
 
-        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]]:
+        def slerp(t, v0, v1, DOT_THRESHOLD=0.9995):
             """
             Spherical linear interpolation
             Args:
@@ -1328,16 +1083,12 @@ class BlendLatentsInvocation(BaseInvocation):
                 v2 = s0 * v0 + s1 * v1
 
             if inputs_are_torch:
-                v2_torch: torch.Tensor = torch.from_numpy(v2).to(device)
-                return v2_torch
-            else:
-                assert isinstance(v2, np.ndarray)
-                return v2
+                v2 = torch.from_numpy(v2).to(device)
+
+            return v2
 
         # blend
-        bl = slerp(self.alpha, latents_a, latents_b)
-        assert isinstance(bl, torch.Tensor)
-        blended_latents: torch.Tensor = bl  # for type checking convenience
+        blended_latents = slerp(self.alpha, latents_a, latents_b)
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         blended_latents = blended_latents.to("cpu")
@@ -1430,16 +1181,15 @@ class IdealSizeInvocation(BaseInvocation):
         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, ...]:
+    def trim_to_multiple_of(self, *args, multiple_of=LATENT_SCALE_FACTOR):
         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 = 512
+        if self.unet.unet.base_model == BaseModelType.StableDiffusion2:
             dimension = 768
-        elif unet_config.base == BaseModelType.StableDiffusionXL:
+        elif self.unet.unet.base_model == BaseModelType.StableDiffusionXL:
             dimension = 1024
         dimension = dimension * self.multiplier
         min_dimension = math.floor(dimension * 0.5)

invokeai/app/invocations/metadata.py

@@ -33,7 +33,7 @@ class MetadataItemField(BaseModel):
 class LoRAMetadataField(BaseModel):
     """LoRA Metadata Field"""
 
-    model: LoRAModelField = Field(description=FieldDescriptions.lora_model)
+    lora: LoRAModelField = Field(description=FieldDescriptions.lora_model)
     weight: float = Field(description=FieldDescriptions.lora_weight)
 
 
@@ -114,7 +114,7 @@ GENERATION_MODES = Literal[
 ]
 
 
-@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.1.1")
+@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.0.1")
 class CoreMetadataInvocation(BaseInvocation):
     """Collects core generation metadata into a MetadataField"""
 

invokeai/app/invocations/model.py

@@ -1,13 +1,13 @@
 import copy
 from typing import List, Optional
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field
 
 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_manager import SubModelType
+from ...backend.model_management import BaseModelType, ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -17,8 +17,12 @@ from .baseinvocation import (
 
 
 class ModelInfo(BaseModel):
-    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")
+    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=())
 
 
 class LoraInfo(ModelInfo):
@@ -48,7 +52,7 @@ 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")
 
@@ -77,13 +81,20 @@ class ModelLoaderOutput(UNetOutput, CLIPOutput, VAEOutput):
 class MainModelField(BaseModel):
     """Main model field"""
 
-    key: str = Field(description="Model key")
+    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=())
 
 
 class LoRAModelField(BaseModel):
     """LoRA model field"""
 
-    key: str = Field(description="LoRA model key")
+    model_name: str = Field(description="Name of the LoRA model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 @invocation(
@@ -100,40 +111,85 @@ class MainModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
-        key = self.model.key
+        base_model = self.model.base_model
+        model_name = self.model.model_name
+        model_type = ModelType.Main
 
         # TODO: not found exceptions
-        if not context.models.exists(key):
-            raise Exception(f"Unknown model {key}")
+        if not context.models.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 ModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.UNet,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.Scheduler,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip=ClipField(
                 tokenizer=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.Tokenizer,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer,
                 ),
                 text_encoder=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.TextEncoder,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.Vae,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
                 ),
             ),
         )
@@ -170,16 +226,21 @@ class LoraLoaderInvocation(BaseInvocation):
         if self.lora is None:
             raise Exception("No LoRA provided")
 
-        lora_key = self.lora.key
+        base_model = self.lora.base_model
+        lora_name = self.lora.model_name
 
-        if not context.models.exists(lora_key):
-            raise Exception(f"Unkown lora: {lora_key}!")
+        if not context.models.exists(
+            base_model=base_model,
+            model_name=lora_name,
+            model_type=ModelType.Lora,
+        ):
+            raise Exception(f"Unkown lora name: {lora_name}!")
 
-        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.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.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.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')
 
         output = LoraLoaderOutput()
 
@@ -187,8 +248,10 @@ class LoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -197,8 +260,10 @@ class LoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -250,19 +315,24 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
         if self.lora is None:
             raise Exception("No LoRA provided")
 
-        lora_key = self.lora.key
+        base_model = self.lora.base_model
+        lora_name = self.lora.model_name
 
-        if not context.models.exists(lora_key):
-            raise Exception(f"Unknown lora: {lora_key}!")
+        if not context.models.exists(
+            base_model=base_model,
+            model_name=lora_name,
+            model_type=ModelType.Lora,
+        ):
+            raise Exception(f"Unknown lora name: {lora_name}!")
 
-        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.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.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.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.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')
+        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')
 
         output = SDXLLoraLoaderOutput()
 
@@ -270,8 +340,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -280,8 +352,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -290,8 +364,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.clip2 = copy.deepcopy(self.clip2)
             output.clip2.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -302,7 +378,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
 class VAEModelField(BaseModel):
     """Vae model field"""
 
-    key: str = Field(description="Model's key")
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 @invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.1")
@@ -316,12 +395,25 @@ class VaeLoaderInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> VAEOutput:
-        key = self.vae_model.key
+        base_model = self.vae_model.base_model
+        model_name = self.vae_model.model_name
+        model_type = ModelType.Vae
 
-        if not context.models.exists(key):
-            raise Exception(f"Unkown vae: {key}!")
-
-        return VAEOutput(vae=VaeField(vae=ModelInfo(key=key)))
+        if not context.models.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,
+                )
+            )
+        )
 
 
 @invocation_output("seamless_output")

invokeai/app/invocations/primitives.py

@@ -14,7 +14,6 @@ from invokeai.app.invocations.fields import (
     Input,
     InputField,
     LatentsField,
-    MaskField,
     OutputField,
     UIComponent,
 )
@@ -230,18 +229,6 @@ class StringCollectionInvocation(BaseInvocation):
 # region Image
 
 
-@invocation_output("mask_output")
-class MaskOutput(BaseInvocationOutput):
-    """A torch mask tensor.
-    dtype: torch.bool
-    shape: (1, height, width).
-    """
-
-    mask: MaskField = OutputField(description="The mask.")
-    width: int = OutputField(description="The width of the mask in pixels.")
-    height: int = OutputField(description="The height of the mask in pixels.")
-
-
 @invocation_output("image_output")
 class ImageOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
@@ -312,13 +299,9 @@ class DenoiseMaskOutput(BaseInvocationOutput):
     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":
+    def build(cls, mask_name: str, masked_latents_name: Optional[str] = None) -> "DenoiseMaskOutput":
         return cls(
-            denoise_mask=DenoiseMaskField(
-                mask_name=mask_name, masked_latents_name=masked_latents_name, gradient=gradient
-            ),
+            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=masked_latents_name),
         )
 
 
@@ -427,6 +410,10 @@ class ConditioningOutput(BaseInvocationOutput):
 
     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):

invokeai/app/invocations/sdxl.py

@@ -1,7 +1,7 @@
 from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.model_manager import SubModelType
 
+from ...backend.model_management import ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -40,52 +40,72 @@ class SDXLModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> SDXLModelLoaderOutput:
-        model_key = self.model.key
+        base_model = self.model.base_model
+        model_name = self.model.model_name
+        model_type = ModelType.Main
 
         # TODO: not found exceptions
-        if not context.models.exists(model_key):
-            raise Exception(f"Unknown model: {model_key}")
+        if not context.models.exists(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+        ):
+            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
 
         return SDXLModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.UNet,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Scheduler,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip=ClipField(
                 tokenizer=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Tokenizer,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer,
                 ),
                 text_encoder=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.TextEncoder,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             clip2=ClipField(
                 tokenizer=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Tokenizer2,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer2,
                 ),
                 text_encoder=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.TextEncoder2,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder2,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Vae,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
                 ),
             ),
         )
@@ -109,40 +129,56 @@ class SDXLRefinerModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> SDXLRefinerModelLoaderOutput:
-        model_key = self.model.key
+        base_model = self.model.base_model
+        model_name = self.model.model_name
+        model_type = ModelType.Main
 
         # TODO: not found exceptions
-        if not context.models.exists(model_key):
-            raise Exception(f"Unknown model: {model_key}")
+        if not context.models.exists(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+        ):
+            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
 
         return SDXLRefinerModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.UNet,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Scheduler,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip2=ClipField(
                 tokenizer=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Tokenizer2,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer2,
                 ),
                 text_encoder=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.TextEncoder2,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder2,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Vae,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
                 ),
             ),
         )

invokeai/app/invocations/t2i_adapter.py

@@ -1,6 +1,6 @@
 from typing import Union
 
-from pydantic import BaseModel, Field, field_validator, model_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -12,10 +12,14 @@ from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESI
 from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField, OutputField
 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_management.models.base import BaseModelType
 
 
 class T2IAdapterModelField(BaseModel):
-    key: str = Field(description="Model record key for the T2I-Adapter model")
+    model_name: str = Field(description="Name of the T2I-Adapter model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class T2IAdapterField(BaseModel):

invokeai/app/services/bulk_download/bulk_download_base.py

@@ -1,44 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import Optional
-
-
-class BulkDownloadBase(ABC):
-    """Responsible for creating a zip file containing the images specified by the given image names or board id."""
-
-    @abstractmethod
-    def handler(
-        self, image_names: Optional[list[str]], board_id: Optional[str], bulk_download_item_id: Optional[str]
-    ) -> None:
-        """
-        Create a zip file containing the images specified by the given image names or board id.
-
-        :param image_names: A list of image names to include in the zip file.
-        :param board_id: The ID of the board. If provided, all images associated with the board will be included in the zip file.
-        :param bulk_download_item_id: The bulk_download_item_id that will be used to retrieve the bulk download item when it is prepared, if none is provided a uuid will be generated.
-        """
-
-    @abstractmethod
-    def get_path(self, bulk_download_item_name: str) -> str:
-        """
-        Get the path to the bulk download file.
-
-        :param bulk_download_item_name: The name of the bulk download item.
-        :return: The path to the bulk download file.
-        """
-
-    @abstractmethod
-    def generate_item_id(self, board_id: Optional[str]) -> str:
-        """
-        Generate an item ID for a bulk download item.
-
-        :param board_id: The ID of the board whose name is to be included in the item id.
-        :return: The generated item ID.
-        """
-
-    @abstractmethod
-    def delete(self, bulk_download_item_name: str) -> None:
-        """
-        Delete the bulk download file.
-
-        :param bulk_download_item_name: The name of the bulk download item.
-        """

invokeai/app/services/bulk_download/bulk_download_common.py

@@ -1,25 +0,0 @@
-DEFAULT_BULK_DOWNLOAD_ID = "default"
-
-
-class BulkDownloadException(Exception):
-    """Exception raised when a bulk download fails."""
-
-    def __init__(self, message="Bulk download failed"):
-        super().__init__(message)
-        self.message = message
-
-
-class BulkDownloadTargetException(BulkDownloadException):
-    """Exception raised when a bulk download target is not found."""
-
-    def __init__(self, message="The bulk download target was not found"):
-        super().__init__(message)
-        self.message = message
-
-
-class BulkDownloadParametersException(BulkDownloadException):
-    """Exception raised when a bulk download parameter is invalid."""
-
-    def __init__(self, message="No image names or board ID provided"):
-        super().__init__(message)
-        self.message = message

invokeai/app/services/bulk_download/bulk_download_default.py

@@ -1,157 +0,0 @@
-from pathlib import Path
-from tempfile import TemporaryDirectory
-from typing import Optional, Union
-from zipfile import ZipFile
-
-from invokeai.app.services.board_records.board_records_common import BoardRecordNotFoundException
-from invokeai.app.services.bulk_download.bulk_download_common import (
-    DEFAULT_BULK_DOWNLOAD_ID,
-    BulkDownloadException,
-    BulkDownloadParametersException,
-    BulkDownloadTargetException,
-)
-from invokeai.app.services.image_records.image_records_common import ImageRecordNotFoundException
-from invokeai.app.services.images.images_common import ImageDTO
-from invokeai.app.services.invoker import Invoker
-from invokeai.app.util.misc import uuid_string
-
-from .bulk_download_base import BulkDownloadBase
-
-
-class BulkDownloadService(BulkDownloadBase):
-    def start(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-
-    def __init__(self):
-        self._temp_directory = TemporaryDirectory()
-        self._bulk_downloads_folder = Path(self._temp_directory.name) / "bulk_downloads"
-        self._bulk_downloads_folder.mkdir(parents=True, exist_ok=True)
-
-    def handler(
-        self, image_names: Optional[list[str]], board_id: Optional[str], bulk_download_item_id: Optional[str]
-    ) -> None:
-        bulk_download_id: str = DEFAULT_BULK_DOWNLOAD_ID
-        bulk_download_item_id = bulk_download_item_id or uuid_string()
-        bulk_download_item_name = bulk_download_item_id + ".zip"
-
-        self._signal_job_started(bulk_download_id, bulk_download_item_id, bulk_download_item_name)
-
-        try:
-            image_dtos: list[ImageDTO] = []
-
-            if board_id:
-                image_dtos = self._board_handler(board_id)
-            elif image_names:
-                image_dtos = self._image_handler(image_names)
-            else:
-                raise BulkDownloadParametersException()
-
-            bulk_download_item_name: str = self._create_zip_file(image_dtos, bulk_download_item_id)
-            self._signal_job_completed(bulk_download_id, bulk_download_item_id, bulk_download_item_name)
-        except (
-            ImageRecordNotFoundException,
-            BoardRecordNotFoundException,
-            BulkDownloadException,
-            BulkDownloadParametersException,
-        ) as e:
-            self._signal_job_failed(bulk_download_id, bulk_download_item_id, bulk_download_item_name, e)
-        except Exception as e:
-            self._signal_job_failed(bulk_download_id, bulk_download_item_id, bulk_download_item_name, e)
-            self._invoker.services.logger.error("Problem bulk downloading images.")
-            raise e
-
-    def _image_handler(self, image_names: list[str]) -> list[ImageDTO]:
-        return [self._invoker.services.images.get_dto(image_name) for image_name in image_names]
-
-    def _board_handler(self, board_id: str) -> list[ImageDTO]:
-        image_names = self._invoker.services.board_image_records.get_all_board_image_names_for_board(board_id)
-        return self._image_handler(image_names)
-
-    def generate_item_id(self, board_id: Optional[str]) -> str:
-        return uuid_string() if board_id is None else self._get_clean_board_name(board_id) + "_" + uuid_string()
-
-    def _get_clean_board_name(self, board_id: str) -> str:
-        if board_id == "none":
-            return "Uncategorized"
-
-        return self._clean_string_to_path_safe(self._invoker.services.board_records.get(board_id).board_name)
-
-    def _create_zip_file(self, image_dtos: list[ImageDTO], bulk_download_item_id: str) -> str:
-        """
-        Create a zip file containing the images specified by the given image names or board id.
-        If download with the same bulk_download_id already exists, it will be overwritten.
-
-        :return: The name of the zip file.
-        """
-        zip_file_name = bulk_download_item_id + ".zip"
-        zip_file_path = self._bulk_downloads_folder / (zip_file_name)
-
-        with ZipFile(zip_file_path, "w") as zip_file:
-            for image_dto in image_dtos:
-                image_zip_path = Path(image_dto.image_category.value) / image_dto.image_name
-                image_disk_path = self._invoker.services.images.get_path(image_dto.image_name)
-                zip_file.write(image_disk_path, arcname=image_zip_path)
-
-        return str(zip_file_name)
-
-    # from https://stackoverflow.com/questions/7406102/create-sane-safe-filename-from-any-unsafe-string
-    def _clean_string_to_path_safe(self, s: str) -> str:
-        """Clean a string to be path safe."""
-        return "".join([c for c in s if c.isalpha() or c.isdigit() or c == " " or c == "_" or c == "-"]).rstrip()
-
-    def _signal_job_started(
-        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
-    ) -> None:
-        """Signal that a bulk download job has started."""
-        if self._invoker:
-            assert bulk_download_id is not None
-            self._invoker.services.events.emit_bulk_download_started(
-                bulk_download_id=bulk_download_id,
-                bulk_download_item_id=bulk_download_item_id,
-                bulk_download_item_name=bulk_download_item_name,
-            )
-
-    def _signal_job_completed(
-        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
-    ) -> None:
-        """Signal that a bulk download job has completed."""
-        if self._invoker:
-            assert bulk_download_id is not None
-            assert bulk_download_item_name is not None
-            self._invoker.services.events.emit_bulk_download_completed(
-                bulk_download_id=bulk_download_id,
-                bulk_download_item_id=bulk_download_item_id,
-                bulk_download_item_name=bulk_download_item_name,
-            )
-
-    def _signal_job_failed(
-        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str, exception: Exception
-    ) -> None:
-        """Signal that a bulk download job has failed."""
-        if self._invoker:
-            assert bulk_download_id is not None
-            assert exception is not None
-            self._invoker.services.events.emit_bulk_download_failed(
-                bulk_download_id=bulk_download_id,
-                bulk_download_item_id=bulk_download_item_id,
-                bulk_download_item_name=bulk_download_item_name,
-                error=str(exception),
-            )
-
-    def stop(self, *args, **kwargs):
-        self._temp_directory.cleanup()
-
-    def delete(self, bulk_download_item_name: str) -> None:
-        path = self.get_path(bulk_download_item_name)
-        Path(path).unlink()
-
-    def get_path(self, bulk_download_item_name: str) -> str:
-        path = str(self._bulk_downloads_folder / bulk_download_item_name)
-        if not self._is_valid_path(path):
-            raise BulkDownloadTargetException()
-        return path
-
-    def _is_valid_path(self, path: Union[str, Path]) -> bool:
-        """Validates the path given for a bulk download."""
-        path = path if isinstance(path, Path) else Path(path)
-        return path.exists()

invokeai/app/services/config/config_base.py

@@ -27,11 +27,11 @@ class InvokeAISettings(BaseSettings):
     """Runtime configuration settings in which default values are read from an omegaconf .yaml file."""
 
     initconf: ClassVar[Optional[DictConfig]] = None
-    argparse_groups: ClassVar[Dict[str, Any]] = {}
+    argparse_groups: ClassVar[Dict] = {}
 
     model_config = SettingsConfigDict(env_file_encoding="utf-8", arbitrary_types_allowed=True, case_sensitive=True)
 
-    def parse_args(self, argv: Optional[List[str]] = sys.argv[1:]) -> None:
+    def parse_args(self, argv: Optional[list] = sys.argv[1:]):
         """Call to parse command-line arguments."""
         parser = self.get_parser()
         opt, unknown_opts = parser.parse_known_args(argv)
@@ -68,7 +68,7 @@ class InvokeAISettings(BaseSettings):
         return OmegaConf.to_yaml(conf)
 
     @classmethod
-    def add_parser_arguments(cls, parser: ArgumentParser) -> None:
+    def add_parser_arguments(cls, parser):
         """Dynamically create arguments for a settings parser."""
         if "type" in get_type_hints(cls):
             settings_stanza = get_args(get_type_hints(cls)["type"])[0]
@@ -117,8 +117,7 @@ class InvokeAISettings(BaseSettings):
         """Return the category of a setting."""
         hints = get_type_hints(cls)
         if command_field in hints:
-            result: str = get_args(hints[command_field])[0]
-            return result
+            return get_args(hints[command_field])[0]
         else:
             return "Uncategorized"
 
@@ -156,11 +155,10 @@ class InvokeAISettings(BaseSettings):
             "lora_dir",
             "embedding_dir",
             "controlnet_dir",
-            "conf_path",
         ]
 
     @classmethod
-    def add_field_argument(cls, command_parser, name: str, field, default_override=None) -> None:
+    def add_field_argument(cls, command_parser, name: str, field, default_override=None):
         """Add the argparse arguments for a setting parser."""
         field_type = get_type_hints(cls).get(name)
         default = (

invokeai/app/services/config/config_common.py

@@ -21,7 +21,7 @@ class PagingArgumentParser(argparse.ArgumentParser):
     It also supports reading defaults from an init file.
     """
 
-    def print_help(self, file=None) -> None:
+    def print_help(self, file=None):
         text = self.format_help()
         pydoc.pager(text)
 

invokeai/app/services/config/config_default.py

@@ -30,6 +30,7 @@ InvokeAI:
     lora_dir: null
     embedding_dir: null
     controlnet_dir: null
+    conf_path: configs/models.yaml
     models_dir: models
     legacy_conf_dir: configs/stable-diffusion
     db_dir: databases
@@ -122,6 +123,7 @@ a Path object:
 
  root_path          - path to InvokeAI root
  output_path        - path to default outputs directory
+ model_conf_path    - path to models.yaml
  conf               - alias for the above
  embedding_path     - path to the embeddings directory
  lora_path          - path to the LoRA directory
@@ -161,17 +163,17 @@ two configs are kept in separate sections of the config file:
   InvokeAI:
      Paths:
         root: /home/lstein/invokeai-main
+        conf_path: configs/models.yaml
         legacy_conf_dir: configs/stable-diffusion
         outdir: outputs
      ...
 
 """
-
 from __future__ import annotations
 
 import os
 from pathlib import Path
-from typing import Any, ClassVar, Dict, List, Literal, Optional
+from typing import Any, ClassVar, Dict, List, Literal, Optional, Union
 
 from omegaconf import DictConfig, OmegaConf
 from pydantic import Field
@@ -183,9 +185,7 @@ from .config_base import InvokeAISettings
 INIT_FILE = Path("invokeai.yaml")
 DB_FILE = Path("invokeai.db")
 LEGACY_INIT_FILE = Path("invokeai.init")
-DEFAULT_RAM_CACHE = 10.0
-DEFAULT_VRAM_CACHE = 0.25
-DEFAULT_CONVERT_CACHE = 20.0
+DEFAULT_MAX_VRAM = 0.5
 
 
 class Categories(object):
@@ -235,8 +235,8 @@ class InvokeAIAppConfig(InvokeAISettings):
     # PATHS
     root                : Optional[Path] = Field(default=None, description='InvokeAI runtime root directory', json_schema_extra=Categories.Paths)
     autoimport_dir      : Path = Field(default=Path('autoimport'), description='Path to a directory of models files to be imported on startup.', json_schema_extra=Categories.Paths)
+    conf_path           : Path = Field(default=Path('configs/models.yaml'), description='Path to models definition file', json_schema_extra=Categories.Paths)
     models_dir          : Path = Field(default=Path('models'), description='Path to the models directory', json_schema_extra=Categories.Paths)
-    convert_cache_dir   : Path = Field(default=Path('models/.cache'), description='Path to the converted models cache directory', json_schema_extra=Categories.Paths)
     legacy_conf_dir     : Path = Field(default=Path('configs/stable-diffusion'), description='Path to directory of legacy checkpoint config files', json_schema_extra=Categories.Paths)
     db_dir              : Path = Field(default=Path('databases'), description='Path to InvokeAI databases directory', json_schema_extra=Categories.Paths)
     outdir              : Path = Field(default=Path('outputs'), description='Default folder for output images', json_schema_extra=Categories.Paths)
@@ -260,10 +260,8 @@ class InvokeAIAppConfig(InvokeAISettings):
     version             : bool = Field(default=False, description="Show InvokeAI version and exit", json_schema_extra=Categories.Other)
 
     # CACHE
-    ram                 : float = Field(default=DEFAULT_RAM_CACHE, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
-    vram                : float = Field(default=DEFAULT_VRAM_CACHE, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
-    convert_cache       : float = Field(default=DEFAULT_CONVERT_CACHE, ge=0, description="Maximum size of on-disk converted models cache (GB)", json_schema_extra=Categories.ModelCache)
-
+    ram                 : float = Field(default=7.5, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
+    vram                : float = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
     lazy_offload        : bool = Field(default=True, description="Keep models in VRAM until their space is needed", json_schema_extra=Categories.ModelCache, )
     log_memory_usage    : bool = Field(default=False, description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.", json_schema_extra=Categories.ModelCache)
 
@@ -298,7 +296,6 @@ class InvokeAIAppConfig(InvokeAISettings):
     lora_dir            : Optional[Path] = Field(default=None, description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', json_schema_extra=Categories.Paths)
     embedding_dir       : Optional[Path] = Field(default=None, description='Path to a directory of Textual Inversion embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
     controlnet_dir      : Optional[Path] = Field(default=None, description='Path to a directory of ControlNet embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
-    conf_path           : Path = Field(default=Path('configs/models.yaml'), description='Path to models definition file', json_schema_extra=Categories.Paths)
 
     # this is not referred to in the source code and can be removed entirely
     #free_gpu_mem        : Optional[bool] = Field(default=None, description="If true, purge model from GPU after each generation.", json_schema_extra=Categories.MemoryPerformance)
@@ -407,11 +404,6 @@ class InvokeAIAppConfig(InvokeAISettings):
         """Path to the models directory."""
         return self._resolve(self.models_dir)
 
-    @property
-    def models_convert_cache_path(self) -> Path:
-        """Path to the converted cache models directory."""
-        return self._resolve(self.convert_cache_dir)
-
     @property
     def custom_nodes_path(self) -> Path:
         """Path to the custom nodes directory."""
@@ -441,20 +433,15 @@ class InvokeAIAppConfig(InvokeAISettings):
         return True
 
     @property
-    def ram_cache_size(self) -> float:
-        """Return the ram cache size using the legacy or modern setting (GB)."""
+    def ram_cache_size(self) -> Union[Literal["auto"], float]:
+        """Return the ram cache size using the legacy or modern setting."""
         return self.max_cache_size or self.ram
 
     @property
-    def vram_cache_size(self) -> float:
-        """Return the vram cache size using the legacy or modern setting (GB)."""
+    def vram_cache_size(self) -> Union[Literal["auto"], float]:
+        """Return the vram cache size using the legacy or modern setting."""
         return self.max_vram_cache_size or self.vram
 
-    @property
-    def convert_cache_size(self) -> float:
-        """Return the convert cache size on disk (GB)."""
-        return self.convert_cache
-
     @property
     def use_cpu(self) -> bool:
         """Return true if the device is set to CPU or the always_use_cpu flag is set."""

invokeai/app/services/download/__init__.py

@@ -1,5 +1,4 @@
 """Init file for download queue."""
-
 from .download_base import DownloadJob, DownloadJobStatus, DownloadQueueServiceBase, UnknownJobIDException
 from .download_default import DownloadQueueService, TqdmProgress
 

invokeai/app/services/download/download_base.py

@@ -260,16 +260,3 @@ class DownloadQueueServiceBase(ABC):
     def join(self) -> None:
         """Wait until all jobs are off the queue."""
         pass
-
-    @abstractmethod
-    def wait_for_job(self, job: DownloadJob, timeout: int = 0) -> DownloadJob:
-        """Wait until the indicated download job has reached a terminal state.
-
-        This will block until the indicated install job has completed,
-        been cancelled, or errored out.
-
-        :param job: The job to wait on.
-        :param timeout: Wait up to indicated number of seconds. Raise a TimeoutError if
-        the job hasn't completed within the indicated time.
-        """
-        pass

invokeai/app/services/download/download_default.py

@@ -4,11 +4,10 @@
 import os
 import re
 import threading
-import time
 import traceback
 from pathlib import Path
 from queue import Empty, PriorityQueue
-from typing import Any, Dict, List, Optional, Set
+from typing import Any, Dict, List, Optional
 
 import requests
 from pydantic.networks import AnyHttpUrl
@@ -49,12 +48,11 @@ class DownloadQueueService(DownloadQueueServiceBase):
         :param max_parallel_dl: Number of simultaneous downloads allowed [5].
         :param requests_session: Optional requests.sessions.Session object, for unit tests.
         """
-        self._jobs: Dict[int, DownloadJob] = {}
+        self._jobs = {}
         self._next_job_id = 0
-        self._queue: PriorityQueue[DownloadJob] = PriorityQueue()
+        self._queue = PriorityQueue()
         self._stop_event = threading.Event()
-        self._job_completed_event = threading.Event()
-        self._worker_pool: Set[threading.Thread] = set()
+        self._worker_pool = set()
         self._lock = threading.Lock()
         self._logger = InvokeAILogger.get_logger("DownloadQueueService")
         self._event_bus = event_bus
@@ -190,16 +188,6 @@ class DownloadQueueService(DownloadQueueServiceBase):
             if not job.in_terminal_state:
                 self.cancel_job(job)
 
-    def wait_for_job(self, job: DownloadJob, timeout: int = 0) -> DownloadJob:
-        """Block until the indicated job has reached terminal state, or when timeout limit reached."""
-        start = time.time()
-        while not job.in_terminal_state:
-            if self._job_completed_event.wait(timeout=0.25):  # in case we miss an event
-                self._job_completed_event.clear()
-            if timeout > 0 and time.time() - start > timeout:
-                raise TimeoutError("Timeout exceeded")
-        return job
-
     def _start_workers(self, max_workers: int) -> None:
         """Start the requested number of worker threads."""
         self._stop_event.clear()
@@ -224,6 +212,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
                 job.job_started = get_iso_timestamp()
                 self._do_download(job)
                 self._signal_job_complete(job)
+
             except (OSError, HTTPError) as excp:
                 job.error_type = excp.__class__.__name__ + f"({str(excp)})"
                 job.error = traceback.format_exc()
@@ -234,7 +223,6 @@ class DownloadQueueService(DownloadQueueServiceBase):
 
             finally:
                 job.job_ended = get_iso_timestamp()
-                self._job_completed_event.set()  # signal a change to terminal state
                 self._queue.task_done()
         self._logger.debug(f"Download queue worker thread {threading.current_thread().name} exiting.")
 
@@ -419,11 +407,11 @@ class DownloadQueueService(DownloadQueueServiceBase):
 
 # Example on_progress event handler to display a TQDM status bar
 # Activate with:
-#   download_service.download(DownloadJob('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().update))
+#   download_service.download('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().job_update
 class TqdmProgress(object):
     """TQDM-based progress bar object to use in on_progress handlers."""
 
-    _bars: Dict[int, tqdm]  # type: ignore
+    _bars: Dict[int, tqdm]  # the tqdm object
     _last: Dict[int, int]  # last bytes downloaded
 
     def __init__(self) -> None:  # noqa D107

invokeai/app/services/events/events_base.py

@@ -3,7 +3,7 @@
 
 from typing import Any, Dict, List, Optional, Union
 
-from invokeai.app.services.session_processor.session_processor_common import ProgressImage
+from invokeai.app.services.invocation_processor.invocation_processor_common import ProgressImage
 from invokeai.app.services.session_queue.session_queue_common import (
     BatchStatus,
     EnqueueBatchResult,
@@ -11,12 +11,12 @@ from invokeai.app.services.session_queue.session_queue_common import (
     SessionQueueStatus,
 )
 from invokeai.app.util.misc import get_timestamp
-from invokeai.backend.model_manager import AnyModelConfig
+from invokeai.backend.model_management.model_manager import LoadedModelInfo
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
 
 
 class EventServiceBase:
     queue_event: str = "queue_event"
-    bulk_download_event: str = "bulk_download_event"
     download_event: str = "download_event"
     model_event: str = "model_event"
 
@@ -25,14 +25,6 @@ class EventServiceBase:
     def dispatch(self, event_name: str, payload: Any) -> None:
         pass
 
-    def _emit_bulk_download_event(self, event_name: str, payload: dict) -> None:
-        """Bulk download events are emitted to a room with queue_id as the room name"""
-        payload["timestamp"] = get_timestamp()
-        self.dispatch(
-            event_name=EventServiceBase.bulk_download_event,
-            payload={"event": event_name, "data": payload},
-        )
-
     def __emit_queue_event(self, event_name: str, payload: dict) -> None:
         """Queue events are emitted to a room with queue_id as the room name"""
         payload["timestamp"] = get_timestamp()
@@ -179,7 +171,10 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        model_config: AnyModelConfig,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: SubModelType,
     ) -> None:
         """Emitted when a model is requested"""
         self.__emit_queue_event(
@@ -189,7 +184,10 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "model_config": model_config.model_dump(),
+                "model_name": model_name,
+                "base_model": base_model,
+                "model_type": model_type,
+                "submodel": submodel,
             },
         )
 
@@ -199,7 +197,11 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        model_config: AnyModelConfig,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: SubModelType,
+        loaded_model_info: LoadedModelInfo,
     ) -> None:
         """Emitted when a model is correctly loaded (returns model info)"""
         self.__emit_queue_event(
@@ -209,7 +211,59 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "model_config": model_config.model_dump(),
+                "model_name": model_name,
+                "base_model": base_model,
+                "model_type": model_type,
+                "submodel": submodel,
+                "hash": loaded_model_info.hash,
+                "location": str(loaded_model_info.location),
+                "precision": str(loaded_model_info.precision),
+            },
+        )
+
+    def emit_session_retrieval_error(
+        self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
+        error_type: str,
+        error: str,
+    ) -> None:
+        """Emitted when session retrieval fails"""
+        self.__emit_queue_event(
+            event_name="session_retrieval_error",
+            payload={
+                "queue_id": queue_id,
+                "queue_item_id": queue_item_id,
+                "queue_batch_id": queue_batch_id,
+                "graph_execution_state_id": graph_execution_state_id,
+                "error_type": error_type,
+                "error": error,
+            },
+        )
+
+    def emit_invocation_retrieval_error(
+        self,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
+        node_id: str,
+        error_type: str,
+        error: str,
+    ) -> None:
+        """Emitted when invocation retrieval fails"""
+        self.__emit_queue_event(
+            event_name="invocation_retrieval_error",
+            payload={
+                "queue_id": queue_id,
+                "queue_item_id": queue_item_id,
+                "queue_batch_id": queue_batch_id,
+                "graph_execution_state_id": graph_execution_state_id,
+                "node_id": node_id,
+                "error_type": error_type,
+                "error": error,
             },
         )
 
@@ -357,7 +411,6 @@ class EventServiceBase:
         bytes: int,
         total_bytes: int,
         parts: List[Dict[str, Union[str, int]]],
-        id: int,
     ) -> None:
         """
         Emit at intervals while the install job is in progress (remote models only).
@@ -377,7 +430,6 @@ class EventServiceBase:
                 "bytes": bytes,
                 "total_bytes": total_bytes,
                 "parts": parts,
-                "id": id,
             },
         )
 
@@ -392,7 +444,7 @@ class EventServiceBase:
             payload={"source": source},
         )
 
-    def emit_model_install_completed(self, source: str, key: str, id: int, total_bytes: Optional[int] = None) -> None:
+    def emit_model_install_completed(self, source: str, key: str, total_bytes: Optional[int] = None) -> None:
         """
         Emit when an install job is completed successfully.
 
@@ -402,7 +454,11 @@ class EventServiceBase:
         """
         self.__emit_model_event(
             event_name="model_install_completed",
-            payload={"source": source, "total_bytes": total_bytes, "key": key, "id": id},
+            payload={
+                "source": source,
+                "total_bytes": total_bytes,
+                "key": key,
+            },
         )
 
     def emit_model_install_cancelled(self, source: str) -> None:
@@ -416,7 +472,12 @@ class EventServiceBase:
             payload={"source": source},
         )
 
-    def emit_model_install_error(self, source: str, error_type: str, error: str, id: int) -> None:
+    def emit_model_install_error(
+        self,
+        source: str,
+        error_type: str,
+        error: str,
+    ) -> None:
         """
         Emit when an install job encounters an exception.
 
@@ -426,45 +487,9 @@ class EventServiceBase:
         """
         self.__emit_model_event(
             event_name="model_install_error",
-            payload={"source": source, "error_type": error_type, "error": error, "id": id},
-        )
-
-    def emit_bulk_download_started(
-        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
-    ) -> None:
-        """Emitted when a bulk download starts"""
-        self._emit_bulk_download_event(
-            event_name="bulk_download_started",
             payload={
-                "bulk_download_id": bulk_download_id,
-                "bulk_download_item_id": bulk_download_item_id,
-                "bulk_download_item_name": bulk_download_item_name,
-            },
-        )
-
-    def emit_bulk_download_completed(
-        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
-    ) -> None:
-        """Emitted when a bulk download completes"""
-        self._emit_bulk_download_event(
-            event_name="bulk_download_completed",
-            payload={
-                "bulk_download_id": bulk_download_id,
-                "bulk_download_item_id": bulk_download_item_id,
-                "bulk_download_item_name": bulk_download_item_name,
-            },
-        )
-
-    def emit_bulk_download_failed(
-        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str, error: str
-    ) -> None:
-        """Emitted when a bulk download fails"""
-        self._emit_bulk_download_event(
-            event_name="bulk_download_failed",
-            payload={
-                "bulk_download_id": bulk_download_id,
-                "bulk_download_item_id": bulk_download_item_id,
-                "bulk_download_item_name": bulk_download_item_name,
+                "source": source,
+                "error_type": error_type,
                 "error": error,
             },
         )

invokeai/app/services/invocation_processor/invocation_processor_base.py

@@ -0,0 +1,5 @@
+from abc import ABC
+
+
+class InvocationProcessorABC(ABC):  # noqa: B024
+    pass

invokeai/app/services/invocation_processor/invocation_processor_common.py

@@ -0,0 +1,15 @@
+from pydantic import BaseModel, Field
+
+
+class ProgressImage(BaseModel):
+    """The progress image sent intermittently during processing"""
+
+    width: int = Field(description="The effective width of the image in pixels")
+    height: int = Field(description="The effective height of the image in pixels")
+    dataURL: str = Field(description="The image data as a b64 data URL")
+
+
+class CanceledException(Exception):
+    """Execution canceled by user."""
+
+    pass

invokeai/app/services/invocation_processor/invocation_processor_default.py

@@ -0,0 +1,241 @@
+import time
+import traceback
+from contextlib import suppress
+from threading import BoundedSemaphore, Event, Thread
+from typing import Optional
+
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.invocation_queue.invocation_queue_common import InvocationQueueItem
+from invokeai.app.services.invocation_stats.invocation_stats_common import (
+    GESStatsNotFoundError,
+)
+from invokeai.app.services.shared.invocation_context import InvocationContextData, build_invocation_context
+from invokeai.app.util.profiler import Profiler
+
+from ..invoker import Invoker
+from .invocation_processor_base import InvocationProcessorABC
+from .invocation_processor_common import CanceledException
+
+
+class DefaultInvocationProcessor(InvocationProcessorABC):
+    __invoker_thread: Thread
+    __stop_event: Event
+    __invoker: Invoker
+    __threadLimit: BoundedSemaphore
+
+    def start(self, invoker: Invoker) -> None:
+        # if we do want multithreading at some point, we could make this configurable
+        self.__threadLimit = BoundedSemaphore(1)
+        self.__invoker = invoker
+        self.__stop_event = Event()
+        self.__invoker_thread = Thread(
+            name="invoker_processor",
+            target=self.__process,
+            kwargs={"stop_event": self.__stop_event},
+        )
+        self.__invoker_thread.daemon = True  # TODO: make async and do not use threads
+        self.__invoker_thread.start()
+
+    def stop(self, *args, **kwargs) -> None:
+        self.__stop_event.set()
+
+    def __process(self, stop_event: Event):
+        try:
+            self.__threadLimit.acquire()
+            queue_item: Optional[InvocationQueueItem] = None
+
+            profiler = (
+                Profiler(
+                    logger=self.__invoker.services.logger,
+                    output_dir=self.__invoker.services.configuration.profiles_path,
+                    prefix=self.__invoker.services.configuration.profile_prefix,
+                )
+                if self.__invoker.services.configuration.profile_graphs
+                else None
+            )
+
+            def stats_cleanup(graph_execution_state_id: str) -> None:
+                if profiler:
+                    profile_path = profiler.stop()
+                    stats_path = profile_path.with_suffix(".json")
+                    self.__invoker.services.performance_statistics.dump_stats(
+                        graph_execution_state_id=graph_execution_state_id, output_path=stats_path
+                    )
+                with suppress(GESStatsNotFoundError):
+                    self.__invoker.services.performance_statistics.log_stats(graph_execution_state_id)
+                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state_id)
+
+            while not stop_event.is_set():
+                try:
+                    queue_item = self.__invoker.services.queue.get()
+                except Exception as e:
+                    self.__invoker.services.logger.error("Exception while getting from queue:\n%s" % e)
+
+                if not queue_item:  # Probably stopping
+                    # do not hammer the queue
+                    time.sleep(0.5)
+                    continue
+
+                if profiler and profiler.profile_id != queue_item.graph_execution_state_id:
+                    profiler.start(profile_id=queue_item.graph_execution_state_id)
+
+                try:
+                    graph_execution_state = self.__invoker.services.graph_execution_manager.get(
+                        queue_item.graph_execution_state_id
+                    )
+                except Exception as e:
+                    self.__invoker.services.logger.error("Exception while retrieving session:\n%s" % e)
+                    self.__invoker.services.events.emit_session_retrieval_error(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
+                        graph_execution_state_id=queue_item.graph_execution_state_id,
+                        error_type=e.__class__.__name__,
+                        error=traceback.format_exc(),
+                    )
+                    continue
+
+                try:
+                    invocation = graph_execution_state.execution_graph.get_node(queue_item.invocation_id)
+                except Exception as e:
+                    self.__invoker.services.logger.error("Exception while retrieving invocation:\n%s" % e)
+                    self.__invoker.services.events.emit_invocation_retrieval_error(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
+                        graph_execution_state_id=queue_item.graph_execution_state_id,
+                        node_id=queue_item.invocation_id,
+                        error_type=e.__class__.__name__,
+                        error=traceback.format_exc(),
+                    )
+                    continue
+
+                # get the source node id to provide to clients (the prepared node id is not as useful)
+                source_node_id = graph_execution_state.prepared_source_mapping[invocation.id]
+
+                # Send starting event
+                self.__invoker.services.events.emit_invocation_started(
+                    queue_batch_id=queue_item.session_queue_batch_id,
+                    queue_item_id=queue_item.session_queue_item_id,
+                    queue_id=queue_item.session_queue_id,
+                    graph_execution_state_id=graph_execution_state.id,
+                    node=invocation.model_dump(),
+                    source_node_id=source_node_id,
+                )
+
+                # Invoke
+                try:
+                    graph_id = graph_execution_state.id
+                    with self.__invoker.services.performance_statistics.collect_stats(invocation, graph_id):
+                        # use the internal invoke_internal(), which wraps the node's invoke() method,
+                        # which handles a few things:
+                        # - nodes that require a value, but get it only from a connection
+                        # - referencing the invocation cache instead of executing the node
+                        context_data = InvocationContextData(
+                            invocation=invocation,
+                            session_id=graph_id,
+                            workflow=queue_item.workflow,
+                            source_node_id=source_node_id,
+                            queue_id=queue_item.session_queue_id,
+                            queue_item_id=queue_item.session_queue_item_id,
+                            batch_id=queue_item.session_queue_batch_id,
+                        )
+                        context = build_invocation_context(
+                            services=self.__invoker.services,
+                            context_data=context_data,
+                        )
+                        outputs = invocation.invoke_internal(context=context, services=self.__invoker.services)
+
+                        # Check queue to see if this is canceled, and skip if so
+                        if self.__invoker.services.queue.is_canceled(graph_execution_state.id):
+                            continue
+
+                        # Save outputs and history
+                        graph_execution_state.complete(invocation.id, outputs)
+
+                        # Save the state changes
+                        self.__invoker.services.graph_execution_manager.set(graph_execution_state)
+
+                        # Send complete event
+                        self.__invoker.services.events.emit_invocation_complete(
+                            queue_batch_id=queue_item.session_queue_batch_id,
+                            queue_item_id=queue_item.session_queue_item_id,
+                            queue_id=queue_item.session_queue_id,
+                            graph_execution_state_id=graph_execution_state.id,
+                            node=invocation.model_dump(),
+                            source_node_id=source_node_id,
+                            result=outputs.model_dump(),
+                        )
+
+                except KeyboardInterrupt:
+                    pass
+
+                except CanceledException:
+                    stats_cleanup(graph_execution_state.id)
+                    pass
+
+                except Exception as e:
+                    error = traceback.format_exc()
+                    logger.error(error)
+
+                    # Save error
+                    graph_execution_state.set_node_error(invocation.id, error)
+
+                    # Save the state changes
+                    self.__invoker.services.graph_execution_manager.set(graph_execution_state)
+
+                    self.__invoker.services.logger.error("Error while invoking:\n%s" % e)
+                    # Send error event
+                    self.__invoker.services.events.emit_invocation_error(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
+                        graph_execution_state_id=graph_execution_state.id,
+                        node=invocation.model_dump(),
+                        source_node_id=source_node_id,
+                        error_type=e.__class__.__name__,
+                        error=error,
+                    )
+                    pass
+
+                # Check queue to see if this is canceled, and skip if so
+                if self.__invoker.services.queue.is_canceled(graph_execution_state.id):
+                    continue
+
+                # Queue any further commands if invoking all
+                is_complete = graph_execution_state.is_complete()
+                if queue_item.invoke_all and not is_complete:
+                    try:
+                        self.__invoker.invoke(
+                            session_queue_batch_id=queue_item.session_queue_batch_id,
+                            session_queue_item_id=queue_item.session_queue_item_id,
+                            session_queue_id=queue_item.session_queue_id,
+                            graph_execution_state=graph_execution_state,
+                            workflow=queue_item.workflow,
+                            invoke_all=True,
+                        )
+                    except Exception as e:
+                        self.__invoker.services.logger.error("Error while invoking:\n%s" % e)
+                        self.__invoker.services.events.emit_invocation_error(
+                            queue_batch_id=queue_item.session_queue_batch_id,
+                            queue_item_id=queue_item.session_queue_item_id,
+                            queue_id=queue_item.session_queue_id,
+                            graph_execution_state_id=graph_execution_state.id,
+                            node=invocation.model_dump(),
+                            source_node_id=source_node_id,
+                            error_type=e.__class__.__name__,
+                            error=traceback.format_exc(),
+                        )
+                elif is_complete:
+                    self.__invoker.services.events.emit_graph_execution_complete(
+                        queue_batch_id=queue_item.session_queue_batch_id,
+                        queue_item_id=queue_item.session_queue_item_id,
+                        queue_id=queue_item.session_queue_id,
+                        graph_execution_state_id=graph_execution_state.id,
+                    )
+                    stats_cleanup(graph_execution_state.id)
+
+        except KeyboardInterrupt:
+            pass  # Log something? KeyboardInterrupt is probably not going to be seen by the processor
+        finally:
+            self.__threadLimit.release()

invokeai/app/services/invocation_queue/invocation_queue_base.py

@@ -0,0 +1,26 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from abc import ABC, abstractmethod
+from typing import Optional
+
+from .invocation_queue_common import InvocationQueueItem
+
+
+class InvocationQueueABC(ABC):
+    """Abstract base class for all invocation queues"""
+
+    @abstractmethod
+    def get(self) -> InvocationQueueItem:
+        pass
+
+    @abstractmethod
+    def put(self, item: Optional[InvocationQueueItem]) -> None:
+        pass
+
+    @abstractmethod
+    def cancel(self, graph_execution_state_id: str) -> None:
+        pass
+
+    @abstractmethod
+    def is_canceled(self, graph_execution_state_id: str) -> bool:
+        pass

invokeai/app/services/invocation_queue/invocation_queue_common.py

@@ -0,0 +1,23 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import time
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
+
+
+class InvocationQueueItem(BaseModel):
+    graph_execution_state_id: str = Field(description="The ID of the graph execution state")
+    invocation_id: str = Field(description="The ID of the node being invoked")
+    session_queue_id: str = Field(description="The ID of the session queue from which this invocation queue item came")
+    session_queue_item_id: int = Field(
+        description="The ID of session queue item from which this invocation queue item came"
+    )
+    session_queue_batch_id: str = Field(
+        description="The ID of the session batch from which this invocation queue item came"
+    )
+    workflow: Optional[WorkflowWithoutID] = Field(description="The workflow associated with this queue item")
+    invoke_all: bool = Field(default=False)
+    timestamp: float = Field(default_factory=time.time)

invokeai/app/services/invocation_queue/invocation_queue_memory.py

@@ -0,0 +1,44 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import time
+from queue import Queue
+from typing import Optional
+
+from .invocation_queue_base import InvocationQueueABC
+from .invocation_queue_common import InvocationQueueItem
+
+
+class MemoryInvocationQueue(InvocationQueueABC):
+    __queue: Queue
+    __cancellations: dict[str, float]
+
+    def __init__(self):
+        self.__queue = Queue()
+        self.__cancellations = {}
+
+    def get(self) -> InvocationQueueItem:
+        item = self.__queue.get()
+
+        while (
+            isinstance(item, InvocationQueueItem)
+            and item.graph_execution_state_id in self.__cancellations
+            and self.__cancellations[item.graph_execution_state_id] > item.timestamp
+        ):
+            item = self.__queue.get()
+
+        # Clear old items
+        for graph_execution_state_id in list(self.__cancellations.keys()):
+            if self.__cancellations[graph_execution_state_id] < item.timestamp:
+                del self.__cancellations[graph_execution_state_id]
+
+        return item
+
+    def put(self, item: Optional[InvocationQueueItem]) -> None:
+        self.__queue.put(item)
+
+    def cancel(self, graph_execution_state_id: str) -> None:
+        if graph_execution_state_id not in self.__cancellations:
+            self.__cancellations[graph_execution_state_id] = time.time()
+
+    def is_canceled(self, graph_execution_state_id: str) -> bool:
+        return graph_execution_state_id in self.__cancellations

invokeai/app/services/invocation_services.py

@@ -16,7 +16,6 @@ if TYPE_CHECKING:
     from .board_images.board_images_base import BoardImagesServiceABC
     from .board_records.board_records_base import BoardRecordStorageBase
     from .boards.boards_base import BoardServiceABC
-    from .bulk_download.bulk_download_base import BulkDownloadBase
     from .config import InvokeAIAppConfig
     from .download import DownloadQueueServiceBase
     from .events.events_base import EventServiceBase
@@ -24,11 +23,17 @@ if TYPE_CHECKING:
     from .image_records.image_records_base import ImageRecordStorageBase
     from .images.images_base import ImageServiceABC
     from .invocation_cache.invocation_cache_base import InvocationCacheBase
+    from .invocation_processor.invocation_processor_base import InvocationProcessorABC
+    from .invocation_queue.invocation_queue_base import InvocationQueueABC
     from .invocation_stats.invocation_stats_base import InvocationStatsServiceBase
+    from .item_storage.item_storage_base import ItemStorageABC
+    from .model_install import ModelInstallServiceBase
     from .model_manager.model_manager_base import ModelManagerServiceBase
+    from .model_records import ModelRecordServiceBase
     from .names.names_base import NameServiceBase
     from .session_processor.session_processor_base import SessionProcessorBase
     from .session_queue.session_queue_base import SessionQueueBase
+    from .shared.graph import GraphExecutionState
     from .urls.urls_base import UrlServiceBase
     from .workflow_records.workflow_records_base import WorkflowRecordsStorageBase
 
@@ -42,16 +47,20 @@ class InvocationServices:
         board_image_records: "BoardImageRecordStorageBase",
         boards: "BoardServiceABC",
         board_records: "BoardRecordStorageBase",
-        bulk_download: "BulkDownloadBase",
         configuration: "InvokeAIAppConfig",
         events: "EventServiceBase",
+        graph_execution_manager: "ItemStorageABC[GraphExecutionState]",
         images: "ImageServiceABC",
         image_files: "ImageFileStorageBase",
         image_records: "ImageRecordStorageBase",
         logger: "Logger",
         model_manager: "ModelManagerServiceBase",
+        model_records: "ModelRecordServiceBase",
         download_queue: "DownloadQueueServiceBase",
+        model_install: "ModelInstallServiceBase",
+        processor: "InvocationProcessorABC",
         performance_statistics: "InvocationStatsServiceBase",
+        queue: "InvocationQueueABC",
         session_queue: "SessionQueueBase",
         session_processor: "SessionProcessorBase",
         invocation_cache: "InvocationCacheBase",
@@ -65,16 +74,20 @@ class InvocationServices:
         self.board_image_records = board_image_records
         self.boards = boards
         self.board_records = board_records
-        self.bulk_download = bulk_download
         self.configuration = configuration
         self.events = events
+        self.graph_execution_manager = graph_execution_manager
         self.images = images
         self.image_files = image_files
         self.image_records = image_records
         self.logger = logger
         self.model_manager = model_manager
+        self.model_records = model_records
         self.download_queue = download_queue
+        self.model_install = model_install
+        self.processor = processor
         self.performance_statistics = performance_statistics
+        self.queue = queue
         self.session_queue = session_queue
         self.session_processor = session_processor
         self.invocation_cache = invocation_cache

invokeai/app/services/invocation_stats/invocation_stats_base.py

@@ -3,7 +3,7 @@
 
 Usage:
 
-statistics = InvocationStatsService()
+statistics = InvocationStatsService(graph_execution_manager)
 with statistics.collect_stats(invocation, graph_execution_state.id):
       ... execute graphs...
 statistics.log_stats()
@@ -29,8 +29,8 @@ writes to the system log is stored in InvocationServices.performance_statistics.
 """
 
 from abc import ABC, abstractmethod
+from contextlib import AbstractContextManager
 from pathlib import Path
-from typing import ContextManager
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation
 from invokeai.app.services.invocation_stats.invocation_stats_common import InvocationStatsSummary
@@ -40,17 +40,18 @@ class InvocationStatsServiceBase(ABC):
     "Abstract base class for recording node memory/time performance statistics"
 
     @abstractmethod
-    def __init__(self) -> None:
+    def __init__(self):
         """
         Initialize the InvocationStatsService and reset counters to zero
         """
+        pass
 
     @abstractmethod
     def collect_stats(
         self,
         invocation: BaseInvocation,
         graph_execution_state_id: str,
-    ) -> ContextManager[None]:
+    ) -> AbstractContextManager:
         """
         Return a context object that will capture the statistics on the execution
         of invocaation. Use with: to place around the part of the code that executes the invocation.
@@ -60,12 +61,16 @@ class InvocationStatsServiceBase(ABC):
         pass
 
     @abstractmethod
-    def reset_stats(self):
-        """Reset all stored statistics."""
+    def reset_stats(self, graph_execution_state_id: str):
+        """
+        Reset all statistics for the indicated graph.
+        :param graph_execution_state_id: The id of the session whose stats to reset.
+        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
+        """
         pass
 
     @abstractmethod
-    def log_stats(self, graph_execution_state_id: str) -> None:
+    def log_stats(self, graph_execution_state_id: str):
         """
         Write out the accumulated statistics to the log or somewhere else.
         :param graph_execution_state_id: The id of the session whose stats to log.

invokeai/app/services/invocation_stats/invocation_stats_default.py

@@ -2,7 +2,6 @@ import json
 import time
 from contextlib import contextmanager
 from pathlib import Path
-from typing import Generator
 
 import psutil
 import torch
@@ -10,7 +9,8 @@ import torch
 import invokeai.backend.util.logging as logger
 from invokeai.app.invocations.baseinvocation import BaseInvocation
 from invokeai.app.services.invoker import Invoker
-from invokeai.backend.model_manager.load.model_cache import CacheStats
+from invokeai.app.services.item_storage.item_storage_common import ItemNotFoundError
+from invokeai.backend.model_management.model_cache import CacheStats
 
 from .invocation_stats_base import InvocationStatsServiceBase
 from .invocation_stats_common import (
@@ -41,23 +41,22 @@ class InvocationStatsService(InvocationStatsServiceBase):
         self._invoker = invoker
 
     @contextmanager
-    def collect_stats(self, invocation: BaseInvocation, graph_execution_state_id: str) -> Generator[None, None, None]:
-        # This is to handle case of the model manager not being initialized, which happens
-        # during some tests.
-        services = self._invoker.services
+    def collect_stats(self, invocation: BaseInvocation, graph_execution_state_id: str):
         if not self._stats.get(graph_execution_state_id):
             # First time we're seeing this graph_execution_state_id.
             self._stats[graph_execution_state_id] = GraphExecutionStats()
             self._cache_stats[graph_execution_state_id] = CacheStats()
 
+            # Prune stale stats. There should be none since we're starting a new graph, but just in case.
+            self._prune_stale_stats()
+
         # Record state before the invocation.
         start_time = time.time()
         start_ram = psutil.Process().memory_info().rss
         if torch.cuda.is_available():
             torch.cuda.reset_peak_memory_stats()
-
-        assert services.model_manager.load is not None
-        services.model_manager.load.ram_cache.stats = self._cache_stats[graph_execution_state_id]
+        if self._invoker.services.model_manager:
+            self._invoker.services.model_manager.collect_cache_stats(self._cache_stats[graph_execution_state_id])
 
         try:
             # Let the invocation run.
@@ -74,9 +73,42 @@ class InvocationStatsService(InvocationStatsServiceBase):
             )
             self._stats[graph_execution_state_id].add_node_execution_stats(node_stats)
 
-    def reset_stats(self):
-        self._stats = {}
-        self._cache_stats = {}
+    def _prune_stale_stats(self):
+        """Check all graphs being tracked and prune any that have completed/errored.
+
+        This shouldn't be necessary, but we don't have totally robust upstream handling of graph completions/errors, so
+        for now we call this function periodically to prevent them from accumulating.
+        """
+        to_prune: list[str] = []
+        for graph_execution_state_id in self._stats:
+            try:
+                graph_execution_state = self._invoker.services.graph_execution_manager.get(graph_execution_state_id)
+            except ItemNotFoundError:
+                # TODO(ryand): What would cause this? Should this exception just be allowed to propagate?
+                logger.warning(f"Failed to get graph state for {graph_execution_state_id}.")
+                continue
+
+            if not graph_execution_state.is_complete():
+                # The graph is still running, don't prune it.
+                continue
+
+            to_prune.append(graph_execution_state_id)
+
+        for graph_execution_state_id in to_prune:
+            del self._stats[graph_execution_state_id]
+            del self._cache_stats[graph_execution_state_id]
+
+        if len(to_prune) > 0:
+            logger.info(f"Pruned stale graph stats for {to_prune}.")
+
+    def reset_stats(self, graph_execution_state_id: str):
+        try:
+            del self._stats[graph_execution_state_id]
+            del self._cache_stats[graph_execution_state_id]
+        except KeyError as e:
+            raise GESStatsNotFoundError(
+                f"Attempted to clear statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
 
     def get_stats(self, graph_execution_state_id: str) -> InvocationStatsSummary:
         graph_stats_summary = self._get_graph_summary(graph_execution_state_id)

invokeai/app/services/invoker.py

@@ -1,7 +1,12 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+from typing import Optional
 
+from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
+
+from .invocation_queue.invocation_queue_common import InvocationQueueItem
 from .invocation_services import InvocationServices
+from .shared.graph import Graph, GraphExecutionState
 
 
 class Invoker:
@@ -13,6 +18,51 @@ class Invoker:
         self.services = services
         self._start()
 
+    def invoke(
+        self,
+        session_queue_id: str,
+        session_queue_item_id: int,
+        session_queue_batch_id: str,
+        graph_execution_state: GraphExecutionState,
+        workflow: Optional[WorkflowWithoutID] = None,
+        invoke_all: bool = False,
+    ) -> Optional[str]:
+        """Determines the next node to invoke and enqueues it, preparing if needed.
+        Returns the id of the queued node, or `None` if there are no nodes left to enqueue."""
+
+        # Get the next invocation
+        invocation = graph_execution_state.next()
+        if not invocation:
+            return None
+
+        # Save the execution state
+        self.services.graph_execution_manager.set(graph_execution_state)
+
+        # Queue the invocation
+        self.services.queue.put(
+            InvocationQueueItem(
+                session_queue_id=session_queue_id,
+                session_queue_item_id=session_queue_item_id,
+                session_queue_batch_id=session_queue_batch_id,
+                graph_execution_state_id=graph_execution_state.id,
+                invocation_id=invocation.id,
+                workflow=workflow,
+                invoke_all=invoke_all,
+            )
+        )
+
+        return invocation.id
+
+    def create_execution_state(self, graph: Optional[Graph] = None) -> GraphExecutionState:
+        """Creates a new execution state for the given graph"""
+        new_state = GraphExecutionState(graph=Graph() if graph is None else graph)
+        self.services.graph_execution_manager.set(new_state)
+        return new_state
+
+    def cancel(self, graph_execution_state_id: str) -> None:
+        """Cancels the given execution state"""
+        self.services.queue.cancel(graph_execution_state_id)
+
     def __start_service(self, service) -> None:
         # Call start() method on any services that have it
         start_op = getattr(service, "start", None)
@@ -35,3 +85,5 @@ class Invoker:
         # First stop all services
         for service in vars(self.services):
             self.__stop_service(getattr(self.services, service))
+
+        self.services.queue.put(None)

invokeai/app/services/model_install/model_install_base.py

@@ -14,13 +14,11 @@ from typing_extensions import Annotated
 
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase
-from invokeai.app.services.events.events_base import EventServiceBase
+from invokeai.app.services.events import EventServiceBase
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.model_records import ModelRecordServiceBase
 from invokeai.backend.model_manager import AnyModelConfig, ModelRepoVariant
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-from ..model_metadata import ModelMetadataStoreBase
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, ModelMetadataStore
 
 
 class InstallStatus(str, Enum):
@@ -28,7 +26,6 @@ class InstallStatus(str, Enum):
 
     WAITING = "waiting"  # waiting to be dequeued
     DOWNLOADING = "downloading"  # downloading of model files in process
-    DOWNLOADS_DONE = "downloads_done"  # downloading done, waiting to run
     RUNNING = "running"  # being processed
     COMPLETED = "completed"  # finished running
     ERROR = "error"  # terminated with an error message
@@ -130,8 +127,8 @@ class HFModelSource(StringLikeSource):
     def __str__(self) -> str:
         """Return string version of repoid when string rep needed."""
         base: str = self.repo_id
-        base += f":{self.variant or ''}"
         base += f":{self.subfolder}" if self.subfolder else ""
+        base += f" ({self.variant})" if self.variant else ""
         return base
 
 
@@ -157,7 +154,6 @@ class ModelInstallJob(BaseModel):
 
     id: int = Field(description="Unique ID for this job")
     status: InstallStatus = Field(default=InstallStatus.WAITING, description="Current status of install process")
-    error_reason: Optional[str] = Field(default=None, description="Information about why the job failed")
     config_in: Dict[str, Any] = Field(
         default_factory=dict, description="Configuration information (e.g. 'description') to apply to model."
     )
@@ -179,12 +175,6 @@ class ModelInstallJob(BaseModel):
     download_parts: Set[DownloadJob] = Field(
         default_factory=set, description="Download jobs contributing to this install"
     )
-    error: Optional[str] = Field(
-        default=None, description="On an error condition, this field will contain the text of the exception"
-    )
-    error_traceback: Optional[str] = Field(
-        default=None, description="On an error condition, this field will contain the exception traceback"
-    )
     # internal flags and transitory settings
     _install_tmpdir: Optional[Path] = PrivateAttr(default=None)
     _exception: Optional[Exception] = PrivateAttr(default=None)
@@ -192,10 +182,7 @@ class ModelInstallJob(BaseModel):
     def set_error(self, e: Exception) -> None:
         """Record the error and traceback from an exception."""
         self._exception = e
-        self.error = str(e)
-        self.error_traceback = self._format_error(e)
         self.status = InstallStatus.ERROR
-        self.error_reason = self._exception.__class__.__name__ if self._exception else None
 
     def cancel(self) -> None:
         """Call to cancel the job."""
@@ -206,9 +193,10 @@ class ModelInstallJob(BaseModel):
         """Class name of the exception that led to status==ERROR."""
         return self._exception.__class__.__name__ if self._exception else None
 
-    def _format_error(self, exception: Exception) -> str:
+    @property
+    def error(self) -> Optional[str]:
         """Error traceback."""
-        return "".join(traceback.format_exception(exception))
+        return "".join(traceback.format_exception(self._exception)) if self._exception else None
 
     @property
     def cancelled(self) -> bool:
@@ -230,11 +218,6 @@ class ModelInstallJob(BaseModel):
         """Return true if job is downloading."""
         return self.status == InstallStatus.DOWNLOADING
 
-    @property
-    def downloads_done(self) -> bool:
-        """Return true if job's downloads ae done."""
-        return self.status == InstallStatus.DOWNLOADS_DONE
-
     @property
     def running(self) -> bool:
         """Return true if job is running."""
@@ -260,7 +243,7 @@ class ModelInstallServiceBase(ABC):
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
         download_queue: DownloadQueueServiceBase,
-        metadata_store: ModelMetadataStoreBase,
+        metadata_store: ModelMetadataStore,
         event_bus: Optional["EventServiceBase"] = None,
     ):
         """
@@ -341,43 +324,6 @@ class ModelInstallServiceBase(ABC):
         :returns id: The string ID of the registered model.
         """
 
-    @abstractmethod
-    def heuristic_import(
-        self,
-        source: str,
-        config: Optional[Dict[str, Any]] = None,
-        access_token: Optional[str] = None,
-    ) -> ModelInstallJob:
-        r"""Install the indicated model using heuristics to interpret user intentions.
-
-        :param source: String source
-        :param config: Optional dict. Any fields in this dict
-         will override corresponding autoassigned probe fields in the
-         model's config record as described in `import_model()`.
-        :param access_token: Optional access token for remote sources.
-
-        The source can be:
-        1. A local file path in posix() format (`/foo/bar` or `C:\foo\bar`)
-        2. An http or https URL (`https://foo.bar/foo`)
-        3. A HuggingFace repo_id (`foo/bar`, `foo/bar:fp16`, `foo/bar:fp16:vae`)
-
-        We extend the HuggingFace repo_id syntax to include the variant and the
-        subfolder or path. The following are acceptable alternatives:
-            stabilityai/stable-diffusion-v4
-            stabilityai/stable-diffusion-v4:fp16
-            stabilityai/stable-diffusion-v4:fp16:vae
-            stabilityai/stable-diffusion-v4::/checkpoints/sd4.safetensors
-            stabilityai/stable-diffusion-v4:onnx:vae
-
-        Because a local file path can look like a huggingface repo_id, the logic
-        first checks whether the path exists on disk, and if not, it is treated as
-        a parseable huggingface repo.
-
-        The previous support for recursing into a local folder and loading all model-like files
-        has been removed.
-        """
-        pass
-
     @abstractmethod
     def import_model(
         self,
@@ -439,18 +385,6 @@ class ModelInstallServiceBase(ABC):
     def cancel_job(self, job: ModelInstallJob) -> None:
         """Cancel the indicated job."""
 
-    @abstractmethod
-    def wait_for_job(self, job: ModelInstallJob, timeout: int = 0) -> ModelInstallJob:
-        """Wait for the indicated job to reach a terminal state.
-
-        This will block until the indicated install job has completed,
-        been cancelled, or errored out.
-
-        :param job: The job to wait on.
-        :param timeout: Wait up to indicated number of seconds. Raise a TimeoutError if
-        the job hasn't completed within the indicated time.
-        """
-
     @abstractmethod
     def wait_for_installs(self, timeout: int = 0) -> List[ModelInstallJob]:
         """
@@ -460,8 +394,7 @@ class ModelInstallServiceBase(ABC):
         completed, been cancelled, or errored out.
 
         :param timeout: Wait up to indicated number of seconds. Raise an Exception('timeout') if
-        installs do not complete within the indicated time. A timeout of zero (the default)
-        will block indefinitely until the installs complete.
+        installs do not complete within the indicated time.
         """
 
     @abstractmethod
@@ -477,22 +410,3 @@ class ModelInstallServiceBase(ABC):
     @abstractmethod
     def sync_to_config(self) -> None:
         """Synchronize models on disk to those in the model record database."""
-
-    @abstractmethod
-    def download_and_cache(self, source: Union[str, AnyHttpUrl], access_token: Optional[str] = None) -> Path:
-        """
-        Download the model file located at source to the models cache and return its Path.
-
-        :param source: A Url or a string that can be converted into one.
-        :param access_token: Optional access token to access restricted resources.
-
-        The model file will be downloaded into the system-wide model cache
-        (`models/.cache`) if it isn't already there. Note that the model cache
-        is periodically cleared of infrequently-used entries when the model
-        converter runs.
-
-        Note that this doesn't automaticallly install or register the model, but is
-        intended for use by nodes that need access to models that aren't directly
-        supported by InvokeAI. The downloading process takes advantage of the download queue
-        to avoid interrupting other operations.
-        """

invokeai/app/services/model_install/model_install_default.py

@@ -7,6 +7,7 @@ import time
 from hashlib import sha256
 from pathlib import Path
 from queue import Empty, Queue
+from random import randbytes
 from shutil import copyfile, copytree, move, rmtree
 from tempfile import mkdtemp
 from typing import Any, Dict, List, Optional, Set, Union
@@ -16,11 +17,10 @@ from pydantic.networks import AnyHttpUrl
 from requests import Session
 
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase, TqdmProgress
+from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase
 from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase
-from invokeai.app.util.misc import uuid_string
+from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase, ModelRecordServiceSQL
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
@@ -28,10 +28,12 @@ from invokeai.backend.model_manager.config import (
     ModelRepoVariant,
     ModelType,
 )
+from invokeai.backend.model_manager.hash import FastModelHash
 from invokeai.backend.model_manager.metadata import (
     AnyModelRepoMetadata,
     CivitaiMetadataFetch,
     HuggingFaceMetadataFetch,
+    ModelMetadataStore,
     ModelMetadataWithFiles,
     RemoteModelFile,
 )
@@ -48,7 +50,6 @@ from .model_install_base import (
     ModelInstallJob,
     ModelInstallServiceBase,
     ModelSource,
-    StringLikeSource,
     URLModelSource,
 )
 
@@ -63,6 +64,7 @@ class ModelInstallService(ModelInstallServiceBase):
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
         download_queue: DownloadQueueServiceBase,
+        metadata_store: Optional[ModelMetadataStore] = None,
         event_bus: Optional[EventServiceBase] = None,
         session: Optional[Session] = None,
     ):
@@ -84,13 +86,19 @@ class ModelInstallService(ModelInstallServiceBase):
         self._lock = threading.Lock()
         self._stop_event = threading.Event()
         self._downloads_changed_event = threading.Event()
-        self._install_completed_event = threading.Event()
         self._download_queue = download_queue
         self._download_cache: Dict[AnyHttpUrl, ModelInstallJob] = {}
         self._running = False
         self._session = session
         self._next_job_id = 0
-        self._metadata_store = record_store.metadata_store  # for convenience
+        # There may not necessarily be a metadata store initialized
+        # so we create one and initialize it with the same sql database
+        # used by the record store service.
+        if metadata_store:
+            self._metadata_store = metadata_store
+        else:
+            assert isinstance(record_store, ModelRecordServiceSQL)
+            self._metadata_store = ModelMetadataStore(record_store.db)
 
     @property
     def app_config(self) -> InvokeAIAppConfig:  # noqa D102
@@ -137,7 +145,7 @@ class ModelInstallService(ModelInstallServiceBase):
     ) -> str:  # noqa D102
         model_path = Path(model_path)
         config = config or {}
-        if not config.get("source"):
+        if config.get("source") is None:
             config["source"] = model_path.resolve().as_posix()
         return self._register(model_path, config)
 
@@ -148,24 +156,20 @@ class ModelInstallService(ModelInstallServiceBase):
     ) -> str:  # noqa D102
         model_path = Path(model_path)
         config = config or {}
-        if not config.get("source"):
+        if config.get("source") is None:
             config["source"] = model_path.resolve().as_posix()
-        config["key"] = config.get("key", uuid_string())
 
         info: AnyModelConfig = self._probe_model(Path(model_path), config)
-
-        if preferred_name := config.get("name"):
-            preferred_name = Path(preferred_name).with_suffix(model_path.suffix)
-
-        dest_path = (
-            self.app_config.models_path / info.base.value / info.type.value / (preferred_name or model_path.name)
-        )
+        old_hash = info.original_hash
+        dest_path = self.app_config.models_path / info.base.value / info.type.value / model_path.name
         try:
             new_path = self._copy_model(model_path, dest_path)
         except FileExistsError as excp:
             raise DuplicateModelException(
                 f"A model named {model_path.name} is already installed at {dest_path.as_posix()}"
             ) from excp
+        new_hash = FastModelHash.hash(new_path)
+        assert new_hash == old_hash, f"{model_path}: Model hash changed during installation, possibly corrupted."
 
         return self._register(
             new_path,
@@ -173,41 +177,7 @@ class ModelInstallService(ModelInstallServiceBase):
             info,
         )
 
-    def heuristic_import(
-        self,
-        source: str,
-        config: Optional[Dict[str, Any]] = None,
-        access_token: Optional[str] = None,
-        inplace: bool = False,
-    ) -> ModelInstallJob:
-        variants = "|".join(ModelRepoVariant.__members__.values())
-        hf_repoid_re = f"^([^/:]+/[^/:]+)(?::({variants})?(?::/?([^:]+))?)?$"
-        source_obj: Optional[StringLikeSource] = None
-
-        if Path(source).exists():  # A local file or directory
-            source_obj = LocalModelSource(path=Path(source), inplace=inplace)
-        elif match := re.match(hf_repoid_re, source):
-            source_obj = HFModelSource(
-                repo_id=match.group(1),
-                variant=match.group(2) if match.group(2) else None,  # pass None rather than ''
-                subfolder=Path(match.group(3)) if match.group(3) else None,
-                access_token=access_token,
-            )
-        elif re.match(r"^https?://[^/]+", source):
-            source_obj = URLModelSource(
-                url=AnyHttpUrl(source),
-                access_token=access_token,
-            )
-        else:
-            raise ValueError(f"Unsupported model source: '{source}'")
-        return self.import_model(source_obj, config)
-
     def import_model(self, source: ModelSource, config: Optional[Dict[str, Any]] = None) -> ModelInstallJob:  # noqa D102
-        similar_jobs = [x for x in self.list_jobs() if x.source == source and not x.in_terminal_state]
-        if similar_jobs:
-            self._logger.warning(f"There is already an active install job for {source}. Not enqueuing.")
-            return similar_jobs[0]
-
         if isinstance(source, LocalModelSource):
             install_job = self._import_local_model(source, config)
             self._install_queue.put(install_job)  # synchronously install
@@ -237,25 +207,14 @@ class ModelInstallService(ModelInstallServiceBase):
         assert isinstance(jobs[0], ModelInstallJob)
         return jobs[0]
 
-    def wait_for_job(self, job: ModelInstallJob, timeout: int = 0) -> ModelInstallJob:
-        """Block until the indicated job has reached terminal state, or when timeout limit reached."""
-        start = time.time()
-        while not job.in_terminal_state:
-            if self._install_completed_event.wait(timeout=5):  # in case we miss an event
-                self._install_completed_event.clear()
-            if timeout > 0 and time.time() - start > timeout:
-                raise TimeoutError("Timeout exceeded")
-        return job
-
-    # TODO: Better name? Maybe wait_for_jobs()? Maybe too easily confused with above
     def wait_for_installs(self, timeout: int = 0) -> List[ModelInstallJob]:  # noqa D102
         """Block until all installation jobs are done."""
         start = time.time()
         while len(self._download_cache) > 0:
-            if self._downloads_changed_event.wait(timeout=0.25):  # in case we miss an event
+            if self._downloads_changed_event.wait(timeout=5):  # in case we miss an event
                 self._downloads_changed_event.clear()
             if timeout > 0 and time.time() - start > timeout:
-                raise TimeoutError("Timeout exceeded")
+                raise Exception("Timeout exceeded")
         self._install_queue.join()
         return self._install_jobs
 
@@ -280,9 +239,9 @@ class ModelInstallService(ModelInstallServiceBase):
         self._logger.info("Model installer (re)initialized")
 
     def scan_directory(self, scan_dir: Path, install: bool = False) -> List[str]:  # noqa D102
-        self._cached_model_paths = {Path(x.path).absolute() for x in self.record_store.all_models()}
+        self._cached_model_paths = {Path(x.path) for x in self.record_store.all_models()}
         callback = self._scan_install if install else self._scan_register
-        search = ModelSearch(on_model_found=callback, config=self._app_config)
+        search = ModelSearch(on_model_found=callback)
         self._models_installed.clear()
         search.search(scan_dir)
         return list(self._models_installed)
@@ -309,38 +268,6 @@ class ModelInstallService(ModelInstallServiceBase):
             path.unlink()
         self.unregister(key)
 
-    def download_and_cache(
-        self,
-        source: Union[str, AnyHttpUrl],
-        access_token: Optional[str] = None,
-        timeout: int = 0,
-    ) -> Path:
-        """Download the model file located at source to the models cache and return its Path."""
-        model_hash = sha256(str(source).encode("utf-8")).hexdigest()[0:32]
-        model_path = self._app_config.models_convert_cache_path / model_hash
-
-        # We expect the cache directory to contain one and only one downloaded file.
-        # We don't know the file's name in advance, as it is set by the download
-        # content-disposition header.
-        if model_path.exists():
-            contents = [x for x in model_path.iterdir() if x.is_file()]
-            if len(contents) > 0:
-                return contents[0]
-
-        model_path.mkdir(parents=True, exist_ok=True)
-        job = self._download_queue.download(
-            source=AnyHttpUrl(str(source)),
-            dest=model_path,
-            access_token=access_token,
-            on_progress=TqdmProgress().update,
-        )
-        self._download_queue.wait_for_job(job, timeout)
-        if job.complete:
-            assert job.download_path is not None
-            return job.download_path
-        else:
-            raise Exception(job.error)
-
     # --------------------------------------------------------------------------------------------
     # Internal functions that manage the installer threads
     # --------------------------------------------------------------------------------------------
@@ -368,12 +295,11 @@ class ModelInstallService(ModelInstallServiceBase):
                     self._signal_job_errored(job)
 
                 elif (
-                    job.waiting or job.downloads_done
+                    job.waiting or job.downloading
                 ):  # local jobs will be in waiting state, remote jobs will be downloading state
                     job.total_bytes = self._stat_size(job.local_path)
                     job.bytes = job.total_bytes
                     self._signal_job_running(job)
-                    job.config_in["source"] = str(job.source)
                     if job.inplace:
                         key = self.register_path(job.local_path, job.config_in)
                     else:
@@ -404,7 +330,6 @@ class ModelInstallService(ModelInstallServiceBase):
                 # if this is an install of a remote file, then clean up the temporary directory
                 if job._install_tmpdir is not None:
                     rmtree(job._install_tmpdir)
-                self._install_completed_event.set()
                 self._install_queue.task_done()
 
         self._logger.info("Install thread exiting")
@@ -446,7 +371,7 @@ class ModelInstallService(ModelInstallServiceBase):
                     installed.update(self.scan_directory(models_dir))
             self._logger.info(f"{len(installed)} new models registered; {len(defunct_models)} unregistered")
 
-    def _sync_model_path(self, key: str) -> AnyModelConfig:
+    def _sync_model_path(self, key: str, ignore_hash_change: bool = False) -> AnyModelConfig:
         """
         Move model into the location indicated by its basetype, type and name.
 
@@ -467,7 +392,14 @@ class ModelInstallService(ModelInstallServiceBase):
         new_path = models_dir / model.base.value / model.type.value / model.name
         self._logger.info(f"Moving {model.name} to {new_path}.")
         new_path = self._move_model(old_path, new_path)
+        new_hash = FastModelHash.hash(new_path)
         model.path = new_path.relative_to(models_dir).as_posix()
+        if model.current_hash != new_hash:
+            assert (
+                ignore_hash_change
+            ), f"{model.name}: Model hash changed during installation, model is possibly corrupted"
+            model.current_hash = new_hash
+            self._logger.info(f"Model has new hash {model.current_hash}, but will continue to be identified by {key}")
         self.record_store.update_model(key, model)
         return model
 
@@ -527,17 +459,14 @@ class ModelInstallService(ModelInstallServiceBase):
                 setattr(info, key, value)
         return info
 
+    def _create_key(self) -> str:
+        return sha256(randbytes(100)).hexdigest()[0:32]
+
     def _register(
         self, model_path: Path, config: Optional[Dict[str, Any]] = None, info: Optional[AnyModelConfig] = None
     ) -> str:
-        # Note that we may be passed a pre-populated AnyModelConfig object,
-        # in which case the key field should have been populated by the caller (e.g. in `install_path`).
-        config["key"] = config.get("key", uuid_string())
         info = info or ModelProbe.probe(model_path, config)
-        override_key: Optional[str] = config.get("key") if config else None
-
-        assert info.original_hash  # always assigned by probe()
-        info.key = override_key or info.original_hash
+        key = self._create_key()
 
         model_path = model_path.absolute()
         if model_path.is_relative_to(self.app_config.models_path):
@@ -550,8 +479,8 @@ class ModelInstallService(ModelInstallServiceBase):
             # make config relative to our root
             legacy_conf = (self.app_config.root_dir / self.app_config.legacy_conf_dir / info.config).resolve()
             info.config = legacy_conf.relative_to(self.app_config.root_dir).as_posix()
-        self.record_store.add_model(info.key, info)
-        return info.key
+        self.record_store.add_model(key, info)
+        return key
 
     def _next_id(self) -> int:
         with self._lock:
@@ -560,10 +489,10 @@ class ModelInstallService(ModelInstallServiceBase):
         return id
 
     @staticmethod
-    def _guess_variant() -> Optional[ModelRepoVariant]:
+    def _guess_variant() -> ModelRepoVariant:
         """Guess the best HuggingFace variant type to download."""
         precision = choose_precision(choose_torch_device())
-        return ModelRepoVariant.FP16 if precision == "float16" else None
+        return ModelRepoVariant.FP16 if precision == "float16" else ModelRepoVariant.DEFAULT
 
     def _import_local_model(self, source: LocalModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
         return ModelInstallJob(
@@ -588,7 +517,7 @@ class ModelInstallService(ModelInstallServiceBase):
         if not source.access_token:
             self._logger.info("No HuggingFace access token present; some models may not be downloadable.")
 
-        metadata = HuggingFaceMetadataFetch(self._session).from_id(source.repo_id, source.variant)
+        metadata = HuggingFaceMetadataFetch(self._session).from_id(source.repo_id)
         assert isinstance(metadata, ModelMetadataWithFiles)
         remote_files = metadata.download_urls(
             variant=source.variant or self._guess_variant(),
@@ -636,8 +565,6 @@ class ModelInstallService(ModelInstallServiceBase):
         # TODO: Replace with tempfile.tmpdir() when multithreading is cleaned up.
         # Currently the tmpdir isn't automatically removed at exit because it is
         # being held in a daemon thread.
-        if len(remote_files) == 0:
-            raise ValueError(f"{source}: No downloadable files found")
         tmpdir = Path(
             mkdtemp(
                 dir=self._app_config.models_path,
@@ -653,16 +580,6 @@ class ModelInstallService(ModelInstallServiceBase):
             bytes=0,
             total_bytes=0,
         )
-        # In the event that there is a subfolder specified in the source,
-        # we need to remove it from the destination path in order to avoid
-        # creating unwanted subfolders
-        if hasattr(source, "subfolder") and source.subfolder:
-            root = Path(remote_files[0].path.parts[0])
-            subfolder = root / source.subfolder
-        else:
-            root = Path(".")
-            subfolder = Path(".")
-
         # we remember the path up to the top of the tmpdir so that it may be
         # removed safely at the end of the install process.
         install_job._install_tmpdir = tmpdir
@@ -672,7 +589,7 @@ class ModelInstallService(ModelInstallServiceBase):
         self._logger.debug(f"remote_files={remote_files}")
         for model_file in remote_files:
             url = model_file.url
-            path = root / model_file.path.relative_to(subfolder)
+            path = model_file.path
             self._logger.info(f"Downloading {url} => {path}")
             install_job.total_bytes += model_file.size
             assert hasattr(source, "access_token")
@@ -735,14 +652,13 @@ class ModelInstallService(ModelInstallServiceBase):
                 self._signal_job_downloading(install_job)
 
     def _download_complete_callback(self, download_job: DownloadJob) -> None:
-        self._logger.info(f"{download_job.source}: model download complete")
         with self._lock:
             install_job = self._download_cache[download_job.source]
             self._download_cache.pop(download_job.source, None)
 
             # are there any more active jobs left in this task?
-            if install_job.downloading and all(x.complete for x in install_job.download_parts):
-                install_job.status = InstallStatus.DOWNLOADS_DONE
+            if all(x.complete for x in install_job.download_parts):
+                #  now enqueue job for actual installation into the models directory
                 self._install_queue.put(install_job)
 
             # Let other threads know that the number of downloads has changed
@@ -768,7 +684,7 @@ class ModelInstallService(ModelInstallServiceBase):
             if not install_job:
                 return
             self._downloads_changed_event.set()
-            self._logger.warning(f"{download_job.source}: model download cancelled")
+            self._logger.warning(f"Download {download_job.source} cancelled.")
             # if install job has already registered an error, then do not replace its status with cancelled
             if not install_job.errored:
                 install_job.cancel()
@@ -815,7 +731,6 @@ class ModelInstallService(ModelInstallServiceBase):
                 parts=parts,
                 bytes=job.bytes,
                 total_bytes=job.total_bytes,
-                id=job.id,
             )
 
     def _signal_job_completed(self, job: ModelInstallJob) -> None:
@@ -828,7 +743,7 @@ class ModelInstallService(ModelInstallServiceBase):
             assert job.local_path is not None
             assert job.config_out is not None
             key = job.config_out.key
-            self._event_bus.emit_model_install_completed(str(job.source), key, id=job.id)
+            self._event_bus.emit_model_install_completed(str(job.source), key)
 
     def _signal_job_errored(self, job: ModelInstallJob) -> None:
         self._logger.info(f"{job.source}: model installation encountered an exception: {job.error_type}\n{job.error}")
@@ -837,7 +752,7 @@ class ModelInstallService(ModelInstallServiceBase):
             error = job.error
             assert error_type is not None
             assert error is not None
-            self._event_bus.emit_model_install_error(str(job.source), error_type, error, id=job.id)
+            self._event_bus.emit_model_install_error(str(job.source), error_type, error)
 
     def _signal_job_cancelled(self, job: ModelInstallJob) -> None:
         self._logger.info(f"{job.source}: model installation was cancelled")

invokeai/app/services/model_load/__init__.py

@@ -1,6 +0,0 @@
-"""Initialization file for model load service module."""
-
-from .model_load_base import ModelLoadServiceBase
-from .model_load_default import ModelLoadService
-
-__all__ = ["ModelLoadServiceBase", "ModelLoadService"]

invokeai/app/services/model_load/model_load_base.py

@@ -1,40 +0,0 @@
-# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Team
-"""Base class for model loader."""
-
-from abc import ABC, abstractmethod
-from typing import Optional
-
-from invokeai.app.services.shared.invocation_context import InvocationContextData
-from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
-from invokeai.backend.model_manager.load import LoadedModel
-from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
-from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
-
-
-class ModelLoadServiceBase(ABC):
-    """Wrapper around AnyModelLoader."""
-
-    @abstractmethod
-    def load_model(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
-        """
-        Given a model's configuration, load it and return the LoadedModel object.
-
-        :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
-        :param submodel: For main (pipeline models), the submodel to fetch.
-        :param context_data: Invocation context data used for event reporting
-        """
-
-    @property
-    @abstractmethod
-    def ram_cache(self) -> ModelCacheBase[AnyModel]:
-        """Return the RAM cache used by this loader."""
-
-    @property
-    @abstractmethod
-    def convert_cache(self) -> ModelConvertCacheBase:
-        """Return the checkpoint convert cache used by this loader."""

invokeai/app/services/model_load/model_load_default.py

@@ -1,113 +0,0 @@
-# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Team
-"""Implementation of model loader service."""
-
-from typing import Optional, Type
-
-from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.shared.invocation_context import InvocationContextData
-from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
-from invokeai.backend.model_manager.load import (
-    LoadedModel,
-    ModelLoaderRegistry,
-    ModelLoaderRegistryBase,
-)
-from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
-from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
-from invokeai.backend.util.logging import InvokeAILogger
-
-from .model_load_base import ModelLoadServiceBase
-
-
-class ModelLoadService(ModelLoadServiceBase):
-    """Wrapper around ModelLoaderRegistry."""
-
-    def __init__(
-        self,
-        app_config: InvokeAIAppConfig,
-        ram_cache: ModelCacheBase[AnyModel],
-        convert_cache: ModelConvertCacheBase,
-        registry: Optional[Type[ModelLoaderRegistryBase]] = ModelLoaderRegistry,
-    ):
-        """Initialize the model load service."""
-        logger = InvokeAILogger.get_logger(self.__class__.__name__)
-        logger.setLevel(app_config.log_level.upper())
-        self._logger = logger
-        self._app_config = app_config
-        self._ram_cache = ram_cache
-        self._convert_cache = convert_cache
-        self._registry = registry
-
-    def start(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-
-    @property
-    def ram_cache(self) -> ModelCacheBase[AnyModel]:
-        """Return the RAM cache used by this loader."""
-        return self._ram_cache
-
-    @property
-    def convert_cache(self) -> ModelConvertCacheBase:
-        """Return the checkpoint convert cache used by this loader."""
-        return self._convert_cache
-
-    def load_model(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
-        """
-        Given a model's configuration, load it and return the LoadedModel object.
-
-        :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
-        :param submodel: For main (pipeline models), the submodel to fetch.
-        :param context: Invocation context used for event reporting
-        """
-        if context_data:
-            self._emit_load_event(
-                context_data=context_data,
-                model_config=model_config,
-            )
-
-        implementation, model_config, submodel_type = self._registry.get_implementation(model_config, submodel_type)  # type: ignore
-        loaded_model: LoadedModel = implementation(
-            app_config=self._app_config,
-            logger=self._logger,
-            ram_cache=self._ram_cache,
-            convert_cache=self._convert_cache,
-        ).load_model(model_config, submodel_type)
-
-        if context_data:
-            self._emit_load_event(
-                context_data=context_data,
-                model_config=model_config,
-                loaded=True,
-            )
-        return loaded_model
-
-    def _emit_load_event(
-        self,
-        context_data: InvocationContextData,
-        model_config: AnyModelConfig,
-        loaded: Optional[bool] = False,
-    ) -> None:
-        if not self._invoker:
-            return
-
-        if not loaded:
-            self._invoker.services.events.emit_model_load_started(
-                queue_id=context_data.queue_item.queue_id,
-                queue_item_id=context_data.queue_item.item_id,
-                queue_batch_id=context_data.queue_item.batch_id,
-                graph_execution_state_id=context_data.queue_item.session_id,
-                model_config=model_config,
-            )
-        else:
-            self._invoker.services.events.emit_model_load_completed(
-                queue_id=context_data.queue_item.queue_id,
-                queue_item_id=context_data.queue_item.item_id,
-                queue_batch_id=context_data.queue_item.batch_id,
-                graph_execution_state_id=context_data.queue_item.session_id,
-                model_config=model_config,
-            )

invokeai/app/services/model_manager/__init__.py

@@ -1,17 +1 @@
-"""Initialization file for model manager service."""
-
-from invokeai.backend.model_manager import AnyModel, AnyModelConfig, BaseModelType, ModelType, SubModelType
-from invokeai.backend.model_manager.load import LoadedModel
-
-from .model_manager_default import ModelManagerService, ModelManagerServiceBase
-
-__all__ = [
-    "ModelManagerServiceBase",
-    "ModelManagerService",
-    "AnyModel",
-    "AnyModelConfig",
-    "BaseModelType",
-    "ModelType",
-    "SubModelType",
-    "LoadedModel",
-]
+from .model_manager_default import ModelManagerService  # noqa F401

invokeai/app/services/model_manager/model_manager_base.py

@@ -1,101 +1,283 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
 
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
-from typing import Optional
+from logging import Logger
+from pathlib import Path
+from typing import Callable, List, Literal, Optional, Tuple, Union
 
-import torch
-from typing_extensions import Self
+from pydantic import Field
 
-from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
 from invokeai.app.services.shared.invocation_context import InvocationContextData
-from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, ModelType, SubModelType
-from invokeai.backend.model_manager.load.load_base import LoadedModel
-
-from ..config import InvokeAIAppConfig
-from ..download import DownloadQueueServiceBase
-from ..events.events_base import EventServiceBase
-from ..model_install import ModelInstallServiceBase
-from ..model_load import ModelLoadServiceBase
-from ..model_records import ModelRecordServiceBase
+from invokeai.backend.model_management import (
+    AddModelResult,
+    BaseModelType,
+    LoadedModelInfo,
+    MergeInterpolationMethod,
+    ModelType,
+    SchedulerPredictionType,
+    SubModelType,
+)
+from invokeai.backend.model_management.model_cache import CacheStats
 
 
 class ModelManagerServiceBase(ABC):
-    """Abstract base class for the model manager service."""
+    """Responsible for managing models on disk and in memory"""
 
-    # attributes:
-    # store: ModelRecordServiceBase = Field(description="An instance of the model record configuration service.")
-    # install: ModelInstallServiceBase = Field(description="An instance of the model install service.")
-    # load: ModelLoadServiceBase = Field(description="An instance of the model load service.")
-
-    @classmethod
     @abstractmethod
-    def build_model_manager(
-        cls,
-        app_config: InvokeAIAppConfig,
-        model_record_service: ModelRecordServiceBase,
-        download_queue: DownloadQueueServiceBase,
-        events: EventServiceBase,
-        execution_device: torch.device,
-    ) -> Self:
+    def __init__(
+        self,
+        config: InvokeAIAppConfig,
+        logger: Logger,
+    ):
         """
-        Construct the model manager service instance.
-
-        Use it rather than the __init__ constructor. This class
-        method simplifies the construction considerably.
+        Initialize with the path to the models.yaml config file.
+        Optional parameters are the torch device type, precision, max_models,
+        and sequential_offload boolean. Note that the default device
+        type and precision are set up for a CUDA system running at half precision.
         """
         pass
 
-    @property
     @abstractmethod
-    def store(self) -> ModelRecordServiceBase:
-        """Return the ModelRecordServiceBase used to store and retrieve configuration records."""
-        pass
-
-    @property
-    @abstractmethod
-    def load(self) -> ModelLoadServiceBase:
-        """Return the ModelLoadServiceBase used to load models from their configuration records."""
-        pass
-
-    @property
-    @abstractmethod
-    def install(self) -> ModelInstallServiceBase:
-        """Return the ModelInstallServiceBase used to download and manipulate model files."""
-        pass
-
-    @abstractmethod
-    def start(self, invoker: Invoker) -> None:
-        pass
-
-    @abstractmethod
-    def stop(self, invoker: Invoker) -> None:
-        pass
-
-    @abstractmethod
-    def load_model_by_config(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
-        pass
-
-    @abstractmethod
-    def load_model_by_key(
-        self,
-        key: str,
-        submodel_type: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
-        pass
-
-    @abstractmethod
-    def load_model_by_attr(
+    def get_model(
         self,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
         submodel: Optional[SubModelType] = None,
         context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
+    ) -> LoadedModelInfo:
+        """Retrieve the indicated model with name and type.
+        submodel can be used to get a part (such as the vae)
+        of a diffusers pipeline."""
+        pass
+
+    @property
+    @abstractmethod
+    def logger(self):
+        pass
+
+    @abstractmethod
+    def model_exists(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ) -> bool:
+        pass
+
+    @abstractmethod
+    def model_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
+        """
+        Given a model name returns a dict-like (OmegaConf) object describing it.
+        Uses the exact format as the omegaconf stanza.
+        """
+        pass
+
+    @abstractmethod
+    def list_models(self, base_model: Optional[BaseModelType] = None, model_type: Optional[ModelType] = None) -> dict:
+        """
+        Return a dict of models in the format:
+        { model_type1:
+          { model_name1: {'status': 'active'|'cached'|'not loaded',
+                         'model_name' : name,
+                         'model_type' : SDModelType,
+                         'description': description,
+                         'format': 'folder'|'safetensors'|'ckpt'
+                         },
+            model_name2: { etc }
+          },
+          model_type2:
+            { model_name_n: etc
+        }
+        """
+        pass
+
+    @abstractmethod
+    def list_model(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
+        """
+        Return information about the model using the same format as list_models()
+        """
+        pass
+
+    @abstractmethod
+    def model_names(self) -> List[Tuple[str, BaseModelType, ModelType]]:
+        """
+        Returns a list of all the model names known.
+        """
+        pass
+
+    @abstractmethod
+    def add_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        model_attributes: dict,
+        clobber: bool = False,
+    ) -> AddModelResult:
+        """
+        Update the named model with a dictionary of attributes. Will fail with an
+        assertion error if the name already exists. Pass clobber=True to overwrite.
+        On a successful update, the config will be changed in memory. Will fail
+        with an assertion error if provided attributes are incorrect or
+        the model name is missing. Call commit() to write changes to disk.
+        """
+        pass
+
+    @abstractmethod
+    def update_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        model_attributes: dict,
+    ) -> AddModelResult:
+        """
+        Update the named model with a dictionary of attributes. Will fail with a
+        ModelNotFoundException if the name does not already exist.
+
+        On a successful update, the config will be changed in memory. Will fail
+        with an assertion error if provided attributes are incorrect or
+        the model name is missing. Call commit() to write changes to disk.
+        """
+        pass
+
+    @abstractmethod
+    def del_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ):
+        """
+        Delete the named model from configuration. If delete_files is true,
+        then the underlying weight file or diffusers directory will be deleted
+        as well. Call commit() to write to disk.
+        """
+        pass
+
+    @abstractmethod
+    def rename_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        new_name: str,
+    ):
+        """
+        Rename the indicated model.
+        """
+        pass
+
+    @abstractmethod
+    def list_checkpoint_configs(self) -> List[Path]:
+        """
+        List the checkpoint config paths from ROOT/configs/stable-diffusion.
+        """
+        pass
+
+    @abstractmethod
+    def convert_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: Literal[ModelType.Main, ModelType.Vae],
+    ) -> AddModelResult:
+        """
+        Convert a checkpoint file into a diffusers folder, deleting the cached
+        version and deleting the original checkpoint file if it is in the models
+        directory.
+        :param model_name: Name of the model to convert
+        :param base_model: Base model type
+        :param model_type: Type of model ['vae' or 'main']
+
+        This will raise a ValueError unless the model is not a checkpoint. It will
+        also raise a ValueError in the event that there is a similarly-named diffusers
+        directory already in place.
+        """
+        pass
+
+    @abstractmethod
+    def heuristic_import(
+        self,
+        items_to_import: set[str],
+        prediction_type_helper: Optional[Callable[[Path], SchedulerPredictionType]] = None,
+    ) -> dict[str, AddModelResult]:
+        """Import a list of paths, repo_ids or URLs. Returns the set of
+        successfully imported items.
+        :param items_to_import: Set of strings corresponding to models to be imported.
+        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
+
+        The prediction type helper is necessary to distinguish between
+        models based on Stable Diffusion 2 Base (requiring
+        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
+        (requiring SchedulerPredictionType.VPrediction). It is
+        generally impossible to do this programmatically, so the
+        prediction_type_helper usually asks the user to choose.
+
+        The result is a set of successfully installed models. Each element
+        of the set is a dict corresponding to the newly-created OmegaConf stanza for
+        that model.
+        """
+        pass
+
+    @abstractmethod
+    def merge_models(
+        self,
+        model_names: List[str] = Field(
+            default=None, min_length=2, max_length=3, description="List of model names to merge"
+        ),
+        base_model: Union[BaseModelType, str] = Field(
+            default=None, description="Base model shared by all models to be merged"
+        ),
+        merged_model_name: str = Field(default=None, description="Name of destination model after merging"),
+        alpha: Optional[float] = 0.5,
+        interp: Optional[MergeInterpolationMethod] = None,
+        force: Optional[bool] = False,
+        merge_dest_directory: Optional[Path] = None,
+    ) -> AddModelResult:
+        """
+        Merge two to three diffusrs pipeline models and save as a new model.
+        :param model_names: List of 2-3 models to merge
+        :param base_model: Base model to use for all models
+        :param merged_model_name: Name of destination merged model
+        :param alpha: Alpha strength to apply to 2d and 3d model
+        :param interp: Interpolation method. None (default)
+        :param merge_dest_directory: Save the merged model to the designated directory (with 'merged_model_name' appended)
+        """
+        pass
+
+    @abstractmethod
+    def search_for_models(self, directory: Path) -> List[Path]:
+        """
+        Return list of all models found in the designated directory.
+        """
+        pass
+
+    @abstractmethod
+    def sync_to_config(self):
+        """
+        Re-read models.yaml, rescan the models directory, and reimport models
+        in the autoimport directories. Call after making changes outside the
+        model manager API.
+        """
+        pass
+
+    @abstractmethod
+    def collect_cache_stats(self, cache_stats: CacheStats):
+        """
+        Reset model cache statistics for graph with graph_id.
+        """
+        pass
+
+    @abstractmethod
+    def commit(self, conf_file: Optional[Path] = None) -> None:
+        """
+        Write current configuration out to the indicated file.
+        If no conf_file is provided, then replaces the
+        original file/database used to initialize the object.
+        """
         pass

invokeai/app/services/model_manager/model_manager_default.py

@@ -1,155 +1,421 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
-"""Implementation of ModelManagerServiceBase."""
 
-from typing import Optional
+from __future__ import annotations
+
+from logging import Logger
+from pathlib import Path
+from typing import TYPE_CHECKING, Callable, List, Literal, Optional, Tuple, Union
 
 import torch
-from typing_extensions import Self
+from pydantic import Field
 
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.shared.invocation_context import InvocationContextData
-from invokeai.backend.model_manager import AnyModelConfig, BaseModelType, LoadedModel, ModelType, SubModelType
-from invokeai.backend.model_manager.load import ModelCache, ModelConvertCache, ModelLoaderRegistry
-from invokeai.backend.util.devices import choose_torch_device
-from invokeai.backend.util.logging import InvokeAILogger
+from invokeai.backend.model_management import (
+    AddModelResult,
+    BaseModelType,
+    LoadedModelInfo,
+    MergeInterpolationMethod,
+    ModelManager,
+    ModelMerger,
+    ModelNotFoundException,
+    ModelType,
+    SchedulerPredictionType,
+    SubModelType,
+)
+from invokeai.backend.model_management.model_cache import CacheStats
+from invokeai.backend.model_management.model_search import FindModels
+from invokeai.backend.util import choose_precision, choose_torch_device
 
-from ..config import InvokeAIAppConfig
-from ..download import DownloadQueueServiceBase
-from ..events.events_base import EventServiceBase
-from ..model_install import ModelInstallService, ModelInstallServiceBase
-from ..model_load import ModelLoadService, ModelLoadServiceBase
-from ..model_records import ModelRecordServiceBase, UnknownModelException
 from .model_manager_base import ModelManagerServiceBase
 
+if TYPE_CHECKING:
+    pass
 
+
+# simple implementation
 class ModelManagerService(ModelManagerServiceBase):
-    """
-    The ModelManagerService handles various aspects of model installation, maintenance and loading.
-
-    It bundles three distinct services:
-    model_manager.store   -- Routines to manage the database of model configuration records.
-    model_manager.install -- Routines to install, move and delete models.
-    model_manager.load    -- Routines to load models into memory.
-    """
+    """Responsible for managing models on disk and in memory"""
 
     def __init__(
         self,
-        store: ModelRecordServiceBase,
-        install: ModelInstallServiceBase,
-        load: ModelLoadServiceBase,
+        config: InvokeAIAppConfig,
+        logger: Logger,
     ):
-        self._store = store
-        self._install = install
-        self._load = load
+        """
+        Initialize with the path to the models.yaml config file.
+        Optional parameters are the torch device type, precision, max_models,
+        and sequential_offload boolean. Note that the default device
+        type and precision are set up for a CUDA system running at half precision.
+        """
+        if config.model_conf_path and config.model_conf_path.exists():
+            config_file = config.model_conf_path
+        else:
+            config_file = config.root_dir / "configs/models.yaml"
 
-    @property
-    def store(self) -> ModelRecordServiceBase:
-        return self._store
+        logger.debug(f"Config file={config_file}")
 
-    @property
-    def install(self) -> ModelInstallServiceBase:
-        return self._install
+        device = torch.device(choose_torch_device())
+        device_name = torch.cuda.get_device_name() if device == torch.device("cuda") else ""
+        logger.info(f"GPU device = {device} {device_name}")
 
-    @property
-    def load(self) -> ModelLoadServiceBase:
-        return self._load
+        precision = config.precision
+        if precision == "auto":
+            precision = choose_precision(device)
+        dtype = torch.float32 if precision == "float32" else torch.float16
+
+        # this is transitional backward compatibility
+        # support for the deprecated `max_loaded_models`
+        # configuration value. If present, then the
+        # cache size is set to 2.5 GB times
+        # the number of max_loaded_models. Otherwise
+        # use new `ram_cache_size` config setting
+        max_cache_size = config.ram_cache_size
+
+        logger.debug(f"Maximum RAM cache size: {max_cache_size} GiB")
+
+        sequential_offload = config.sequential_guidance
+
+        self.mgr = ModelManager(
+            config=config_file,
+            device_type=device,
+            precision=dtype,
+            max_cache_size=max_cache_size,
+            sequential_offload=sequential_offload,
+            logger=logger,
+        )
+        logger.info("Model manager service initialized")
 
     def start(self, invoker: Invoker) -> None:
-        for service in [self._store, self._install, self._load]:
-            if hasattr(service, "start"):
-                service.start(invoker)
+        self._invoker: Optional[Invoker] = invoker
 
-    def stop(self, invoker: Invoker) -> None:
-        for service in [self._store, self._install, self._load]:
-            if hasattr(service, "stop"):
-                service.stop(invoker)
-
-    def load_model_by_config(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
-        return self.load.load_model(model_config, submodel_type, context_data)
-
-    def load_model_by_key(
-        self,
-        key: str,
-        submodel_type: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
-        config = self.store.get_model(key)
-        return self.load.load_model(config, submodel_type, context_data)
-
-    def load_model_by_attr(
+    def get_model(
         self,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
         submodel: Optional[SubModelType] = None,
         context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
+    ) -> LoadedModelInfo:
         """
-        Given a model's attributes, search the database for it, and if found, load and return the LoadedModel object.
-
-        This is provided for API compatability with the get_model() method
-        in the original model manager. However, note that LoadedModel is
-        not the same as the original ModelInfo that ws returned.
-
-        :param model_name: Name of to be fetched.
-        :param base_model: Base model
-        :param model_type: Type of the model
-        :param submodel: For main (pipeline models), the submodel to fetch
-        :param context: The invocation context.
-
-        Exceptions: UnknownModelException -- model with this key not known
-                    NotImplementedException -- a model loader was not provided at initialization time
-                    ValueError -- more than one model matches this combination
+        Retrieve the indicated model. submodel can be used to get a
+        part (such as the vae) of a diffusers mode.
         """
-        configs = self.store.search_by_attr(model_name, base_model, model_type)
-        if len(configs) == 0:
-            raise UnknownModelException(f"{base_model}/{model_type}/{model_name}: Unknown model")
-        elif len(configs) > 1:
-            raise ValueError(f"{base_model}/{model_type}/{model_name}: More than one model matches.")
+
+        # we can emit model loading events if we are executing with access to the invocation context
+        if context_data is not None:
+            self._emit_load_event(
+                context_data=context_data,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+            )
+
+        loaded_model_info = self.mgr.get_model(
+            model_name,
+            base_model,
+            model_type,
+            submodel,
+        )
+
+        if context_data is not None:
+            self._emit_load_event(
+                context_data=context_data,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+                loaded_model_info=loaded_model_info,
+            )
+
+        return loaded_model_info
+
+    def model_exists(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ) -> bool:
+        """
+        Given a model name, returns True if it is a valid
+        identifier.
+        """
+        return self.mgr.model_exists(
+            model_name,
+            base_model,
+            model_type,
+        )
+
+    def model_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> Union[dict, None]:
+        """
+        Given a model name returns a dict-like (OmegaConf) object describing it.
+        """
+        return self.mgr.model_info(model_name, base_model, model_type)
+
+    def model_names(self) -> List[Tuple[str, BaseModelType, ModelType]]:
+        """
+        Returns a list of all the model names known.
+        """
+        return self.mgr.model_names()
+
+    def list_models(
+        self, base_model: Optional[BaseModelType] = None, model_type: Optional[ModelType] = None
+    ) -> list[dict]:
+        """
+        Return a list of models.
+        """
+        return self.mgr.list_models(base_model, model_type)
+
+    def list_model(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> Union[dict, None]:
+        """
+        Return information about the model using the same format as list_models()
+        """
+        return self.mgr.list_model(model_name=model_name, base_model=base_model, model_type=model_type)
+
+    def add_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        model_attributes: dict,
+        clobber: bool = False,
+    ) -> AddModelResult:
+        """
+        Update the named model with a dictionary of attributes. Will fail with an
+        assertion error if the name already exists. Pass clobber=True to overwrite.
+        On a successful update, the config will be changed in memory. Will fail
+        with an assertion error if provided attributes are incorrect or
+        the model name is missing. Call commit() to write changes to disk.
+        """
+        self.logger.debug(f"add/update model {model_name}")
+        return self.mgr.add_model(model_name, base_model, model_type, model_attributes, clobber)
+
+    def update_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        model_attributes: dict,
+    ) -> AddModelResult:
+        """
+        Update the named model with a dictionary of attributes. Will fail with a
+        ModelNotFoundException exception if the name does not already exist.
+        On a successful update, the config will be changed in memory. Will fail
+        with an assertion error if provided attributes are incorrect or
+        the model name is missing. Call commit() to write changes to disk.
+        """
+        self.logger.debug(f"update model {model_name}")
+        if not self.model_exists(model_name, base_model, model_type):
+            raise ModelNotFoundException(f"Unknown model {model_name}")
+        return self.add_model(model_name, base_model, model_type, model_attributes, clobber=True)
+
+    def del_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ):
+        """
+        Delete the named model from configuration. If delete_files is true,
+        then the underlying weight file or diffusers directory will be deleted
+        as well.
+        """
+        self.logger.debug(f"delete model {model_name}")
+        self.mgr.del_model(model_name, base_model, model_type)
+        self.mgr.commit()
+
+    def convert_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: Literal[ModelType.Main, ModelType.Vae],
+        convert_dest_directory: Optional[Path] = Field(
+            default=None, description="Optional directory location for merged model"
+        ),
+    ) -> AddModelResult:
+        """
+        Convert a checkpoint file into a diffusers folder, deleting the cached
+        version and deleting the original checkpoint file if it is in the models
+        directory.
+        :param model_name: Name of the model to convert
+        :param base_model: Base model type
+        :param model_type: Type of model ['vae' or 'main']
+        :param convert_dest_directory: Save the converted model to the designated directory (`models/etc/etc` by default)
+
+        This will raise a ValueError unless the model is not a checkpoint. It will
+        also raise a ValueError in the event that there is a similarly-named diffusers
+        directory already in place.
+        """
+        self.logger.debug(f"convert model {model_name}")
+        return self.mgr.convert_model(model_name, base_model, model_type, convert_dest_directory)
+
+    def collect_cache_stats(self, cache_stats: CacheStats):
+        """
+        Reset model cache statistics for graph with graph_id.
+        """
+        self.mgr.cache.stats = cache_stats
+
+    def commit(self, conf_file: Optional[Path] = None):
+        """
+        Write current configuration out to the indicated file.
+        If no conf_file is provided, then replaces the
+        original file/database used to initialize the object.
+        """
+        return self.mgr.commit(conf_file)
+
+    def _emit_load_event(
+        self,
+        context_data: InvocationContextData,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: Optional[SubModelType] = None,
+        loaded_model_info: Optional[LoadedModelInfo] = None,
+    ):
+        if self._invoker is None:
+            return
+
+        if self._invoker.services.queue.is_canceled(context_data.session_id):
+            raise CanceledException()
+
+        if loaded_model_info:
+            self._invoker.services.events.emit_model_load_completed(
+                queue_id=context_data.queue_id,
+                queue_item_id=context_data.queue_item_id,
+                queue_batch_id=context_data.batch_id,
+                graph_execution_state_id=context_data.session_id,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+                loaded_model_info=loaded_model_info,
+            )
         else:
-            return self.load.load_model(configs[0], submodel, context_data)
+            self._invoker.services.events.emit_model_load_started(
+                queue_id=context_data.queue_id,
+                queue_item_id=context_data.queue_item_id,
+                queue_batch_id=context_data.batch_id,
+                graph_execution_state_id=context_data.session_id,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+            )
 
-    @classmethod
-    def build_model_manager(
-        cls,
-        app_config: InvokeAIAppConfig,
-        model_record_service: ModelRecordServiceBase,
-        download_queue: DownloadQueueServiceBase,
-        events: EventServiceBase,
-        execution_device: torch.device = choose_torch_device(),
-    ) -> Self:
+    @property
+    def logger(self):
+        return self.mgr.logger
+
+    def heuristic_import(
+        self,
+        items_to_import: set[str],
+        prediction_type_helper: Optional[Callable[[Path], SchedulerPredictionType]] = None,
+    ) -> dict[str, AddModelResult]:
+        """Import a list of paths, repo_ids or URLs. Returns the set of
+        successfully imported items.
+        :param items_to_import: Set of strings corresponding to models to be imported.
+        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
+
+        The prediction type helper is necessary to distinguish between
+        models based on Stable Diffusion 2 Base (requiring
+        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
+        (requiring SchedulerPredictionType.VPrediction). It is
+        generally impossible to do this programmatically, so the
+        prediction_type_helper usually asks the user to choose.
+
+        The result is a set of successfully installed models. Each element
+        of the set is a dict corresponding to the newly-created OmegaConf stanza for
+        that model.
         """
-        Construct the model manager service instance.
+        return self.mgr.heuristic_import(items_to_import, prediction_type_helper)
 
-        For simplicity, use this class method rather than the __init__ constructor.
+    def merge_models(
+        self,
+        model_names: List[str] = Field(
+            default=None, min_length=2, max_length=3, description="List of model names to merge"
+        ),
+        base_model: Union[BaseModelType, str] = Field(
+            default=None, description="Base model shared by all models to be merged"
+        ),
+        merged_model_name: str = Field(default=None, description="Name of destination model after merging"),
+        alpha: float = 0.5,
+        interp: Optional[MergeInterpolationMethod] = None,
+        force: bool = False,
+        merge_dest_directory: Optional[Path] = Field(
+            default=None, description="Optional directory location for merged model"
+        ),
+    ) -> AddModelResult:
         """
-        logger = InvokeAILogger.get_logger(cls.__name__)
-        logger.setLevel(app_config.log_level.upper())
+        Merge two to three diffusrs pipeline models and save as a new model.
+        :param model_names: List of 2-3 models to merge
+        :param base_model: Base model to use for all models
+        :param merged_model_name: Name of destination merged model
+        :param alpha: Alpha strength to apply to 2d and 3d model
+        :param interp: Interpolation method. None (default)
+        :param merge_dest_directory: Save the merged model to the designated directory (with 'merged_model_name' appended)
+        """
+        merger = ModelMerger(self.mgr)
+        try:
+            result = merger.merge_diffusion_models_and_save(
+                model_names=model_names,
+                base_model=base_model,
+                merged_model_name=merged_model_name,
+                alpha=alpha,
+                interp=interp,
+                force=force,
+                merge_dest_directory=merge_dest_directory,
+            )
+        except AssertionError as e:
+            raise ValueError(e)
+        return result
 
-        ram_cache = ModelCache(
-            max_cache_size=app_config.ram_cache_size,
-            max_vram_cache_size=app_config.vram_cache_size,
-            logger=logger,
-            execution_device=execution_device,
+    def search_for_models(self, directory: Path) -> List[Path]:
+        """
+        Return list of all models found in the designated directory.
+        """
+        search = FindModels([directory], self.logger)
+        return search.list_models()
+
+    def sync_to_config(self):
+        """
+        Re-read models.yaml, rescan the models directory, and reimport models
+        in the autoimport directories. Call after making changes outside the
+        model manager API.
+        """
+        return self.mgr.sync_to_config()
+
+    def list_checkpoint_configs(self) -> List[Path]:
+        """
+        List the checkpoint config paths from ROOT/configs/stable-diffusion.
+        """
+        config = self.mgr.app_config
+        conf_path = config.legacy_conf_path
+        root_path = config.root_path
+        return [(conf_path / x).relative_to(root_path) for x in conf_path.glob("**/*.yaml")]
+
+    def rename_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        new_name: Optional[str] = None,
+        new_base: Optional[BaseModelType] = None,
+    ):
+        """
+        Rename the indicated model. Can provide a new name and/or a new base.
+        :param model_name: Current name of the model
+        :param base_model: Current base of the model
+        :param model_type: Model type (can't be changed)
+        :param new_name: New name for the model
+        :param new_base: New base for the model
+        """
+        self.mgr.rename_model(
+            base_model=base_model,
+            model_type=model_type,
+            model_name=model_name,
+            new_name=new_name,
+            new_base=new_base,
         )
-        convert_cache = ModelConvertCache(
-            cache_path=app_config.models_convert_cache_path, max_size=app_config.convert_cache_size
-        )
-        loader = ModelLoadService(
-            app_config=app_config,
-            ram_cache=ram_cache,
-            convert_cache=convert_cache,
-            registry=ModelLoaderRegistry,
-        )
-        installer = ModelInstallService(
-            app_config=app_config,
-            record_store=model_record_service,
-            download_queue=download_queue,
-            event_bus=events,
-        )
-        return cls(store=model_record_service, install=installer, load=loader)

invokeai/app/services/model_metadata/__init__.py

@@ -1,9 +0,0 @@
-"""Init file for ModelMetadataStoreService module."""
-
-from .metadata_store_base import ModelMetadataStoreBase
-from .metadata_store_sql import ModelMetadataStoreSQL
-
-__all__ = [
-    "ModelMetadataStoreBase",
-    "ModelMetadataStoreSQL",
-]

invokeai/app/services/model_metadata/metadata_store_base.py

@@ -1,81 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Development Team
-"""
-Storage for Model Metadata
-"""
-
-from abc import ABC, abstractmethod
-from typing import List, Optional, Set, Tuple
-
-from pydantic import Field
-
-from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-from invokeai.backend.model_manager.metadata.metadata_base import ModelDefaultSettings
-
-
-class ModelMetadataChanges(BaseModelExcludeNull, extra="allow"):
-    """A set of changes to apply to model metadata.
-    Only limited changes are valid:
-      - `default_settings`: the user-configured default settings for this model
-    """
-
-    default_settings: Optional[ModelDefaultSettings] = Field(
-        default=None, description="The user-configured default settings for this model"
-    )
-    """The user-configured default settings for this model"""
-
-
-class ModelMetadataStoreBase(ABC):
-    """Store, search and fetch model metadata retrieved from remote repositories."""
-
-    @abstractmethod
-    def add_metadata(self, model_key: str, metadata: AnyModelRepoMetadata) -> None:
-        """
-        Add a block of repo metadata to a model record.
-
-        The model record config must already exist in the database with the
-        same key. Otherwise a FOREIGN KEY constraint exception will be raised.
-
-        :param model_key: Existing model key in the `model_config` table
-        :param metadata: ModelRepoMetadata object to store
-        """
-
-    @abstractmethod
-    def get_metadata(self, model_key: str) -> AnyModelRepoMetadata:
-        """Retrieve the ModelRepoMetadata corresponding to model key."""
-
-    @abstractmethod
-    def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:  # key, metadata
-        """Dump out all the metadata."""
-
-    @abstractmethod
-    def update_metadata(self, model_key: str, metadata: AnyModelRepoMetadata) -> AnyModelRepoMetadata:
-        """
-        Update metadata corresponding to the model with the indicated key.
-
-        :param model_key: Existing model key in the `model_config` table
-        :param metadata: ModelRepoMetadata object to update
-        """
-
-    @abstractmethod
-    def list_tags(self) -> Set[str]:
-        """Return all tags in the tags table."""
-
-    @abstractmethod
-    def search_by_tag(self, tags: Set[str]) -> Set[str]:
-        """Return the keys of models containing all of the listed tags."""
-
-    @abstractmethod
-    def search_by_author(self, author: str) -> Set[str]:
-        """Return the keys of models authored by the indicated author."""
-
-    @abstractmethod
-    def search_by_name(self, name: str) -> Set[str]:
-        """
-        Return the keys of models with the indicated name.
-
-        Note that this is the name of the model given to it by
-        the remote source. The user may have changed the local
-        name. The local name will be located in the model config
-        record object.
-        """

invokeai/app/services/model_metadata/metadata_store_sql.py

@@ -1,223 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Development Team
-"""
-SQL Storage for Model Metadata
-"""
-
-import sqlite3
-from typing import List, Optional, Set, Tuple
-
-from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, UnknownMetadataException
-from invokeai.backend.model_manager.metadata.fetch import ModelMetadataFetchBase
-
-from .metadata_store_base import ModelMetadataStoreBase
-
-
-class ModelMetadataStoreSQL(ModelMetadataStoreBase):
-    """Store, search and fetch model metadata retrieved from remote repositories."""
-
-    def __init__(self, db: SqliteDatabase):
-        """
-        Initialize a new object from preexisting sqlite3 connection and threading lock objects.
-
-        :param conn: sqlite3 connection object
-        :param lock: threading Lock object
-        """
-        super().__init__()
-        self._db = db
-        self._cursor = self._db.conn.cursor()
-
-    def add_metadata(self, model_key: str, metadata: AnyModelRepoMetadata) -> None:
-        """
-        Add a block of repo metadata to a model record.
-
-        The model record config must already exist in the database with the
-        same key. Otherwise a FOREIGN KEY constraint exception will be raised.
-
-        :param model_key: Existing model key in the `model_config` table
-        :param metadata: ModelRepoMetadata object to store
-        """
-        json_serialized = metadata.model_dump_json()
-        with self._db.lock:
-            try:
-                self._cursor.execute(
-                    """--sql
-                    INSERT INTO model_metadata(
-                       id,
-                       metadata
-                    )
-                    VALUES (?,?);
-                    """,
-                    (
-                        model_key,
-                        json_serialized,
-                    ),
-                )
-                self._update_tags(model_key, metadata.tags)
-                self._db.conn.commit()
-            except sqlite3.IntegrityError as excp:  # FOREIGN KEY error: the key was not in model_config table
-                self._db.conn.rollback()
-                raise UnknownMetadataException from excp
-            except sqlite3.Error as excp:
-                self._db.conn.rollback()
-                raise excp
-
-    def get_metadata(self, model_key: str) -> AnyModelRepoMetadata:
-        """Retrieve the ModelRepoMetadata corresponding to model key."""
-        with self._db.lock:
-            self._cursor.execute(
-                """--sql
-                SELECT metadata FROM model_metadata
-                WHERE id=?;
-                """,
-                (model_key,),
-            )
-            rows = self._cursor.fetchone()
-            if not rows:
-                raise UnknownMetadataException("model metadata not found")
-            return ModelMetadataFetchBase.from_json(rows[0])
-
-    def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:  # key, metadata
-        """Dump out all the metadata."""
-        with self._db.lock:
-            self._cursor.execute(
-                """--sql
-                SELECT id,metadata FROM model_metadata;
-                """,
-                (),
-            )
-            rows = self._cursor.fetchall()
-        return [(x[0], ModelMetadataFetchBase.from_json(x[1])) for x in rows]
-
-    def update_metadata(self, model_key: str, metadata: AnyModelRepoMetadata) -> AnyModelRepoMetadata:
-        """
-        Update metadata corresponding to the model with the indicated key.
-
-        :param model_key: Existing model key in the `model_config` table
-        :param metadata: ModelRepoMetadata object to update
-        """
-        json_serialized = metadata.model_dump_json()  # turn it into a json string.
-        with self._db.lock:
-            try:
-                self._cursor.execute(
-                    """--sql
-                    UPDATE model_metadata
-                    SET
-                        metadata=?
-                    WHERE id=?;
-                    """,
-                    (json_serialized, model_key),
-                )
-                if self._cursor.rowcount == 0:
-                    raise UnknownMetadataException("model metadata not found")
-                self._update_tags(model_key, metadata.tags)
-                self._db.conn.commit()
-            except sqlite3.Error as e:
-                self._db.conn.rollback()
-                raise e
-
-        return self.get_metadata(model_key)
-
-    def list_tags(self) -> Set[str]:
-        """Return all tags in the tags table."""
-        self._cursor.execute(
-            """--sql
-            select tag_text from tags;
-            """
-        )
-        return {x[0] for x in self._cursor.fetchall()}
-
-    def search_by_tag(self, tags: Set[str]) -> Set[str]:
-        """Return the keys of models containing all of the listed tags."""
-        with self._db.lock:
-            try:
-                matches: Optional[Set[str]] = None
-                for tag in tags:
-                    self._cursor.execute(
-                        """--sql
-                        SELECT a.model_id FROM model_tags AS a,
-                                                     tags AS b
-                        WHERE a.tag_id=b.tag_id
-                          AND b.tag_text=?;
-                        """,
-                        (tag,),
-                    )
-                    model_keys = {x[0] for x in self._cursor.fetchall()}
-                    if matches is None:
-                        matches = model_keys
-                    matches = matches.intersection(model_keys)
-            except sqlite3.Error as e:
-                raise e
-        return matches if matches else set()
-
-    def search_by_author(self, author: str) -> Set[str]:
-        """Return the keys of models authored by the indicated author."""
-        self._cursor.execute(
-            """--sql
-            SELECT id FROM model_metadata
-            WHERE author=?;
-            """,
-            (author,),
-        )
-        return {x[0] for x in self._cursor.fetchall()}
-
-    def search_by_name(self, name: str) -> Set[str]:
-        """
-        Return the keys of models with the indicated name.
-
-        Note that this is the name of the model given to it by
-        the remote source. The user may have changed the local
-        name. The local name will be located in the model config
-        record object.
-        """
-        self._cursor.execute(
-            """--sql
-            SELECT id FROM model_metadata
-            WHERE name=?;
-            """,
-            (name,),
-        )
-        return {x[0] for x in self._cursor.fetchall()}
-
-    def _update_tags(self, model_key: str, tags: Optional[Set[str]]) -> None:
-        """Update tags for the model referenced by model_key."""
-        if tags:
-            # remove previous tags from this model
-            self._cursor.execute(
-                """--sql
-                DELETE FROM model_tags
-                WHERE model_id=?;
-                """,
-                (model_key,),
-            )
-
-            for tag in tags:
-                self._cursor.execute(
-                    """--sql
-                    INSERT OR IGNORE INTO tags (
-                    tag_text
-                    )
-                    VALUES (?);
-                    """,
-                    (tag,),
-                )
-                self._cursor.execute(
-                    """--sql
-                    SELECT tag_id
-                    FROM tags
-                    WHERE tag_text = ?
-                    LIMIT 1;
-                    """,
-                    (tag,),
-                )
-                tag_id = self._cursor.fetchone()[0]
-                self._cursor.execute(
-                    """--sql
-                    INSERT OR IGNORE INTO model_tags (
-                    model_id,
-                    tag_id
-                    )
-                    VALUES (?,?);
-                    """,
-                    (model_key, tag_id),
-                )

invokeai/app/services/model_records/__init__.py

@@ -1,5 +1,4 @@
 """Init file for model record services."""
-
 from .model_records_base import (  # noqa F401
     DuplicateModelException,
     InvalidModelException,

invokeai/app/services/model_records/model_records_base.py

@@ -11,15 +11,8 @@ from typing import Any, Dict, List, Optional, Set, Tuple, Union
 from pydantic import BaseModel, Field
 
 from invokeai.app.services.shared.pagination import PaginatedResults
-from invokeai.backend.model_manager import (
-    AnyModelConfig,
-    BaseModelType,
-    ModelFormat,
-    ModelType,
-)
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-from ..model_metadata import ModelMetadataStoreBase
+from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, ModelFormat, ModelType
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, ModelMetadataStore
 
 
 class DuplicateModelException(Exception):
@@ -111,7 +104,7 @@ class ModelRecordServiceBase(ABC):
 
     @property
     @abstractmethod
-    def metadata_store(self) -> ModelMetadataStoreBase:
+    def metadata_store(self) -> ModelMetadataStore:
         """Return a ModelMetadataStore initialized on the same database."""
         pass
 
@@ -153,7 +146,7 @@ class ModelRecordServiceBase(ABC):
     @abstractmethod
     def exists(self, key: str) -> bool:
         """
-        Return True if a model with the indicated key exists in the database.
+        Return True if a model with the indicated key exists in the databse.
 
         :param key: Unique key for the model to be deleted
         """

invokeai/app/services/model_records/model_records_sql.py

@@ -39,6 +39,7 @@ Typical usage:
   configs = store.search_by_attr(base_model='sd-2', model_type='main')
 """
 
+
 import json
 import sqlite3
 from math import ceil
@@ -53,9 +54,8 @@ from invokeai.backend.model_manager.config import (
     ModelFormat,
     ModelType,
 )
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, UnknownMetadataException
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, ModelMetadataStore, UnknownMetadataException
 
-from ..model_metadata import ModelMetadataStoreBase, ModelMetadataStoreSQL
 from ..shared.sqlite.sqlite_database import SqliteDatabase
 from .model_records_base import (
     DuplicateModelException,
@@ -69,16 +69,16 @@ from .model_records_base import (
 class ModelRecordServiceSQL(ModelRecordServiceBase):
     """Implementation of the ModelConfigStore ABC using a SQL database."""
 
-    def __init__(self, db: SqliteDatabase, metadata_store: ModelMetadataStoreBase):
+    def __init__(self, db: SqliteDatabase):
         """
         Initialize a new object from preexisting sqlite3 connection and threading lock objects.
 
-        :param db: Sqlite connection object
+        :param conn: sqlite3 connection object
+        :param lock: threading Lock object
         """
         super().__init__()
         self._db = db
-        self._cursor = db.conn.cursor()
-        self._metadata_store = metadata_store
+        self._cursor = self._db.conn.cursor()
 
     @property
     def db(self) -> SqliteDatabase:
@@ -158,7 +158,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
                 self._db.conn.rollback()
                 raise e
 
-    def update_model(self, key: str, config: Union[Dict[str, Any], AnyModelConfig]) -> AnyModelConfig:
+    def update_model(self, key: str, config: Union[dict, AnyModelConfig]) -> AnyModelConfig:
         """
         Update the model, returning the updated version.
 
@@ -199,7 +199,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config, strftime('%s',updated_at) FROM model_config
+                SELECT config FROM model_config
                 WHERE id=?;
                 """,
                 (key,),
@@ -207,7 +207,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
             rows = self._cursor.fetchone()
             if not rows:
                 raise UnknownModelException("model not found")
-            model = ModelConfigFactory.make_config(json.loads(rows[0]), timestamp=rows[1])
+            model = ModelConfigFactory.make_config(json.loads(rows[0]))
         return model
 
     def exists(self, key: str) -> bool:
@@ -265,14 +265,12 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 f"""--sql
-                select config, strftime('%s',updated_at) FROM model_config
+                select config FROM model_config
                 {where};
                 """,
                 tuple(bindings),
             )
-            results = [
-                ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in self._cursor.fetchall()
-            ]
+            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
         return results
 
     def search_by_path(self, path: Union[str, Path]) -> List[AnyModelConfig]:
@@ -281,14 +279,12 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config, strftime('%s',updated_at) FROM model_config
+                SELECT config FROM model_config
                 WHERE path=?;
                 """,
                 (str(path),),
             )
-            results = [
-                ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in self._cursor.fetchall()
-            ]
+            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
         return results
 
     def search_by_hash(self, hash: str) -> List[AnyModelConfig]:
@@ -297,20 +293,18 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config, strftime('%s',updated_at) FROM model_config
+                SELECT config FROM model_config
                 WHERE original_hash=?;
                 """,
                 (hash,),
             )
-            results = [
-                ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in self._cursor.fetchall()
-            ]
+            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
         return results
 
     @property
-    def metadata_store(self) -> ModelMetadataStoreBase:
+    def metadata_store(self) -> ModelMetadataStore:
         """Return a ModelMetadataStore initialized on the same database."""
-        return self._metadata_store
+        return ModelMetadataStore(self._db)
 
     def get_metadata(self, key: str) -> Optional[AnyModelRepoMetadata]:
         """
@@ -331,18 +325,18 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
 
         :param tags: Set of tags to search for. All tags must be present.
         """
-        store = ModelMetadataStoreSQL(self._db)
+        store = ModelMetadataStore(self._db)
         keys = store.search_by_tag(tags)
         return [self.get_model(x) for x in keys]
 
     def list_tags(self) -> Set[str]:
         """Return a unique set of all the model tags in the metadata database."""
-        store = ModelMetadataStoreSQL(self._db)
+        store = ModelMetadataStore(self._db)
         return store.list_tags()
 
     def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:
         """List metadata for all models that have it."""
-        store = ModelMetadataStoreSQL(self._db)
+        store = ModelMetadataStore(self._db)
         return store.list_all_metadata()
 
     def list_models(

invokeai/app/services/session_processor/session_processor_common.py

@@ -4,17 +4,3 @@ from pydantic import BaseModel, Field
 class SessionProcessorStatus(BaseModel):
     is_started: bool = Field(description="Whether the session processor is started")
     is_processing: bool = Field(description="Whether a session is being processed")
-
-
-class CanceledException(Exception):
-    """Execution canceled by user."""
-
-    pass
-
-
-class ProgressImage(BaseModel):
-    """The progress image sent intermittently during processing"""
-
-    width: int = Field(description="The effective width of the image in pixels")
-    height: int = Field(description="The effective height of the image in pixels")
-    dataURL: str = Field(description="The image data as a b64 data URL")

invokeai/app/services/session_processor/session_processor_default.py

@@ -1,5 +1,4 @@
 import traceback
-from contextlib import suppress
 from threading import BoundedSemaphore, Thread
 from threading import Event as ThreadEvent
 from typing import Optional
@@ -7,271 +6,136 @@ from typing import Optional
 from fastapi_events.handlers.local import local_handler
 from fastapi_events.typing import Event as FastAPIEvent
 
-from invokeai.app.invocations.baseinvocation import BaseInvocation
 from invokeai.app.services.events.events_base import EventServiceBase
-from invokeai.app.services.invocation_stats.invocation_stats_common import GESStatsNotFoundError
-from invokeai.app.services.session_processor.session_processor_common import CanceledException
 from invokeai.app.services.session_queue.session_queue_common import SessionQueueItem
-from invokeai.app.services.shared.invocation_context import InvocationContextData, build_invocation_context
-from invokeai.app.util.profiler import Profiler
 
 from ..invoker import Invoker
 from .session_processor_base import SessionProcessorBase
 from .session_processor_common import SessionProcessorStatus
 
+POLLING_INTERVAL = 1
+THREAD_LIMIT = 1
+
 
 class DefaultSessionProcessor(SessionProcessorBase):
-    def start(self, invoker: Invoker, thread_limit: int = 1, polling_interval: int = 1) -> None:
-        self._invoker: Invoker = invoker
-        self._queue_item: Optional[SessionQueueItem] = None
-        self._invocation: Optional[BaseInvocation] = None
+    def start(self, invoker: Invoker) -> None:
+        self.__invoker: Invoker = invoker
+        self.__queue_item: Optional[SessionQueueItem] = None
 
-        self._resume_event = ThreadEvent()
-        self._stop_event = ThreadEvent()
-        self._poll_now_event = ThreadEvent()
-        self._cancel_event = ThreadEvent()
+        self.__resume_event = ThreadEvent()
+        self.__stop_event = ThreadEvent()
+        self.__poll_now_event = ThreadEvent()
 
         local_handler.register(event_name=EventServiceBase.queue_event, _func=self._on_queue_event)
 
-        self._thread_limit = thread_limit
-        self._thread_semaphore = BoundedSemaphore(thread_limit)
-        self._polling_interval = polling_interval
-
-        # If profiling is enabled, create a profiler. The same profiler will be used for all sessions. Internally,
-        # the profiler will create a new profile for each session.
-        self._profiler = (
-            Profiler(
-                logger=self._invoker.services.logger,
-                output_dir=self._invoker.services.configuration.profiles_path,
-                prefix=self._invoker.services.configuration.profile_prefix,
-            )
-            if self._invoker.services.configuration.profile_graphs
-            else None
-        )
-
-        self._thread = Thread(
+        self.__threadLimit = BoundedSemaphore(THREAD_LIMIT)
+        self.__thread = Thread(
             name="session_processor",
-            target=self._process,
+            target=self.__process,
             kwargs={
-                "stop_event": self._stop_event,
-                "poll_now_event": self._poll_now_event,
-                "resume_event": self._resume_event,
-                "cancel_event": self._cancel_event,
+                "stop_event": self.__stop_event,
+                "poll_now_event": self.__poll_now_event,
+                "resume_event": self.__resume_event,
             },
         )
-        self._thread.start()
+        self.__thread.start()
 
     def stop(self, *args, **kwargs) -> None:
-        self._stop_event.set()
+        self.__stop_event.set()
 
     def _poll_now(self) -> None:
-        self._poll_now_event.set()
+        self.__poll_now_event.set()
 
     async def _on_queue_event(self, event: FastAPIEvent) -> None:
         event_name = event[1]["event"]
 
-        if event_name == "session_canceled" or event_name == "queue_cleared":
-            # These both mean we should cancel the current session.
-            self._cancel_event.set()
+        # This was a match statement, but match is not supported on python 3.9
+        if event_name in [
+            "graph_execution_state_complete",
+            "invocation_error",
+            "session_retrieval_error",
+            "invocation_retrieval_error",
+        ]:
+            self.__queue_item = None
+            self._poll_now()
+        elif (
+            event_name == "session_canceled"
+            and self.__queue_item is not None
+            and self.__queue_item.session_id == event[1]["data"]["graph_execution_state_id"]
+        ):
+            self.__queue_item = None
             self._poll_now()
         elif event_name == "batch_enqueued":
             self._poll_now()
+        elif event_name == "queue_cleared":
+            self.__queue_item = None
+            self._poll_now()
 
     def resume(self) -> SessionProcessorStatus:
-        if not self._resume_event.is_set():
-            self._resume_event.set()
+        if not self.__resume_event.is_set():
+            self.__resume_event.set()
         return self.get_status()
 
     def pause(self) -> SessionProcessorStatus:
-        if self._resume_event.is_set():
-            self._resume_event.clear()
+        if self.__resume_event.is_set():
+            self.__resume_event.clear()
         return self.get_status()
 
     def get_status(self) -> SessionProcessorStatus:
         return SessionProcessorStatus(
-            is_started=self._resume_event.is_set(),
-            is_processing=self._queue_item is not None,
+            is_started=self.__resume_event.is_set(),
+            is_processing=self.__queue_item is not None,
         )
 
-    def _process(
+    def __process(
         self,
         stop_event: ThreadEvent,
         poll_now_event: ThreadEvent,
         resume_event: ThreadEvent,
-        cancel_event: ThreadEvent,
     ):
-        # Outermost processor try block; any unhandled exception is a fatal processor error
         try:
-            self._thread_semaphore.acquire()
             stop_event.clear()
             resume_event.set()
-            cancel_event.clear()
-
+            self.__threadLimit.acquire()
+            queue_item: Optional[SessionQueueItem] = None
             while not stop_event.is_set():
                 poll_now_event.clear()
-                # Middle processor try block; any unhandled exception is a non-fatal processor error
                 try:
-                    # Get the next session to process
-                    self._queue_item = self._invoker.services.session_queue.dequeue()
-                    if self._queue_item is not None and resume_event.is_set():
-                        self._invoker.services.logger.debug(f"Executing queue item {self._queue_item.item_id}")
-                        cancel_event.clear()
+                    # do not dequeue if there is already a session running
+                    if self.__queue_item is None and resume_event.is_set():
+                        queue_item = self.__invoker.services.session_queue.dequeue()
 
-                        # If profiling is enabled, start the profiler
-                        if self._profiler is not None:
-                            self._profiler.start(profile_id=self._queue_item.session_id)
-
-                        # Prepare invocations and take the first
-                        self._invocation = self._queue_item.session.next()
-
-                        # Loop over invocations until the session is complete or canceled
-                        while self._invocation is not None and not cancel_event.is_set():
-                            # get the source node id to provide to clients (the prepared node id is not as useful)
-                            source_invocation_id = self._queue_item.session.prepared_source_mapping[self._invocation.id]
-
-                            # Send starting event
-                            self._invoker.services.events.emit_invocation_started(
-                                queue_batch_id=self._queue_item.batch_id,
-                                queue_item_id=self._queue_item.item_id,
-                                queue_id=self._queue_item.queue_id,
-                                graph_execution_state_id=self._queue_item.session_id,
-                                node=self._invocation.model_dump(),
-                                source_node_id=source_invocation_id,
+                        if queue_item is not None:
+                            self.__invoker.services.logger.debug(f"Executing queue item {queue_item.item_id}")
+                            self.__queue_item = queue_item
+                            self.__invoker.services.graph_execution_manager.set(queue_item.session)
+                            self.__invoker.invoke(
+                                session_queue_batch_id=queue_item.batch_id,
+                                session_queue_id=queue_item.queue_id,
+                                session_queue_item_id=queue_item.item_id,
+                                graph_execution_state=queue_item.session,
+                                workflow=queue_item.workflow,
+                                invoke_all=True,
                             )
+                            queue_item = None
 
-                            # Innermost processor try block; any unhandled exception is an invocation error & will fail the graph
-                            try:
-                                with self._invoker.services.performance_statistics.collect_stats(
-                                    self._invocation, self._queue_item.session.id
-                                ):
-                                    # Build invocation context (the node-facing API)
-                                    data = InvocationContextData(
-                                        invocation=self._invocation,
-                                        source_invocation_id=source_invocation_id,
-                                        queue_item=self._queue_item,
-                                    )
-                                    context = build_invocation_context(
-                                        data=data,
-                                        services=self._invoker.services,
-                                        cancel_event=self._cancel_event,
-                                    )
-
-                                    # Invoke the node
-                                    outputs = self._invocation.invoke_internal(
-                                        context=context, services=self._invoker.services
-                                    )
-
-                                    # Save outputs and history
-                                    self._queue_item.session.complete(self._invocation.id, outputs)
-
-                                    # Send complete event
-                                    self._invoker.services.events.emit_invocation_complete(
-                                        queue_batch_id=self._queue_item.batch_id,
-                                        queue_item_id=self._queue_item.item_id,
-                                        queue_id=self._queue_item.queue_id,
-                                        graph_execution_state_id=self._queue_item.session.id,
-                                        node=self._invocation.model_dump(),
-                                        source_node_id=source_invocation_id,
-                                        result=outputs.model_dump(),
-                                    )
-
-                            except KeyboardInterrupt:
-                                # TODO(MM2): Create an event for this
-                                pass
-
-                            except CanceledException:
-                                # When the user cancels the graph, we first set the cancel event. The event is checked
-                                # between invocations, in this loop. Some invocations are long-running, and we need to
-                                # be able to cancel them mid-execution.
-                                #
-                                # For example, denoising is a long-running invocation with many steps. A step callback
-                                # is executed after each step. This step callback checks if the canceled event is set,
-                                # then raises a CanceledException to stop execution immediately.
-                                #
-                                # When we get a CanceledException, we don't need to do anything - just pass and let the
-                                # loop go to its next iteration, and the cancel event will be handled correctly.
-                                pass
-
-                            except Exception as e:
-                                error = traceback.format_exc()
-
-                                # Save error
-                                self._queue_item.session.set_node_error(self._invocation.id, error)
-                                self._invoker.services.logger.error(
-                                    f"Error while invoking session {self._queue_item.session_id}, invocation {self._invocation.id} ({self._invocation.get_type()}):\n{e}"
-                                )
-                                self._invoker.services.logger.error(error)
-
-                                # Send error event
-                                self._invoker.services.events.emit_invocation_error(
-                                    queue_batch_id=self._queue_item.session_id,
-                                    queue_item_id=self._queue_item.item_id,
-                                    queue_id=self._queue_item.queue_id,
-                                    graph_execution_state_id=self._queue_item.session.id,
-                                    node=self._invocation.model_dump(),
-                                    source_node_id=source_invocation_id,
-                                    error_type=e.__class__.__name__,
-                                    error=error,
-                                )
-                                pass
-
-                            # The session is complete if the all invocations are complete or there was an error
-                            if self._queue_item.session.is_complete() or cancel_event.is_set():
-                                # Send complete event
-                                self._invoker.services.events.emit_graph_execution_complete(
-                                    queue_batch_id=self._queue_item.batch_id,
-                                    queue_item_id=self._queue_item.item_id,
-                                    queue_id=self._queue_item.queue_id,
-                                    graph_execution_state_id=self._queue_item.session.id,
-                                )
-                                # If we are profiling, stop the profiler and dump the profile & stats
-                                if self._profiler:
-                                    profile_path = self._profiler.stop()
-                                    stats_path = profile_path.with_suffix(".json")
-                                    self._invoker.services.performance_statistics.dump_stats(
-                                        graph_execution_state_id=self._queue_item.session.id, output_path=stats_path
-                                    )
-                                # We'll get a GESStatsNotFoundError if we try to log stats for an untracked graph, but in the processor
-                                # we don't care about that - suppress the error.
-                                with suppress(GESStatsNotFoundError):
-                                    self._invoker.services.performance_statistics.log_stats(self._queue_item.session.id)
-                                    self._invoker.services.performance_statistics.reset_stats()
-
-                                # Set the invocation to None to prepare for the next session
-                                self._invocation = None
-                            else:
-                                # Prepare the next invocation
-                                self._invocation = self._queue_item.session.next()
-
-                        # The session is complete, immediately poll for next session
-                        self._queue_item = None
-                        poll_now_event.set()
-                    else:
-                        # The queue was empty, wait for next polling interval or event to try again
-                        self._invoker.services.logger.debug("Waiting for next polling interval or event")
-                        poll_now_event.wait(self._polling_interval)
+                    if queue_item is None:
+                        self.__invoker.services.logger.debug("Waiting for next polling interval or event")
+                        poll_now_event.wait(POLLING_INTERVAL)
                         continue
-                except Exception:
-                    # Non-fatal error in processor
-                    self._invoker.services.logger.error(
-                        f"Non-fatal error in session processor:\n{traceback.format_exc()}"
-                    )
-                    # Cancel the queue item
-                    if self._queue_item is not None:
-                        self._invoker.services.session_queue.cancel_queue_item(
-                            self._queue_item.item_id, error=traceback.format_exc()
+                except Exception as e:
+                    self.__invoker.services.logger.error(f"Error in session processor: {e}")
+                    if queue_item is not None:
+                        self.__invoker.services.session_queue.cancel_queue_item(
+                            queue_item.item_id, error=traceback.format_exc()
                         )
-                    # Reset the invocation to None to prepare for the next session
-                    self._invocation = None
-                    # Immediately poll for next queue item
-                    poll_now_event.wait(self._polling_interval)
+                    poll_now_event.wait(POLLING_INTERVAL)
                     continue
-        except Exception:
-            # Fatal error in processor, log and pass - we're done here
-            self._invoker.services.logger.error(f"Fatal Error in session processor:\n{traceback.format_exc()}")
+        except Exception as e:
+            self.__invoker.services.logger.error(f"Fatal Error in session processor: {e}")
             pass
         finally:
             stop_event.clear()
             poll_now_event.clear()
-            self._queue_item = None
-            self._thread_semaphore.release()
+            self.__queue_item = None
+            self.__threadLimit.release()

invokeai/app/services/session_queue/session_queue_sqlite.py

@@ -60,7 +60,7 @@ class SqliteSessionQueue(SessionQueueBase):
         # This was a match statement, but match is not supported on python 3.9
         if event_name == "graph_execution_state_complete":
             await self._handle_complete_event(event)
-        elif event_name == "invocation_error":
+        elif event_name in ["invocation_error", "session_retrieval_error", "invocation_retrieval_error"]:
             await self._handle_error_event(event)
         elif event_name == "session_canceled":
             await self._handle_cancel_event(event)
@@ -429,6 +429,7 @@ class SqliteSessionQueue(SessionQueueBase):
         if queue_item.status not in ["canceled", "failed", "completed"]:
             status = "failed" if error is not None else "canceled"
             queue_item = self._set_queue_item_status(item_id=item_id, status=status, error=error)  # type: ignore [arg-type] # mypy seems to not narrow the Literals here
+            self.__invoker.services.queue.cancel(queue_item.session_id)
             self.__invoker.services.events.emit_session_canceled(
                 queue_item_id=queue_item.item_id,
                 queue_id=queue_item.queue_id,
@@ -470,6 +471,7 @@ class SqliteSessionQueue(SessionQueueBase):
             )
             self.__conn.commit()
             if current_queue_item is not None and current_queue_item.batch_id in batch_ids:
+                self.__invoker.services.queue.cancel(current_queue_item.session_id)
                 self.__invoker.services.events.emit_session_canceled(
                     queue_item_id=current_queue_item.item_id,
                     queue_id=current_queue_item.queue_id,
@@ -521,6 +523,7 @@ class SqliteSessionQueue(SessionQueueBase):
             )
             self.__conn.commit()
             if current_queue_item is not None and current_queue_item.queue_id == queue_id:
+                self.__invoker.services.queue.cancel(current_queue_item.session_id)
                 self.__invoker.services.events.emit_session_canceled(
                     queue_item_id=current_queue_item.item_id,
                     queue_id=current_queue_item.queue_id,

invokeai/app/services/shared/default_graphs.py

@@ -0,0 +1,92 @@
+from invokeai.app.services.item_storage.item_storage_base import ItemStorageABC
+
+from ...invocations.compel import CompelInvocation
+from ...invocations.image import ImageNSFWBlurInvocation
+from ...invocations.latent import DenoiseLatentsInvocation, LatentsToImageInvocation
+from ...invocations.noise import NoiseInvocation
+from ...invocations.primitives import IntegerInvocation
+from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph
+
+default_text_to_image_graph_id = "539b2af5-2b4d-4d8c-8071-e54a3255fc74"
+
+
+def create_text_to_image() -> LibraryGraph:
+    graph = Graph(
+        nodes={
+            "width": IntegerInvocation(id="width", value=512),
+            "height": IntegerInvocation(id="height", value=512),
+            "seed": IntegerInvocation(id="seed", value=-1),
+            "3": NoiseInvocation(id="3"),
+            "4": CompelInvocation(id="4"),
+            "5": CompelInvocation(id="5"),
+            "6": DenoiseLatentsInvocation(id="6"),
+            "7": LatentsToImageInvocation(id="7"),
+            "8": ImageNSFWBlurInvocation(id="8"),
+        },
+        edges=[
+            Edge(
+                source=EdgeConnection(node_id="width", field="value"),
+                destination=EdgeConnection(node_id="3", field="width"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="height", field="value"),
+                destination=EdgeConnection(node_id="3", field="height"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="seed", field="value"),
+                destination=EdgeConnection(node_id="3", field="seed"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="3", field="noise"),
+                destination=EdgeConnection(node_id="6", field="noise"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="6", field="latents"),
+                destination=EdgeConnection(node_id="7", field="latents"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="4", field="conditioning"),
+                destination=EdgeConnection(node_id="6", field="positive_conditioning"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="5", field="conditioning"),
+                destination=EdgeConnection(node_id="6", field="negative_conditioning"),
+            ),
+            Edge(
+                source=EdgeConnection(node_id="7", field="image"),
+                destination=EdgeConnection(node_id="8", field="image"),
+            ),
+        ],
+    )
+    return LibraryGraph(
+        id=default_text_to_image_graph_id,
+        name="t2i",
+        description="Converts text to an image",
+        graph=graph,
+        exposed_inputs=[
+            ExposedNodeInput(node_path="4", field="prompt", alias="positive_prompt"),
+            ExposedNodeInput(node_path="5", field="prompt", alias="negative_prompt"),
+            ExposedNodeInput(node_path="width", field="value", alias="width"),
+            ExposedNodeInput(node_path="height", field="value", alias="height"),
+            ExposedNodeInput(node_path="seed", field="value", alias="seed"),
+        ],
+        exposed_outputs=[ExposedNodeOutput(node_path="8", field="image", alias="image")],
+    )
+
+
+def create_system_graphs(graph_library: ItemStorageABC[LibraryGraph]) -> list[LibraryGraph]:
+    """Creates the default system graphs, or adds new versions if the old ones don't match"""
+
+    # TODO: Uncomment this when we are ready to fix this up to prevent breaking changes
+    graphs: list[LibraryGraph] = []
+
+    text_to_image = graph_library.get(default_text_to_image_graph_id)
+
+    # TODO: Check if the graph is the same as the default one, and if not, update it
+    # if text_to_image is None:
+    text_to_image = create_text_to_image()
+    graph_library.set(text_to_image)
+
+    graphs.append(text_to_image)
+
+    return graphs

invokeai/app/services/shared/graph.py

@@ -5,14 +5,8 @@ import itertools
 from typing import Annotated, Any, Optional, TypeVar, Union, get_args, get_origin, get_type_hints
 
 import networkx as nx
-from pydantic import (
-    BaseModel,
-    GetJsonSchemaHandler,
-    field_validator,
-)
+from pydantic import BaseModel, ConfigDict, field_validator, model_validator
 from pydantic.fields import Field
-from pydantic.json_schema import JsonSchemaValue
-from pydantic_core import CoreSchema
 
 # Importing * is bad karma but needed here for node detection
 from invokeai.app.invocations import *  # noqa: F401 F403
@@ -182,6 +176,10 @@ class NodeIdMismatchError(ValueError):
     pass
 
 
+class InvalidSubGraphError(ValueError):
+    pass
+
+
 class CyclicalGraphError(ValueError):
     pass
 
@@ -190,6 +188,25 @@ class UnknownGraphValidationError(ValueError):
     pass
 
 
+# TODO: Create and use an Empty output?
+@invocation_output("graph_output")
+class GraphInvocationOutput(BaseInvocationOutput):
+    pass
+
+
+# TODO: Fill this out and move to invocations
+@invocation("graph", version="1.0.0")
+class GraphInvocation(BaseInvocation):
+    """Execute a graph"""
+
+    # TODO: figure out how to create a default here
+    graph: "Graph" = InputField(description="The graph to run", default=None)
+
+    def invoke(self, context: InvocationContext) -> GraphInvocationOutput:
+        """Invoke with provided services and return outputs."""
+        return GraphInvocationOutput()
+
+
 @invocation_output("iterate_output")
 class IterateInvocationOutput(BaseInvocationOutput):
     """Used to connect iteration outputs. Will be expanded to a specific output."""
@@ -243,73 +260,21 @@ class CollectInvocation(BaseInvocation):
         return CollectInvocationOutput(collection=copy.copy(self.collection))
 
 
+InvocationsUnion: Any = BaseInvocation.get_invocations_union()
+InvocationOutputsUnion: Any = BaseInvocationOutput.get_outputs_union()
+
+
 class Graph(BaseModel):
     id: str = Field(description="The id of this graph", default_factory=uuid_string)
     # TODO: use a list (and never use dict in a BaseModel) because pydantic/fastapi hates me
-    nodes: dict[str, BaseInvocation] = Field(description="The nodes in this graph", default_factory=dict)
+    nodes: dict[str, Annotated[InvocationsUnion, Field(discriminator="type")]] = Field(
+        description="The nodes in this graph", default_factory=dict
+    )
     edges: list[Edge] = Field(
         description="The connections between nodes and their fields in this graph",
         default_factory=list,
     )
 
-    @field_validator("nodes", mode="plain")
-    @classmethod
-    def validate_nodes(cls, v: dict[str, Any]):
-        """Validates the nodes in the graph by retrieving a union of all node types and validating each node."""
-
-        # Invocations register themselves as their python modules are executed. The union of all invocations is
-        # constructed at runtime. We use pydantic to validate `Graph.nodes` using that union.
-        #
-        # It's possible that when `graph.py` is executed, not all invocation-containing modules will have executed. If
-        # we construct the invocation union as `graph.py` is executed, we may miss some invocations. Those missing
-        # invocations will cause a graph to fail if they are used.
-        #
-        # We can get around this by validating the nodes in the graph using a "plain" validator, which overrides the
-        # pydantic validation entirely. This allows us to validate the nodes using the union of invocations at runtime.
-        #
-        # This same pattern is used in `GraphExecutionState`.
-
-        nodes: dict[str, BaseInvocation] = {}
-        typeadapter = BaseInvocation.get_typeadapter()
-        for node_id, node in v.items():
-            nodes[node_id] = typeadapter.validate_python(node)
-        return nodes
-
-    @classmethod
-    def __get_pydantic_json_schema__(cls, core_schema: CoreSchema, handler: GetJsonSchemaHandler) -> JsonSchemaValue:
-        # We use a "plain" validator to validate the nodes in the graph. Pydantic is unable to create a JSON Schema for
-        # fields that use "plain" validators, so we have to hack around this. Also, we need to add all invocations to
-        # the generated schema as options for the `nodes` field.
-        #
-        # The workaround is to create a new BaseModel that has the same fields as `Graph` but without the validator and
-        # with the invocation union as the type for the `nodes` field. Pydantic then generates the JSON Schema as
-        # expected.
-        #
-        # You might be tempted to do something like this:
-        #
-        # ```py
-        # cloned_model = create_model(cls.__name__, __base__=cls, nodes=...)
-        # delattr(cloned_model, "validate_nodes")
-        # cloned_model.model_rebuild(force=True)
-        # json_schema = handler(cloned_model.__pydantic_core_schema__)
-        # ```
-        #
-        # Unfortunately, this does not work. Calling `handler` here results in infinite recursion as pydantic attempts
-        # to build the JSON Schema for the cloned model. Instead, we have to manually clone the model.
-        #
-        # This same pattern is used in `GraphExecutionState`.
-
-        class Graph(BaseModel):
-            id: Optional[str] = Field(default=None, description="The id of this graph")
-            nodes: dict[
-                str, Annotated[Union[tuple(BaseInvocation._invocation_classes)], Field(discriminator="type")]
-            ] = Field(description="The nodes in this graph")
-            edges: list[Edge] = Field(description="The connections between nodes and their fields in this graph")
-
-        json_schema = handler(Graph.__pydantic_core_schema__)
-        json_schema = handler.resolve_ref_schema(json_schema)
-        return json_schema
-
     def add_node(self, node: BaseInvocation) -> None:
         """Adds a node to a graph
 
@@ -321,21 +286,41 @@ class Graph(BaseModel):
 
         self.nodes[node.id] = node
 
-    def delete_node(self, node_id: str) -> None:
+    def _get_graph_and_node(self, node_path: str) -> tuple["Graph", str]:
+        """Returns the graph and node id for a node path."""
+        # Materialized graphs may have nodes at the top level
+        if node_path in self.nodes:
+            return (self, node_path)
+
+        node_id = node_path if "." not in node_path else node_path[: node_path.index(".")]
+        if node_id not in self.nodes:
+            raise NodeNotFoundError(f"Node {node_path} not found in graph")
+
+        node = self.nodes[node_id]
+
+        if not isinstance(node, GraphInvocation):
+            # There's more node path left but this isn't a graph - failure
+            raise NodeNotFoundError("Node path terminated early at a non-graph node")
+
+        return node.graph._get_graph_and_node(node_path[node_path.index(".") + 1 :])
+
+    def delete_node(self, node_path: str) -> None:
         """Deletes a node from a graph"""
 
         try:
+            graph, node_id = self._get_graph_and_node(node_path)
+
             # Delete edges for this node
-            input_edges = self._get_input_edges(node_id)
-            output_edges = self._get_output_edges(node_id)
+            input_edges = self._get_input_edges_and_graphs(node_path)
+            output_edges = self._get_output_edges_and_graphs(node_path)
 
-            for edge in input_edges:
-                self.delete_edge(edge)
+            for edge_graph, _, edge in input_edges:
+                edge_graph.delete_edge(edge)
 
-            for edge in output_edges:
-                self.delete_edge(edge)
+            for edge_graph, _, edge in output_edges:
+                edge_graph.delete_edge(edge)
 
-            del self.nodes[node_id]
+            del graph.nodes[node_id]
 
         except NodeNotFoundError:
             pass  # Ignore, not doesn't exist (should this throw?)
@@ -385,6 +370,13 @@ class Graph(BaseModel):
             if k != v.id:
                 raise NodeIdMismatchError(f"Node ids must match, got {k} and {v.id}")
 
+        # Validate all subgraphs
+        for gn in (n for n in self.nodes.values() if isinstance(n, GraphInvocation)):
+            try:
+                gn.graph.validate_self()
+            except Exception as e:
+                raise InvalidSubGraphError(f"Subgraph {gn.id} is invalid") from e
+
         # Validate that all edges match nodes and fields in the graph
         for edge in self.edges:
             source_node = self.nodes.get(edge.source.node_id, None)
@@ -446,6 +438,7 @@ class Graph(BaseModel):
         except (
             DuplicateNodeIdError,
             NodeIdMismatchError,
+            InvalidSubGraphError,
             NodeNotFoundError,
             NodeFieldNotFoundError,
             CyclicalGraphError,
@@ -466,7 +459,7 @@ class Graph(BaseModel):
     def _validate_edge(self, edge: Edge):
         """Validates that a new edge doesn't create a cycle in the graph"""
 
-        # Validate that the nodes exist
+        # Validate that the nodes exist (edges may contain node paths, so we can't just check for nodes directly)
         try:
             from_node = self.get_node(edge.source.node_id)
             to_node = self.get_node(edge.destination.node_id)
@@ -533,90 +526,171 @@ class Graph(BaseModel):
                     f"Collector input type does not match collector output type: {edge.source.node_id}.{edge.source.field} to {edge.destination.node_id}.{edge.destination.field}"
                 )
 
-    def has_node(self, node_id: str) -> bool:
+    def has_node(self, node_path: str) -> bool:
         """Determines whether or not a node exists in the graph."""
         try:
-            _ = self.get_node(node_id)
-            return True
+            n = self.get_node(node_path)
+            if n is not None:
+                return True
+            else:
+                return False
         except NodeNotFoundError:
             return False
 
-    def get_node(self, node_id: str) -> BaseInvocation:
-        """Gets a node from the graph."""
-        try:
-            return self.nodes[node_id]
-        except KeyError as e:
-            raise NodeNotFoundError(f"Node {node_id} not found in graph") from e
+    def get_node(self, node_path: str) -> BaseInvocation:
+        """Gets a node from the graph using a node path."""
+        # Materialized graphs may have nodes at the top level
+        graph, node_id = self._get_graph_and_node(node_path)
+        return graph.nodes[node_id]
 
-    def update_node(self, node_id: str, new_node: BaseInvocation) -> None:
+    def _get_node_path(self, node_id: str, prefix: Optional[str] = None) -> str:
+        return node_id if prefix is None or prefix == "" else f"{prefix}.{node_id}"
+
+    def update_node(self, node_path: str, new_node: BaseInvocation) -> None:
         """Updates a node in the graph."""
-        node = self.nodes[node_id]
+        graph, node_id = self._get_graph_and_node(node_path)
+        node = graph.nodes[node_id]
 
         # Ensure the node type matches the new node
         if type(node) is not type(new_node):
-            raise TypeError(f"Node {node_id} is type {type(node)} but new node is type {type(new_node)}")
+            raise TypeError(f"Node {node_path} is type {type(node)} but new node is type {type(new_node)}")
 
         # Ensure the new id is either the same or is not in the graph
-        if new_node.id != node.id and self.has_node(new_node.id):
-            raise NodeAlreadyInGraphError(f"Node with id {new_node.id} already exists in graph")
+        prefix = None if "." not in node_path else node_path[: node_path.rindex(".")]
+        new_path = self._get_node_path(new_node.id, prefix=prefix)
+        if new_node.id != node.id and self.has_node(new_path):
+            raise NodeAlreadyInGraphError("Node with id {new_node.id} already exists in graph")
 
         # Set the new node in the graph
-        self.nodes[new_node.id] = new_node
+        graph.nodes[new_node.id] = new_node
         if new_node.id != node.id:
-            input_edges = self._get_input_edges(node_id)
-            output_edges = self._get_output_edges(node_id)
+            input_edges = self._get_input_edges_and_graphs(node_path)
+            output_edges = self._get_output_edges_and_graphs(node_path)
 
             # Delete node and all edges
-            self.delete_node(node_id)
+            graph.delete_node(node_path)
 
             # Create new edges for each input and output
-            for edge in input_edges:
-                self.add_edge(
+            for graph, _, edge in input_edges:
+                # Remove the graph prefix from the node path
+                new_graph_node_path = (
+                    new_node.id
+                    if "." not in edge.destination.node_id
+                    else f'{edge.destination.node_id[edge.destination.node_id.rindex("."):]}.{new_node.id}'
+                )
+                graph.add_edge(
                     Edge(
                         source=edge.source,
-                        destination=EdgeConnection(node_id=new_node.id, field=edge.destination.field),
+                        destination=EdgeConnection(node_id=new_graph_node_path, field=edge.destination.field),
                     )
                 )
 
-            for edge in output_edges:
-                self.add_edge(
+            for graph, _, edge in output_edges:
+                # Remove the graph prefix from the node path
+                new_graph_node_path = (
+                    new_node.id
+                    if "." not in edge.source.node_id
+                    else f'{edge.source.node_id[edge.source.node_id.rindex("."):]}.{new_node.id}'
+                )
+                graph.add_edge(
                     Edge(
-                        source=EdgeConnection(node_id=new_node.id, field=edge.source.field),
+                        source=EdgeConnection(node_id=new_graph_node_path, field=edge.source.field),
                         destination=edge.destination,
                     )
                 )
 
-    def _get_input_edges(self, node_id: str, field: Optional[str] = None) -> list[Edge]:
-        """Gets all input edges for a node. If field is provided, only edges to that field are returned."""
+    def _get_input_edges(self, node_path: str, field: Optional[str] = None) -> list[Edge]:
+        """Gets all input edges for a node"""
+        edges = self._get_input_edges_and_graphs(node_path)
 
-        edges = [e for e in self.edges if e.destination.node_id == node_id]
+        # Filter to edges that match the field
+        filtered_edges = (e for e in edges if field is None or e[2].destination.field == field)
 
-        if field is None:
-            return edges
+        # Create full node paths for each edge
+        return [
+            Edge(
+                source=EdgeConnection(
+                    node_id=self._get_node_path(e.source.node_id, prefix=prefix),
+                    field=e.source.field,
+                ),
+                destination=EdgeConnection(
+                    node_id=self._get_node_path(e.destination.node_id, prefix=prefix),
+                    field=e.destination.field,
+                ),
+            )
+            for _, prefix, e in filtered_edges
+        ]
 
-        filtered_edges = [e for e in edges if e.destination.field == field]
+    def _get_input_edges_and_graphs(
+        self, node_path: str, prefix: Optional[str] = None
+    ) -> list[tuple["Graph", Union[str, None], Edge]]:
+        """Gets all input edges for a node along with the graph they are in and the graph's path"""
+        edges = []
 
-        return filtered_edges
+        # Return any input edges that appear in this graph
+        edges.extend([(self, prefix, e) for e in self.edges if e.destination.node_id == node_path])
 
-    def _get_output_edges(self, node_id: str, field: Optional[str] = None) -> list[Edge]:
-        """Gets all output edges for a node. If field is provided, only edges from that field are returned."""
-        edges = [e for e in self.edges if e.source.node_id == node_id]
+        node_id = node_path if "." not in node_path else node_path[: node_path.index(".")]
+        node = self.nodes[node_id]
 
-        if field is None:
-            return edges
+        if isinstance(node, GraphInvocation):
+            graph = node.graph
+            graph_path = node.id if prefix is None or prefix == "" else self._get_node_path(node.id, prefix=prefix)
+            graph_edges = graph._get_input_edges_and_graphs(node_path[(len(node_id) + 1) :], prefix=graph_path)
+            edges.extend(graph_edges)
 
-        filtered_edges = [e for e in edges if e.source.field == field]
+        return edges
 
-        return filtered_edges
+    def _get_output_edges(self, node_path: str, field: str) -> list[Edge]:
+        """Gets all output edges for a node"""
+        edges = self._get_output_edges_and_graphs(node_path)
+
+        # Filter to edges that match the field
+        filtered_edges = (e for e in edges if e[2].source.field == field)
+
+        # Create full node paths for each edge
+        return [
+            Edge(
+                source=EdgeConnection(
+                    node_id=self._get_node_path(e.source.node_id, prefix=prefix),
+                    field=e.source.field,
+                ),
+                destination=EdgeConnection(
+                    node_id=self._get_node_path(e.destination.node_id, prefix=prefix),
+                    field=e.destination.field,
+                ),
+            )
+            for _, prefix, e in filtered_edges
+        ]
+
+    def _get_output_edges_and_graphs(
+        self, node_path: str, prefix: Optional[str] = None
+    ) -> list[tuple["Graph", Union[str, None], Edge]]:
+        """Gets all output edges for a node along with the graph they are in and the graph's path"""
+        edges = []
+
+        # Return any input edges that appear in this graph
+        edges.extend([(self, prefix, e) for e in self.edges if e.source.node_id == node_path])
+
+        node_id = node_path if "." not in node_path else node_path[: node_path.index(".")]
+        node = self.nodes[node_id]
+
+        if isinstance(node, GraphInvocation):
+            graph = node.graph
+            graph_path = node.id if prefix is None or prefix == "" else self._get_node_path(node.id, prefix=prefix)
+            graph_edges = graph._get_output_edges_and_graphs(node_path[(len(node_id) + 1) :], prefix=graph_path)
+            edges.extend(graph_edges)
+
+        return edges
 
     def _is_iterator_connection_valid(
         self,
-        node_id: str,
+        node_path: str,
         new_input: Optional[EdgeConnection] = None,
         new_output: Optional[EdgeConnection] = None,
     ) -> bool:
-        inputs = [e.source for e in self._get_input_edges(node_id, "collection")]
-        outputs = [e.destination for e in self._get_output_edges(node_id, "item")]
+        inputs = [e.source for e in self._get_input_edges(node_path, "collection")]
+        outputs = [e.destination for e in self._get_output_edges(node_path, "item")]
 
         if new_input is not None:
             inputs.append(new_input)
@@ -644,12 +718,12 @@ class Graph(BaseModel):
 
     def _is_collector_connection_valid(
         self,
-        node_id: str,
+        node_path: str,
         new_input: Optional[EdgeConnection] = None,
         new_output: Optional[EdgeConnection] = None,
     ) -> bool:
-        inputs = [e.source for e in self._get_input_edges(node_id, "item")]
-        outputs = [e.destination for e in self._get_output_edges(node_id, "collection")]
+        inputs = [e.source for e in self._get_input_edges(node_path, "item")]
+        outputs = [e.destination for e in self._get_output_edges(node_path, "collection")]
 
         if new_input is not None:
             inputs.append(new_input)
@@ -705,17 +779,27 @@ class Graph(BaseModel):
         g.add_edges_from({(e.source.node_id, e.destination.node_id) for e in self.edges})
         return g
 
-    def nx_graph_flat(self, nx_graph: Optional[nx.DiGraph] = None) -> nx.DiGraph:
+    def nx_graph_flat(self, nx_graph: Optional[nx.DiGraph] = None, prefix: Optional[str] = None) -> nx.DiGraph:
         """Returns a flattened NetworkX DiGraph, including all subgraphs (but not with iterations expanded)"""
         g = nx_graph or nx.DiGraph()
 
         # Add all nodes from this graph except graph/iteration nodes
-        g.add_nodes_from([n.id for n in self.nodes.values() if not isinstance(n, IterateInvocation)])
+        g.add_nodes_from(
+            [
+                self._get_node_path(n.id, prefix)
+                for n in self.nodes.values()
+                if not isinstance(n, GraphInvocation) and not isinstance(n, IterateInvocation)
+            ]
+        )
+
+        # Expand graph nodes
+        for sgn in (gn for gn in self.nodes.values() if isinstance(gn, GraphInvocation)):
+            g = sgn.graph.nx_graph_flat(g, self._get_node_path(sgn.id, prefix))
 
         # TODO: figure out if iteration nodes need to be expanded
 
         unique_edges = {(e.source.node_id, e.destination.node_id) for e in self.edges}
-        g.add_edges_from([(e[0], e[1]) for e in unique_edges])
+        g.add_edges_from([(self._get_node_path(e[0], prefix), self._get_node_path(e[1], prefix)) for e in unique_edges])
         return g
 
 
@@ -740,7 +824,9 @@ class GraphExecutionState(BaseModel):
     )
 
     # The results of executed nodes
-    results: dict[str, BaseInvocationOutput] = Field(description="The results of node executions", default_factory=dict)
+    results: dict[str, Annotated[InvocationOutputsUnion, Field(discriminator="type")]] = Field(
+        description="The results of node executions", default_factory=dict
+    )
 
     # Errors raised when executing nodes
     errors: dict[str, str] = Field(description="Errors raised when executing nodes", default_factory=dict)
@@ -757,51 +843,27 @@ class GraphExecutionState(BaseModel):
         default_factory=dict,
     )
 
-    @field_validator("results", mode="plain")
-    @classmethod
-    def validate_results(cls, v: dict[str, BaseInvocationOutput]):
-        """Validates the results in the GES by retrieving a union of all output types and validating each result."""
-
-        # See the comment in `Graph.validate_nodes` for an explanation of this logic.
-        results: dict[str, BaseInvocationOutput] = {}
-        typeadapter = BaseInvocationOutput.get_typeadapter()
-        for result_id, result in v.items():
-            results[result_id] = typeadapter.validate_python(result)
-        return results
-
     @field_validator("graph")
     def graph_is_valid(cls, v: Graph):
         """Validates that the graph is valid"""
         v.validate_self()
         return v
 
-    @classmethod
-    def __get_pydantic_json_schema__(cls, core_schema: CoreSchema, handler: GetJsonSchemaHandler) -> JsonSchemaValue:
-        # See the comment in `Graph.__get_pydantic_json_schema__` for an explanation of this logic.
-        class GraphExecutionState(BaseModel):
-            """Tracks the state of a graph execution"""
-
-            id: str = Field(description="The id of the execution state")
-            graph: Graph = Field(description="The graph being executed")
-            execution_graph: Graph = Field(description="The expanded graph of activated and executed nodes")
-            executed: set[str] = Field(description="The set of node ids that have been executed")
-            executed_history: list[str] = Field(
-                description="The list of node ids that have been executed, in order of execution"
-            )
-            results: dict[
-                str, Annotated[Union[tuple(BaseInvocationOutput._output_classes)], Field(discriminator="type")]
-            ] = Field(description="The results of node executions")
-            errors: dict[str, str] = Field(description="Errors raised when executing nodes")
-            prepared_source_mapping: dict[str, str] = Field(
-                description="The map of prepared nodes to original graph nodes"
-            )
-            source_prepared_mapping: dict[str, set[str]] = Field(
-                description="The map of original graph nodes to prepared nodes"
-            )
-
-        json_schema = handler(GraphExecutionState.__pydantic_core_schema__)
-        json_schema = handler.resolve_ref_schema(json_schema)
-        return json_schema
+    model_config = ConfigDict(
+        json_schema_extra={
+            "required": [
+                "id",
+                "graph",
+                "execution_graph",
+                "executed",
+                "executed_history",
+                "results",
+                "errors",
+                "prepared_source_mapping",
+                "source_prepared_mapping",
+            ]
+        }
+    )
 
     def next(self) -> Optional[BaseInvocation]:
         """Gets the next node ready to execute."""
@@ -857,17 +919,17 @@ class GraphExecutionState(BaseModel):
         """Returns true if the graph has any errors"""
         return len(self.errors) > 0
 
-    def _create_execution_node(self, node_id: str, iteration_node_map: list[tuple[str, str]]) -> list[str]:
+    def _create_execution_node(self, node_path: str, iteration_node_map: list[tuple[str, str]]) -> list[str]:
         """Prepares an iteration node and connects all edges, returning the new node id"""
 
-        node = self.graph.get_node(node_id)
+        node = self.graph.get_node(node_path)
 
         self_iteration_count = -1
 
         # If this is an iterator node, we must create a copy for each iteration
         if isinstance(node, IterateInvocation):
             # Get input collection edge (should error if there are no inputs)
-            input_collection_edge = next(iter(self.graph._get_input_edges(node_id, "collection")))
+            input_collection_edge = next(iter(self.graph._get_input_edges(node_path, "collection")))
             input_collection_prepared_node_id = next(
                 n[1] for n in iteration_node_map if n[0] == input_collection_edge.source.node_id
             )
@@ -881,7 +943,7 @@ class GraphExecutionState(BaseModel):
             return new_nodes
 
         # Get all input edges
-        input_edges = self.graph._get_input_edges(node_id)
+        input_edges = self.graph._get_input_edges(node_path)
 
         # Create new edges for this iteration
         # For collect nodes, this may contain multiple inputs to the same field
@@ -908,10 +970,10 @@ class GraphExecutionState(BaseModel):
 
             # Add to execution graph
             self.execution_graph.add_node(new_node)
-            self.prepared_source_mapping[new_node.id] = node_id
-            if node_id not in self.source_prepared_mapping:
-                self.source_prepared_mapping[node_id] = set()
-            self.source_prepared_mapping[node_id].add(new_node.id)
+            self.prepared_source_mapping[new_node.id] = node_path
+            if node_path not in self.source_prepared_mapping:
+                self.source_prepared_mapping[node_path] = set()
+            self.source_prepared_mapping[node_path].add(new_node.id)
 
             # Add new edges to execution graph
             for edge in new_edges:
@@ -1015,13 +1077,13 @@ class GraphExecutionState(BaseModel):
 
     def _get_iteration_node(
         self,
-        source_node_id: str,
+        source_node_path: str,
         graph: nx.DiGraph,
         execution_graph: nx.DiGraph,
         prepared_iterator_nodes: list[str],
     ) -> Optional[str]:
         """Gets the prepared version of the specified source node that matches every iteration specified"""
-        prepared_nodes = self.source_prepared_mapping[source_node_id]
+        prepared_nodes = self.source_prepared_mapping[source_node_path]
         if len(prepared_nodes) == 1:
             return next(iter(prepared_nodes))
 
@@ -1032,7 +1094,7 @@ class GraphExecutionState(BaseModel):
 
         # Filter to only iterator nodes that are a parent of the specified node, in tuple format (prepared, source)
         iterator_source_node_mapping = [(n, self.prepared_source_mapping[n]) for n in prepared_iterator_nodes]
-        parent_iterators = [itn for itn in iterator_source_node_mapping if nx.has_path(graph, itn[1], source_node_id)]
+        parent_iterators = [itn for itn in iterator_source_node_mapping if nx.has_path(graph, itn[1], source_node_path)]
 
         return next(
             (n for n in prepared_nodes if all(nx.has_path(execution_graph, pit[0], n) for pit in parent_iterators)),
@@ -1101,19 +1163,19 @@ class GraphExecutionState(BaseModel):
     def add_node(self, node: BaseInvocation) -> None:
         self.graph.add_node(node)
 
-    def update_node(self, node_id: str, new_node: BaseInvocation) -> None:
-        if not self._is_node_updatable(node_id):
+    def update_node(self, node_path: str, new_node: BaseInvocation) -> None:
+        if not self._is_node_updatable(node_path):
             raise NodeAlreadyExecutedError(
-                f"Node {node_id} has already been prepared or executed and cannot be updated"
+                f"Node {node_path} has already been prepared or executed and cannot be updated"
             )
-        self.graph.update_node(node_id, new_node)
+        self.graph.update_node(node_path, new_node)
 
-    def delete_node(self, node_id: str) -> None:
-        if not self._is_node_updatable(node_id):
+    def delete_node(self, node_path: str) -> None:
+        if not self._is_node_updatable(node_path):
             raise NodeAlreadyExecutedError(
-                f"Node {node_id} has already been prepared or executed and cannot be deleted"
+                f"Node {node_path} has already been prepared or executed and cannot be deleted"
             )
-        self.graph.delete_node(node_id)
+        self.graph.delete_node(node_path)
 
     def add_edge(self, edge: Edge) -> None:
         if not self._is_node_updatable(edge.destination.node_id):
@@ -1128,3 +1190,63 @@ class GraphExecutionState(BaseModel):
                 f"Destination node {edge.destination.node_id} has already been prepared or executed and cannot have a source edge deleted"
             )
         self.graph.delete_edge(edge)
+
+
+class ExposedNodeInput(BaseModel):
+    node_path: str = Field(description="The node path to the node with the input")
+    field: str = Field(description="The field name of the input")
+    alias: str = Field(description="The alias of the input")
+
+
+class ExposedNodeOutput(BaseModel):
+    node_path: str = Field(description="The node path to the node with the output")
+    field: str = Field(description="The field name of the output")
+    alias: str = Field(description="The alias of the output")
+
+
+class LibraryGraph(BaseModel):
+    id: str = Field(description="The unique identifier for this library graph", default_factory=uuid_string)
+    graph: Graph = Field(description="The graph")
+    name: str = Field(description="The name of the graph")
+    description: str = Field(description="The description of the graph")
+    exposed_inputs: list[ExposedNodeInput] = Field(description="The inputs exposed by this graph", default_factory=list)
+    exposed_outputs: list[ExposedNodeOutput] = Field(
+        description="The outputs exposed by this graph", default_factory=list
+    )
+
+    @field_validator("exposed_inputs", "exposed_outputs")
+    def validate_exposed_aliases(cls, v: list[Union[ExposedNodeInput, ExposedNodeOutput]]):
+        if len(v) != len({i.alias for i in v}):
+            raise ValueError("Duplicate exposed alias")
+        return v
+
+    @model_validator(mode="after")
+    def validate_exposed_nodes(cls, values):
+        graph = values.graph
+
+        # Validate exposed inputs
+        for exposed_input in values.exposed_inputs:
+            if not graph.has_node(exposed_input.node_path):
+                raise ValueError(f"Exposed input node {exposed_input.node_path} does not exist")
+            node = graph.get_node(exposed_input.node_path)
+            if get_input_field(node, exposed_input.field) is None:
+                raise ValueError(
+                    f"Exposed input field {exposed_input.field} does not exist on node {exposed_input.node_path}"
+                )
+
+        # Validate exposed outputs
+        for exposed_output in values.exposed_outputs:
+            if not graph.has_node(exposed_output.node_path):
+                raise ValueError(f"Exposed output node {exposed_output.node_path} does not exist")
+            node = graph.get_node(exposed_output.node_path)
+            if get_output_field(node, exposed_output.field) is None:
+                raise ValueError(
+                    f"Exposed output field {exposed_output.field} does not exist on node {exposed_output.node_path}"
+                )
+
+        return values
+
+
+GraphInvocation.model_rebuild(force=True)
+Graph.model_rebuild(force=True)
+GraphExecutionState.model_rebuild(force=True)

invokeai/app/services/shared/invocation_context.py

@@ -1,28 +1,24 @@
-import threading
 from dataclasses import dataclass
-from pathlib import Path
 from typing import TYPE_CHECKING, Optional
 
 from PIL.Image import Image
 from torch import Tensor
 
-from invokeai.app.invocations.constants import IMAGE_MODES
 from invokeai.app.invocations.fields import MetadataField, WithBoard, WithMetadata
 from invokeai.app.services.boards.boards_common import BoardDTO
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 from invokeai.app.services.images.images_common import ImageDTO
 from invokeai.app.services.invocation_services import InvocationServices
+from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
-from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, ModelFormat, ModelType, SubModelType
-from invokeai.backend.model_manager.load.load_base import LoadedModel
-from invokeai.backend.model_manager.metadata.metadata_base import AnyModelRepoMetadata
+from invokeai.backend.model_management.model_manager import LoadedModelInfo
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
 from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineIntermediateState
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
 
 if TYPE_CHECKING:
     from invokeai.app.invocations.baseinvocation import BaseInvocation
-    from invokeai.app.services.session_queue.session_queue_common import SessionQueueItem
 
 """
 The InvocationContext provides access to various services and data about the current invocation.
@@ -49,102 +45,99 @@ Note: The docstrings are in weird places, but that's where they must be to get I
 
 @dataclass
 class InvocationContextData:
-    queue_item: "SessionQueueItem"
-    """The queue item that is being executed."""
     invocation: "BaseInvocation"
     """The invocation that is being executed."""
-    source_invocation_id: str
-    """The ID of the invocation from which the currently executing invocation was prepared."""
+    session_id: str
+    """The session that is being executed."""
+    queue_id: str
+    """The queue in which the session is being executed."""
+    source_node_id: str
+    """The ID of the node from which the currently executing invocation was prepared."""
+    queue_item_id: int
+    """The ID of the queue item that is being executed."""
+    batch_id: str
+    """The ID of the batch that is being executed."""
+    workflow: Optional[WorkflowWithoutID] = None
+    """The workflow associated with this queue item, if any."""
 
 
 class InvocationContextInterface:
-    def __init__(self, services: InvocationServices, data: InvocationContextData) -> None:
+    def __init__(self, services: InvocationServices, context_data: InvocationContextData) -> None:
         self._services = services
-        self._data = data
+        self._context_data = context_data
 
 
 class BoardsInterface(InvocationContextInterface):
     def create(self, board_name: str) -> BoardDTO:
-        """Creates a board.
+        """
+        Creates a board.
 
-        Args:
-            board_name: The name of the board to create.
-
-        Returns:
-            The created board DTO.
+        :param board_name: The name of the board to create.
         """
         return self._services.boards.create(board_name)
 
     def get_dto(self, board_id: str) -> BoardDTO:
-        """Gets a board DTO.
+        """
+        Gets a board DTO.
 
-        Args:
-            board_id: The ID of the board to get.
-
-        Returns:
-            The board DTO.
+        :param board_id: The ID of the board to get.
         """
         return self._services.boards.get_dto(board_id)
 
     def get_all(self) -> list[BoardDTO]:
-        """Gets all boards.
-
-        Returns:
-            A list of all boards.
+        """
+        Gets all boards.
         """
         return self._services.boards.get_all()
 
     def add_image_to_board(self, board_id: str, image_name: str) -> None:
-        """Adds an image to a board.
+        """
+        Adds an image to a board.
 
-        Args:
-            board_id: The ID of the board to add the image to.
-            image_name: The name of the image to add to the board.
+        :param board_id: The ID of the board to add the image to.
+        :param image_name: The name of the image to add to the board.
         """
         return self._services.board_images.add_image_to_board(board_id, image_name)
 
     def get_all_image_names_for_board(self, board_id: str) -> list[str]:
-        """Gets all image names for a board.
+        """
+        Gets all image names for a board.
 
-        Args:
-            board_id: The ID of the board to get the image names for.
-
-        Returns:
-            A list of all image names for the board.
+        :param board_id: The ID of the board to get the image names for.
         """
         return self._services.board_images.get_all_board_image_names_for_board(board_id)
 
 
 class LoggerInterface(InvocationContextInterface):
     def debug(self, message: str) -> None:
-        """Logs a debug message.
+        """
+        Logs a debug message.
 
-        Args:
-            message: The message to log.
+        :param message: The message to log.
         """
         self._services.logger.debug(message)
 
     def info(self, message: str) -> None:
-        """Logs an info message.
+        """
+        Logs an info message.
 
-        Args:
-            message: The message to log.
+        :param message: The message to log.
         """
         self._services.logger.info(message)
 
     def warning(self, message: str) -> None:
-        """Logs a warning message.
+        """
+        Logs a warning message.
 
-        Args:
-            message: The message to log.
+        :param message: The message to log.
         """
         self._services.logger.warning(message)
 
     def error(self, message: str) -> None:
-        """Logs an error message.
+        """
+        Logs an error message.
 
-        Args:
-            message: The message to log.
+        :param message: The message to log.
         """
         self._services.logger.error(message)
 
@@ -157,286 +150,164 @@ class ImagesInterface(InvocationContextInterface):
         image_category: ImageCategory = ImageCategory.GENERAL,
         metadata: Optional[MetadataField] = None,
     ) -> ImageDTO:
-        """Saves an image, returning its DTO.
+        """
+        Saves an image, returning its DTO.
 
         If the current queue item has a workflow or metadata, it is automatically saved with the image.
 
-        Args:
-            image: The image to save, as a PIL image.
-            board_id: The board ID to add the image to, if it should be added. It the invocation \
+        :param image: The image to save, as a PIL image.
+        :param board_id: The board ID to add the image to, if it should be added. It the invocation \
             inherits from `WithBoard`, that board will be used automatically. **Use this only if \
             you want to override or provide a board manually!**
-            image_category: The category of the image. Only the GENERAL category is added \
+        :param image_category: The category of the image. Only the GENERAL category is added \
             to the gallery.
-            metadata: The metadata to save with the image, if it should have any. If the \
+        :param metadata: The metadata to save with the image, if it should have any. If the \
             invocation inherits from `WithMetadata`, that metadata will be used automatically. \
             **Use this only if you want to override or provide metadata manually!**
-
-        Returns:
-            The saved image DTO.
         """
 
         # If `metadata` is provided directly, use that. Else, use the metadata provided by `WithMetadata`, falling back to None.
         metadata_ = None
         if metadata:
             metadata_ = metadata
-        elif isinstance(self._data.invocation, WithMetadata):
-            metadata_ = self._data.invocation.metadata
+        elif isinstance(self._context_data.invocation, WithMetadata):
+            metadata_ = self._context_data.invocation.metadata
 
         # If `board_id` is provided directly, use that. Else, use the board provided by `WithBoard`, falling back to None.
         board_id_ = None
         if board_id:
             board_id_ = board_id
-        elif isinstance(self._data.invocation, WithBoard) and self._data.invocation.board:
-            board_id_ = self._data.invocation.board.board_id
+        elif isinstance(self._context_data.invocation, WithBoard) and self._context_data.invocation.board:
+            board_id_ = self._context_data.invocation.board.board_id
 
         return self._services.images.create(
             image=image,
-            is_intermediate=self._data.invocation.is_intermediate,
+            is_intermediate=self._context_data.invocation.is_intermediate,
             image_category=image_category,
             board_id=board_id_,
             metadata=metadata_,
             image_origin=ResourceOrigin.INTERNAL,
-            workflow=self._data.queue_item.workflow,
-            session_id=self._data.queue_item.session_id,
-            node_id=self._data.invocation.id,
+            workflow=self._context_data.workflow,
+            session_id=self._context_data.session_id,
+            node_id=self._context_data.invocation.id,
         )
 
-    def get_pil(self, image_name: str, mode: IMAGE_MODES | None = None) -> Image:
-        """Gets an image as a PIL Image object.
-
-        Args:
-            image_name: The name of the image to get.
-            mode: The color mode to convert the image to. If None, the original mode is used.
-
-        Returns:
-            The image as a PIL Image object.
+    def get_pil(self, image_name: str) -> Image:
         """
-        image = self._services.images.get_pil_image(image_name)
-        if mode and mode != image.mode:
-            try:
-                image = image.convert(mode)
-            except ValueError:
-                self._services.logger.warning(
-                    f"Could not convert image from {image.mode} to {mode}. Using original mode instead."
-                )
-        return image
+        Gets an image as a PIL Image object.
+
+        :param image_name: The name of the image to get.
+        """
+        return self._services.images.get_pil_image(image_name)
 
     def get_metadata(self, image_name: str) -> Optional[MetadataField]:
-        """Gets an image's metadata, if it has any.
+        """
+        Gets an image's metadata, if it has any.
 
-        Args:
-            image_name: The name of the image to get the metadata for.
-
-        Returns:
-            The image's metadata, if it has any.
+        :param image_name: The name of the image to get the metadata for.
         """
         return self._services.images.get_metadata(image_name)
 
     def get_dto(self, image_name: str) -> ImageDTO:
-        """Gets an image as an ImageDTO object.
+        """
+        Gets an image as an ImageDTO object.
 
-        Args:
-            image_name: The name of the image to get.
-
-        Returns:
-            The image as an ImageDTO object.
+        :param image_name: The name of the image to get.
         """
         return self._services.images.get_dto(image_name)
 
 
 class TensorsInterface(InvocationContextInterface):
     def save(self, tensor: Tensor) -> str:
-        """Saves a tensor, returning its name.
+        """
+        Saves a tensor, returning its name.
 
-        Args:
-            tensor: The tensor to save.
-
-        Returns:
-            The name of the saved tensor.
+        :param tensor: The tensor to save.
         """
 
         name = self._services.tensors.save(obj=tensor)
         return name
 
     def load(self, name: str) -> Tensor:
-        """Loads a tensor by name.
+        """
+        Loads a tensor by name.
 
-        Args:
-            name: The name of the tensor to load.
-
-        Returns:
-            The loaded tensor.
+        :param name: The name of the tensor to load.
         """
         return self._services.tensors.load(name)
 
 
 class ConditioningInterface(InvocationContextInterface):
     def save(self, conditioning_data: ConditioningFieldData) -> str:
-        """Saves a conditioning data object, returning its name.
+        """
+        Saves a conditioning data object, returning its name.
 
-        Args:
-            conditioning_data: The conditioning data to save.
-
-        Returns:
-            The name of the saved conditioning data.
+        :param conditioning_context_data: The conditioning data to save.
         """
 
         name = self._services.conditioning.save(obj=conditioning_data)
         return name
 
     def load(self, name: str) -> ConditioningFieldData:
-        """Loads conditioning data by name.
+        """
+        Loads conditioning data by name.
 
-        Args:
-            name: The name of the conditioning data to load.
-
-        Returns:
-            The loaded conditioning data.
+        :param name: The name of the conditioning data to load.
         """
 
         return self._services.conditioning.load(name)
 
 
 class ModelsInterface(InvocationContextInterface):
-    def exists(self, key: str) -> bool:
-        """Checks if a model exists.
-
-        Args:
-            key: The key of the model.
-
-        Returns:
-            True if the model exists, False if not.
+    def exists(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> bool:
         """
-        return self._services.model_manager.store.exists(key)
+        Checks if a model exists.
 
-    def load(self, key: str, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
-        """Loads a model.
+        :param model_name: The name of the model to check.
+        :param base_model: The base model of the model to check.
+        :param model_type: The type of the model to check.
+        """
+        return self._services.model_manager.model_exists(model_name, base_model, model_type)
 
-        Args:
-            key: The key of the model.
-            submodel_type: The submodel of the model to get.
+    def load(
+        self, model_name: str, base_model: BaseModelType, model_type: ModelType, submodel: Optional[SubModelType] = None
+    ) -> LoadedModelInfo:
+        """
+        Loads a model.
 
-        Returns:
-            An object representing the loaded model.
+        :param model_name: The name of the model to get.
+        :param base_model: The base model of the model to get.
+        :param model_type: The type of the model to get.
+        :param submodel: The submodel of the model to get.
+        :returns: An object representing the loaded model.
         """
 
         # The model manager emits events as it loads the model. It needs the context data to build
         # the event payloads.
 
-        return self._services.model_manager.load_model_by_key(
-            key=key, submodel_type=submodel_type, context_data=self._data
+        return self._services.model_manager.get_model(
+            model_name, base_model, model_type, submodel, context_data=self._context_data
         )
 
-    def load_by_attrs(
-        self, name: str, base: BaseModelType, type: ModelType, submodel_type: Optional[SubModelType] = None
-    ) -> LoadedModel:
-        """Loads a model by its attributes.
-
-        Args:
-            name: Name of the model.
-            base: The models' base type, e.g. `BaseModelType.StableDiffusion1`, `BaseModelType.StableDiffusionXL`, etc.
-            type: Type of the model, e.g. `ModelType.Main`, `ModelType.Vae`, etc.
-            submodel_type: The type of submodel to load, e.g. `SubModelType.UNet`, `SubModelType.TextEncoder`, etc. Only main
-            models have submodels.
-
-        Returns:
-            An object representing the loaded model.
+    def get_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
         """
-        return self._services.model_manager.load_model_by_attr(
-            model_name=name,
-            base_model=base,
-            model_type=type,
-            submodel=submodel_type,
-            context_data=self._data,
-        )
+        Gets a model's info, an dict-like object.
 
-    def get_config(self, key: str) -> AnyModelConfig:
-        """Gets a model's config.
-
-        Args:
-            key: The key of the model.
-
-        Returns:
-            The model's config.
+        :param model_name: The name of the model to get.
+        :param base_model: The base model of the model to get.
+        :param model_type: The type of the model to get.
         """
-        return self._services.model_manager.store.get_model(key=key)
-
-    def get_metadata(self, key: str) -> Optional[AnyModelRepoMetadata]:
-        """Gets a model's metadata, if it has any.
-
-        Args:
-            key: The key of the model.
-
-        Returns:
-            The model's metadata, if it has any.
-        """
-        return self._services.model_manager.store.get_metadata(key=key)
-
-    def search_by_path(self, path: Path) -> list[AnyModelConfig]:
-        """Searches for models by path.
-
-        Args:
-            path: The path to search for.
-
-        Returns:
-            A list of models that match the path.
-        """
-        return self._services.model_manager.store.search_by_path(path)
-
-    def search_by_attrs(
-        self,
-        name: Optional[str] = None,
-        base: Optional[BaseModelType] = None,
-        type: Optional[ModelType] = None,
-        format: Optional[ModelFormat] = None,
-    ) -> list[AnyModelConfig]:
-        """Searches for models by attributes.
-
-        Args:
-            name: The name to search for (exact match).
-            base: The base to search for, e.g. `BaseModelType.StableDiffusion1`, `BaseModelType.StableDiffusionXL`, etc.
-            type: Type type of model to search for, e.g. `ModelType.Main`, `ModelType.Vae`, etc.
-            format: The format of model to search for, e.g. `ModelFormat.Checkpoint`, `ModelFormat.Diffusers`, etc.
-
-        Returns:
-            A list of models that match the attributes.
-        """
-
-        return self._services.model_manager.store.search_by_attr(
-            model_name=name,
-            base_model=base,
-            model_type=type,
-            model_format=format,
-        )
+        return self._services.model_manager.model_info(model_name, base_model, model_type)
 
 
 class ConfigInterface(InvocationContextInterface):
     def get(self) -> InvokeAIAppConfig:
-        """Gets the app's config.
-
-        Returns:
-            The app's config.
-        """
+        """Gets the app's config."""
 
         return self._services.configuration.get_config()
 
 
 class UtilInterface(InvocationContextInterface):
-    def __init__(
-        self, services: InvocationServices, data: InvocationContextData, cancel_event: threading.Event
-    ) -> None:
-        super().__init__(services, data)
-        self._cancel_event = cancel_event
-
-    def is_canceled(self) -> bool:
-        """Checks if the current session has been canceled.
-
-        Returns:
-            True if the current session has been canceled, False if not.
-        """
-        return self._cancel_event.is_set()
-
     def sd_step_callback(self, intermediate_state: PipelineIntermediateState, base_model: BaseModelType) -> None:
         """
         The step callback emits a progress event with the current step, the total number of
@@ -444,32 +315,27 @@ class UtilInterface(InvocationContextInterface):
 
         This should be called after each denoising step.
 
-        Args:
-            intermediate_state: The intermediate state of the diffusion pipeline.
-            base_model: The base model for the current denoising step.
+        :param intermediate_state: The intermediate state of the diffusion pipeline.
+        :param base_model: The base model for the current denoising step.
         """
 
+        # The step callback needs access to the events and the invocation queue services, but this
+        # represents a dangerous level of access.
+        #
+        # We wrap the step callback so that nodes do not have direct access to these services.
+
         stable_diffusion_step_callback(
-            context_data=self._data,
+            context_data=self._context_data,
             intermediate_state=intermediate_state,
             base_model=base_model,
+            invocation_queue=self._services.queue,
             events=self._services.events,
-            is_canceled=self.is_canceled,
         )
 
 
 class InvocationContext:
-    """Provides access to various services and data for the current invocation.
-
-    Attributes:
-        images (ImagesInterface): Methods to save, get and update images and their metadata.
-        tensors (TensorsInterface): Methods to save and get tensors, including image, noise, masks, and masked images.
-        conditioning (ConditioningInterface): Methods to save and get conditioning data.
-        models (ModelsInterface): Methods to check if a model exists, get a model, and get a model's info.
-        logger (LoggerInterface): The app logger.
-        config (ConfigInterface): The app config.
-        util (UtilInterface): Utility methods, including a method to check if an invocation was canceled and step callbacks.
-        boards (BoardsInterface): Methods to interact with boards.
+    """
+    The `InvocationContext` provides access to various services and data for the current invocation.
     """
 
     def __init__(
@@ -482,54 +348,50 @@ class InvocationContext:
         config: ConfigInterface,
         util: UtilInterface,
         boards: BoardsInterface,
-        data: InvocationContextData,
+        context_data: InvocationContextData,
         services: InvocationServices,
     ) -> None:
         self.images = images
-        """Methods to save, get and update images and their metadata."""
+        """Provides methods to save, get and update images and their metadata."""
         self.tensors = tensors
-        """Methods to save and get tensors, including image, noise, masks, and masked images."""
+        """Provides methods to save and get tensors, including image, noise, masks, and masked images."""
         self.conditioning = conditioning
-        """Methods to save and get conditioning data."""
+        """Provides methods to save and get conditioning data."""
         self.models = models
-        """Methods to check if a model exists, get a model, and get a model's info."""
+        """Provides methods to check if a model exists, get a model, and get a model's info."""
         self.logger = logger
-        """The app logger."""
+        """Provides access to the app logger."""
         self.config = config
-        """The app config."""
+        """Provides access to the app's config."""
         self.util = util
-        """Utility methods, including a method to check if an invocation was canceled and step callbacks."""
+        """Provides utility methods."""
         self.boards = boards
-        """Methods to interact with boards."""
-        self._data = data
-        """An internal API providing access to data about the current queue item and invocation. You probably shouldn't use this. It may change without warning."""
+        """Provides methods to interact with boards."""
+        self._data = context_data
+        """Provides data about the current queue item and invocation. This is an internal API and may change without warning."""
         self._services = services
-        """An internal API providing access to all application services. You probably shouldn't use this. It may change without warning."""
+        """Provides access to the full application services. This is an internal API and may change without warning."""
 
 
 def build_invocation_context(
     services: InvocationServices,
-    data: InvocationContextData,
-    cancel_event: threading.Event,
+    context_data: InvocationContextData,
 ) -> InvocationContext:
-    """Builds the invocation context for a specific invocation execution.
+    """
+    Builds the invocation context for a specific invocation execution.
 
-    Args:
-        services: The invocation services to wrap.
-        data: The invocation context data.
-
-    Returns:
-        The invocation context.
+    :param invocation_services: The invocation services to wrap.
+    :param invocation_context_data: The invocation context data.
     """
 
-    logger = LoggerInterface(services=services, data=data)
-    images = ImagesInterface(services=services, data=data)
-    tensors = TensorsInterface(services=services, data=data)
-    models = ModelsInterface(services=services, data=data)
-    config = ConfigInterface(services=services, data=data)
-    util = UtilInterface(services=services, data=data, cancel_event=cancel_event)
-    conditioning = ConditioningInterface(services=services, data=data)
-    boards = BoardsInterface(services=services, data=data)
+    logger = LoggerInterface(services=services, context_data=context_data)
+    images = ImagesInterface(services=services, context_data=context_data)
+    tensors = TensorsInterface(services=services, context_data=context_data)
+    models = ModelsInterface(services=services, context_data=context_data)
+    config = ConfigInterface(services=services, context_data=context_data)
+    util = UtilInterface(services=services, context_data=context_data)
+    conditioning = ConditioningInterface(services=services, context_data=context_data)
+    boards = BoardsInterface(services=services, context_data=context_data)
 
     ctx = InvocationContext(
         images=images,
@@ -537,7 +399,7 @@ def build_invocation_context(
         config=config,
         tensors=tensors,
         models=models,
-        data=data,
+        context_data=context_data,
         util=util,
         conditioning=conditioning,
         services=services,

invokeai/app/services/shared/sqlite/sqlite_util.py

@@ -8,7 +8,6 @@ from invokeai.app.services.shared.sqlite_migrator.migrations.migration_2 import
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_3 import build_migration_3
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_4 import build_migration_4
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_5 import build_migration_5
-from invokeai.app.services.shared.sqlite_migrator.migrations.migration_6 import build_migration_6
 from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_impl import SqliteMigrator
 
 
@@ -34,7 +33,6 @@ def init_db(config: InvokeAIAppConfig, logger: Logger, image_files: ImageFileSto
     migrator.register_migration(build_migration_3(app_config=config, logger=logger))
     migrator.register_migration(build_migration_4())
     migrator.register_migration(build_migration_5())
-    migrator.register_migration(build_migration_6())
     migrator.run_migrations()
 
     return db

invokeai/app/services/shared/sqlite_migrator/migrations/migration_6.py

@@ -1,62 +0,0 @@
-import sqlite3
-
-from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
-
-
-class Migration6Callback:
-    def __call__(self, cursor: sqlite3.Cursor) -> None:
-        self._recreate_model_triggers(cursor)
-        self._delete_ip_adapters(cursor)
-
-    def _recreate_model_triggers(self, cursor: sqlite3.Cursor) -> None:
-        """
-        Adds the timestamp trigger to the model_config table.
-
-        This trigger was inadvertently dropped in earlier migration scripts.
-        """
-
-        cursor.execute(
-            """--sql
-            CREATE TRIGGER IF NOT EXISTS model_config_updated_at
-            AFTER UPDATE
-            ON model_config FOR EACH ROW
-            BEGIN
-                UPDATE model_config SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
-                    WHERE id = old.id;
-            END;
-            """
-        )
-
-    def _delete_ip_adapters(self, cursor: sqlite3.Cursor) -> None:
-        """
-        Delete all the IP adapters.
-
-        The model manager will automatically find and re-add them after the migration
-        is done. This allows the manager to add the correct image encoder to their
-        configuration records.
-        """
-
-        cursor.execute(
-            """--sql
-            DELETE FROM model_config
-              WHERE type='ip_adapter';
-            """
-        )
-
-
-def build_migration_6() -> Migration:
-    """
-    Build the migration from database version 5 to 6.
-
-    This migration does the following:
-    - Adds the model_config_updated_at trigger if it does not exist
-    - Delete all ip_adapter models so that the model prober can find and
-      update with the correct image processor model.
-    """
-    migration_6 = Migration(
-        from_version=5,
-        to_version=6,
-        callback=Migration6Callback(),
-    )
-
-    return migration_6

invokeai/app/services/shared/sqlite_migrator/migrations/util/migrate_yaml_config_1.py

@@ -3,6 +3,7 @@
 
 import json
 import sqlite3
+from hashlib import sha1
 from logging import Logger
 from pathlib import Path
 from typing import Optional
@@ -21,7 +22,7 @@ from invokeai.backend.model_manager.config import (
     ModelConfigFactory,
     ModelType,
 )
-from invokeai.backend.model_manager.hash import ModelHash
+from invokeai.backend.model_manager.hash import FastModelHash
 
 ModelsValidator = TypeAdapter(AnyModelConfig)
 
@@ -72,27 +73,19 @@ class MigrateModelYamlToDb1:
 
             base_type, model_type, model_name = str(model_key).split("/")
             try:
-                hash = ModelHash().hash(self.config.models_path / stanza.path)
+                hash = FastModelHash.hash(self.config.models_path / stanza.path)
             except OSError:
                 self.logger.warning(f"The model at {stanza.path} is not a valid file or directory. Skipping migration.")
                 continue
 
+            assert isinstance(model_key, str)
+            new_key = sha1(model_key.encode("utf-8")).hexdigest()
+
             stanza["base"] = BaseModelType(base_type)
             stanza["type"] = ModelType(model_type)
             stanza["name"] = model_name
             stanza["original_hash"] = hash
             stanza["current_hash"] = hash
-            new_key = hash  # deterministic key assignment
-
-            # special case for ip adapters, which need the new `image_encoder_model_id` field
-            if stanza["type"] == ModelType.IPAdapter:
-                try:
-                    stanza["image_encoder_model_id"] = self._get_image_encoder_model_id(
-                        self.config.models_path / stanza.path
-                    )
-                except OSError:
-                    self.logger.warning(f"Could not determine image encoder for {stanza.path}. Skipping.")
-                    continue
 
             new_config: AnyModelConfig = ModelsValidator.validate_python(stanza)  # type: ignore # see https://github.com/pydantic/pydantic/discussions/7094
 
@@ -102,7 +95,7 @@ class MigrateModelYamlToDb1:
                     self.logger.info(f"Updating model {model_name} with information from models.yaml using key {key}")
                     self._update_model(key, new_config)
                 else:
-                    self.logger.info(f"Adding model {model_name} with key {new_key}")
+                    self.logger.info(f"Adding model {model_name} with key {model_key}")
                     self._add_model(new_key, new_config)
             except DuplicateModelException:
                 self.logger.warning(f"Model {model_name} is already in the database")
@@ -156,8 +149,3 @@ class MigrateModelYamlToDb1:
             )
         except sqlite3.IntegrityError as exc:
             raise DuplicateModelException(f"{record.name}: model is already in database") from exc
-
-    def _get_image_encoder_model_id(self, model_path: Path) -> str:
-        with open(model_path / "image_encoder.txt") as f:
-            encoder = f.read()
-        return encoder.strip()

invokeai/app/services/shared/sqlite_migrator/sqlite_migrator_common.py

@@ -17,7 +17,8 @@ class MigrateCallback(Protocol):
     See :class:`Migration` for an example.
     """
 
-    def __call__(self, cursor: sqlite3.Cursor) -> None: ...
+    def __call__(self, cursor: sqlite3.Cursor) -> None:
+        ...
 
 
 class MigrationError(RuntimeError):

invokeai/app/util/misc.py

@@ -5,7 +5,7 @@ import uuid
 import numpy as np
 
 
-def get_timestamp() -> int:
+def get_timestamp():
     return int(datetime.datetime.now(datetime.timezone.utc).timestamp())
 
 
@@ -20,16 +20,16 @@ def get_datetime_from_iso_timestamp(iso_timestamp: str) -> datetime.datetime:
 SEED_MAX = np.iinfo(np.uint32).max
 
 
-def get_random_seed() -> int:
+def get_random_seed():
     rng = np.random.default_rng(seed=None)
     return int(rng.integers(0, SEED_MAX))
 
 
-def uuid_string() -> str:
+def uuid_string():
     res = uuid.uuid4()
     return str(res)
 
 
-def is_optional(value: typing.Any) -> bool:
+def is_optional(value: typing.Any):
     """Checks if a value is typed as Optional. Note that Optional is sugar for Union[x, None]."""
     return typing.get_origin(value) is typing.Union and type(None) in typing.get_args(value)

invokeai/app/util/step_callback.py

@@ -1,16 +1,17 @@
-from typing import TYPE_CHECKING, Callable
+from typing import TYPE_CHECKING
 
 import torch
 from PIL import Image
 
-from invokeai.app.services.session_processor.session_processor_common import CanceledException, ProgressImage
-from invokeai.backend.model_manager.config import BaseModelType
+from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException, ProgressImage
 
+from ...backend.model_management.models import BaseModelType
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.util.util import image_to_dataURL
 
 if TYPE_CHECKING:
     from invokeai.app.services.events.events_base import EventServiceBase
+    from invokeai.app.services.invocation_queue.invocation_queue_base import InvocationQueueABC
     from invokeai.app.services.shared.invocation_context import InvocationContextData
 
 
@@ -33,10 +34,10 @@ def stable_diffusion_step_callback(
     context_data: "InvocationContextData",
     intermediate_state: PipelineIntermediateState,
     base_model: BaseModelType,
+    invocation_queue: "InvocationQueueABC",
     events: "EventServiceBase",
-    is_canceled: Callable[[], bool],
 ) -> None:
-    if is_canceled():
+    if invocation_queue.is_canceled(context_data.session_id):
         raise CanceledException
 
     # Some schedulers report not only the noisy latents at the current timestep,
@@ -114,12 +115,12 @@ def stable_diffusion_step_callback(
     dataURL = image_to_dataURL(image, image_format="JPEG")
 
     events.emit_generator_progress(
-        queue_id=context_data.queue_item.queue_id,
-        queue_item_id=context_data.queue_item.item_id,
-        queue_batch_id=context_data.queue_item.batch_id,
-        graph_execution_state_id=context_data.queue_item.session_id,
+        queue_id=context_data.queue_id,
+        queue_item_id=context_data.queue_item_id,
+        queue_batch_id=context_data.batch_id,
+        graph_execution_state_id=context_data.session_id,
         node_id=context_data.invocation.id,
-        source_node_id=context_data.source_invocation_id,
+        source_node_id=context_data.source_node_id,
         progress_image=ProgressImage(width=width, height=height, dataURL=dataURL),
         step=intermediate_state.step,
         order=intermediate_state.order,

invokeai/app/util/ti_utils.py

@@ -1,47 +1,8 @@
 import re
-from typing import List, Tuple
-
-import invokeai.backend.util.logging as logger
-from invokeai.app.services.model_records import UnknownModelException
-from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.model_manager.config import BaseModelType, ModelType
-from invokeai.backend.textual_inversion import TextualInversionModelRaw
 
 
-def extract_ti_triggers_from_prompt(prompt: str) -> List[str]:
-    ti_triggers: List[str] = []
+def extract_ti_triggers_from_prompt(prompt: str) -> list[str]:
+    ti_triggers = []
     for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", prompt):
-        ti_triggers.append(str(trigger))
+        ti_triggers.append(trigger)
     return ti_triggers
-
-
-def generate_ti_list(
-    prompt: str, base: BaseModelType, context: InvocationContext
-) -> List[Tuple[str, TextualInversionModelRaw]]:
-    ti_list: List[Tuple[str, TextualInversionModelRaw]] = []
-    for trigger in extract_ti_triggers_from_prompt(prompt):
-        name_or_key = trigger[1:-1]
-        try:
-            loaded_model = context.models.load(key=name_or_key)
-            model = loaded_model.model
-            assert isinstance(model, TextualInversionModelRaw)
-            assert loaded_model.config.base == base
-            ti_list.append((name_or_key, model))
-        except UnknownModelException:
-            try:
-                loaded_model = context.models.load_by_attrs(
-                    name=name_or_key, base=base, type=ModelType.TextualInversion
-                )
-                model = loaded_model.model
-                assert isinstance(model, TextualInversionModelRaw)
-                assert loaded_model.config.base == base
-                ti_list.append((name_or_key, model))
-            except UnknownModelException:
-                pass
-        except ValueError:
-            logger.warning(f'trigger: "{trigger}" more than one similarly-named textual inversion models')
-        except AssertionError:
-            logger.warning(f'trigger: "{trigger}" not a valid textual inversion model for this graph')
-        except Exception:
-            logger.warning(f'Failed to load TI model for trigger: "{trigger}"')
-    return ti_list

invokeai/backend/__init__.py

@@ -1,3 +1,12 @@
 """
 Initialization file for invokeai.backend
 """
+from .model_management import (  # noqa: F401
+    BaseModelType,
+    LoadedModelInfo,
+    ModelCache,
+    ModelManager,
+    ModelType,
+    SubModelType,
+)
+from .model_management.models import SilenceWarnings  # noqa: F401