feat(api): change implementation for path endpoint

- `MetadataModule` is stateless and needed in places where the `InvocationContext` is not available, so have not made it a `service`
- Handles loading/parsing/building metadata, and creating png info objects
- added tests for MetadataModule
- Lifted thumbnail stuff to util

.github/CODEOWNERS

@@ -1,16 +1,16 @@
 # continuous integration
-/.github/workflows/  @lstein @blessedcoolant
+/.github/workflows/ @mauwii @lstein @blessedcoolant
 
 # documentation
-/docs/ @lstein @blessedcoolant @hipsterusername
-/mkdocs.yml @lstein  @blessedcoolant
+/docs/ @lstein @mauwii @tildebyte @blessedcoolant
+/mkdocs.yml @lstein @mauwii @blessedcoolant
 
 # nodes
 /invokeai/app/ @Kyle0654 @blessedcoolant
 
 # installation and configuration
-/pyproject.toml  @lstein @blessedcoolant
-/docker/  @lstein @blessedcoolant
+/pyproject.toml @mauwii @lstein @blessedcoolant
+/docker/ @mauwii @lstein @blessedcoolant
 /scripts/ @ebr @lstein
 /installer/ @lstein @ebr
 /invokeai/assets @lstein @ebr
@@ -18,17 +18,17 @@
 /invokeai/version @lstein @blessedcoolant
 
 # web ui
-/invokeai/frontend @blessedcoolant @psychedelicious @lstein @maryhipp
-/invokeai/backend @blessedcoolant @psychedelicious @lstein @maryhipp
+/invokeai/frontend @blessedcoolant @psychedelicious @lstein
+/invokeai/backend @blessedcoolant @psychedelicious @lstein
 
 # generation, model management, postprocessing
-/invokeai/backend  @damian0815 @lstein @blessedcoolant @jpphoto @gregghelt2 @StAlKeR7779
+/invokeai/backend @keturn @damian0815 @lstein @blessedcoolant @jpphoto
 
 # front ends
 /invokeai/frontend/CLI @lstein
-/invokeai/frontend/install @lstein @ebr  
-/invokeai/frontend/merge @lstein @blessedcoolant 
-/invokeai/frontend/training @lstein @blessedcoolant 
-/invokeai/frontend/web @psychedelicious @blessedcoolant @maryhipp 
+/invokeai/frontend/install @lstein @ebr @mauwii 
+/invokeai/frontend/merge @lstein @blessedcoolant @hipsterusername
+/invokeai/frontend/training @lstein @blessedcoolant @hipsterusername
+/invokeai/frontend/web @psychedelicious @blessedcoolant
 
 

.github/workflows/mkdocs-material.yml

@@ -2,7 +2,8 @@ name: mkdocs-material
 on:
   push:
     branches:
-      - 'refs/heads/v2.3'
+      - 'main'
+      - 'development'
 
 permissions:
     contents: write
@@ -11,10 +12,6 @@ jobs:
   mkdocs-material:
     if: github.event.pull_request.draft == false
     runs-on: ubuntu-latest
-    env:
-      REPO_URL: '${{ github.server_url }}/${{ github.repository }}'
-      REPO_NAME: '${{ github.repository }}'
-      SITE_URL: 'https://${{ github.repository_owner }}.github.io/InvokeAI'
     steps:
       - name: checkout sources
         uses: actions/checkout@v3
@@ -25,15 +22,11 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: '3.10'
-          cache: pip
-          cache-dependency-path: pyproject.toml
 
       - name: install requirements
-        env:
-          PIP_USE_PEP517: 1
         run: |
           python -m \
-            pip install ".[docs]"
+            pip install -r docs/requirements-mkdocs.txt
 
       - name: confirm buildability
         run: |
@@ -43,7 +36,7 @@ jobs:
             --verbose
 
       - name: deploy to gh-pages
-        if: ${{ github.ref == 'refs/heads/v2.3' }}
+        if: ${{ github.ref == 'refs/heads/main' }}
         run: |
           python -m \
             mkdocs gh-deploy \

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

@@ -1,16 +1,10 @@
 name: Test invoke.py pip
-
-# This is a dummy stand-in for the actual tests
-# we don't need to run python tests on non-Python changes
-# But PRs require passing tests to be mergeable
-
 on:
   pull_request:
     paths:
       - '**'
       - '!pyproject.toml'
       - '!invokeai/**'
-      - '!tests/**'
       - 'invokeai/frontend/web/**'
   merge_group:
   workflow_dispatch:
@@ -25,26 +19,48 @@ jobs:
     strategy:
       matrix:
         python-version:
+          # - '3.9'
           - '3.10'
         pytorch:
+          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
+          # - windows-cuda-11_6
+          # - windows-cuda-11_7
         include:
+          # - pytorch: linux-cuda-11_6
+          #   os: ubuntu-22.04
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $GITHUB_ENV
           - 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
+          # - pytorch: windows-cuda-11_6
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_7
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
+          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     steps:
-      - name: skip
-        run: echo "no build required"
+      - run: 'echo "No build required"'

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

@@ -11,7 +11,6 @@ on:
     paths:
       - 'pyproject.toml'
       - 'invokeai/**'
-      - 'tests/**'
       - '!invokeai/frontend/web/**'
     types:
       - 'ready_for_review'
@@ -33,12 +32,19 @@ jobs:
           # - '3.9'
           - '3.10'
         pytorch:
+          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
+          # - windows-cuda-11_6
+          # - windows-cuda-11_7
         include:
+          # - pytorch: linux-cuda-11_6
+          #   os: ubuntu-22.04
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $GITHUB_ENV
           - pytorch: linux-cuda-11_7
             os: ubuntu-22.04
             github-env: $GITHUB_ENV
@@ -56,6 +62,14 @@ jobs:
           - pytorch: windows-cpu
             os: windows-2022
             github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_6
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_7
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
+          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     env:
@@ -66,6 +80,11 @@ jobs:
         uses: actions/checkout@v3
 
       - name: set test prompt to main branch validation
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> ${{ matrix.github-env }}
+
+      - name: set test prompt to Pull Request validation
+        if: ${{ github.ref != 'refs/heads/main' }}
         run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
 
       - name: setup python
@@ -86,38 +105,40 @@ jobs:
         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: set INVOKEAI_OUTDIR
+        run: >
+          python -c
+          "import os;from invokeai.backend.globals import Globals;OUTDIR=os.path.join(Globals.root,str('outputs'));print(f'INVOKEAI_OUTDIR={OUTDIR}')"
+          >> ${{ matrix.github-env }}
 
-      # - 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: run invokeai-configure
+        id: run-preload-models
+        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: Archive results
-      #   env:
-      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-      #   uses: actions/upload-artifact@v3
-      #   with:
-      #     name: results
-      #     path: ${{ env.INVOKEAI_OUTDIR }}
+      - 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
+        run: >
+          invokeai
+          --no-patchmatch
+          --no-nsfw_checker
+          --from_file ${{ env.TEST_PROMPTS }}
+          --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+
+      - name: Archive results
+        id: archive-results
+        uses: actions/upload-artifact@v3
+        with:
+          name: results
+          path: ${{ env.INVOKEAI_OUTDIR }}

.gitignore

@@ -9,8 +9,6 @@ models/ldm/stable-diffusion-v1/model.ckpt
 configs/models.user.yaml
 config/models.user.yml
 invokeai.init
-.version
-.last_model
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -201,8 +199,6 @@ checkpoints
 # If it's a Mac
 .DS_Store
 
-invokeai/frontend/web/dist/*
-
 # Let the frontend manage its own gitignore
 !invokeai/frontend/web/*
 

README.md

@@ -1,11 +1,8 @@
 <div align="center">
 
-![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/1a917d94-e099-4fa1-a70f-7dd8d0691018)
-
-# Invoke AI - Generative AI for Professional Creatives
-## Image Generation for Stable Diffusion, Custom-Trained Models, and more. 
-  Learn more about us and get started instantly at [invoke.ai](https://invoke.ai)
+![project logo](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/invoke_ai_banner.png)
 
+# InvokeAI: A Stable Diffusion Toolkit
 
 [![discord badge]][discord link]
 
@@ -36,32 +33,13 @@
 
 </div>
 
-_**Note: This is an alpha release. Bugs are expected and not all
-features are fully implemented. Please use the GitHub [Issues
-pages](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen)
-to report unexpected problems. Also note that InvokeAI root directory
-which contains models, outputs and configuration files, has changed
-between the 2.x and 3.x release. If you wish to use your v2.3 root
-directory with v3.0, please follow the directions in [Migrating a 2.3
-root directory to 3.0](#migrating-to-3).**_
+InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
 
-InvokeAI is a leading creative engine built to empower professionals
-and enthusiasts alike. Generate and create stunning visual media using
-the latest AI-driven technologies. InvokeAI offers an industry leading
-Web Interface, interactive Command Line Interface, and also serves as
-the foundation for multiple commercial products.
+**Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
 
-**Quick links**: [[How to
-  Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a
-  href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a
-  href="https://invoke-ai.github.io/InvokeAI/">Documentation and
-  Tutorials</a>] [<a
-  href="https://github.com/invoke-ai/InvokeAI/">Code and
-  Downloads</a>] [<a
-  href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>]
-  [<a
-  href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion,
-  Ideas & Q&A</a>]
+_Note: InvokeAI is rapidly evolving. Please use the
+[Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
+requests. Be sure to use the provided templates. They will help us diagnose issues faster._
 
 <div align="center">
 
@@ -71,30 +49,22 @@ the foundation for multiple commercial products.
 
 ## Table of Contents
 
-Table of Contents 📝
+1. [Quick Start](#getting-started-with-invokeai)
+2. [Installation](#detailed-installation-instructions)
+3. [Hardware Requirements](#hardware-requirements)
+4. [Features](#features)
+5. [Latest Changes](#latest-changes)
+6. [Troubleshooting](#troubleshooting)
+7. [Contributing](#contributing)
+8. [Contributors](#contributors)
+9. [Support](#support)
+10. [Further Reading](#further-reading)
 
-**Getting Started**
-1. 🏁 [Quick Start](#quick-start) 
-3. 🖥️ [Hardware Requirements](#hardware-requirements) 
-
-**More About Invoke**
-1. 🌟 [Features](#features) 
-2. 📣 [Latest Changes](#latest-changes) 
-3. 🛠️ [Troubleshooting](#troubleshooting) 
-
-**Supporting the Project**
-1. 🤝 [Contributing](#contributing) 
-2. 👥 [Contributors](#contributors) 
-3. 💕 [Support](#support) 
-
-## Quick Start
+## Getting Started with InvokeAI
 
 For full installation and upgrade instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
 
-If upgrading from version 2.3, please read [Migrating a 2.3 root
-directory to 3.0](#migrating-to-3) first.
-
 ### Automatic Installer (suggested for 1st time users)
 
 1. Go to the bottom of the [Latest Release Page](https://github.com/invoke-ai/InvokeAI/releases/latest)
@@ -103,8 +73,9 @@ directory to 3.0](#migrating-to-3) first.
 
 3. Unzip the file.
 
-4. **Windows:** double-click on the `install.bat` script. **macOS:** Open a Terminal window, drag the file `install.sh` from Finder
-into the Terminal, and press return. **Linux:** run `install.sh`.
+4. If you are on Windows, double-click on the `install.bat` script. On
+macOS, open a Terminal window, drag the file `install.sh` from Finder
+into the Terminal, and press return. On Linux, run `install.sh`.
 
 5. You'll be asked to confirm the location of the folder in which
 to install InvokeAI and its image generation model files. Pick a
@@ -130,7 +101,7 @@ and go to http://localhost:9090.
 
 10. Type `banana sushi` in the box on the top left and click `Invoke`
 
-### Command-Line Installation (for developers and users familiar with Terminals)
+### Command-Line Installation (for users familiar with Terminals)
 
 You must have Python 3.9 or 3.10 installed on your machine. Earlier or later versions are
 not supported.
@@ -177,11 +148,6 @@ not supported.
     pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
     ```
 
-    _For non-GPU systems:_
-    ```terminal
-    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
-    ``` 
-
     _For Macintoshes, either Intel or M1/M2:_
 
     ```sh
@@ -206,7 +172,7 @@ not supported.
 Be sure to activate the virtual environment each time before re-launching InvokeAI,
 using `source .venv/bin/activate` or `.venv\Scripts\activate`.
 
-## Detailed Installation Instructions
+### Detailed Installation Instructions
 
 This fork is supported across Linux, Windows and Macintosh. Linux
 users can use either an Nvidia-based card (with CUDA support) or an
@@ -214,87 +180,6 @@ AMD card (using the ROCm driver). For full installation and upgrade
 instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_SOURCE/)
 
-<a name="migrating-to-3"></a>
-### Migrating a v2.3 InvokeAI root directory
-
-The InvokeAI root directory is where the InvokeAI startup file,
-installed models, and generated images are stored. It is ordinarily
-named `invokeai` and located in your home directory. The contents and
-layout of this directory has changed between versions 2.3 and 3.0 and
-cannot be used directly.
-
-We currently recommend that you use the installer to create a new root
-directory named differently from the 2.3 one, e.g. `invokeai-3` and
-then use a migration script to copy your 2.3 models into the new
-location. However, if you choose, you can upgrade this directory in
-place.  This section gives both recipes.
-
-#### Creating a new root directory and migrating old models
-
-This is the safer recipe because it leaves your old root directory in
-place to fall back on.
-
-1. Follow the instructions above to create and install InvokeAI in a
-directory that has a different name from the 2.3 invokeai directory.
-In this example, we will use "invokeai-3"
-
-2. When you are prompted to select models to install, select a minimal
-set of models, such as stable-diffusion-v1.5 only.
-
-3. After installation is complete launch `invokeai.sh` (Linux/Mac) or
-`invokeai.bat` and select option 8 "Open the developers console". This
-will take you to the command line.
-
-4. Issue the command `invokeai-migrate3 --from /path/to/v2.3-root --to
-/path/to/invokeai-3-root`. Provide the correct `--from` and `--to`
-paths for your v2.3 and v3.0 root directories respectively.
-
-This will copy and convert your old models from 2.3 format to 3.0
-format and create a new `models` directory in the 3.0 directory. The
-old models directory (which contains the models selected at install
-time) will be renamed `models.orig` and can be deleted once you have
-confirmed that the migration was successful.
-
-#### Migrating in place
-
-For the adventurous, you may do an in-place upgrade from 2.3 to 3.0
-without touching the command line. The recipe is as follows>
-
-1. Launch the InvokeAI launcher script in your current v2.3 root directory.
-
-2. Select option [9] "Update InvokeAI" to bring up the updater dialog.
-
-3a. During the alpha release phase, select option [3] and manually
-enter the tag name `v3.0.0+a2`.
-
-3b. Once 3.0 is released, select option [1] to upgrade to the latest release.
-
-4. Once the upgrade is finished you will be returned to the launcher
-menu. Select option [7] "Re-run the configure script to fix a broken
-install or to complete a major upgrade".
-
-This will run the configure script against the v2.3 directory and
-update it to the 3.0 format. The following files will be replaced:
-
-  - The invokeai.init file, replaced by invokeai.yaml
-  - The models directory
-  - The configs/models.yaml model index
-  
-The original versions of these files will be saved with the suffix
-".orig" appended to the end. Once you have confirmed that the upgrade
-worked, you can safely remove these files. Alternatively you can
-restore a working v2.3 directory by removing the new files and
-restoring the ".orig" files' original names.
-
-#### Migration Caveats
-
-The migration script will migrate your invokeai settings and models,
-including textual inversion models, LoRAs and merges that you may have
-installed previously. However it does **not** migrate the generated
-images stored in your 2.3-format outputs directory. The released
-version of 3.0 is expected to have an interface for importing an
-entire directory of image files as a batch.
-
 ## Hardware Requirements
 
 InvokeAI is supported across Linux, Windows and macOS. Linux
@@ -313,9 +198,13 @@ We do not recommend the GTX 1650 or 1660 series video cards. They are
 unable to run in half-precision mode and do not have sufficient VRAM
 to render 512x512 images.
 
-**Memory** - At least 12 GB Main Memory RAM.
+### Memory
 
-**Disk** - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
+- At least 12 GB Main Memory RAM.
+
+### Disk
+
+- At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
 ## Features
 
@@ -331,7 +220,7 @@ The Unified Canvas is a fully integrated canvas implementation with support for
 
 ### *Advanced Prompt Syntax*
 
-Invoke AI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space. 
+InvokeAI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space.
 
 ### *Command Line Interface*
 
@@ -341,12 +230,16 @@ For users utilizing a terminal-based environment, or who want to take advantage
 
 - *Support for both ckpt and diffusers models*
 - *SD 2.0, 2.1 support*
+- *Noise Control & Tresholding*
+- *Popular Sampler Support*
 - *Upscaling & Face Restoration Tools*
 - *Embedding Manager & Support*
 - *Model Manager & Support*
-- *Node-Based Architecture*
-- *Node-Based Plug-&-Play UI (Beta)*
-- *Boards & Gallery Management
+
+### Coming Soon
+
+- *Node-Based Architecture & UI*
+- And more...
 
 ### Latest Changes
 
@@ -354,12 +247,12 @@ For our latest changes, view our [Release
 Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
 [CHANGELOG](docs/CHANGELOG.md).
 
-### Troubleshooting
+## Troubleshooting
 
 Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
 problems and other issues.
 
-## 🤝 Contributing
+## Contributing
 
 Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code
 cleanup, testing, or code reviews, is very much encouraged to do so.
@@ -378,12 +271,14 @@ to become part of our community.
 
 Welcome to InvokeAI!
 
-### 👥 Contributors
+### Contributors
 
 This fork is a combined effort of various people from across the world.
 [Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
 their time, hard work and effort.
 
+Thanks to [Weblate](https://weblate.org/) for generously providing translation services to this project.
+
 ### Support
 
 For support, please use this repository's GitHub Issues tracking service, or join the Discord.

binary_installer/install.bat.in

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

binary_installer/install.sh.in

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

binary_installer/invoke.bat.in

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

binary_installer/invoke.sh.in

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

binary_installer/readme.txt

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

binary_installer/requirements.in

@@ -0,0 +1,33 @@
+--prefer-binary
+--extra-index-url https://download.pytorch.org/whl/torch_stable.html
+--extra-index-url https://download.pytorch.org/whl/cu116
+--trusted-host https://download.pytorch.org
+accelerate~=0.15
+albumentations
+diffusers[torch]~=0.11
+einops
+eventlet
+flask_cors
+flask_socketio
+flaskwebgui==1.0.3
+getpass_asterisk
+imageio-ffmpeg
+pyreadline3
+realesrgan
+send2trash
+streamlit
+taming-transformers-rom1504
+test-tube
+torch-fidelity
+torch==1.12.1 ; platform_system == 'Darwin'
+torch==1.12.0+cu116 ; platform_system == 'Linux' or platform_system == 'Windows'
+torchvision==0.13.1 ; platform_system == 'Darwin'
+torchvision==0.13.0+cu116 ; platform_system == 'Linux' or platform_system == 'Windows'
+transformers
+picklescan
+https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip
+https://github.com/invoke-ai/clipseg/archive/1f754751c85d7d4255fa681f4491ff5711c1c288.zip
+https://github.com/invoke-ai/GFPGAN/archive/3f5d2397361199bc4a91c08bb7d80f04d7805615.zip ; platform_system=='Windows'
+https://github.com/invoke-ai/GFPGAN/archive/c796277a1cf77954e5fc0b288d7062d162894248.zip ; platform_system=='Linux' or platform_system=='Darwin'
+https://github.com/Birch-san/k-diffusion/archive/363386981fee88620709cf8f6f2eea167bd6cd74.zip
+https://github.com/invoke-ai/PyPatchMatch/archive/129863937a8ab37f6bbcec327c994c0f932abdbc.zip

docs/CHANGELOG.md

@@ -4,236 +4,6 @@ title: Changelog
 
 # :octicons-log-16: **Changelog**
 
-## v2.3.5 <small>(22 May 2023)</small>
-
-This release (along with the post1 and post2 follow-on releases) expands support for additional LoRA and LyCORIS models, upgrades diffusers versions, and fixes a few bugs.
-
-### LoRA and LyCORIS Support Improvement
-
-    A number of LoRA/LyCORIS fine-tune files (those which alter the text encoder as well as the unet model) were not having the desired effect in InvokeAI. This bug has now been fixed. Full documentation of LoRA support is available at InvokeAI LoRA Support.
-    Previously, InvokeAI did not distinguish between LoRA/LyCORIS models based on Stable Diffusion v1.5 vs those based on v2.0 and 2.1, leading to a crash when an incompatible model was loaded. This has now been fixed. In addition, the web pulldown menus for LoRA and Textual Inversion selection have been enhanced to show only those files that are compatible with the currently-selected Stable Diffusion model.
-    Support for the newer LoKR LyCORIS files has been added.
-
-### Library Updates and Speed/Reproducibility Advancements
-The major enhancement in this version is that NVIDIA users no longer need to decide between speed and reproducibility. Previously, if you activated the Xformers library, you would see improvements in speed and memory usage, but multiple images generated with the same seed and other parameters would be slightly different from each other. This is no longer the case. Relative to 2.3.5 you will see improved performance when running without Xformers, and even better performance when Xformers is activated. In both cases, images generated with the same settings will be identical.
-
-Here are the new library versions:
-Library 	Version
-Torch 	2.0.0
-Diffusers 	0.16.1
-Xformers 	0.0.19
-Compel 	1.1.5
-Other Improvements
-
-### Performance Improvements
-
-    When a model is loaded for the first time, InvokeAI calculates its checksum for incorporation into the PNG metadata. This process could take up to a minute on network-mounted disks and WSL mounts. This release noticeably speeds up the process.
-
-### Bug Fixes
-
-    The "import models from directory" and "import from URL" functionality in the console-based model installer has now been fixed.
-    When running the WebUI, we have reduced the number of times that InvokeAI reaches out to HuggingFace to fetch the list of embeddable Textual Inversion models. We have also caught and fixed a problem with the updater not correctly detecting when another instance of the updater is running 
-
-
-## v2.3.4 <small>(7 April 2023)</small>
-
-What's New in 2.3.4
-
-This features release adds support for LoRA (Low-Rank Adaptation) and LyCORIS (Lora beYond Conventional) models, as well as some minor bug fixes.
-### LoRA and LyCORIS Support
-
-LoRA files contain fine-tuning weights that enable particular styles, subjects or concepts to be applied to generated images. LyCORIS files are an extended variant of LoRA. InvokeAI supports the most common LoRA/LyCORIS format, which ends in the suffix .safetensors. You will find numerous LoRA and LyCORIS models for download at Civitai, and a small but growing number at Hugging Face. Full documentation of LoRA support is available at InvokeAI LoRA Support.( Pre-release note: this page will only be available after release)
-
-To use LoRA/LyCORIS models in InvokeAI:
-
-    Download the .safetensors files of your choice and place in /path/to/invokeai/loras. This directory was not present in earlier version of InvokeAI but will be created for you the first time you run the command-line or web client. You can also create the directory manually.
-
-    Add withLora(lora-file,weight) to your prompts. The weight is optional and will default to 1.0. A few examples, assuming that a LoRA file named loras/sushi.safetensors is present:
-
-family sitting at dinner table eating sushi withLora(sushi,0.9)
-family sitting at dinner table eating sushi withLora(sushi, 0.75)
-family sitting at dinner table eating sushi withLora(sushi)
-
-Multiple withLora() prompt fragments are allowed. The weight can be arbitrarily large, but the useful range is roughly 0.5 to 1.0. Higher weights make the LoRA's influence stronger. Negative weights are also allowed, which can lead to some interesting effects.
-
-    Generate as you usually would! If you find that the image is too "crisp" try reducing the overall CFG value or reducing individual LoRA weights. As is the case with all fine-tunes, you'll get the best results when running the LoRA on top of the model similar to, or identical with, the one that was used during the LoRA's training. Don't try to load a SD 1.x-trained LoRA into a SD 2.x model, and vice versa. This will trigger a non-fatal error message and generation will not proceed.
-
-    You can change the location of the loras directory by passing the --lora_directory option to `invokeai.
-
-### New WebUI LoRA and Textual Inversion Buttons
-
-This version adds two new web interface buttons for inserting LoRA and Textual Inversion triggers into the prompt as shown in the screenshot below.
-
-Clicking on one or the other of the buttons will bring up a menu of available LoRA/LyCORIS or Textual Inversion trigger terms. Select a menu item to insert the properly-formatted withLora() or <textual-inversion> prompt fragment into the positive prompt. The number in parentheses indicates the number of trigger terms currently in the prompt. You may click the button again and deselect the LoRA or trigger to remove it from the prompt, or simply edit the prompt directly.
-
-Currently terms are inserted into the positive prompt textbox only. However, some textual inversion embeddings are designed to be used with negative prompts. To move a textual inversion trigger into the negative prompt, simply cut and paste it.
-
-By default the Textual Inversion menu only shows locally installed models found at startup time in /path/to/invokeai/embeddings. However, InvokeAI has the ability to dynamically download and install additional Textual Inversion embeddings from the HuggingFace Concepts Library. You may choose to display the most popular of these (with five or more likes) in the Textual Inversion menu by going to Settings and turning on "Show Textual Inversions from HF Concepts Library." When this option is activated, the locally-installed TI embeddings will be shown first, followed by uninstalled terms from Hugging Face. See The Hugging Face Concepts Library and Importing Textual Inversion files for more information.
-### Minor features and fixes
-
-This release changes model switching behavior so that the command-line and Web UIs save the last model used and restore it the next time they are launched. It also improves the behavior of the installer so that the pip utility is kept up to date.
-  
-### Known Bugs in 2.3.4
-
-These are known bugs in the release.
-
-    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
-    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
-
-
-## v2.3.3 <small>(28 March 2023)</small>
-
-This is a bugfix and minor feature release.
-### Bugfixes
-
-Since version 2.3.2 the following bugs have been fixed:
-Bugs
-
-    When using legacy checkpoints with an external VAE, the VAE file is now scanned for malware prior to loading. Previously only the main model weights file was scanned.
-    Textual inversion will select an appropriate batchsize based on whether xformers is active, and will default to xformers enabled if the library is detected.
-    The batch script log file names have been fixed to be compatible with Windows.
-    Occasional corruption of the .next_prefix file (which stores the next output file name in sequence) on Windows systems is now detected and corrected.
-    Support loading of legacy config files that have no personalization (textual inversion) section.
-    An infinite loop when opening the developer's console from within the invoke.sh script has been corrected.
-    Documentation fixes, including a recipe for detecting and fixing problems with the AMD GPU ROCm driver.
-
-Enhancements
-
-    It is now possible to load and run several community-contributed SD-2.0 based models, including the often-requested "Illuminati" model.
-    The "NegativePrompts" embedding file, and others like it, can now be loaded by placing it in the InvokeAI embeddings directory.
-    If no --model is specified at launch time, InvokeAI will remember the last model used and restore it the next time it is launched.
-    On Linux systems, the invoke.sh launcher now uses a prettier console-based interface. To take advantage of it, install the dialog package using your package manager (e.g. sudo apt install dialog).
-    When loading legacy models (safetensors/ckpt) you can specify a custom config file and/or a VAE by placing like-named files in the same directory as the model following this example:
-
-my-favorite-model.ckpt
-my-favorite-model.yaml
-my-favorite-model.vae.pt      # or my-favorite-model.vae.safetensors
-
-### Known Bugs in 2.3.3
-
-These are known bugs in the release.
-
-    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
-    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
-
-
-## v2.3.2 <small>(11 March 2023)</small>
-This is a bugfix and minor feature release.
-
-### Bugfixes
-
-Since version 2.3.1 the following bugs have been fixed:
-
-    Black images appearing for potential NSFW images when generating with legacy checkpoint models and both --no-nsfw_checker and --ckpt_convert turned on.
-    Black images appearing when generating from models fine-tuned on Stable-Diffusion-2-1-base. When importing V2-derived models, you may be asked to select whether the model was derived from a "base" model (512 pixels) or the 768-pixel SD-2.1 model.
-    The "Use All" button was not restoring the Hi-Res Fix setting on the WebUI
-    When using the model installer console app, models failed to import correctly when importing from directories with spaces in their names. A similar issue with the output directory was also fixed.
-    Crashes that occurred during model merging.
-    Restore previous naming of Stable Diffusion base and 768 models.
-    Upgraded to latest versions of diffusers, transformers, safetensors and accelerate libraries upstream. We hope that this will fix the assertion NDArray > 2**32 issue that MacOS users have had when generating images larger than 768x768 pixels. Please report back.
-
-As part of the upgrade to diffusers, the location of the diffusers-based models has changed from models/diffusers to models/hub. When you launch InvokeAI for the first time, it will prompt you to OK a one-time move. This should be quick and harmless, but if you have modified your models/diffusers directory in some way, for example using symlinks, you may wish to cancel the migration and make appropriate adjustments.
-New "Invokeai-batch" script
-
-### Invoke AI Batch
-2.3.2 introduces a new command-line only script called invokeai-batch that can be used to generate hundreds of images from prompts and settings that vary systematically. This can be used to try the same prompt across multiple combinations of models, steps, CFG settings and so forth. It also allows you to template prompts and generate a combinatorial list like:
-
-a shack in the mountains, photograph
-a shack in the mountains, watercolor
-a shack in the mountains, oil painting
-a chalet in the mountains, photograph
-a chalet in the mountains, watercolor
-a chalet in the mountains, oil painting
-a shack in the desert, photograph
-...
-
-If you have a system with multiple GPUs, or a single GPU with lots of VRAM, you can parallelize generation across the combinatorial set, reducing wait times and using your system's resources efficiently (make sure you have good GPU cooling).
-
-To try invokeai-batch out. Launch the "developer's console" using the invoke launcher script, or activate the invokeai virtual environment manually. From the console, give the command invokeai-batch --help in order to learn how the script works and create your first template file for dynamic prompt generation.
-
-
-### Known Bugs in 2.3.2
-
-These are known bugs in the release.
-
-    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
-    Windows Defender will sometimes raise a Trojan alert for the codeformer.pth face restoration model. As far as we have been able to determine, this is a false positive and can be safely whitelisted.
-
-
-## v2.3.1 <small>(22 February 2023)</small>
-This is primarily a bugfix release, but it does provide several new features that will improve the user experience.
-
-### Enhanced support for model management
-
-InvokeAI now makes it convenient to add, remove and modify models. You can individually import models that are stored on your local system, scan an entire folder and its subfolders for models and import them automatically, and even directly import models from the internet by providing their download URLs. You also have the option of designating a local folder to scan for new models each time InvokeAI is restarted.
-
-There are three ways of accessing the model management features:
-
-    From the WebUI, click on the cube to the right of the model selection menu. This will bring up a form that allows you to import models individually from your local disk or scan a directory for models to import.
-
-    Using the Model Installer App
-
-Choose option (5) download and install models from the invoke launcher script to start a new console-based application for model management. You can use this to select from a curated set of starter models, or import checkpoint, safetensors, and diffusers models from a local disk or the internet. The example below shows importing two checkpoint URLs from popular SD sites and a HuggingFace diffusers model using its Repository ID. It also shows how to designate a folder to be scanned at startup time for new models to import.
-
-Command-line users can start this app using the command invokeai-model-install.
-
-    Using the Command Line Client (CLI)
-
-The !install_model and !convert_model commands have been enhanced to allow entering of URLs and local directories to scan and import. The first command installs .ckpt and .safetensors files as-is. The second one converts them into the faster diffusers format before installation.
-
-Internally InvokeAI is able to probe the contents of a .ckpt or .safetensors file to distinguish among v1.x, v2.x and inpainting models. This means that you do not need to include "inpaint" in your model names to use an inpainting model. Note that Stable Diffusion v2.x models will be autoconverted into a diffusers model the first time you use it.
-
-Please see INSTALLING MODELS for more information on model management.
-
-### An Improved Installer Experience
-
-The installer now launches a console-based UI for setting and changing commonly-used startup options:
-
-After selecting the desired options, the installer installs several support models needed by InvokeAI's face reconstruction and upscaling features and then launches the interface for selecting and installing models shown earlier. At any time, you can edit the startup options by launching invoke.sh/invoke.bat and entering option (6) change InvokeAI startup options
-
-Command-line users can launch the new configure app using invokeai-configure.
-
-This release also comes with a renewed updater. To do an update without going through a whole reinstallation, launch invoke.sh or invoke.bat and choose option (9) update InvokeAI . This will bring you to a screen that prompts you to update to the latest released version, to the most current development version, or any released or unreleased version you choose by selecting the tag or branch of the desired version.
-
-Command-line users can run this interface by typing invokeai-configure
-
-### Image Symmetry Options
-
-There are now features to generate horizontal and vertical symmetry during generation. The way these work is to wait until a selected step in the generation process and then to turn on a mirror image effect. In addition to generating some cool images, you can also use this to make side-by-side comparisons of how an image will look with more or fewer steps. Access this option from the WebUI by selecting Symmetry from the image generation settings, or within the CLI by using the options --h_symmetry_time_pct and --v_symmetry_time_pct (these can be abbreviated to --h_sym and --v_sym like all other options).
-
-### A New Unified Canvas Look
-
-This release introduces a beta version of the WebUI Unified Canvas. To try it out, open up the settings dialogue in the WebUI (gear icon) and select Use Canvas Beta Layout:
-
-Refresh the screen and go to to Unified Canvas (left side of screen, third icon from the top). The new layout is designed to provide more space to work in and to keep the image controls close to the image itself:
-
-Model conversion and merging within the WebUI
-
-The WebUI now has an intuitive interface for model merging, as well as for permanent conversion of models from legacy .ckpt/.safetensors formats into diffusers format. These options are also available directly from the invoke.sh/invoke.bat scripts.
-An easier way to contribute translations to the WebUI
-
-We have migrated our translation efforts to Weblate, a FOSS translation product. Maintaining the growing project's translations is now far simpler for the maintainers and community. Please review our brief translation guide for more information on how to contribute.
-Numerous internal bugfixes and performance issues
-
-### Bug Fixes
-This releases quashes multiple bugs that were reported in 2.3.0. Major internal changes include upgrading to diffusers 0.13.0, and using the compel library for prompt parsing. See Detailed Change Log for a detailed list of bugs caught and squished.
-Summary of InvokeAI command line scripts (all accessible via the launcher menu)
-Command 	Description
-invokeai 	Command line interface
-invokeai --web 	Web interface
-invokeai-model-install 	Model installer with console forms-based front end
-invokeai-ti --gui 	Textual inversion, with a console forms-based front end
-invokeai-merge --gui 	Model merging, with a console forms-based front end
-invokeai-configure 	Startup configuration; can also be used to reinstall support models
-invokeai-update 	InvokeAI software updater
-
-### Known Bugs in 2.3.1
-
-These are known bugs in the release.
-    MacOS users generating 768x768 pixel images or greater using diffusers models may experience a hard crash with assertion NDArray > 2**32 This appears to be an issu...
-
-
-
 ## v2.3.0 <small>(15 January 2023)</small>
 
 **Transition to diffusers
@@ -494,7 +264,7 @@ sections describe what's new for InvokeAI.
   [Manual Installation](installation/020_INSTALL_MANUAL.md).
 - The ability to save frequently-used startup options (model to load, steps,
   sampler, etc) in a `.invokeai` file. See
-  [Client](deprecated/CLI.md)
+  [Client](features/CLI.md)
 - Support for AMD GPU cards (non-CUDA) on Linux machines.
 - Multiple bugs and edge cases squashed.
 
@@ -617,7 +387,7 @@ sections describe what's new for InvokeAI.
 - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for
   backward compatibility.
 - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
-- Support for [inpainting](deprecated/INPAINTING.md) and
+- Support for [inpainting](features/INPAINTING.md) and
   [outpainting](features/OUTPAINTING.md)
 - img2img runs on all k\* samplers
 - Support for
@@ -629,7 +399,7 @@ sections describe what's new for InvokeAI.
   using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E
   infinite canvas), and "embiggen" upscaling. See the `!fix` command.
 - New `--hires` option on `invoke>` line allows
-  [larger images to be created without duplicating elements](deprecated/CLI.md#this-is-an-example-of-txt2img),
+  [larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img),
   at the cost of some performance.
 - New `--perlin` and `--threshold` options allow you to add and control
   variation during image generation (see
@@ -638,7 +408,7 @@ sections describe what's new for InvokeAI.
   of images and tweaking of previous settings.
 - Command-line completion in `invoke.py` now works on Windows, Linux and Mac
   platforms.
-- Improved [command-line completion behavior](deprecated/CLI.md) New commands
+- Improved [command-line completion behavior](features/CLI.md) New commands
   added:
   - List command-line history with `!history`
   - Search command-line history with `!search`

docs/contributing/CONTRIBUTING.md

@@ -1,54 +0,0 @@
-## Welcome to Invoke AI
-
-We're thrilled to have you here and we're excited for you to contribute. 
-
-Invoke AI originated as a project built by the community, and that vision carries forward today as we aim to build the best pro-grade tools available. We work together to incorporate the latest in AI/ML research, making these tools available in over 20 languages to artists and creatives around the world as part of our fully permissive OSS project designed for individual users to self-host and use.
-
-Here are some guidelines to help you get started:
-
-### Technical Prerequisites
-
-Front-end: You'll need a working knowledge of React and TypeScript.
-
-Back-end: Depending on the scope of your contribution, you may need to know SQLite, FastAPI, Python, and Socketio. Also, a good majority of the backend logic involved in processing images is built in a modular way using a concept called "Nodes", which are isolated functions that carry out individual, discrete operations. This design allows for easy contributions of novel pipelines and capabilities.
-
-### How to Submit Contributions
-
-To start contributing, please follow these steps:
-
-1. Familiarize yourself with our roadmap and open projects to see where your skills and interests align. These documents can serve as a source of inspiration.
-2. Open a Pull Request (PR) with a clear description of the feature you're adding or the problem you're solving. Make sure your contribution aligns with the project's vision.
-3. Adhere to general best practices. This includes assuming interoperability with other nodes, keeping the scope of your functions as small as possible, and organizing your code according to our architecture documents.
-
-### Types of Contributions We're Looking For
-
-We welcome all contributions that improve the project. Right now, we're especially looking for:
-
-1. Quality of life (QOL) enhancements on the front-end.
-2. New backend capabilities added through nodes.
-3. Incorporating additional optimizations from the broader open-source software community.
-
-### Communication and Decision-making Process
-
-Project maintainers and code owners review PRs to ensure they align with the project's goals. They may provide design or architectural guidance, suggestions on user experience, or provide more significant feedback on the contribution itself. Expect to receive feedback on your submissions, and don't hesitate to ask questions or propose changes.
-
-For more robust discussions, or if you're planning to add capabilities not currently listed on our roadmap, please reach out to us on our Discord server. That way, we can ensure your proposed contribution aligns with the project's direction before you start writing code.
-
-### Code of Conduct and Contribution Expectations
-
-We want everyone in our community to have a positive experience. To facilitate this, we've established a code of conduct and a statement of values that we expect all contributors to adhere to. Please take a moment to review these documents—they're essential to maintaining a respectful and inclusive environment.
-
-By making a contribution to this project, you certify that:
-
-1. The contribution was created in whole or in part by you and you have the right to submit it under the open-source license indicated in this project’s GitHub repository; or
-2. The contribution is based upon previous work that, to the best of your knowledge, is covered under an appropriate open-source license and you have the right under that license to submit that work with modifications, whether created in whole or in part by you, under the same open-source license (unless you are permitted to submit under a different license); or
-3. The contribution was provided directly to you by some other person who certified (1) or (2) and you have not modified it; or
-4. You understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information you submit with it, including your sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open-source license(s) involved.
-
-This disclaimer is not a license and does not grant any rights or permissions. You must obtain necessary permissions and licenses, including from third parties, before contributing to this project.
-
-This disclaimer is provided "as is" without warranty of any kind, whether expressed or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, or non-infringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the contribution or the use or other dealings in the contribution.
-
----
-
-Remember, your contributions help make this project great. We're excited to see what you'll bring to our community!

docs/contributing/INVOCATIONS.md

@@ -19,56 +19,31 @@ An invocation looks like this:
 ```py
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
-
-    # fmt: off
-    type: Literal["upscale"] = "upscale"
+    type: Literal['upscale'] = 'upscale'
 
     # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
-    strength: float                = Field(default=0.75, gt=0, le=1, description="The strength")
-    level: Literal[2, 4]           = Field(default=2, description="The upscale level")
-    # fmt: on
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["upscaling", "image"],
-            },
-        }
+    image: Union[ImageField,None] = Field(description="The input image")
+    strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2,4]           = Field(default=2, description = "The upscale level")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
-        results = context.services.restoration.upscale_and_reconstruct(
-            image_list=[[image, 0]],
-            upscale=(self.level, self.strength),
-            strength=0.0,  # GFPGAN strength
-            save_original=False,
-            image_callback=None,
+        image = context.services.images.get(self.image.image_type, self.image.image_name)
+        results = context.services.generate.upscale_and_reconstruct(
+            image_list     = [[image, 0]],
+            upscale        = (self.level, self.strength),
+            strength       = 0.0, # GFPGAN strength
+            save_original  = False,
+            image_callback = None,
         )
 
         # Results are image and seed, unwrap for now
         # TODO: can this return multiple results?
-        image_dto = context.services.images.create(
-            image=results[0][0],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
+        context.services.images.save(image_type, image_name, results[0][0])
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
-            width=image_dto.width,
-            height=image_dto.height,
+            image = ImageField(image_type = image_type, image_name = image_name)
         )
-
 ```
 
 Each portion is important to implement correctly.
@@ -120,67 +95,25 @@ Finally, note that for all linking, the `type` of the linked fields must match.
 If the `name` also matches, then the field can be **automatically linked** to a
 previous invocation by name and matching.
 
-### Config
-
-```py
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["upscaling", "image"],
-            },
-        }
-```
-
-This is an optional configuration for the invocation. It inherits from
-pydantic's model `Config` class, and it used primarily to customize the
-autogenerated OpenAPI schema.
-
-The UI relies on the OpenAPI schema in two ways:
-
-- An API client & Typescript types are generated from it. This happens at build
-  time.
-- The node editor parses the schema into a template used by the UI to create the
-  node editor UI. This parsing happens at runtime.
-
-In this example, a `ui` key has been added to the `schema_extra` dict to provide
-some tags for the UI, to facilitate filtering nodes.
-
-See the Schema Generation section below for more information.
-
 ### Invoke Function
 
 ```py
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
-        results = context.services.restoration.upscale_and_reconstruct(
-            image_list=[[image, 0]],
-            upscale=(self.level, self.strength),
-            strength=0.0,  # GFPGAN strength
-            save_original=False,
-            image_callback=None,
+        image = context.services.images.get(self.image.image_type, self.image.image_name)
+        results = context.services.generate.upscale_and_reconstruct(
+            image_list     = [[image, 0]],
+            upscale        = (self.level, self.strength),
+            strength       = 0.0, # GFPGAN strength
+            save_original  = False,
+            image_callback = None,
         )
 
         # Results are image and seed, unwrap for now
-        # TODO: can this return multiple results?
-        image_dto = context.services.images.create(
-            image=results[0][0],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
+        context.services.images.save(image_type, image_name, results[0][0])
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
-            width=image_dto.width,
-            height=image_dto.height,
+            image = ImageField(image_type = image_type, image_name = image_name)
         )
 ```
 
@@ -202,16 +135,9 @@ scenarios. If you need functionality, please provide it as a service in the
 ```py
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
+    type: Literal['image'] = 'image'
 
-    # fmt: off
-    type: Literal["image_output"] = "image_output"
-    image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
-    # fmt: on
-
-    class Config:
-        schema_extra = {"required": ["type", "image", "width", "height"]}
+    image: ImageField = Field(default=None, description="The output image")
 ```
 
 Output classes look like an invocation class without the invoke method. Prefer
@@ -242,36 +168,35 @@ Here's that `ImageOutput` class, without the needed schema customisation:
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
 
-    # fmt: off
-    type: Literal["image_output"] = "image_output"
+    type: Literal["image"] = "image"
     image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
-    # fmt: on
 ```
 
-The OpenAPI schema that results from this `ImageOutput` will have the `type`,
-`image`, `width` and `height` properties marked as optional, even though we know
-they will always have a value.
+The generated OpenAPI schema, and all clients/types generated from it, will have
+the `type` and `image` properties marked as optional, even though we know they
+will always have a value by the time we can interact with them via the API.
+
+Here's the same class, but with the schema customisation added:
 
 ```python
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
 
-    # fmt: off
-    type: Literal["image_output"] = "image_output"
+    type: Literal["image"] = "image"
     image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
-    # fmt: on
 
-    # Add schema customization
     class Config:
-        schema_extra = {"required": ["type", "image", "width", "height"]}
+        schema_extra = {
+            'required': [
+                'type',
+                'image',
+            ]
+        }
 ```
 
-With the customization in place, the schema will now show these properties as
-required, obviating the need for extensive null checks in client code.
+The resultant schema (and any API client or types generated from it) will now
+have see `type` as string literal `"image"` and `image` as an `ImageField`
+object.
 
 See this `pydantic` issue for discussion on this solution:
 <https://github.com/pydantic/pydantic/discussions/4577>

docs/features/CLI.md

@@ -205,14 +205,14 @@ Here are the invoke> command that apply to txt2img:
 | `--seamless`                              |                                           | `False`                                  | Activate seamless tiling for interesting effects                                                                                                                                                                                                 |
 | `--seamless_axes`                         |                                           | `x,y`                                    | Specify which axes to use circular convolution on.                                                                                                                                                                                               |
 | `--log_tokenization`                      | `-t`                                      | `False`                                  | Display a color-coded list of the parsed tokens derived from the prompt                                                                                                                                                                          |
-| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](../features/OTHER.md#weighted-prompts)                                                                                                                                                  |
+| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts)                                                                                                                                                  |
 | `--upscale <int> <float>`                 | `-U <int> <float>`                        | `-U 1 0.75`                              | Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75.                                                                                                                |
 | `--facetool_strength <float>`             | `-G <float> `                             | `-G0`                                    | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0)                                                                                                                               |
 | `--facetool <name>`                       | `-ft <name>`                              | `-ft gfpgan`                             | Select face restoration algorithm to use: gfpgan, codeformer                                                                                                                                                                                     |
 | `--codeformer_fidelity`                   | `-cf <float>`                             | `0.75`                                   | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality                                                                                                     |
 | `--save_original`                         | `-save_orig`                              | `False`                                  | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced.                                                                                                                                             |
-| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](../features/VARIATIONS.md). |
-| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](../features/VARIATIONS.md) for now to use this.                                                                                                                                                           |
+| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
+| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this.                                                                                                                                                           |
 | `--save_intermediates <n>`                |                                           | `None`                                   | Save the image from every nth step into an "intermediates" folder inside the output directory                                                                                                                                                    |
 | `--h_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
 | `--v_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
@@ -257,7 +257,7 @@ additional options:
     by `-M`. You may also supply just a single initial image with the areas
     to overpaint made transparent, but you must be careful not to destroy
     the pixels underneath when you create the transparent areas. See
-    [Inpainting](INPAINTING.md) for details.
+    [Inpainting](./INPAINTING.md) for details.
 
 inpainting accepts all the arguments used for txt2img and img2img, as well as
 the --mask (-M) and --text_mask (-tm) arguments:
@@ -297,7 +297,7 @@ invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
 
 You can load and use hundreds of community-contributed Textual
 Inversion models just by typing the appropriate trigger phrase. Please
-see [Concepts Library](../features/CONCEPTS.md) for more details.
+see [Concepts Library](CONCEPTS.md) for more details.
 
 ## Other Commands
 

docs/features/CONCEPTS.md

@@ -65,21 +65,39 @@ find out what each concept is for, you can browse the
 [Hugging Face concepts library](https://huggingface.co/sd-concepts-library) and
 look at examples of what each concept produces.
 
-To load concepts, you will need to open the Web UI's configuration
-dialogue and activate "Show Textual Inversions from HF Concepts
-Library". This will then add a list of HF Concepts to the dropdown
-"Add Textual Inversion" menu. Select the concept(s) of your choice and
-they will be incorporated into the positive prompt. A few concepts are
-designed for the negative prompt, in which case you can add them to
-the negative prompt box by select the down arrow icon next to the
-textual inversion menu.
+When you have an idea of a concept you wish to try, go to the command-line
+client (CLI) and type a `<` character and the beginning of the Hugging Face
+concept name you wish to load. Press ++tab++, and the CLI will show you all
+matching concepts. You can also type `<` and hit ++tab++ to get a listing of all
+~800 concepts, but be prepared to scroll up to see them all! If there is more
+than one match you can continue to type and ++tab++ until the concept is
+completed.
 
-There are nearly 1000 HF concepts, more than will fit into a menu. For
-this reason we only show the most popular concepts (those which have
-received 5 or more likes). If you wish to use a concept that is not on
-the list, you may simply type its name surrounded by brackets. For
-example, to load the concept named "xidiversity", add `<xidiversity>`
-to the positive or negative prompt text.
+!!! example
+
+    if you type in `<x` and hit ++tab++, you'll be prompted with the completions:
+
+    ```py
+    <xatu2>        <xatu>         <xbh>          <xi>           <xidiversity>  <xioboma>      <xuna>         <xyz>
+    ```
+
+    Now type `id` and press ++tab++. It will be autocompleted to `<xidiversity>`
+    because this is a unique match.
+
+    Finish your prompt and generate as usual. You may include multiple concept terms
+    in the prompt.
+
+If you have never used this concept before, you will see a message that the TI
+model is being downloaded and installed. After this, the concept will be saved
+locally (in the `models/sd-concepts-library` directory) for future use.
+
+Several steps happen during downloading and installation, including a scan of
+the file for malicious code. Should any errors occur, you will be warned and the
+concept will fail to load. Generation will then continue treating the trigger
+term as a normal string of characters (e.g. as literal `<ghibli-face>`).
+
+You can also use `<concept-names>` in the WebGUI's prompt textbox. There is no
+autocompletion at this time.
 
 ## Installing your Own TI Files
 
@@ -94,11 +112,18 @@ At startup time, InvokeAI will scan the `embeddings` directory and load any TI
 files it finds there. At startup you will see a message similar to this one:
 
 ```bash
->> Current embedding manager terms: <HOI4-Leader>, <princess-knight>
+>> Current embedding manager terms: *, <HOI4-Leader>, <princess-knight>
 ```
 
-The terms you can use will appear in the "Add Textual Inversion"
-dropdown menu above the HF Concepts.
+Note the `*` trigger term. This is a placeholder term that many early TI
+tutorials taught people to use rather than a more descriptive term.
+Unfortunately, if you have multiple TI files that all use this term, only the
+first one loaded will be triggered by use of the term.
+
+To avoid this problem, you can use the `merge_embeddings.py` script to merge two
+or more TI files together. If it encounters a collision of terms, the script
+will prompt you to select new terms that do not collide. See
+[Textual Inversion](TEXTUAL_INVERSION.md) for details.
 
 ## Further Reading
 

docs/features/CONTROLNET.md

@@ -1,92 +0,0 @@
----
-title: ControlNet
----
-
-# :material-loupe: ControlNet
-
-## ControlNet
-
-ControlNet
-
-ControlNet is a powerful set of features developed by the open-source community (notably, Stanford researcher [**@ilyasviel**](https://github.com/lllyasviel)) that allows you to apply a secondary neural network model to your image generation process in Invoke.
-
-With ControlNet, you can get more control over the output of your image generation, providing you with a way to direct the network towards generating images that better fit your desired style or outcome.
-
-
-### How it works
-
-ControlNet works by analyzing an input image, pre-processing that image to identify relevant information that can be interpreted by each specific ControlNet model, and then inserting that control information into the generation process. This can be used to adjust the style, composition, or other aspects of the image to better achieve a specific result.
-
-
-### Models
-
-As part of the model installation, ControlNet models can be selected including a variety of pre-trained models that have been added to achieve different effects or styles in your generated images. Further ControlNet models may require additional code functionality to also be incorporated into Invoke's Invocations folder. You should expect to follow any installation instructions for ControlNet models loaded  outside the default models provided by Invoke. The default models include:
-
-
-**Canny**:
-
-When the Canny model is used in ControlNet, Invoke will attempt to generate images that match the edges detected. 
-
-Canny edge detection works by detecting the edges in an image by looking for abrupt changes in intensity. It is known for its ability to detect edges accurately while reducing noise and false edges, and the preprocessor can identify more information by decreasing the thresholds.
-
-**M-LSD**: 
-
-M-LSD is another edge detection algorithm used in ControlNet. It stands for Multi-Scale Line Segment Detector. 
-
-It detects straight line segments in an image by analyzing the local structure of the image at multiple scales.  It can be useful for architectural imagery, or anything where straight-line structural information is needed for the resulting output. 
-
-**Lineart**: 
-
-The Lineart model in ControlNet generates line drawings from an input image. The resulting pre-processed image is a simplified version of the original, with only the outlines of objects visible.The Lineart model in ControlNet is known for its ability to accurately capture the contours of the objects in an input sketch. 
-
-**Lineart Anime**: 
-
-A variant of the Lineart model that generates line drawings with a distinct style inspired by anime and manga art styles.
-
-**Depth**: 
-A model that generates depth maps of images, allowing you to create more realistic 3D models or to simulate depth effects in post-processing.
-
-**Normal Map (BAE):** 
-A model that generates normal maps from input images, allowing for more realistic lighting effects in 3D rendering.
-		
-**Image Segmentation**: 
-A model that divides input images into segments or regions, each of which corresponds to a different object or part of the image. (More details coming soon)
-
-
-**Openpose**: 
-The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
-
-**Mediapipe Face**:
-
-The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.
-
-**Tile (experimental)**:
-
-The Tile model fills out details in the image to match the image, rather than the prompt. The Tile Model is a versatile tool that offers a range of functionalities. Its primary capabilities can be boiled down to two main behaviors:
-
-- It can reinterpret specific details within an image and create fresh, new elements.
-- It has the ability to disregard global instructions if there's a discrepancy between them and the local context or specific parts of the image. In such cases, it uses the local context to guide the process.
-
-The Tile Model can be a powerful tool in your arsenal for enhancing image quality and details. If there are undesirable elements in your images, such as blurriness caused by resizing, this model can effectively eliminate these issues, resulting in cleaner, crisper images. Moreover, it can generate and add refined details to your images, improving their overall quality and appeal. 
-
-**Pix2Pix (experimental)**
-
-With Pix2Pix, you can input an image into the controlnet, and then "instruct" the model to change it using your prompt. For example, you can say "Make it winter" to add more wintry elements to a scene.
-
-**Inpaint**: Coming Soon - Currently this model is available but not functional on the Canvas. An upcoming release will provide additional capabilities for using this model when inpainting.
-
-Each of these models can be adjusted and combined with other ControlNet models to achieve different results, giving you even more control over your image generation process.
-
-
-## Using ControlNet
-
-To use ControlNet, you can simply select the desired model and adjust both the ControlNet and Pre-processor settings to achieve the desired result. You can also use multiple ControlNet models at the same time, allowing you to achieve even more complex effects or styles in your generated images.
-
-
-Each ControlNet has two settings that are applied to the ControlNet.
-
-Weight - Strength of the Controlnet model applied to the generation for the section, defined by start/end.
-
-Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
-
-Additionally, each ControlNet section can be expanded in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in when you Invoke.

docs/features/IMG2IMG.md

@@ -4,13 +4,86 @@ title: Image-to-Image
 
 # :material-image-multiple: Image-to-Image
 
-InvokeAI provides an "img2img" feature that lets you seed your
-creations with an initial drawing or photo. This is a really cool
-feature that tells stable diffusion to build the prompt on top of the
-image you provide, preserving the original's basic shape and layout.
+Both the Web and command-line interfaces provide an "img2img" feature
+that lets you seed your creations with an initial drawing or
+photo. This is a really cool feature that tells stable diffusion to
+build the prompt on top of the image you provide, preserving the
+original's basic shape and layout.
 
-For a walkthrough of using Image-to-Image in the Web UI, see [InvokeAI
-Web Server](./WEB.md#image-to-image).
+See the [WebUI Guide](WEB.md) for a walkthrough of the img2img feature
+in the InvokeAI web server. This document describes how to use img2img
+in the command-line tool.
+
+## Basic Usage
+
+Launch the command-line client by launching `invoke.sh`/`invoke.bat`
+and choosing option (1). Alternative, activate the InvokeAI
+environment and issue the command `invokeai`.
+
+Once the `invoke> ` prompt appears, you can start an img2img render by
+pointing to a seed file with the `-I` option as shown here:
+
+!!! example ""
+
+    ```commandline
+    tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
+    ```
+
+    <figure markdown>
+
+    | original image | generated image |
+    | :------------: | :-------------: |
+    | ![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 } | ![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 } |
+
+    </figure>
+
+The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
+(`-f`) controls how much the original will be modified, ranging from `0.0` (keep
+the original intact), to `1.0` (ignore the original completely). The default is
+`0.75`, and ranges from `0.25-0.90` give interesting results. Other relevant
+options include `-C` (classification free guidance scale), and `-s` (steps).
+Unlike `txt2img`, adding steps will continuously change the resulting image and
+it will not converge.
+
+You may also pass a `-v<variation_amount>` option to generate `-n<iterations>`
+count variants on the original image. This is done by passing the first
+generated image back into img2img the requested number of times. It generates
+interesting variants.
+
+Note that the prompt makes a big difference. For example, this slight variation
+on the prompt produces a very different image:
+
+<figure markdown>
+![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png){ width=320 }
+<caption markdown>photograph of a tree on a hill with a river</caption>
+</figure>
+
+!!! tip
+
+    When designing prompts, think about how the images scraped from the internet were
+    captioned. Very few photographs will be labeled "photograph" or "photorealistic."
+    They will, however, be captioned with the publication, photographer, camera model,
+    or film settings.
+
+If the initial image contains transparent regions, then Stable Diffusion will
+only draw within the transparent regions, a process called
+[`inpainting`](./INPAINTING.md#creating-transparent-regions-for-inpainting).
+However, for this to work correctly, the color information underneath the
+transparent needs to be preserved, not erased.
+
+!!! warning "**IMPORTANT ISSUE** "
+
+    `img2img` does not work properly on initial images smaller
+    than 512x512. Please scale your image to at least 512x512 before using it.
+    Larger images are not a problem, but may run out of VRAM on your GPU card. To
+    fix this, use the --fit option, which downscales the initial image to fit within
+    the box specified by width x height:
+
+    ```
+    tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
+    ```
+
+## How does it actually work, though?
 
 The main difference between `img2img` and `prompt2img` is the starting point.
 While `prompt2img` always starts with pure gaussian noise and progressively
@@ -26,6 +99,10 @@ seed `1592514025` develops something like this:
 
 !!! example ""
 
+    ```bash
+    invoke> "fire" -s10 -W384 -H384 -S1592514025
+    ```
+
     <figure markdown>
     ![latent steps](../assets/img2img/000019.steps.png){ width=720 }
     </figure>
@@ -80,8 +157,17 @@ Diffusion has less chance to refine itself, so the result ends up inheriting all
 the problems of my bad drawing.
 
 If you want to try this out yourself, all of these are using a seed of
-`1592514025` with a width/height of `384`, step count `10`, the
-`k_lms` sampler, and the single-word prompt `"fire"`.
+`1592514025` with a width/height of `384`, step count `10`, the default sampler
+(`k_lms`), and the single-word prompt `"fire"`:
+
+```bash
+invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
+```
+
+The code for rendering intermediates is on my (damian0815's) branch
+[document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) -
+run `invoke.py` and check your `outputs/img-samples/intermediates` folder while
+generating an image.
 
 ### Compensating for the reduced step count
 
@@ -94,6 +180,10 @@ give each generation 20 steps.
 Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD
 does `20` steps from my image):
 
+```bash
+invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
+```
+
 <figure markdown>
 ![000035.1592514025](../assets/img2img/000035.1592514025.png)
 </figure>
@@ -101,6 +191,10 @@ does `20` steps from my image):
 and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to
 make sure SD does `20` steps from my image):
 
+```commandline
+invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
+```
+
 <figure markdown>
 ![000046.1592514025](../assets/img2img/000046.1592514025.png)
 </figure>

docs/features/LOGGING.md

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

docs/features/MODEL_MERGING.md

@@ -71,3 +71,6 @@ under the selected name and register it with InvokeAI.
   use InvokeAI conventions - only alphanumeric letters and the
   characters ".+-".
 
+## Caveats
+
+This is a new script and may contain bugs.

docs/features/NSFW.md

@@ -31,22 +31,10 @@ turned on and off on the command line using `--nsfw_checker` and
 
 At installation time, InvokeAI will ask whether the checker should be
 activated by default (neither argument given on the command line). The
-response is stored in the InvokeAI initialization file
-(`invokeai.yaml` in the InvokeAI root directory).  You can change the
-default at any time by opening this file in a text editor and
-changing the line `nsfw_checker:` from true to false or vice-versa:
-
-
-```
-...
-  Features:
-    esrgan: true
-    internet_available: true
-    log_tokenization: false
-    nsfw_checker: true
-    patchmatch: true
-    restore: true
-```
+response is stored in the InvokeAI initialization file (usually
+`.invokeai` in your home directory). You can change the default at any
+time by opening this file in a text editor and commenting or
+uncommenting the line `--nsfw_checker`.
 
 ## Caveats
 
@@ -91,3 +79,11 @@ generates. However, it does write metadata into the PNG data area,
 including the prompt used to generate the image and relevant parameter
 settings. These fields can be examined using the `sd-metadata.py`
 script that comes with the InvokeAI package.
+
+Note that several other Stable Diffusion distributions offer
+wavelet-based "invisible" watermarking. We have experimented with the
+library used to generate these watermarks and have reached the
+conclusion that while the watermarking library may be adding
+watermarks to PNG images, the currently available version is unable to
+retrieve them successfully. If and when a functioning version of the
+library becomes available, we will offer this feature as well.

docs/features/OTHER.md

@@ -18,16 +18,43 @@ Output Example:
 
 ## **Seamless Tiling**
 
-The seamless tiling mode causes generated images to seamlessly tile
-with itself creating repetitive wallpaper-like patterns. To use it,
-activate the Seamless Tiling option in the Web GUI and then select
-whether to tile on the X (horizontal) and/or Y (vertical) axes. Tiling
-will then be active for the next set of generations.
-
-A nice prompt to test seamless tiling with is:
+The seamless tiling mode causes generated images to seamlessly tile with itself. To use it, add the
+`--seamless` option when starting the script which will result in all generated images to tile, or
+for each `invoke>` prompt as shown here:
 
+```python
+invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
 ```
-pond garden with lotus by claude monet"
+
+By default this will tile on both the X and Y axes. However, you can also specify specific axes to tile on with `--seamless_axes`.
+Possible values are `x`, `y`, and `x,y`:
+```python
+invoke> "pond garden with lotus by claude monet" --seamless --seamless_axes=x -s100 -n4
+```
+
+---
+
+## **Shortcuts: Reusing Seeds**
+
+Since it is so common to reuse seeds while refining a prompt, there is now a shortcut as of version
+1.11. Provide a `-S` (or `--seed`) switch of `-1` to use the seed of the most recent image
+generated. If you produced multiple images with the `-n` switch, then you can go back further
+using `-2`, `-3`, etc. up to the first image generated by the previous command. Sorry, but you can't go
+back further than one command.
+
+Here's an example of using this to do a quick refinement. It also illustrates using the new `-G`
+switch to turn on upscaling and face enhancement (see previous section):
+
+```bash
+invoke> a cute child playing hopscotch -G0.5
+[...]
+outputs/img-samples/000039.3498014304.png: "a cute child playing hopscotch" -s50 -W512 -H512 -C7.5 -mk_lms -S3498014304
+
+# I wonder what it will look like if I bump up the steps and set facial enhancement to full strength?
+invoke> a cute child playing hopscotch -G1.0 -s100 -S -1
+reusing previous seed 3498014304
+[...]
+outputs/img-samples/000040.3498014304.png: "a cute child playing hopscotch" -G1.0 -s100 -W512 -H512 -C7.5 -mk_lms -S3498014304
 ```
 
 ---
@@ -46,27 +73,66 @@ This will tell the sampler to invest 25% of its effort on the tabby cat aspect o
 on the white duck aspect (surprisingly, this example actually works). The prompt weights can use any
 combination of integers and floating point numbers, and they do not need to add up to 1.
 
+---
+
+## **Filename Format**
+
+The argument `--fnformat` allows to specify the filename of the
+ image. Supported wildcards are all arguments what can be set such as
+ `perlin`, `seed`, `threshold`, `height`, `width`, `gfpgan_strength`,
+ `sampler_name`, `steps`, `model`, `upscale`, `prompt`, `cfg_scale`,
+ `prefix`.
+
+The following prompt
+```bash
+dream> a red car --steps 25 -C 9.8 --perlin 0.1 --fnformat {prompt}_steps.{steps}_cfg.{cfg_scale}_perlin.{perlin}.png
+```
+
+generates a file with the name: `outputs/img-samples/a red car_steps.25_cfg.9.8_perlin.0.1.png`
+
+---
+
 ## **Thresholding and Perlin Noise Initialization Options**
 
-Under the Noise section of the Web UI, you will find two options named
-Perlin Noise and Noise Threshold. [Perlin
-noise](https://en.wikipedia.org/wiki/Perlin_noise) is a type of
-structured noise used to simulate terrain and other natural
-textures. The slider controls the percentage of perlin noise that will
-be mixed into the image at the beginning of generation. Adding a little
-perlin noise to a generation will alter the image substantially.
-
-The noise threshold limits the range of the latent values during
-sampling and helps combat the oversharpening seem with higher CFG
-scale values.
+Two new options are the thresholding (`--threshold`) and the perlin noise initialization (`--perlin`) options. Thresholding limits the range of the latent values during optimization, which helps combat oversaturation with higher CFG scale values. Perlin noise initialization starts with a percentage (a value ranging from 0 to 1) of perlin noise mixed into the initial noise. Both features allow for more variations and options in the course of generating images.
 
 For better intuition into what these options do in practice:
 
 ![here is a graphic demonstrating them both](../assets/truncation_comparison.jpg)
 
-In generating this graphic, perlin noise at initialization was
-programmatically varied going across on the diagram by values 0.0,
-0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied
-going down from 0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are
-fixed using the prompt "a portrait of a beautiful young lady" a CFG of
-20, 100 steps, and a seed of 1950357039.
+In generating this graphic, perlin noise at initialization was programmatically varied going across on the diagram by values 0.0, 0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied going down from
+0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are fixed, so the initial prompt is as follows (no thresholding or perlin noise):
+
+```bash
+invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 0 --perlin 0
+```
+
+Here's an example of another prompt used when setting the threshold to 5 and perlin noise to 0.2:
+
+```bash
+invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 5 --perlin 0.2
+```
+
+!!! note
+
+    currently the thresholding feature is only implemented for the k-diffusion style samplers, and empirically appears to work best with `k_euler_a` and `k_dpm_2_a`. Using 0 disables thresholding. Using 0 for perlin noise disables using perlin noise for initialization. Finally, using 1 for perlin noise uses only perlin noise for initialization.
+
+---
+
+## **Simplified API**
+
+For programmers who wish to incorporate stable-diffusion into other products, this repository
+includes a simplified API for text to image generation, which lets you create images from a prompt
+in just three lines of code:
+
+```bash
+from ldm.generate import Generate
+g       = Generate()
+outputs = g.txt2img("a unicorn in manhattan")
+```
+
+Outputs is a list of lists in the format [filename1,seed1],[filename2,seed2]...].
+
+Please see the documentation in ldm/generate.py for more information.
+
+---

docs/features/POSTPROCESS.md

@@ -8,6 +8,12 @@ title: Postprocessing
 
 This extension provides the ability to restore faces and upscale images.
 
+Face restoration and upscaling can be applied at the time you generate the
+images, or at any later time against a previously-generated PNG file, using the
+[!fix](#fixing-previously-generated-images) command.
+[Outpainting and outcropping](OUTPAINTING.md) can only be applied after the
+fact.
+
 ## Face Fixing
 
 The default face restoration module is GFPGAN. The default upscale is
@@ -17,7 +23,8 @@ Real-ESRGAN. For an alternative face restoration module, see
 As of version 1.14, environment.yaml will install the Real-ESRGAN package into
 the standard install location for python packages, and will put GFPGAN into a
 subdirectory of "src" in the InvokeAI directory. Upscaling with Real-ESRGAN
-should "just work" without further intervention. Simply indicate the desired scale on
+should "just work" without further intervention. Simply pass the `--upscale`
+(`-U`) option on the `invoke>` command line, or indicate the desired scale on
 the popup in the Web GUI.
 
 **GFPGAN** requires a series of downloadable model files to work. These are
@@ -34,75 +41,48 @@ reconstruction.
 
 ### Upscaling
 
-Open the upscaling dialog by clicking on the "expand" icon located
-above the image display area in the Web UI:
+`-U : <upscaling_factor> <upscaling_strength>`
 
-<figure markdown>
-![upscale1](../assets/features/upscale-dialog.png)
-</figure>
+The upscaling prompt argument takes two values. The first value is a scaling
+factor and should be set to either `2` or `4` only. This will either scale the
+image 2x or 4x respectively using different models.
 
-There are three different upscaling parameters that you can
-adjust. The first is the scale itself, either 2x or 4x.
+You can set the scaling stength between `0` and `1.0` to control intensity of
+the of the scaling. This is handy because AI upscalers generally tend to smooth
+out texture details. If you wish to retain some of those for natural looking
+results, we recommend using values between `0.5 to 0.8`.
 
-The second is the "Denoising Strength." Higher values will smooth out
-the image and remove digital chatter, but may lose fine detail at
-higher values.
-
-Third, "Upscale Strength" allows you to adjust how the You can set the
-scaling stength between `0` and `1.0` to control the intensity of the
-scaling. AI upscalers generally tend to smooth out texture details. If
-you wish to retain some of those for natural looking results, we
-recommend using values between `0.5 to 0.8`.
-
-[This figure](../assets/features/upscaling-montage.png) illustrates
-the effects of denoising and strength. The original image was 512x512,
-4x scaled to 2048x2048. The "original" version on the upper left was
-scaled using simple pixel averaging. The remainder use the ESRGAN
-upscaling algorithm at different levels of denoising and strength.
-
-<figure markdown>
-![upscaling](../assets/features/upscaling-montage.png){ width=720 }
-</figure>
-
-Both denoising and strength default to 0.75.
+If you do not explicitly specify an upscaling_strength, it will default to 0.75.
 
 ### Face Restoration
 
-InvokeAI offers alternative two face restoration algorithms,
-[GFPGAN](https://github.com/TencentARC/GFPGAN) and
-[CodeFormer](https://huggingface.co/spaces/sczhou/CodeFormer). These
-algorithms improve the appearance of faces, particularly eyes and
-mouths. Issues with faces are less common with the latest set of
-Stable Diffusion models than with the original 1.4 release, but the
-restoration algorithms can still make a noticeable improvement in
-certain cases. You can also apply restoration to old photographs you
-upload.
+`-G : <facetool_strength>`
 
-To access face restoration, click the "smiley face" icon in the
-toolbar above the InvokeAI image panel. You will be presented with a
-dialog that offers a choice between the two algorithm and sliders that
-allow you to adjust their parameters. Alternatively, you may open the
-left-hand accordion panel labeled "Face Restoration" and have the
-restoration algorithm of your choice applied to generated images
-automatically.
+This prompt argument controls the strength of the face restoration that is being
+applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.
 
+You can use either one or both without any conflicts. In cases where you use
+both, the image will be first upscaled and then the face restoration process
+will be executed to ensure you get the highest quality facial features.
 
-Like upscaling, there are a number of parameters that adjust the face
-restoration output. GFPGAN has a single parameter, `strength`, which
-controls how much the algorithm is allowed to adjust the
-image. CodeFormer has two parameters, `strength`, and `fidelity`,
-which together control the quality of the output image as described in
-the [CodeFormer project
-page](https://shangchenzhou.com/projects/CodeFormer/). Default values
-are 0.75 for both parameters, which achieves a reasonable balance
-between changing the image too much and not enough.
+`--save_orig`
 
-[This figure](../assets/features/restoration-montage.png) illustrates
-the effects of adjusting GFPGAN and CodeFormer parameters.
+When you use either `-U` or `-G`, the final result you get is upscaled or face
+modified. If you want to save the original Stable Diffusion generation, you can
+use the `-save_orig` prompt argument to save the original unaffected version
+too.
 
-<figure markdown>
-![upscaling](../assets/features/restoration-montage.png){ width=720 }
-</figure>
+### Example Usage
+
+```bash
+invoke> "superman dancing with a panda bear" -U 2 0.6 -G 0.4
+```
+
+This also works with img2img:
+
+```bash
+invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
+```
 
 !!! note
 
@@ -115,8 +95,69 @@ the effects of adjusting GFPGAN and CodeFormer parameters.
     process is complete. While the image generation is taking place, you will still be able to preview
     the base images.
 
+If you wish to stop during the image generation but want to upscale or face
+restore a particular generated image, pass it again with the same prompt and
+generated seed along with the `-U` and `-G` prompt arguments to perform those
+actions.
+
+## CodeFormer Support
+
+This repo also allows you to perform face restoration using
+[CodeFormer](https://github.com/sczhou/CodeFormer).
+
+In order to setup CodeFormer to work, you need to download the models like with
+GFPGAN. You can do this either by running `invokeai-configure` or by manually
+downloading the
+[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
+and saving it to `ldm/invoke/restoration/codeformer/weights` folder.
+
+You can use `-ft` prompt argument to swap between CodeFormer and the default
+GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
+strength of the restoration effect.
+
+### CodeFormer Usage
+
+The following command will perform face restoration with CodeFormer instead of
+the default gfpgan.
+
+`<prompt> -G 0.8 -ft codeformer`
+
+### Other Options
+
+- `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces
+  high quality results but low accuracy and 1 produces lower quality results but
+  higher accuacy to your original face.
+
+The following command will perform face restoration with CodeFormer. CodeFormer
+will output a result that is closely matching to the input face.
+
+`<prompt> -G 1.0 -ft codeformer -cf 0.9`
+
+The following command will perform face restoration with CodeFormer. CodeFormer
+will output a result that is the best restoration possible. This may deviate
+slightly from the original face. This is an excellent option to use in
+situations when there is very little facial data to work with.
+
+`<prompt> -G 1.0 -ft codeformer -cf 0.1`
+
+## Fixing Previously-Generated Images
+
+It is easy to apply face restoration and/or upscaling to any
+previously-generated file. Just use the syntax
+`!fix path/to/file.png <options>`. For example, to apply GFPGAN at strength 0.8
+and upscale 2X for a file named `./outputs/img-samples/000044.2945021133.png`,
+just run:
+
+```bash
+invoke> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
+```
+
+A new file named `000044.2945021133.fixed.png` will be created in the output
+directory. Note that the `!fix` command does not replace the original file,
+unlike the behavior at generate time.
+
 ## How to disable
 
 If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
 you can disable them on the invoke.py command line with the `--no_restore` and
-`--no_esrgan` options, respectively.
+`--no_upscale` options, respectively.

docs/features/PROMPTS.md

@@ -4,12 +4,77 @@ title: Prompting-Features
 
 # :octicons-command-palette-24: Prompting-Features
 
+## **Reading Prompts from a File**
+
+You can automate `invoke.py` by providing a text file with the prompts you want
+to run, one line per prompt. The text file must be composed with a text editor
+(e.g. Notepad) and not a word processor. Each line should look like what you
+would type at the invoke> prompt:
+
+```bash
+"a beautiful sunny day in the park, children playing" -n4 -C10
+"stormy weather on a mountain top, goats grazing" -s100
+"innovative packaging for a squid's dinner" -S137038382
+```
+
+Then pass this file's name to `invoke.py` when you invoke it:
+
+```bash
+python scripts/invoke.py --from_file "/path/to/prompts.txt"
+```
+
+You may also read a series of prompts from standard input by providing
+a filename of `-`. For example, here is a python script that creates a
+matrix of prompts, each one varying slightly:
+
+```bash
+#!/usr/bin/env python
+
+adjectives = ['sunny','rainy','overcast']
+samplers = ['k_lms','k_euler_a','k_heun']
+cfg = [7.5, 9, 11]
+
+for adj in adjectives:
+    for samp in samplers:
+        for cg in cfg:
+            print(f'a {adj} day -A{samp} -C{cg}')
+```
+
+Its output looks like this (abbreviated):
+
+```bash
+a sunny day -Aklms -C7.5
+a sunny day -Aklms -C9
+a sunny day -Aklms -C11
+a sunny day -Ak_euler_a -C7.5
+a sunny day -Ak_euler_a -C9
+...
+a overcast day -Ak_heun -C9
+a overcast day -Ak_heun -C11
+```
+
+To feed it to invoke.py, pass the filename of "-"
+
+```bash
+python matrix.py | python scripts/invoke.py --from_file -
+```
+
+When the script is finished, each of the 27 combinations
+of adjective, sampler and CFG will be executed.
+
+The command-line interface provides `!fetch` and `!replay` commands
+which allow you to read the prompts from a single previously-generated
+image or a whole directory of them, write the prompts to a file, and
+then replay them. Or you can create your own file of prompts and feed
+them to the command-line client from within an interactive session.
+See [Command-Line Interface](CLI.md) for details.
+
+---
+
 ## **Negative and Unconditioned Prompts**
 
-Any words between a pair of square brackets will instruct Stable
-Diffusion to attempt to ban the concept from the generated image. The
-same effect is achieved by placing words in the "Negative Prompts"
-textbox in the Web UI.
+Any words between a pair of square brackets will instruct Stable Diffusion to
+attempt to ban the concept from the generated image.
 
 ```text
 this is a test prompt [not really] to make you understand [cool] how this works.
@@ -22,9 +87,7 @@ Here's a prompt that depicts what it does.
 
 original prompt:
 
-`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve"`
-
-`#!bash parameters: steps=20, dimensions=512x768, CFG=7.5, Scheduler=k_euler_a, seed=1654590180`
+`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
 
@@ -36,8 +99,7 @@ That image has a woman, so if we want the horse without a rider, we can
 influence the image not to have a woman by putting [woman] in the prompt, like
 this:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]"`
-(same parameters as above)
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
 
@@ -48,8 +110,7 @@ this:
 That's nice - but say we also don't want the image to be quite so blue. We can
 add "blue" to the list of negative prompts, so it's now [woman blue]:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]"`
-(same parameters as above)
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
 
@@ -60,8 +121,7 @@ add "blue" to the list of negative prompts, so it's now [woman blue]:
 Getting close - but there's no sense in having a saddle when our horse doesn't
 have a rider, so we'll add one more negative prompt: [woman blue saddle].
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]"`
-(same parameters as above)
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
 
@@ -201,6 +261,19 @@ Prompt2prompt `.swap()` is not compatible with xformers, which will be temporari
 The `prompt2prompt` code is based off
 [bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
 
+Note that `prompt2prompt` is not currently working with the runwayML inpainting
+model, and may never work due to the way this model is set up. If you attempt to
+use `prompt2prompt` you will get the original image back. However, since this
+model is so good at inpainting, a good substitute is to use the `clipseg` text
+masking option:
+
+```bash
+invoke> a fluffy cat eating a hotdog
+Outputs:
+[1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
+invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat
+```
+
 ### Escaping parantheses () and speech marks ""
 
 If the model you are using has parentheses () or speech marks "" as part of its
@@ -301,5 +374,6 @@ summoning up the concept of some sort of scifi creature? Let's find out.
 Indeed, removing the word "hybrid" produces an image that is more like what we'd
 expect.
 
-In conclusion, prompt blending is great for exploring creative space,
-but takes some trial and error to achieve the desired effect.
+In conclusion, prompt blending is great for exploring creative space, but can be
+difficult to direct. A forthcoming release of InvokeAI will feature more
+deterministic prompt weighting.

docs/features/TEXTUAL_INVERSION.md

@@ -46,19 +46,11 @@ start the front end by selecting choice (3):
 
 ```sh
 Do you want to generate images using the
-1: Browser-based UI
-2: Command-line interface
-3: Run textual inversion training
-4: Merge models (diffusers type only)
-5: Download and install models
-6: Change InvokeAI startup options
-7: Re-run the configure script to fix a broken install
-8: Open the developer console
-9: Update InvokeAI
-10: Command-line help
-Q: Quit
-
-Please enter 1-10, Q: [1] 
+1. command-line
+2. browser-based UI
+3. textual inversion training
+4. open the developer console
+Please enter 1, 2, 3, or 4: [1] 3
 ```
 
 From the command line, with the InvokeAI virtual environment active,

docs/features/VARIATIONS.md

@@ -6,7 +6,9 @@ title: Variations
 
 ## Intro
 
-InvokeAI's support for variations enables you to do the following:
+Release 1.13 of SD-Dream adds support for image variations.
+
+You are able to do the following:
 
 1. Generate a series of systematic variations of an image, given a prompt. The
    amount of variation from one image to the next can be controlled.
@@ -28,7 +30,19 @@ The prompt we will use throughout is:
 This will be indicated as `#!bash "prompt"` in the examples below.
 
 First we let SD create a series of images in the usual way, in this case
-requesting six iterations.
+requesting six iterations:
+
+```bash
+invoke> lucy lawless as xena, warrior princess, character portrait, high resolution -n6
+...
+Outputs:
+./outputs/Xena/000001.1579445059.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1579445059
+./outputs/Xena/000001.1880768722.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1880768722
+./outputs/Xena/000001.332057179.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S332057179
+./outputs/Xena/000001.2224800325.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S2224800325
+./outputs/Xena/000001.465250761.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S465250761
+./outputs/Xena/000001.3357757885.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S3357757885
+```
 
 <figure markdown>
 ![var1](../assets/variation_walkthru/000001.3357757885.png)
@@ -39,16 +53,22 @@ requesting six iterations.
 
 ## Step 2 - Generating Variations
 
-Let's try to generate some variations on this image. We select the "*"
-symbol in the line of icons above the image in order to fix the prompt
-and seed. Then we open up the "Variations" section of the generation
-panel and use the slider to set the variation amount to 0.2. The
-higher this value, the more each generated image will differ from the
-previous one.
+Let's try to generate some variations. Using the same seed, we pass the argument
+`-v0.1` (or --variant_amount), which generates a series of variations each
+differing by a variation amount of 0.2. This number ranges from `0` to `1.0`,
+with higher numbers being larger amounts of variation.
 
-Now we run the prompt a second time, requesting six iterations. You
-will see six images that are thematically related to each other. Try
-increasing and decreasing the variation amount and see what happens.
+```bash
+invoke> "prompt" -n6 -S3357757885 -v0.2
+...
+Outputs:
+./outputs/Xena/000002.784039624.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 784039624:0.2 -S3357757885
+./outputs/Xena/000002.3647897225.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.2 -S3357757885
+./outputs/Xena/000002.917731034.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 917731034:0.2 -S3357757885
+./outputs/Xena/000002.4116285959.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 4116285959:0.2 -S3357757885
+./outputs/Xena/000002.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1614299449:0.2 -S3357757885
+./outputs/Xena/000002.1335553075.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1335553075:0.2 -S3357757885
+```
 
 ### **Variation Sub Seeding**
 

docs/features/WEB.md

@@ -299,6 +299,14 @@ initial image" icons are located.
 
 See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
 
+## Parting remarks
+
+This concludes the walkthrough, but there are several more features that you can
+explore. Please check out the [Command Line Interface](CLI.md) documentation for
+further explanation of the advanced features that were not covered here.
+
+The WebUI is only rapid development. Check back regularly for updates!
+
 ## Reference
 
 ### Additional Options
@@ -341,9 +349,11 @@ the settings configured in the toolbar.
 
 See below for additional documentation related to each feature:
 
+- [Core Prompt Settings](./CLI.md)
 - [Variations](./VARIATIONS.md)
 - [Upscaling](./POSTPROCESS.md#upscaling)
 - [Image to Image](./IMG2IMG.md)
+- [Inpainting](./INPAINTING.md)
 - [Other](./OTHER.md)
 
 #### Invocation Gallery

docs/features/index.md

@@ -13,16 +13,28 @@ Build complex scenes by combine and modifying multiple images in a stepwise
 fashion. This feature combines img2img, inpainting and outpainting in
 a single convenient digital artist-optimized user interface.
 
+### * The [Command Line Interface (CLI)](CLI.md)
+Scriptable access to InvokeAI's features.
+
 ## Image Generation
 ### * [Prompt Engineering](PROMPTS.md)
 Get the images you want with the InvokeAI  prompt engineering language.
 
+## * [Post-Processing](POSTPROCESS.md)
+Restore mangled faces and make images larger with upscaling. Also see the [Embiggen Upscaling Guide](EMBIGGEN.md).
+
 ## * The [Concepts Library](CONCEPTS.md)
 Add custom subjects and styles using HuggingFace's repository of embeddings.
 
-### * [Image-to-Image Guide](IMG2IMG.md)
+### * [Image-to-Image Guide for the CLI](IMG2IMG.md)
 Use a seed image to build new creations in the CLI.
 
+### * [Inpainting Guide for the CLI](INPAINTING.md)
+Selectively erase and replace portions of an existing image in the CLI.
+
+### * [Outpainting Guide for the CLI](OUTPAINTING.md)
+Extend the borders of the image with an "outcrop" function within the CLI.
+
 ### * [Generating Variations](VARIATIONS.md)
 Have an image you like and want to generate many more like it? Variations
 are the ticket.
@@ -45,9 +57,6 @@ Personalize models by adding your own style or subjects.
 ## * [The NSFW Checker](NSFW.md)
 Prevent InvokeAI from displaying unwanted racy images.
 
-## * [Controlling Logging](LOGGING.md)
-Control how InvokeAI logs status messages.
-
 ## * [Miscellaneous](OTHER.md)
 Run InvokeAI on Google Colab, generate images with repeating patterns,
 batch process a file of prompts, increase the "creativity" of image

docs/index.md

@@ -13,7 +13,6 @@ title: Home
 
 <div align="center" markdown>
 
-
 [![project logo](assets/invoke_ai_banner.png)](https://github.com/invoke-ai/InvokeAI)
 
 [![discord badge]][discord link]
@@ -68,7 +67,7 @@ title: Home
 implementation of Stable Diffusion, the open source text-to-image and
 image-to-image generator. It provides a streamlined process with various new
 features and options to aid the image generation process. It runs on Windows,
-Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
+Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM.
 
 **Quick links**: [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>]
 [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a
@@ -132,13 +131,17 @@ This method is recommended for those familiar with running Docker containers
 - [WebUI overview](features/WEB.md)
 - [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
 - [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
-
 <!-- separator -->
-
+### The InvokeAI Command Line Interface
+- [Command Line Interace Reference Guide](features/CLI.md)
+<!-- separator -->
 ### Image Management
 - [Image2Image](features/IMG2IMG.md)
+- [Inpainting](features/INPAINTING.md)
+- [Outpainting](features/OUTPAINTING.md)
 - [Adding custom styles and subjects](features/CONCEPTS.md)
 - [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
+- [Embiggen upscaling](features/EMBIGGEN.md)
 - [Other Features](features/OTHER.md)
 
 <!-- separator -->
@@ -153,60 +156,83 @@ This method is recommended for those familiar with running Docker containers
 - [Prompt Syntax](features/PROMPTS.md)
 - [Generating Variations](features/VARIATIONS.md)
 
-## :octicons-log-16: Important Changes Since Version 2.3
+## :octicons-log-16: Latest Changes
 
-### Nodes
+### v2.3.0 <small>(9 February 2023)</small>
 
-Behind the scenes, InvokeAI has been completely rewritten to support
-"nodes," small unitary operations that can be combined into graphs to
-form arbitrary workflows. For example, there is a prompt node that
-processes the prompt string and feeds it to a text2latent node that
-generates a latent image. The latents are then fed to a latent2image
-node that translates the latent image into a PNG.
+#### Migration to Stable Diffusion `diffusers` models
 
-The WebGUI has a node editor that allows you to graphically design and
-execute custom node graphs. The ability to save and load graphs is
-still a work in progress, but coming soon.
+Previous versions of InvokeAI supported the original model file format introduced with Stable Diffusion 1.4. In the original format, known variously as "checkpoint", or "legacy" format, there is a single large weights file ending with `.ckpt` or `.safetensors`. Though this format has served the community well, it has a number of disadvantages, including file size, slow loading times, and a variety of non-standard variants that require special-case code to handle. In addition, because checkpoint files are actually a bundle of multiple machine learning sub-models, it is hard to swap different sub-models in and out, or to share common sub-models. A new format, introduced by the StabilityAI company in collaboration with HuggingFace, is called `diffusers` and consists of a directory of individual models. The most immediate benefit of `diffusers` is that they load from disk very quickly. A longer term benefit is that in the near future `diffusers` models will be able to share common sub-models, dramatically reducing disk space when you have multiple fine-tune models derived from the same base.
 
-### Command-Line Interface Retired
+When you perform a new install of version 2.3.0, you will be offered the option to install the `diffusers` versions of a number of popular SD models, including Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of 2.1). These will act and work just like the checkpoint versions. Do not be concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk! InvokeAI 2.3.0 can still load these and generate images from them without any extra intervention on your part.
 
-The original "invokeai" command-line interface has been retired. The
-`invokeai` command will now launch a new command-line client that can
-be used by developers to create and test nodes. It is not intended to
-be used for routine image generation or manipulation.
+To take advantage of the optimized loading times of `diffusers` models, InvokeAI offers options to convert legacy checkpoint models into optimized `diffusers` models. If you use the `invokeai` command line interface, the relevant commands are:
 
-To launch the Web GUI from the command-line, use the command
-`invokeai-web` rather than the traditional `invokeai --web`.
+* `!convert_model` -- Take the path to a local checkpoint file or a URL that is pointing to one, convert it into a `diffusers` model, and import it into InvokeAI's models registry file.
+* `!optimize_model` -- If you already have a checkpoint model in your InvokeAI models file, this command will accept its short name and convert it into a like-named `diffusers` model, optionally deleting the original checkpoint file.
+* `!import_model` -- Take the local path of either a checkpoint file or a `diffusers` model directory and import it into InvokeAI's registry file. You may also provide the ID of any diffusers model that has been published on the [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads) and it will be downloaded and installed automatically.
 
-### ControlNet
+The WebGUI offers similar functionality for model management.
 
-This version of InvokeAI features ControlNet, a system that allows you
-to achieve exact poses for human and animal figures by providing a
-model to follow. Full details are found in [ControlNet](features/CONTROLNET.md)
+For advanced users, new command-line options provide additional functionality. Launching `invokeai` with the argument `--autoconvert <path to directory>` takes the path to a directory of checkpoint files, automatically converts them into `diffusers` models and imports them. Each time the script is launched, the directory will be scanned for new checkpoint files to be loaded. Alternatively, the `--ckpt_convert` argument will cause any checkpoint or safetensors model that is already registered with InvokeAI to be converted into a `diffusers` model on the fly, allowing you to take advantage of future diffusers-only features without explicitly converting the model and saving it to disk.
 
-### New Schedulers
+Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management in both the command-line and Web interfaces.
 
-The list of schedulers has been completely revamped and brought up to date:
+#### Support for the `XFormers` Memory-Efficient Crossattention Package
 
-| **Short Name** | **Scheduler**                   | **Notes**                   |
-|----------------|---------------------------------|-----------------------------|
-| **ddim**       | DDIMScheduler                   |                             |
-| **ddpm**       | DDPMScheduler                   |                             |
-| **deis**       | DEISMultistepScheduler          |                             |
-| **lms**        | LMSDiscreteScheduler            |                             |
-| **pndm**       | PNDMScheduler                   |                             |
-| **heun**       | HeunDiscreteScheduler           | original noise schedule     |
-| **heun_k**     | HeunDiscreteScheduler           | using karras noise schedule |
-| **euler**      | EulerDiscreteScheduler          | original noise schedule     |
-| **euler_k**    | EulerDiscreteScheduler          | using karras noise schedule |
-| **kdpm_2**     | KDPM2DiscreteScheduler          |                             |
-| **kdpm_2_a**   | KDPM2AncestralDiscreteScheduler |                             |
-| **dpmpp_2s**   | DPMSolverSinglestepScheduler    |                             |
-| **dpmpp_2m**   | DPMSolverMultistepScheduler     | original noise scnedule     |
-| **dpmpp_2m_k** | DPMSolverMultistepScheduler     | using karras noise schedule |
-| **unipc**      | UniPCMultistepScheduler         | CPU only                    |
+On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once installed,  the`xformers` package dramatically reduces the memory footprint of loaded Stable Diffusion models files and modestly increases image generation speed. `xformers` will be installed and activated automatically if you specify a CUDA system at install time.
 
-Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details.
+The caveat with using `xformers` is that it introduces slightly non-deterministic behavior, and images generated using the same seed and other settings will be subtly different between invocations. Generally the changes are unnoticeable unless you rapidly shift back and forth between images, but to disable `xformers` and restore fully deterministic behavior, you may launch InvokeAI using the `--no-xformers` option. This is most conveniently done by opening the file `invokeai/invokeai.init` with a text editor, and adding the line `--no-xformers` at the bottom.
+
+#### A Negative Prompt Box in the WebUI
+
+There is now a separate text input box for negative prompts in the WebUI. This is convenient for stashing frequently-used negative prompts ("mangled limbs, bad anatomy"). The `[negative prompt]` syntax continues to work in the main prompt box as well.
+
+To see exactly how your prompts are being parsed, launch `invokeai` with the `--log_tokenization` option. The console window will then display the tokenization process for both positive and negative prompts.
+
+#### Model Merging
+
+Version 2.3.0 offers an intuitive user interface for merging up to three Stable Diffusion models using an intuitive user interface. Model merging allows you to mix the behavior of models to achieve very interesting effects. To use this, each of the models must already be imported into InvokeAI and saved in `diffusers` format, then launch the merger using a new menu item in the InvokeAI launcher script (`invoke.sh`, `invoke.bat`) or directly from the command line with `invokeai-merge --gui`. You will be prompted to select the models to merge, the proportions in which to mix them, and the mixing algorithm. The script will create a new merged `diffusers` model and import it into InvokeAI for your use.
+
+See [MODEL MERGING](https://invoke-ai.github.io/InvokeAI/features/MODEL_MERGING/) for more details.
+
+#### Textual Inversion Training
+
+Textual Inversion (TI) is a technique for training a Stable Diffusion model to emit a particular subject or style when triggered by a keyword phrase. You can perform TI training by placing a small number of images of the subject or style in a directory, and choosing a distinctive trigger phrase, such as "pointillist-style". After successful training, The subject or style will be activated by including `<pointillist-style>` in your prompt.
+
+Previous versions of InvokeAI were able to perform TI, but it required using a command-line script with dozens of obscure command-line arguments. Version 2.3.0 features an intuitive TI frontend that will build a TI model on top of any `diffusers` model. To access training you can launch from a new item in the launcher script or from the command line using `invokeai-ti --gui`.
+
+See [TEXTUAL INVERSION](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/) for further details.
+
+#### A New Installer Experience
+
+The InvokeAI installer has been upgraded in order to provide a smoother and hopefully more glitch-free experience. In addition, InvokeAI is now packaged as a PyPi project, allowing developers and power-users to install InvokeAI with the command `pip install InvokeAI  --use-pep517`. Please see [Installation](#installation) for details.
+
+Developers should be aware that the `pip` installation procedure has been simplified and that the `conda` method is no longer supported at all. Accordingly, the `environments_and_requirements` directory has been deleted from the repository.
+
+#### Command-line name changes
+
+All of InvokeAI's functionality, including the WebUI, command-line interface, textual inversion training and model merging, can all be accessed from the `invoke.sh` and `invoke.bat` launcher scripts. The menu of options has been expanded to add the new functionality. For the convenience of developers and power users, we have normalized the names of the InvokeAI command-line scripts:
+
+* `invokeai` -- Command-line client
+* `invokeai --web` -- Web GUI
+* `invokeai-merge --gui` -- Model merging script with graphical front end
+* `invokeai-ti --gui` -- Textual inversion script with graphical front end
+* `invokeai-configure` -- Configuration tool for initializing the `invokeai` directory and selecting popular starter models.
+
+For backward compatibility, the old command names are also recognized, including `invoke.py` and `configure-invokeai.py`. However, these are deprecated and will eventually be removed.
+
+Developers should be aware that the locations of the script's source code has been moved. The new locations are:
+* `invokeai` =>  `ldm/invoke/CLI.py`
+* `invokeai-configure` => `ldm/invoke/config/configure_invokeai.py`
+* `invokeai-ti`=> `ldm/invoke/training/textual_inversion.py`
+* `invokeai-merge` => `ldm/invoke/merge_diffusers`
+
+Developers are strongly encouraged to perform an "editable" install of InvokeAI using `pip install -e .  --use-pep517` in the Git repository, and then to call the scripts using their 2.3.0 names, rather than executing the scripts directly. Developers should also be aware that the several important data files have been relocated into a new directory named `invokeai`. This includes the WebGUI's `frontend` and `backend` directories, and the `INITIAL_MODELS.yaml` files used by the installer to select starter models. Eventually all InvokeAI modules will be in subdirectories of `invokeai`.
+
+Please see [2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0) for further details.
+For older changelogs, please visit the
+**[CHANGELOG](CHANGELOG/#v223-2-december-2022)**.
 
 ## :material-target: Troubleshooting
 
@@ -242,3 +268,8 @@ free to send me an email if you use and like the script.
 Original portions of the software are Copyright (c) 2022-23
 by [The InvokeAI Team](https://github.com/invoke-ai).
 
+## :octicons-book-24: Further Reading
+
+Please see the original README for more information on this software and
+underlying algorithm, located in the file
+[README-CompViz.md](other/README-CompViz.md).

docs/installation/010_INSTALL_AUTOMATED.md

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

docs/installation/020_INSTALL_MANUAL.md

@@ -216,7 +216,7 @@ manager, please follow these steps:
 9.  Run the command-line- or the web- interface:
 
     From within INVOKEAI_ROOT, activate the environment
-    (with `source .venv/bin/activate` or `.venv\scripts\activate`), and then run
+    (with `source .venv/bin/activate` or `.venv\scripts\activate), and then run
     the script `invokeai`. If the virtual environment you selected is NOT inside
     INVOKEAI_ROOT, then you must specify the path to the root directory by adding
     `--root_dir \path\to\invokeai` to the commands below:

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -87,18 +87,18 @@ Prior to installing PyPatchMatch, you need to take the following steps:
     sudo pacman -S --needed base-devel
     ```
 
-2. Install `opencv` and `blas`:
+2. Install `opencv`:
 
     ```sh
-    sudo pacman -S opencv blas
+    sudo pacman -S opencv
     ```
 
     or for CUDA support
 
     ```sh
-    sudo pacman -S opencv-cuda blas
+    sudo pacman -S opencv-cuda
     ```
-    
+
 3. Fix the naming of the `opencv` package configuration file:
 
     ```sh

installer/install.bat.in

@@ -38,7 +38,6 @@ echo    https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist
 echo.
 echo See %INSTRUCTIONS% for more details.
 echo.
-echo "For the best user experience we suggest enlarging or maximizing this window now."
 pause
 
 @rem ---------------------------- check Python version ---------------

installer/install.sh.in

@@ -25,8 +25,7 @@ done
 
 if [ -z "$PYTHON" ]; then
     echo "A suitable Python interpreter could not be found"
-    echo "Please install Python $MINIMUM_PYTHON_VERSION or higher (maximum $MAXIMUM_PYTHON_VERSION) before running this script. See instructions at $INSTRUCTIONS for help."
-    echo "For the best user experience we suggest enlarging or maximizing this window now."
+    echo "Please install Python 3.9 or higher before running this script. See instructions at $INSTRUCTIONS for help."
     read -p "Press any key to exit"
     exit -1
 fi

installer/lib/installer.py

@@ -149,7 +149,7 @@ class Installer:
 
         return venv_dir
 
-    def install(self, root: str = "~/invokeai-3", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
+    def install(self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
         """
         Install the InvokeAI application into the given runtime path
 
@@ -247,8 +247,8 @@ class InvokeAiInstance:
             pip[
                 "install",
                 "--require-virtualenv",
-                "torch~=2.0.0",
-                "torchvision>=0.14.1",
+                "torch",
+                "torchvision",
                 "--force-reinstall",
                 "--find-links" if find_links is not None else None,
                 find_links,

installer/lib/messages.py

@@ -293,8 +293,6 @@ def introduction() -> None:
                 "3. Create initial configuration files.",
                 "",
                 "[i]At any point you may interrupt this program and resume later.",
-                "",
-                "[b]For the best user experience, please enlarge or maximize this window",
             ),
         )
     )

installer/templates/invoke.bat.in

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

installer/templates/invoke.sh.in

@@ -1,10 +1,5 @@
 #!/bin/bash
 
-# MIT License
-
-# Coauthored by Lincoln Stein, Eugene Brodsky and Joshua Kimsey
-# Copyright 2023, The InvokeAI Development Team
-
 ####
 # This launch script assumes that:
 # 1. it is located in the runtime directory,
@@ -16,168 +11,85 @@
 
 set -eu
 
-# Ensure we're in the correct folder in case user's CWD is somewhere else
+# ensure we're in the correct folder in case user's CWD is somewhere else
 scriptdir=$(dirname "$0")
 cd "$scriptdir"
 
 . .venv/bin/activate
 
 export INVOKEAI_ROOT="$scriptdir"
-PARAMS=$@
 
-# Check to see if dialog is installed (it seems to be fairly standard, but good to check regardless) and if the user has passed the --no-tui argument to disable the dialog TUI
-tui=true
-if command -v dialog &>/dev/null; then
-    # This must use $@ to properly loop through the arguments passed by the user
-    for arg in "$@"; do
-        if [ "$arg" == "--no-tui" ]; then
-            tui=false
-            # Remove the --no-tui argument to avoid errors later on when passing arguments to InvokeAI
-            PARAMS=$(echo "$PARAMS" | sed 's/--no-tui//')
-            break
-        fi
-    done
-else
-    tui=false
-fi
-
-# Set required env var for torch on mac MPS
+# set required env var for torch on mac MPS
 if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
-# Primary function for the case statement to determine user input
-do_choice() {
-    case $1 in
-    1)
-        clear
-        printf "Generate images with a browser-based interface\n"
-        invokeai-web $PARAMS
-        ;;
-    2)
-        clear
-        printf "Explore InvokeAI nodes using a command-line interface\n"
-        invokeai $PARAMS
-        ;;
-    3)
-        clear
-        printf "Textual inversion training\n"
-        invokeai-ti --gui $PARAMS
-        ;;
-    4)
-        clear
-        printf "Merge models (diffusers type only)\n"
-        invokeai-merge --gui $PARAMS
-        ;;
-    5)
-        clear
-        printf "Download and install models\n"
-        invokeai-model-install --root ${INVOKEAI_ROOT}
-        ;;
-    6)
-        clear
-        printf "Change InvokeAI startup options\n"
-        invokeai-configure --root ${INVOKEAI_ROOT} --skip-sd-weights --skip-support-models
-        ;;
-    7)
-        clear
-        printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
-        invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
-        ;;
-    8)
-        clear
-        printf "Open the developer console\n"
-        file_name=$(basename "${BASH_SOURCE[0]}")
-        bash --init-file "$file_name"
-        ;;
-    9)
-        clear
-        printf "Update InvokeAI\n"
-        invokeai-update
-        ;;
-    10)
-        clear
-        printf "Command-line help\n"
-        invokeai --help
-        ;;
-    "HELP 1")
-        clear
-        printf "Command-line help\n"
-        invokeai --help
-        ;;
-    *)
-        clear
-        printf "Exiting...\n"
-        exit
-        ;;
-    esac
-    clear
-}
-
-# Dialog-based TUI for launcing Invoke functions
-do_dialog() {
-    options=(
-        1 "Generate images with a browser-based interface"
-        2 "Explore InvokeAI nodes using a command-line interface"
-        3 "Textual inversion training"
-        4 "Merge models (diffusers type only)"
-        5 "Download and install models"
-        6 "Change InvokeAI startup options"
-        7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
-        8 "Open the developer console"
-        9 "Update InvokeAI")
-
-    choice=$(dialog --clear \
-        --backtitle "\Zb\Zu\Z3InvokeAI" \
-        --colors \
-        --title "What would you like to do?" \
-        --ok-label "Run" \
-        --cancel-label "Exit" \
-        --help-button \
-        --help-label "CLI Help" \
-        --menu "Select an option:" \
-        0 0 0 \
-        "${options[@]}" \
-        2>&1 >/dev/tty) || clear
-    do_choice "$choice"
-    clear
-}
-
-# Command-line interface for launching Invoke functions
-do_line_input() {
-    clear
-    printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
-    printf "What would you like to do?\n"
-    printf "1: Generate images using the browser-based interface\n"
-    printf "2: Explore InvokeAI nodes using the command-line interface\n"
-    printf "3: Run textual inversion training\n"
-    printf "4: Merge models (diffusers type only)\n"
-    printf "5: Download and install models\n"
-    printf "6: Change InvokeAI startup options\n"
-    printf "7: Re-run the configure script to fix a broken install\n"
-    printf "8: Open the developer console\n"
-    printf "9: Update InvokeAI\n"
-    printf "10: Command-line help\n"
-    printf "Q: Quit\n\n"
-    read -p "Please enter 1-10, Q: [1] " yn
-    choice=${yn:='1'}
-    do_choice $choice
-    clear
-}
-
-# Main IF statement for launching Invoke with either the TUI or CLI, and for checking if the user is in the developer console
 if [ "$0" != "bash" ]; then
-    while true; do
-        if $tui; then
-            # .dialogrc must be located in the same directory as the invoke.sh script
-            export DIALOGRC="./.dialogrc"
-            do_dialog
-        else
-            do_line_input
-        fi
-    done
+  while true
+  do
+    echo "Do you want to generate images using the"
+    echo "1. command-line interface"
+    echo "2. browser-based UI"
+    echo "3. run textual inversion training"
+    echo "4. merge models (diffusers type only)"
+    echo "5. download and install models"
+    echo "6. change InvokeAI startup options"
+    echo "7. re-run the configure script to fix a broken install"
+    echo "8. open the developer console"
+    echo "9. update InvokeAI"
+    echo "10. command-line help"
+    echo "Q - Quit"
+    echo ""
+    read -p "Please enter 1-10, Q: [2] " yn
+    choice=${yn:='2'}
+    case $choice in
+        1)
+            echo "Starting the InvokeAI command-line..."
+            invokeai $@
+            ;;
+        2)
+            echo "Starting the InvokeAI browser-based UI..."
+            invokeai --web $@
+            ;;
+        3)
+            echo "Starting Textual Inversion:"
+            invokeai-ti --gui $@
+            ;;
+        4)
+            echo "Merging Models:"
+            invokeai-merge --gui $@
+            ;;
+        5)
+            invokeai-model-install --root ${INVOKEAI_ROOT}
+            ;;
+        6)
+            invokeai-configure --root ${INVOKEAI_ROOT} --skip-sd-weights --skip-support-models
+            ;;
+        7)
+            invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
+            ;;
+        8)
+            echo "Developer Console:"
+            file_name=$(basename "${BASH_SOURCE[0]}")
+            bash --init-file "$file_name"
+            ;;
+        9)
+            echo "Update:"
+            invokeai-update
+            ;;
+        10)
+            invokeai --help
+            ;;
+        [qQ])
+            exit 0
+            ;;
+        *)
+            echo "Invalid selection"
+            exit;;
+    esac
+ done
 else # in developer console
     python --version
-    printf "Press ^D to exit\n"
+    echo "Press ^D to exit"
     export PS1="(InvokeAI) \u@\h \w> "
 fi

invokeai/app/api/dependencies.py

@@ -1,34 +1,22 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from logging import Logger
 import os
-from invokeai.app.services.board_image_record_storage import (
-    SqliteBoardImageRecordStorage,
-)
-from invokeai.app.services.board_images import (
-    BoardImagesService,
-    BoardImagesServiceDependencies,
-)
-from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
-from invokeai.app.services.boards import BoardService, BoardServiceDependencies
-from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-from invokeai.app.services.images import ImageService, ImageServiceDependencies
-from invokeai.app.services.metadata import CoreMetadataService
-from invokeai.app.services.resource_name import SimpleNameService
-from invokeai.app.services.urls import LocalUrlService
-from invokeai.backend.util.logging import InvokeAILogger
+from argparse import Namespace
 
 from ..services.default_graphs import create_system_graphs
+
 from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
+
+from ...backend import Globals
+from ..services.model_manager_initializer import get_model_manager
 from ..services.restoration_services import RestorationServices
 from ..services.graph import GraphExecutionState, LibraryGraph
-from ..services.image_file_storage import DiskImageFileStorage
+from ..services.image_storage import DiskImageStorage
 from ..services.invocation_queue import MemoryInvocationQueue
 from ..services.invocation_services import InvocationServices
 from ..services.invoker import Invoker
 from ..services.processor import DefaultInvocationProcessor
 from ..services.sqlite import SqliteItemStorage
-from ..services.model_manager_service import ModelManagerService
 from .events import FastAPIEventService
 
 
@@ -48,91 +36,49 @@ def check_internet() -> bool:
         return False
 
 
-logger = InvokeAILogger.getLogger()
-
-
 class ApiDependencies:
     """Contains and initializes all dependencies for the API"""
 
     invoker: Invoker = None
 
     @staticmethod
-    def initialize(config, event_handler_id: int, logger: Logger = logger):
-        logger.info(f"Internet connectivity is {config.internet_available}")
+    def initialize(config, event_handler_id: int):
+        Globals.try_patchmatch = config.patchmatch
+        Globals.always_use_cpu = config.always_use_cpu
+        Globals.internet_available = config.internet_available and check_internet()
+        Globals.disable_xformers = not config.xformers
+        Globals.ckpt_convert = config.ckpt_convert
+
+        # TODO: Use a logger
+        print(f">> Internet connectivity is {Globals.internet_available}")
 
         events = FastAPIEventService(event_handler_id)
 
-        output_folder = config.output_path
+        output_folder = os.path.abspath(
+            os.path.join(os.path.dirname(__file__), "../../../../outputs")
+        )
+
+        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents'))
+
+        images = DiskImageStorage(f'{output_folder}/images')
 
         # TODO: build a file/path manager?
-        db_location = config.db_path
-        db_location.parent.mkdir(parents=True, exist_ok=True)
-
-        graph_execution_manager = SqliteItemStorage[GraphExecutionState](
-            filename=db_location, table_name="graph_executions"
-        )
-
-        urls = LocalUrlService()
-        metadata = CoreMetadataService()
-        image_record_storage = SqliteImageRecordStorage(db_location)
-        image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
-        names = SimpleNameService()
-        latents = ForwardCacheLatentsStorage(
-            DiskLatentsStorage(f"{output_folder}/latents")
-        )
-
-        board_record_storage = SqliteBoardRecordStorage(db_location)
-        board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
-
-        boards = BoardService(
-            services=BoardServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                board_record_storage=board_record_storage,
-                image_record_storage=image_record_storage,
-                url=urls,
-                logger=logger,
-            )
-        )
-
-        board_images = BoardImagesService(
-            services=BoardImagesServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                board_record_storage=board_record_storage,
-                image_record_storage=image_record_storage,
-                url=urls,
-                logger=logger,
-            )
-        )
-
-        images = ImageService(
-            services=ImageServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                image_record_storage=image_record_storage,
-                image_file_storage=image_file_storage,
-                metadata=metadata,
-                url=urls,
-                logger=logger,
-                names=names,
-                graph_execution_manager=graph_execution_manager,
-            )
-        )
+        db_location = os.path.join(output_folder, "invokeai.db")
 
         services = InvocationServices(
-            model_manager=ModelManagerService(config,logger),
+            model_manager=get_model_manager(config),
             events=events,
             latents=latents,
             images=images,
-            boards=boards,
-            board_images=board_images,
             queue=MemoryInvocationQueue(),
             graph_library=SqliteItemStorage[LibraryGraph](
                 filename=db_location, table_name="graphs"
             ),
-            graph_execution_manager=graph_execution_manager,
+            graph_execution_manager=SqliteItemStorage[GraphExecutionState](
+                filename=db_location, table_name="graph_executions"
+            ),
             processor=DefaultInvocationProcessor(),
-            restoration=RestorationServices(config, logger),
-            configuration=config,
-            logger=logger,
+            restoration=RestorationServices(config),
         )
 
         create_system_graphs(services.graph_library)

invokeai/app/api/events.py

@@ -45,7 +45,7 @@ class FastAPIEventService(EventServiceBase):
                 )
 
             except Empty:
-                await asyncio.sleep(0.1)
+                await asyncio.sleep(0.001)
                 pass
 
             except asyncio.CancelledError as e:

invokeai/app/api/models/images.py

@@ -0,0 +1,21 @@
+from pydantic import BaseModel, Field
+
+from invokeai.app.models.image import ImageType
+from invokeai.app.modules.metadata import ImageMetadata
+
+
+class ImageResponse(BaseModel):
+    """The response type for images"""
+
+    image_type: ImageType = Field(description="The type of the image")
+    image_name: str = Field(description="The name of the image")
+    image_url: str = Field(description="The url of the image")
+    thumbnail_url: str = Field(description="The url of the image's thumbnail")
+    metadata: ImageMetadata = Field(description="The image's metadata")
+
+
+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/api/routers/board_images.py

@@ -1,69 +0,0 @@
-from fastapi import Body, HTTPException, Path, Query
-from fastapi.routing import APIRouter
-from invokeai.app.services.board_record_storage import BoardRecord, BoardChanges
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.board_record import BoardDTO
-from invokeai.app.services.models.image_record import ImageDTO
-
-from ..dependencies import ApiDependencies
-
-board_images_router = APIRouter(prefix="/v1/board_images", tags=["boards"])
-
-
-@board_images_router.post(
-    "/",
-    operation_id="create_board_image",
-    responses={
-        201: {"description": "The image was added to a board successfully"},
-    },
-    status_code=201,
-)
-async def create_board_image(
-    board_id: str = Body(description="The id of the board to add to"),
-    image_name: str = Body(description="The name of the image to add"),
-):
-    """Creates a board_image"""
-    try:
-        result = ApiDependencies.invoker.services.board_images.add_image_to_board(board_id=board_id, image_name=image_name)
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to add to board")
-    
-@board_images_router.delete(
-    "/",
-    operation_id="remove_board_image",
-    responses={
-        201: {"description": "The image was removed from the board successfully"},
-    },
-    status_code=201,
-)
-async def remove_board_image(
-    board_id: str = Body(description="The id of the board"),
-    image_name: str = Body(description="The name of the image to remove"),
-):
-    """Deletes a board_image"""
-    try:
-        result = ApiDependencies.invoker.services.board_images.remove_image_from_board(board_id=board_id, image_name=image_name)
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to update board")
-
-
-
-@board_images_router.get(
-    "/{board_id}",
-    operation_id="list_board_images",
-    response_model=OffsetPaginatedResults[ImageDTO],
-)
-async def list_board_images(
-    board_id: str = Path(description="The id of the board"),
-    offset: int = Query(default=0, description="The page offset"),
-    limit: int = Query(default=10, description="The number of boards per page"),
-) -> OffsetPaginatedResults[ImageDTO]:
-    """Gets a list of images for a board"""
-
-    results = ApiDependencies.invoker.services.board_images.get_images_for_board(
-        board_id,
-    )
-    return results
-

invokeai/app/api/routers/boards.py

@@ -1,117 +0,0 @@
-from typing import Optional, Union
-from fastapi import Body, HTTPException, Path, Query
-from fastapi.routing import APIRouter
-from invokeai.app.services.board_record_storage import BoardChanges
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.board_record import BoardDTO
-
-
-from ..dependencies import ApiDependencies
-
-boards_router = APIRouter(prefix="/v1/boards", tags=["boards"])
-
-
-@boards_router.post(
-    "/",
-    operation_id="create_board",
-    responses={
-        201: {"description": "The board was created successfully"},
-    },
-    status_code=201,
-    response_model=BoardDTO,
-)
-async def create_board(
-    board_name: str = Query(description="The name of the board to create"),
-) -> BoardDTO:
-    """Creates a board"""
-    try:
-        result = ApiDependencies.invoker.services.boards.create(board_name=board_name)
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to create board")
-
-
-@boards_router.get("/{board_id}", operation_id="get_board", response_model=BoardDTO)
-async def get_board(
-    board_id: str = Path(description="The id of board to get"),
-) -> BoardDTO:
-    """Gets a board"""
-
-    try:
-        result = ApiDependencies.invoker.services.boards.get_dto(board_id=board_id)
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=404, detail="Board not found")
-
-
-@boards_router.patch(
-    "/{board_id}",
-    operation_id="update_board",
-    responses={
-        201: {
-            "description": "The board was updated successfully",
-        },
-    },
-    status_code=201,
-    response_model=BoardDTO,
-)
-async def update_board(
-    board_id: str = Path(description="The id of board to update"),
-    changes: BoardChanges = Body(description="The changes to apply to the board"),
-) -> BoardDTO:
-    """Updates a board"""
-    try:
-        result = ApiDependencies.invoker.services.boards.update(
-            board_id=board_id, changes=changes
-        )
-        return result
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to update board")
-
-
-@boards_router.delete("/{board_id}", operation_id="delete_board")
-async def delete_board(
-    board_id: str = Path(description="The id of board to delete"),
-    include_images: Optional[bool] = Query(
-        description="Permanently delete all images on the board", default=False
-    ),
-) -> None:
-    """Deletes a board"""
-    try:
-        if include_images is True:
-            ApiDependencies.invoker.services.images.delete_images_on_board(
-                board_id=board_id
-            )
-            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
-        else:
-            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
-    except Exception as e:
-        # TODO: Does this need any exception handling at all?
-        pass
-
-
-@boards_router.get(
-    "/",
-    operation_id="list_boards",
-    response_model=Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]],
-)
-async def list_boards(
-    all: Optional[bool] = Query(default=None, description="Whether to list all boards"),
-    offset: Optional[int] = Query(default=None, description="The page offset"),
-    limit: Optional[int] = Query(
-        default=None, description="The number of boards per page"
-    ),
-) -> Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]]:
-    """Gets a list of boards"""
-    if all:
-        return ApiDependencies.invoker.services.boards.get_all()
-    elif offset is not None and limit is not None:
-        return ApiDependencies.invoker.services.boards.get_many(
-            offset,
-            limit,
-        )
-    else:
-        raise HTTPException(
-            status_code=400,
-            detail="Invalid request: Must provide either 'all' or both 'offset' and 'limit'",
-        )

invokeai/app/api/routers/images.py

@@ -1,241 +1,144 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 import io
-from typing import Optional
-from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
-from fastapi.routing import APIRouter
-from fastapi.responses import FileResponse
-from PIL import Image
-from invokeai.app.models.image import (
-    ImageCategory,
-    ResourceOrigin,
-)
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.image_record import (
-    ImageDTO,
-    ImageRecordChanges,
-    ImageUrlsDTO,
-)
-from invokeai.app.services.item_storage import PaginatedResults
+from datetime import datetime, timezone
+import json
+import os
+import uuid
 
+from fastapi import HTTPException, Path, Query, Request, UploadFile
+from fastapi.responses import FileResponse, Response
+from fastapi.routing import APIRouter
+from PIL import Image
+from invokeai.app.api.models.images import ImageResponse
+from invokeai.app.modules.metadata import ImageMetadata, InvokeAIMetadata
+from invokeai.app.services.item_storage import PaginatedResults
+from invokeai.app.util.image_paths import build_image_path
+
+from ...services.image_storage import ImageType
 from ..dependencies import ApiDependencies
 
 images_router = APIRouter(prefix="/v1/images", tags=["images"])
 
 
+@images_router.get("/{image_type}/{image_name}", operation_id="get_image")
+async def get_image(
+    image_type: ImageType = Path(description="The type of image to get"),
+    image_name: str = Path(description="The name of the image to get"),
+) -> FileResponse | Response:
+    """Gets a result"""
+
+    path = ApiDependencies.invoker.services.images.get_path(
+        image_type=image_type, image_name=image_name
+    )
+
+    if ApiDependencies.invoker.services.images.validate_path(path):
+        return FileResponse(path)
+    else:
+        raise HTTPException(status_code=404)
+    
+@images_router.get("/path/{image_type}/{image_name}", operation_id="get_image_path")
+async def get_image_path(
+    image_type: ImageType = Path(description="The type of image to get"),
+    image_name: str = Path(description="The name of the image to get"),
+) -> str:
+    """Gets a result location"""
+
+    path = build_image_path(image_type=image_type, image_name=image_name)
+
+    return path
+
+
+
+@images_router.get(
+    "/{image_type}/thumbnails/{image_name}", operation_id="get_thumbnail"
+)
+async def get_thumbnail(
+    image_type: ImageType = Path(description="The type of image to get"),
+    image_name: str = Path(description="The name of the image to get"),
+) -> FileResponse | Response:
+    """Gets a thumbnail"""
+
+    path = ApiDependencies.invoker.services.images.get_path(
+        image_type=image_type, image_name=image_name, is_thumbnail=True
+    )
+
+    if ApiDependencies.invoker.services.images.validate_path(path):
+        return FileResponse(path)
+    else:
+        raise HTTPException(status_code=404)
+
+
 @images_router.post(
-    "/",
+    "/uploads/",
     operation_id="upload_image",
     responses={
-        201: {"description": "The image was uploaded successfully"},
+        201: {
+            "description": "The image was uploaded successfully",
+            "model": ImageResponse,
+        },
         415: {"description": "Image upload failed"},
     },
     status_code=201,
-    response_model=ImageDTO,
 )
 async def upload_image(
-    file: UploadFile,
-    request: Request,
-    response: Response,
-    image_category: ImageCategory = Query(description="The category of the image"),
-    is_intermediate: bool = Query(description="Whether this is an intermediate image"),
-    session_id: Optional[str] = Query(
-        default=None, description="The session ID associated with this upload, if any"
-    ),
-) -> ImageDTO:
-    """Uploads an image"""
+    file: UploadFile, request: Request, response: Response
+) -> ImageResponse:
     if not file.content_type.startswith("image"):
         raise HTTPException(status_code=415, detail="Not an image")
 
     contents = await file.read()
-
     try:
-        pil_image = Image.open(io.BytesIO(contents))
+        img = Image.open(io.BytesIO(contents))
     except:
         # Error opening the image
         raise HTTPException(status_code=415, detail="Failed to read image")
 
-    try:
-        image_dto = ApiDependencies.invoker.services.images.create(
-            image=pil_image,
-            image_origin=ResourceOrigin.EXTERNAL,
-            image_category=image_category,
-            session_id=session_id,
-            is_intermediate=is_intermediate,
-        )
+    filename = f"{uuid.uuid4()}_{str(int(datetime.now(timezone.utc).timestamp()))}.png"
+    (image_path, thumbnail_path, ctime) = ApiDependencies.invoker.services.images.save(
+        ImageType.UPLOAD, filename, img
+    )
 
-        response.status_code = 201
-        response.headers["Location"] = image_dto.image_url
+    # TODO: handle old `sd-metadata` style metadata
+    invokeai_metadata = img.info.get("invokeai", None)
 
-        return image_dto
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="Failed to create image")
+    if invokeai_metadata is not None:
+        invokeai_metadata = InvokeAIMetadata(**json.loads(invokeai_metadata))
 
+    # TODO: should creation of this object should happen elsewhere?
+    res = ImageResponse(
+        image_type=ImageType.UPLOAD,
+        image_name=filename,
+        image_url=f"api/v1/images/{ImageType.UPLOAD.value}/{filename}",
+        thumbnail_url=f"api/v1/images/{ImageType.UPLOAD.value}/thumbnails/{os.path.splitext(filename)[0]}.webp",
+        metadata=ImageMetadata(
+            created=ctime,
+            width=img.width,
+            height=img.height,
+            mode=img.mode,
+            invokeai=invokeai_metadata,
+        ),
+    )
 
-@images_router.delete("/{image_name}", operation_id="delete_image")
-async def delete_image(
-    image_name: str = Path(description="The name of the image to delete"),
-) -> None:
-    """Deletes an image"""
+    response.status_code = 201
+    response.headers["Location"] = request.url_for(
+        "get_image", image_type=ImageType.UPLOAD.value, image_name=filename
+    )
 
-    try:
-        ApiDependencies.invoker.services.images.delete(image_name)
-    except Exception as e:
-        # TODO: Does this need any exception handling at all?
-        pass
-
-
-@images_router.patch(
-    "/{image_name}",
-    operation_id="update_image",
-    response_model=ImageDTO,
-)
-async def update_image(
-    image_name: str = Path(description="The name of the image to update"),
-    image_changes: ImageRecordChanges = Body(
-        description="The changes to apply to the image"
-    ),
-) -> ImageDTO:
-    """Updates an image"""
-
-    try:
-        return ApiDependencies.invoker.services.images.update(image_name, image_changes)
-    except Exception as e:
-        raise HTTPException(status_code=400, detail="Failed to update image")
-
-
-@images_router.get(
-    "/{image_name}/metadata",
-    operation_id="get_image_metadata",
-    response_model=ImageDTO,
-)
-async def get_image_metadata(
-    image_name: str = Path(description="The name of image to get"),
-) -> ImageDTO:
-    """Gets an image's metadata"""
-
-    try:
-        return ApiDependencies.invoker.services.images.get_dto(image_name)
-    except Exception as e:
-        raise HTTPException(status_code=404)
-
-
-@images_router.get(
-    "/{image_name}",
-    operation_id="get_image_full",
-    response_class=Response,
-    responses={
-        200: {
-            "description": "Return the full-resolution image",
-            "content": {"image/png": {}},
-        },
-        404: {"description": "Image not found"},
-    },
-)
-async def get_image_full(
-    image_name: str = Path(description="The name of full-resolution image file to get"),
-) -> FileResponse:
-    """Gets a full-resolution image file"""
-
-    try:
-        path = ApiDependencies.invoker.services.images.get_path(image_name)
-
-        if not ApiDependencies.invoker.services.images.validate_path(path):
-            raise HTTPException(status_code=404)
-
-        return FileResponse(
-            path,
-            media_type="image/png",
-            filename=image_name,
-            content_disposition_type="inline",
-        )
-    except Exception as e:
-        raise HTTPException(status_code=404)
-
-
-@images_router.get(
-    "/{image_name}/thumbnail",
-    operation_id="get_image_thumbnail",
-    response_class=Response,
-    responses={
-        200: {
-            "description": "Return the image thumbnail",
-            "content": {"image/webp": {}},
-        },
-        404: {"description": "Image not found"},
-    },
-)
-async def get_image_thumbnail(
-    image_name: str = Path(description="The name of thumbnail image file to get"),
-) -> FileResponse:
-    """Gets a thumbnail image file"""
-
-    try:
-        path = ApiDependencies.invoker.services.images.get_path(
-            image_name, thumbnail=True
-        )
-        if not ApiDependencies.invoker.services.images.validate_path(path):
-            raise HTTPException(status_code=404)
-
-        return FileResponse(
-            path, media_type="image/webp", content_disposition_type="inline"
-        )
-    except Exception as e:
-        raise HTTPException(status_code=404)
-
-
-@images_router.get(
-    "/{image_name}/urls",
-    operation_id="get_image_urls",
-    response_model=ImageUrlsDTO,
-)
-async def get_image_urls(
-    image_name: str = Path(description="The name of the image whose URL to get"),
-) -> ImageUrlsDTO:
-    """Gets an image and thumbnail URL"""
-
-    try:
-        image_url = ApiDependencies.invoker.services.images.get_url(image_name)
-        thumbnail_url = ApiDependencies.invoker.services.images.get_url(
-            image_name, thumbnail=True
-        )
-        return ImageUrlsDTO(
-            image_name=image_name,
-            image_url=image_url,
-            thumbnail_url=thumbnail_url,
-        )
-    except Exception as e:
-        raise HTTPException(status_code=404)
+    return res
 
 
 @images_router.get(
     "/",
-    operation_id="list_images_with_metadata",
-    response_model=OffsetPaginatedResults[ImageDTO],
+    operation_id="list_images",
+    responses={200: {"model": PaginatedResults[ImageResponse]}},
 )
-async def list_images_with_metadata(
-    image_origin: Optional[ResourceOrigin] = Query(
-        default=None, description="The origin of images to list"
+async def list_images(
+    image_type: ImageType = Query(
+        default=ImageType.RESULT, description="The type of images to get"
     ),
-    categories: Optional[list[ImageCategory]] = Query(
-        default=None, description="The categories of image to include"
-    ),
-    is_intermediate: Optional[bool] = Query(
-        default=None, description="Whether to list intermediate images"
-    ),
-    board_id: Optional[str] = Query(
-        default=None, description="The board id to filter by"
-    ),
-    offset: int = Query(default=0, description="The page offset"),
-    limit: int = Query(default=10, description="The number of images per page"),
-) -> OffsetPaginatedResults[ImageDTO]:
+    page: int = Query(default=0, description="The page of images to get"),
+    per_page: int = Query(default=10, description="The number of images per page"),
+) -> PaginatedResults[ImageResponse]:
     """Gets a list of images"""
-
-    image_dtos = ApiDependencies.invoker.services.images.get_many(
-        offset,
-        limit,
-        image_origin,
-        categories,
-        is_intermediate,
-        board_id,
-    )
-
-    return image_dtos
+    result = ApiDependencies.invoker.services.images.list(image_type, page, per_page)
+    return result

invokeai/app/api/routers/models.py

@@ -1,14 +1,17 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and 2023 Kent Keirsey (https://github.com/hipsterusername)
 
-from typing import Literal, Optional, Union
+import shutil
+import asyncio
+from typing import Annotated, Any, List, Literal, Optional, Union
 
-from fastapi import Query
 from fastapi.routing import APIRouter, HTTPException
 from pydantic import BaseModel, Field, parse_obj_as
+from pathlib import Path
 from ..dependencies import ApiDependencies
-from invokeai.backend import BaseModelType, ModelType
-from invokeai.backend.model_management.models import OPENAPI_MODEL_CONFIGS, SchedulerPredictionType
-MODEL_CONFIGS = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+from invokeai.backend.globals import Globals, global_converted_ckpts_dir
+from invokeai.backend.args import Args
+
+
 
 models_router = APIRouter(prefix="/v1/models", tags=["models"])
 
@@ -20,15 +23,6 @@ class VaeRepo(BaseModel):
 
 class ModelInfo(BaseModel):
     description: Optional[str] = Field(description="A description of the model")
-    model_name: str = Field(description="The name of the model")
-    model_type: str = Field(description="The type of the model")
-    
-class DiffusersModelInfo(ModelInfo):
-    format: Literal['folder'] = 'folder'
-
-    vae: Optional[VaeRepo] = Field(description="The VAE repo to use for this model")
-    repo_id: Optional[str] = Field(description="The repo ID to use for this model")
-    path: Optional[str] = Field(description="The path to the model")
     
 class CkptModelInfo(ModelInfo):
     format: Literal['ckpt'] = 'ckpt'
@@ -39,8 +33,12 @@ class CkptModelInfo(ModelInfo):
     width: Optional[int] = Field(description="The width of the model")
     height: Optional[int] = Field(description="The height of the model")
 
-class SafetensorsModelInfo(CkptModelInfo):
-    format: Literal['safetensors'] = 'safetensors'
+class DiffusersModelInfo(ModelInfo):
+    format: Literal['diffusers'] = 'diffusers'
+
+    vae: Optional[VaeRepo] = Field(description="The VAE repo to use for this model")
+    repo_id: Optional[str] = Field(description="The repo ID to use for this model")
+    path: Optional[str] = Field(description="The path to the model")
 
 class CreateModelRequest(BaseModel):
     name: str = Field(description="The name of the model")
@@ -51,21 +49,18 @@ class CreateModelResponse(BaseModel):
     info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
     status: str = Field(description="The status of the API response")
 
-class ImportModelRequest(BaseModel):
-    name: str = Field(description="A model path, repo_id or URL to import")
-    prediction_type: Optional[Literal['epsilon','v_prediction','sample']] = Field(description='Prediction type for SDv2 checkpoint files')
-
 class ConversionRequest(BaseModel):
     name: str = Field(description="The name of the new model")
     info: CkptModelInfo = Field(description="The converted model info")
     save_location: str = Field(description="The path to save the converted model weights")
+    
 
 class ConvertedModelResponse(BaseModel):
     name: str = Field(description="The name of the new model")
     info: DiffusersModelInfo = Field(description="The converted model info")
 
 class ModelsList(BaseModel):
-    models: list[MODEL_CONFIGS]
+    models: dict[str, Annotated[Union[(CkptModelInfo,DiffusersModelInfo)], Field(discriminator="format")]]
 
 
 @models_router.get(
@@ -73,16 +68,9 @@ class ModelsList(BaseModel):
     operation_id="list_models",
     responses={200: {"model": ModelsList }},
 )
-async def list_models(
-    base_model: Optional[BaseModelType] = Query(
-        default=None, description="Base model"
-    ),
-    model_type: Optional[ModelType] = Query(
-        default=None, description="The type of model to get"
-    ),
-) -> ModelsList:
+async def list_models() -> ModelsList:
     """Gets a list of models"""
-    models_raw = ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type)
+    models_raw = ApiDependencies.invoker.services.model_manager.list_models()
     models = parse_obj_as(ModelsList, { "models": models_raw })
     return models
 
@@ -108,28 +96,6 @@ async def update_model(
 
     return model_response
 
-@models_router.post(
-    "/",
-    operation_id="import_model",
-    responses={200: {"status": "success"}},
-)
-async def import_model(
-    model_request: ImportModelRequest
-) -> None:
-    """ Add Model """
-    items_to_import = set([model_request.name])
-    prediction_types = { x.value: x for x in SchedulerPredictionType }
-    logger = ApiDependencies.invoker.services.logger
-    
-    installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
-        items_to_import = items_to_import,
-        prediction_type_helper = lambda x: prediction_types.get(model_request.prediction_type)
-    )
-    if len(installed_models) > 0:
-        logger.info(f'Successfully imported {model_request.name}')
-    else:
-        logger.error(f'Model {model_request.name} not imported')
-        raise HTTPException(status_code=500, detail=f'Model {model_request.name} not imported')
 
 @models_router.delete(
     "/{model_name}",
@@ -146,20 +112,19 @@ async def import_model(
 async def delete_model(model_name: str) -> None:
     """Delete Model"""
     model_names = ApiDependencies.invoker.services.model_manager.model_names()
-    logger = ApiDependencies.invoker.services.logger
     model_exists = model_name in model_names
 
     # check if model exists
-    logger.info(f"Checking for model {model_name}...")
+    print(f">> Checking for model {model_name}...")
            
     if model_exists:
-        logger.info(f"Deleting Model: {model_name}")
+        print(f">> Deleting Model: {model_name}")
         ApiDependencies.invoker.services.model_manager.del_model(model_name, delete_files=True)
-        logger.info(f"Model Deleted: {model_name}")
+        print(f">> Model Deleted: {model_name}")
         raise HTTPException(status_code=204, detail=f"Model '{model_name}' deleted successfully")
     
     else:
-        logger.error("Model not found")
+        print(f">> Model not found")
         raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
     
 
@@ -283,4 +248,4 @@ async def delete_model(model_name: str) -> None:
         #         )
         #         print(f">> Models Merged: {models_to_merge}")
         #         print(f">> New Model Added: {model_merge_info['merged_model_name']}")
-        #     except Exception as e:
+        #     except Exception as e:

invokeai/app/api/routers/sessions.py

@@ -2,7 +2,8 @@
 
 from typing import Annotated, List, Optional, Union
 
-from fastapi import Body, HTTPException, Path, Query, Response
+from fastapi import Body, Path, Query
+from fastapi.responses import Response
 from fastapi.routing import APIRouter
 from pydantic.fields import Field
 
@@ -75,7 +76,7 @@ async def get_session(
     """Gets a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        raise HTTPException(status_code=404)
+        return Response(status_code=404)
     else:
         return session
 
@@ -98,7 +99,7 @@ async def add_node(
     """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)
+        return Response(status_code=404)
 
     try:
         session.add_node(node)
@@ -107,9 +108,9 @@ async def add_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session.id
     except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
     except IndexError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
 
 
 @session_router.put(
@@ -131,7 +132,7 @@ async def update_node(
     """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)
+        return Response(status_code=404)
 
     try:
         session.update_node(node_path, node)
@@ -140,9 +141,9 @@ async def update_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
     except IndexError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
 
 
 @session_router.delete(
@@ -161,7 +162,7 @@ async def delete_node(
     """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)
+        return Response(status_code=404)
 
     try:
         session.delete_node(node_path)
@@ -170,9 +171,9 @@ async def delete_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
     except IndexError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
 
 
 @session_router.post(
@@ -191,7 +192,7 @@ async def add_edge(
     """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)
+        return Response(status_code=404)
 
     try:
         session.add_edge(edge)
@@ -200,9 +201,9 @@ async def add_edge(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
     except IndexError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
 
 
 # TODO: the edge being in the path here is really ugly, find a better solution
@@ -225,7 +226,7 @@ async def delete_edge(
     """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)
+        return Response(status_code=404)
 
     try:
         edge = Edge(
@@ -238,9 +239,9 @@ async def delete_edge(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
     except IndexError:
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
 
 
 @session_router.put(
@@ -258,14 +259,14 @@ async def invoke_session(
     all: bool = Query(
         default=False, description="Whether or not to invoke all remaining invocations"
     ),
-) -> Response:
+) -> None:
     """Invokes a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        raise HTTPException(status_code=404)
+        return Response(status_code=404)
 
     if session.is_complete():
-        raise HTTPException(status_code=400)
+        return Response(status_code=400)
 
     ApiDependencies.invoker.invoke(session, invoke_all=all)
     return Response(status_code=202)
@@ -280,7 +281,7 @@ async def invoke_session(
 )
 async def cancel_session_invoke(
     session_id: str = Path(description="The id of the session to cancel"),
-) -> Response:
+) -> None:
     """Invokes a session"""
     ApiDependencies.invoker.cancel(session_id)
     return Response(status_code=202)

invokeai/app/api_app.py

@@ -3,7 +3,6 @@ import asyncio
 from inspect import signature
 
 import uvicorn
-
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
@@ -11,21 +10,13 @@ from fastapi.openapi.utils import get_openapi
 from fastapi.staticfiles import StaticFiles
 from fastapi_events.handlers.local import local_handler
 from fastapi_events.middleware import EventHandlerASGIMiddleware
-from pathlib import Path
 from pydantic.schema import schema
 
-#This should come early so that modules can log their initialization properly
-from .services.config import InvokeAIAppConfig
-from ..backend.util.logging import InvokeAILogger
-app_config = InvokeAIAppConfig.get_config()
-app_config.parse_args()
-logger = InvokeAILogger.getLogger(config=app_config)
-
-import invokeai.frontend.web as web_dir
-
+from ..backend import Args
 from .api.dependencies import ApiDependencies
-from .api.routers import sessions, models, images, boards, board_images
+from .api.routers import images, sessions, models
 from .api.sockets import SocketIO
+from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
 
 # Create the app
@@ -42,21 +33,30 @@ app.add_middleware(
     middleware_id=event_handler_id,
 )
 
+# Add CORS
+# TODO: use configuration for this
+origins = []
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
 socket_io = SocketIO(app)
 
+config = {}
+
+
 # Add startup event to load dependencies
 @app.on_event("startup")
 async def startup_event():
-    app.add_middleware(
-        CORSMiddleware,
-        allow_origins=app_config.allow_origins,
-        allow_credentials=app_config.allow_credentials,
-        allow_methods=app_config.allow_methods,
-        allow_headers=app_config.allow_headers,
-    )
+    config = Args()
+    config.parse_args()
 
     ApiDependencies.initialize(
-        config=app_config, event_handler_id=event_handler_id, logger=logger
+        config=config, event_handler_id=event_handler_id
     )
 
 
@@ -74,13 +74,10 @@ async def shutdown_event():
 
 app.include_router(sessions.session_router, prefix="/api")
 
-app.include_router(models.models_router, prefix="/api")
-
 app.include_router(images.images_router, prefix="/api")
 
-app.include_router(boards.boards_router, prefix="/api")
+app.include_router(models.models_router, prefix="/api")
 
-app.include_router(board_images.board_images_router, prefix="/api")
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?
@@ -120,22 +117,6 @@ def custom_openapi():
 
         invoker_schema["output"] = outputs_ref
 
-    from invokeai.backend.model_management.models import get_model_config_enums
-    for model_config_format_enum in set(get_model_config_enums()):
-        name = model_config_format_enum.__qualname__
-
-        if name in openapi_schema["components"]["schemas"]:
-            # print(f"Config with name {name} already defined")
-            continue
-
-        # "BaseModelType":{"title":"BaseModelType","description":"An enumeration.","enum":["sd-1","sd-2"],"type":"string"}
-        openapi_schema["components"]["schemas"][name] = dict(
-            title=name,
-            description="An enumeration.",
-            type="string",
-            enum=list(v.value for v in model_config_format_enum),
-        )
-
     app.openapi_schema = openapi_schema
     return app.openapi_schema
 
@@ -143,7 +124,8 @@ def custom_openapi():
 app.openapi = custom_openapi
 
 # Override API doc favicons
-app.mount("/static", StaticFiles(directory=Path(web_dir.__path__[0], 'static/dream_web')), name="static")
+app.mount("/static", StaticFiles(directory="static/dream_web"), name="static")
+
 
 @app.get("/docs", include_in_schema=False)
 def overridden_swagger():
@@ -163,20 +145,16 @@ def overridden_redoc():
     )
 
 
-# Must mount *after* the other routes else it borks em
-app.mount("/", 
-          StaticFiles(directory=Path(web_dir.__path__[0],"dist"), 
-                      html=True
-                     ), name="ui"
-         )
-
 def invoke_api():
     # Start our own event loop for eventing usage
+    # TODO: determine if there's a better way to do this
     loop = asyncio.new_event_loop()
-    config = uvicorn.Config(app=app, host=app_config.host, port=app_config.port, loop=loop)
+    config = uvicorn.Config(app=app, host="0.0.0.0", port=9090, loop=loop)
     # Use access_log to turn off logging
+
     server = uvicorn.Server(config)
     loop.run_until_complete(server.serve())
 
+
 if __name__ == "__main__":
     invoke_api()

invokeai/app/cli/commands.py

@@ -2,15 +2,14 @@
 
 from abc import ABC, abstractmethod
 import argparse
-from typing import Any, Callable, Iterable, Literal, Union, get_args, get_origin, get_type_hints
+from typing import Any, Callable, Iterable, Literal, get_args, get_origin, get_type_hints
 from pydantic import BaseModel, Field
 import networkx as nx
 import matplotlib.pyplot as plt
 
-import invokeai.backend.util.logging as logger
 from ..invocations.baseinvocation import BaseInvocation
 from ..invocations.image import ImageField
-from ..services.graph import GraphExecutionState, LibraryGraph, Edge
+from ..services.graph import GraphExecutionState, LibraryGraph, GraphInvocation, Edge
 from ..services.invoker import Invoker
 
 
@@ -230,7 +229,7 @@ class HistoryCommand(BaseCommand):
         for i in range(min(self.count, len(history))):
             entry_id = history[-1 - i]
             entry = context.get_session().graph.get_node(entry_id)
-            logger.info(f"{entry_id}: {get_invocation_command(entry)}")
+            print(f"{entry_id}: {get_invocation_command(entry)}")
 
 
 class SetDefaultCommand(BaseCommand):
@@ -285,19 +284,3 @@ class DrawExecutionGraphCommand(BaseCommand):
         nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
         plt.axis("off")
         plt.show()
-
-class SortedHelpFormatter(argparse.HelpFormatter):
-    def _iter_indented_subactions(self, action):
-        try:
-            get_subactions = action._get_subactions
-        except AttributeError:
-            pass
-        else:
-            self._indent()
-            if isinstance(action, argparse._SubParsersAction):
-                for subaction in sorted(get_subactions(), key=lambda x: x.dest):
-                    yield subaction
-            else:
-                for subaction in get_subactions():
-                    yield subaction
-                self._dedent()

invokeai/app/cli/completer.py

@@ -10,11 +10,9 @@ import shlex
 from pathlib import Path
 from typing import List, Dict, Literal, get_args, get_type_hints, get_origin
 
-import invokeai.backend.util.logging as logger
-from ...backend import ModelManager
+from ...backend import ModelManager, Globals
 from ..invocations.baseinvocation import BaseInvocation
 from .commands import BaseCommand
-from ..services.invocation_services import InvocationServices
 
 # singleton object, class variable
 completer = None
@@ -132,13 +130,13 @@ class Completer(object):
             readline.redisplay()
             self.linebuffer = None
     
-def set_autocompleter(services: InvocationServices) -> Completer:
+def set_autocompleter(model_manager: ModelManager) -> Completer:
     global completer
     
     if completer:
         return completer
     
-    completer = Completer(services.model_manager)
+    completer = Completer(model_manager)
 
     readline.set_completer(completer.complete)
     # pyreadline3 does not have a set_auto_history() method
@@ -154,7 +152,7 @@ def set_autocompleter(services: InvocationServices) -> Completer:
     readline.parse_and_bind("set skip-completed-text on")
     readline.parse_and_bind("set show-all-if-ambiguous on")
 
-    histfile = Path(services.configuration.root_dir / ".invoke_history")
+    histfile = Path(Globals.root, ".invoke_history")
     try:
         readline.read_history_file(histfile)
         readline.set_history_length(1000)
@@ -162,8 +160,8 @@ def set_autocompleter(services: InvocationServices) -> Completer:
         pass
     except OSError:  # file likely corrupted
         newname = f"{histfile}.old"
-        logger.error(
-            f"Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}"
+        print(
+            f"## Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}"
         )
         histfile.replace(Path(newname))
     atexit.register(readline.write_history_file, histfile)

invokeai/app/cli_app.py

@@ -4,53 +4,34 @@ import argparse
 import os
 import re
 import shlex
-import sys
 import time
-from typing import Union, get_type_hints
+from typing import (
+    Union,
+    get_type_hints,
+)
 
-from pydantic import BaseModel, ValidationError
+from pydantic import BaseModel
 from pydantic.fields import Field
 
-# This should come early so that the logger can pick up its configuration options
-from .services.config import InvokeAIAppConfig
-from invokeai.backend.util.logging import InvokeAILogger
-config = InvokeAIAppConfig.get_config()
-config.parse_args()
-logger = InvokeAILogger().getLogger(config=config)
+from .services.default_graphs import create_system_graphs
 
-from invokeai.app.services.board_image_record_storage import (
-    SqliteBoardImageRecordStorage,
-)
-from invokeai.app.services.board_images import (
-    BoardImagesService,
-    BoardImagesServiceDependencies,
-)
-from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
-from invokeai.app.services.boards import BoardService, BoardServiceDependencies
-from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-from invokeai.app.services.images import ImageService, ImageServiceDependencies
-from invokeai.app.services.metadata import CoreMetadataService
-from invokeai.app.services.resource_name import SimpleNameService
-from invokeai.app.services.urls import LocalUrlService
-from .services.default_graphs import (default_text_to_image_graph_id,
-                                      create_system_graphs)
 from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
 
-from .cli.commands import (BaseCommand, CliContext, ExitCli,
-                           SortedHelpFormatter, add_graph_parsers, add_parsers)
+from ..backend import Args
+from .cli.commands import BaseCommand, CliContext, ExitCli, add_graph_parsers, add_parsers, get_graph_execution_history
 from .cli.completer import set_autocompleter
+from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
 from .services.events import EventServiceBase
-from .services.graph import (Edge, EdgeConnection, GraphExecutionState,
-                             GraphInvocation, LibraryGraph,
-                             are_connection_types_compatible)
-from .services.image_file_storage import DiskImageFileStorage
+from .services.model_manager_initializer import get_model_manager
+from .services.restoration_services import RestorationServices
+from .services.graph import Edge, EdgeConnection, ExposedNodeInput, GraphExecutionState, GraphInvocation, LibraryGraph, are_connection_types_compatible
+from .services.default_graphs import default_text_to_image_graph_id
+from .services.image_storage import DiskImageStorage
 from .services.invocation_queue import MemoryInvocationQueue
 from .services.invocation_services import InvocationServices
 from .services.invoker import Invoker
-from .services.model_manager_service import ModelManagerService
 from .services.processor import DefaultInvocationProcessor
-from .services.restoration_services import RestorationServices
 from .services.sqlite import SqliteItemStorage
 
 
@@ -61,6 +42,7 @@ class CliCommand(BaseModel):
 class InvalidArgs(Exception):
     pass
 
+
 def add_invocation_args(command_parser):
     # Add linking capability
     command_parser.add_argument(
@@ -81,7 +63,7 @@ def add_invocation_args(command_parser):
 
 def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
     # Create invocation parser
-    parser = argparse.ArgumentParser(formatter_class=SortedHelpFormatter)
+    parser = argparse.ArgumentParser()
 
     def exit(*args, **kwargs):
         raise InvalidArgs
@@ -198,105 +180,51 @@ def invoke_all(context: CliContext):
     # Print any errors
     if context.session.has_error():
         for n in context.session.errors:
-            context.invoker.services.logger.error(
+            print(
                 f"Error in node {n} (source node {context.session.prepared_source_mapping[n]}): {context.session.errors[n]}"
             )
         
         raise SessionError()
 
-def invoke_cli():
-    # get the optional list of invocations to execute on the command line
-    parser = config.get_parser()
-    parser.add_argument('commands',nargs='*')
-    invocation_commands = parser.parse_args().commands
 
-    # get the optional file to read commands from.
-    # Simplest is to use it for STDIN
-    if infile := config.from_file:
-        sys.stdin = open(infile,"r")
-    
-    model_manager = ModelManagerService(config,logger)
+def invoke_cli():
+    config = Args()
+    config.parse_args()
+    model_manager = get_model_manager(config)
+
+    # This initializes the autocompleter and returns it.
+    # Currently nothing is done with the returned Completer
+    # object, but the object can be used to change autocompletion
+    # behavior on the fly, if desired.
+    completer = set_autocompleter(model_manager)
 
     events = EventServiceBase()
-    output_folder = config.output_path
+
+    output_folder = os.path.abspath(
+        os.path.join(os.path.dirname(__file__), "../../../outputs")
+    )
 
     # TODO: build a file/path manager?
-    if config.use_memory_db:
-        db_location = ":memory:"
-    else:
-        db_location = config.db_path
-        db_location.parent.mkdir(parents=True,exist_ok=True)
+    db_location = os.path.join(output_folder, "invokeai.db")
 
-    logger.info(f'InvokeAI database location is "{db_location}"')
-
-    graph_execution_manager = SqliteItemStorage[GraphExecutionState](
-            filename=db_location, table_name="graph_executions"
-        )
-
-    urls = LocalUrlService()
-    metadata = CoreMetadataService()
-    image_record_storage = SqliteImageRecordStorage(db_location)
-    image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
-    names = SimpleNameService()
-
-    board_record_storage = SqliteBoardRecordStorage(db_location)
-    board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
-
-    boards = BoardService(
-        services=BoardServiceDependencies(
-            board_image_record_storage=board_image_record_storage,
-            board_record_storage=board_record_storage,
-            image_record_storage=image_record_storage,
-            url=urls,
-            logger=logger,
-        )
-    )
-
-    board_images = BoardImagesService(
-        services=BoardImagesServiceDependencies(
-            board_image_record_storage=board_image_record_storage,
-            board_record_storage=board_record_storage,
-            image_record_storage=image_record_storage,
-            url=urls,
-            logger=logger,
-        )
-    )
-
-    images = ImageService(
-        services=ImageServiceDependencies(
-            board_image_record_storage=board_image_record_storage,
-            image_record_storage=image_record_storage,
-            image_file_storage=image_file_storage,
-            metadata=metadata,
-            url=urls,
-            logger=logger,
-            names=names,
-            graph_execution_manager=graph_execution_manager,
-        )
-    )
-        
     services = InvocationServices(
         model_manager=model_manager,
         events=events,
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
-        images=images,
-        boards=boards,
-        board_images=board_images,
+        images=DiskImageStorage(f'{output_folder}/images'),
         queue=MemoryInvocationQueue(),
         graph_library=SqliteItemStorage[LibraryGraph](
             filename=db_location, table_name="graphs"
         ),
-        graph_execution_manager=graph_execution_manager,
+        graph_execution_manager=SqliteItemStorage[GraphExecutionState](
+            filename=db_location, table_name="graph_executions"
+        ),
         processor=DefaultInvocationProcessor(),
-        restoration=RestorationServices(config,logger=logger),
-        logger=logger,
-        configuration=config,
+        restoration=RestorationServices(config),
     )
-    
 
     system_graphs = create_system_graphs(services.graph_library)
     system_graph_names = set([g.name for g in system_graphs])
-    set_autocompleter(services)
 
     invoker = Invoker(services)
     session: GraphExecutionState = invoker.create_execution_state()
@@ -308,18 +236,10 @@ def invoke_cli():
     # print(services.session_manager.list())
 
     context = CliContext(invoker, session, parser)
-    set_autocompleter(services)
 
-    command_line_args_exist = len(invocation_commands) > 0
-    done = False
-    
-    while not done:
+    while True:
         try:
-            if command_line_args_exist:
-                cmd_input = invocation_commands.pop(0)
-                done = len(invocation_commands) == 0
-            else:
-                cmd_input = input("invoke> ")
+            cmd_input = input("invoke> ")
         except (KeyboardInterrupt, EOFError):
             # Ctrl-c exits
             break
@@ -440,15 +360,12 @@ def invoke_cli():
             invoke_all(context)
 
         except InvalidArgs:
-            invoker.services.logger.warning('Invalid command, use "help" to list commands')
+            print('Invalid command, use "help" to list commands')
             continue
 
-        except ValidationError:
-            invoker.services.logger.warning('Invalid command arguments, run "<command> --help" for summary')
-
         except SessionError:
             # Start a new session
-            invoker.services.logger.warning("Session error: creating a new session")
+            print("Session error: creating a new session")
             context.reset()
 
         except ExitCli:

invokeai/app/invocations/baseinvocation.py

@@ -1,15 +1,12 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from __future__ import annotations
-
 from abc import ABC, abstractmethod
 from inspect import signature
-from typing import get_args, get_type_hints, Dict, List, Literal, TypedDict, TYPE_CHECKING
+from typing import get_args, get_type_hints, Dict, List, Literal, TypedDict
 
 from pydantic import BaseModel, Field
 
-if TYPE_CHECKING:
-    from ..services.invocation_services import InvocationServices
+from ..services.invocation_services import InvocationServices
 
 
 class InvocationContext:
@@ -78,7 +75,6 @@ class BaseInvocation(ABC, BaseModel):
     
     #fmt: off
     id: str = Field(description="The id of this node. Must be unique among all nodes.")
-    is_intermediate: bool = Field(default=False, description="Whether or not this node is an intermediate node.")
     #fmt: on
 
 
@@ -96,7 +92,6 @@ class UIConfig(TypedDict, total=False):
             "image",
             "latents",
             "model",
-            "control",
         ],
     ]
     tags: List[str]

invokeai/app/invocations/collections.py

@@ -1,14 +1,14 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Literal
+from typing import Literal, Optional
 
 import numpy as np
-from pydantic import Field, validator
-
-from invokeai.app.util.misc import SEED_MAX, get_random_seed
+import numpy.random
+from pydantic import Field
 
 from .baseinvocation import (
     BaseInvocation,
+    InvocationConfig,
     InvocationContext,
     BaseInvocationOutput,
 )
@@ -22,17 +22,9 @@ class IntCollectionOutput(BaseInvocationOutput):
     # Outputs
     collection: list[int] = Field(default=[], description="The int collection")
 
-class FloatCollectionOutput(BaseInvocationOutput):
-    """A collection of floats"""
-
-    type: Literal["float_collection"] = "float_collection"
-
-    # Outputs
-    collection: list[float] = Field(default=[], description="The float collection")
-
 
 class RangeInvocation(BaseInvocation):
-    """Creates a range of numbers from start to stop with step"""
+    """Creates a range"""
 
     type: Literal["range"] = "range"
 
@@ -41,34 +33,12 @@ class RangeInvocation(BaseInvocation):
     stop: int = Field(default=10, description="The stop of the range")
     step: int = Field(default=1, description="The step of the range")
 
-    @validator("stop")
-    def stop_gt_start(cls, v, values):
-        if "start" in values and v <= values["start"]:
-            raise ValueError("stop must be greater than start")
-        return v
-
     def invoke(self, context: InvocationContext) -> IntCollectionOutput:
         return IntCollectionOutput(
             collection=list(range(self.start, self.stop, self.step))
         )
 
 
-class RangeOfSizeInvocation(BaseInvocation):
-    """Creates a range from start to start + size with step"""
-
-    type: Literal["range_of_size"] = "range_of_size"
-
-    # Inputs
-    start: int = Field(default=0, description="The start of the range")
-    size: int = Field(default=1, description="The number of values")
-    step: int = Field(default=1, description="The step of the range")
-
-    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
-        return IntCollectionOutput(
-            collection=list(range(self.start, self.start + self.size, self.step))
-        )
-
-
 class RandomRangeInvocation(BaseInvocation):
     """Creates a collection of random numbers"""
 
@@ -80,11 +50,11 @@ class RandomRangeInvocation(BaseInvocation):
         default=np.iinfo(np.int32).max, description="The exclusive high value"
     )
     size: int = Field(default=1, description="The number of values to generate")
-    seed: int = Field(
+    seed: Optional[int] = Field(
         ge=0,
-        le=SEED_MAX,
-        description="The seed for the RNG (omit for random)",
-        default_factory=get_random_seed,
+        le=np.iinfo(np.int32).max,
+        description="The seed for the RNG",
+        default_factory=lambda: numpy.random.randint(0, np.iinfo(np.int32).max),
     )
 
     def invoke(self, context: InvocationContext) -> IntCollectionOutput:

invokeai/app/invocations/compel.py

@@ -1,266 +0,0 @@
-from typing import Literal, Optional, Union
-from pydantic import BaseModel, Field
-from contextlib import ExitStack
-import re
-
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
-from .model import ClipField
-
-from ...backend.util.devices import torch_dtype
-from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
-from ...backend.model_management import BaseModelType, ModelType, SubModelType
-from ...backend.model_management.lora import ModelPatcher
-
-from compel import Compel
-from compel.prompt_parser import (
-    Blend,
-    CrossAttentionControlSubstitute,
-    FlattenedPrompt,
-    Fragment, Conjunction,
-)
-
-
-class ConditioningField(BaseModel):
-    conditioning_name: Optional[str] = Field(default=None, description="The name of conditioning data")
-    class Config:
-        schema_extra = {"required": ["conditioning_name"]}
-
-
-class CompelOutput(BaseInvocationOutput):
-    """Compel parser output"""
-
-    #fmt: off
-    type: Literal["compel_output"] = "compel_output"
-
-    conditioning: ConditioningField = Field(default=None, description="Conditioning")
-    #fmt: on
-
-
-class CompelInvocation(BaseInvocation):
-    """Parse prompt using compel package to conditioning."""
-
-    type: Literal["compel"] = "compel"
-
-    prompt: str = Field(default="", description="Prompt")
-    clip: ClipField = Field(None, description="Clip to use")
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "title": "Prompt (Compel)",
-                "tags": ["prompt", "compel"],
-                "type_hints": {
-                  "model": "model"
-                }
-            },
-        }
-
-    def invoke(self, context: InvocationContext) -> CompelOutput:
-
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.dict(),
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.dict(),
-        )
-        with tokenizer_info as orig_tokenizer,\
-             text_encoder_info as text_encoder:
-
-            loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
-
-            ti_list = []
-            for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
-                name = trigger[1:-1]
-                try:
-                    ti_list.append(
-                        context.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=self.clip.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                        ).context.model
-                    )
-                except Exception:
-                    #print(e)
-                    #import traceback
-                    #print(traceback.format_exc())
-                    print(f"Warn: trigger: \"{trigger}\" not found")
-
-            with ModelPatcher.apply_lora_text_encoder(text_encoder, loras),\
-                 ModelPatcher.apply_ti(orig_tokenizer, text_encoder, ti_list) as (tokenizer, ti_manager):
-
-                compel = Compel(
-                    tokenizer=tokenizer,
-                    text_encoder=text_encoder,
-                    textual_inversion_manager=ti_manager,
-                    dtype_for_device_getter=torch_dtype,
-                    truncate_long_prompts=True, # TODO:
-                )
-                
-                conjunction = Compel.parse_prompt_string(self.prompt)
-                prompt: Union[FlattenedPrompt, Blend] = conjunction.prompts[0]
-
-                if context.services.configuration.log_tokenization:
-                    log_tokenization_for_prompt_object(prompt, tokenizer)
-
-                c, options = compel.build_conditioning_tensor_for_prompt_object(prompt)
-                
-                # TODO: long prompt support
-                #if not self.truncate_long_prompts:
-                #    [c, uc] = compel.pad_conditioning_tensors_to_same_length([c, uc])
-                ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
-                    tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
-                    cross_attention_control_args=options.get("cross_attention_control", None),
-                )
-                
-            conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-
-            # TODO: hacky but works ;D maybe rename latents somehow?
-            context.services.latents.save(conditioning_name, (c, ec))
-
-            return CompelOutput(
-                conditioning=ConditioningField(
-                    conditioning_name=conditioning_name,
-                ),
-            )
-
-
-def get_max_token_count(
-    tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction], truncate_if_too_long=False
-) -> int:
-    if type(prompt) is Blend:
-        blend: Blend = prompt
-        return max(
-            [
-                get_max_token_count(tokenizer, p, truncate_if_too_long)
-                for p in blend.prompts
-            ]
-        )
-    elif type(prompt) is Conjunction:
-        conjunction: Conjunction = prompt
-        return sum(
-            [
-                get_max_token_count(tokenizer, p, truncate_if_too_long)
-                for p in conjunction.prompts
-            ]
-        )
-    else:
-        return len(
-            get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long)
-        )
-
-
-def get_tokens_for_prompt_object(
-    tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True
-) -> [str]:
-    if type(parsed_prompt) is Blend:
-        raise ValueError(
-            "Blend is not supported here - you need to get tokens for each of its .children"
-        )
-
-    text_fragments = [
-        x.text
-        if type(x) is Fragment
-        else (
-            " ".join([f.text for f in x.original])
-            if type(x) is CrossAttentionControlSubstitute
-            else str(x)
-        )
-        for x in parsed_prompt.children
-    ]
-    text = " ".join(text_fragments)
-    tokens = tokenizer.tokenize(text)
-    if truncate_if_too_long:
-        max_tokens_length = tokenizer.model_max_length - 2  # typically 75
-        tokens = tokens[0:max_tokens_length]
-    return tokens
-
-
-def log_tokenization_for_conjunction(
-    c: Conjunction, tokenizer, display_label_prefix=None
-):
-    display_label_prefix = display_label_prefix or ""
-    for i, p in enumerate(c.prompts):
-        if len(c.prompts)>1:
-            this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
-        else:
-            this_display_label_prefix = display_label_prefix
-        log_tokenization_for_prompt_object(
-            p,
-            tokenizer,
-            display_label_prefix=this_display_label_prefix
-        )
-
-
-def log_tokenization_for_prompt_object(
-    p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None
-):
-    display_label_prefix = display_label_prefix or ""
-    if type(p) is Blend:
-        blend: Blend = p
-        for i, c in enumerate(blend.prompts):
-            log_tokenization_for_prompt_object(
-                c,
-                tokenizer,
-                display_label_prefix=f"{display_label_prefix}(blend part {i + 1}, weight={blend.weights[i]})",
-            )
-    elif type(p) is FlattenedPrompt:
-        flattened_prompt: FlattenedPrompt = p
-        if flattened_prompt.wants_cross_attention_control:
-            original_fragments = []
-            edited_fragments = []
-            for f in flattened_prompt.children:
-                if type(f) is CrossAttentionControlSubstitute:
-                    original_fragments += f.original
-                    edited_fragments += f.edited
-                else:
-                    original_fragments.append(f)
-                    edited_fragments.append(f)
-
-            original_text = " ".join([x.text for x in original_fragments])
-            log_tokenization_for_text(
-                original_text,
-                tokenizer,
-                display_label=f"{display_label_prefix}(.swap originals)",
-            )
-            edited_text = " ".join([x.text for x in edited_fragments])
-            log_tokenization_for_text(
-                edited_text,
-                tokenizer,
-                display_label=f"{display_label_prefix}(.swap replacements)",
-            )
-        else:
-            text = " ".join([x.text for x in flattened_prompt.children])
-            log_tokenization_for_text(
-                text, tokenizer, display_label=display_label_prefix
-            )
-
-
-def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
-    """shows how the prompt is tokenized
-    # usually tokens have '</w>' to indicate end-of-word,
-    # but for readability it has been replaced with ' '
-    """
-    tokens = tokenizer.tokenize(text)
-    tokenized = ""
-    discarded = ""
-    usedTokens = 0
-    totalTokens = len(tokens)
-
-    for i in range(0, totalTokens):
-        token = tokens[i].replace("</w>", " ")
-        # alternate color
-        s = (usedTokens % 6) + 1
-        if truncate_if_too_long and i >= tokenizer.model_max_length:
-            discarded = discarded + f"\x1b[0;3{s};40m{token}"
-        else:
-            tokenized = tokenized + f"\x1b[0;3{s};40m{token}"
-            usedTokens += 1
-
-    if usedTokens > 0:
-        print(f'\n>> [TOKENLOG] Tokens {display_label or ""} ({usedTokens}):')
-        print(f"{tokenized}\x1b[0m")
-
-    if discarded != "":
-        print(f"\n>> [TOKENLOG] Tokens Discarded ({totalTokens - usedTokens}):")
-        print(f"{discarded}\x1b[0m")

invokeai/app/invocations/controlnet_image_processors.py

@@ -1,565 +0,0 @@
-# Invocations for ControlNet image preprocessors
-# initial implementation by Gregg Helt, 2023
-# heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
-from builtins import float, bool
-
-import cv2
-import numpy as np
-from typing import Literal, Optional, Union, List, Dict
-from PIL import Image, ImageFilter, ImageOps
-from pydantic import BaseModel, Field, validator
-
-from ..models.image import ImageField, ImageCategory, ResourceOrigin
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    InvocationContext,
-    InvocationConfig,
-)
-
-from controlnet_aux import (
-    CannyDetector,
-    HEDdetector,
-    LineartDetector,
-    LineartAnimeDetector,
-    MidasDetector,
-    MLSDdetector,
-    NormalBaeDetector,
-    OpenposeDetector,
-    PidiNetDetector,
-    ContentShuffleDetector,
-    ZoeDetector,
-    MediapipeFaceDetector,
-    SamDetector,
-    LeresDetector,
-)
-
-from controlnet_aux.util import HWC3, ade_palette
-
-
-from .image import ImageOutput, PILInvocationConfig
-
-CONTROLNET_DEFAULT_MODELS = [
-    ###########################################
-    # lllyasviel sd v1.5, ControlNet v1.0 models
-    ##############################################
-    "lllyasviel/sd-controlnet-canny",
-    "lllyasviel/sd-controlnet-depth",
-    "lllyasviel/sd-controlnet-hed",
-    "lllyasviel/sd-controlnet-seg",
-    "lllyasviel/sd-controlnet-openpose",
-    "lllyasviel/sd-controlnet-scribble",
-    "lllyasviel/sd-controlnet-normal",
-    "lllyasviel/sd-controlnet-mlsd",
-
-    #############################################
-    # lllyasviel sd v1.5, ControlNet v1.1 models
-    #############################################
-    "lllyasviel/control_v11p_sd15_canny",
-    "lllyasviel/control_v11p_sd15_openpose",
-    "lllyasviel/control_v11p_sd15_seg",
-    # "lllyasviel/control_v11p_sd15_depth",  # broken
-    "lllyasviel/control_v11f1p_sd15_depth",
-    "lllyasviel/control_v11p_sd15_normalbae",
-    "lllyasviel/control_v11p_sd15_scribble",
-    "lllyasviel/control_v11p_sd15_mlsd",
-    "lllyasviel/control_v11p_sd15_softedge",
-    "lllyasviel/control_v11p_sd15s2_lineart_anime",
-    "lllyasviel/control_v11p_sd15_lineart",
-    "lllyasviel/control_v11p_sd15_inpaint",
-    # "lllyasviel/control_v11u_sd15_tile",
-    # problem (temporary?) with huffingface "lllyasviel/control_v11u_sd15_tile",
-    # so for now replace  "lllyasviel/control_v11f1e_sd15_tile",
-    "lllyasviel/control_v11e_sd15_shuffle",
-    "lllyasviel/control_v11e_sd15_ip2p",
-    "lllyasviel/control_v11f1e_sd15_tile",
-
-     #################################################
-     #  thibaud sd v2.1 models (ControlNet v1.0? or v1.1?
-     ##################################################
-     "thibaud/controlnet-sd21-openpose-diffusers",
-     "thibaud/controlnet-sd21-canny-diffusers",
-     "thibaud/controlnet-sd21-depth-diffusers",
-     "thibaud/controlnet-sd21-scribble-diffusers",
-     "thibaud/controlnet-sd21-hed-diffusers",
-     "thibaud/controlnet-sd21-zoedepth-diffusers",
-     "thibaud/controlnet-sd21-color-diffusers",
-     "thibaud/controlnet-sd21-openposev2-diffusers",
-     "thibaud/controlnet-sd21-lineart-diffusers",
-     "thibaud/controlnet-sd21-normalbae-diffusers",
-     "thibaud/controlnet-sd21-ade20k-diffusers",
-
-     ##############################################
-     #  ControlNetMediaPipeface, ControlNet v1.1
-     ##############################################
-     # ["CrucibleAI/ControlNetMediaPipeFace", "diffusion_sd15"],  # SD 1.5
-     #    diffusion_sd15 needs to be passed to from_pretrained() as subfolder arg
-     #    hacked t2l to split to model & subfolder if format is "model,subfolder"
-     "CrucibleAI/ControlNetMediaPipeFace,diffusion_sd15",  # SD 1.5
-     "CrucibleAI/ControlNetMediaPipeFace",  # SD 2.1?
-]
-
-CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)]
-CONTROLNET_MODE_VALUES = Literal[tuple(["balanced", "more_prompt", "more_control", "unbalanced"])]
-# crop and fill options not ready yet
-# CONTROLNET_RESIZE_VALUES = Literal[tuple(["just_resize", "crop_resize", "fill_resize"])]
-
-
-class ControlField(BaseModel):
-    image: ImageField = Field(default=None, description="The control image")
-    control_model: Optional[str] = Field(default=None, description="The ControlNet model to use")
-    # control_weight: Optional[float] = Field(default=1, description="weight given to controlnet")
-    control_weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
-    begin_step_percent: float = Field(default=0, ge=0, le=1,
-                                      description="When the ControlNet is first applied (% of total steps)")
-    end_step_percent: float = Field(default=1, ge=0, le=1,
-                                    description="When the ControlNet is last applied (% of total steps)")
-    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
-    # resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
-
-    @validator("control_weight")
-    def abs_le_one(cls, v):
-        """validate that all abs(values) are <=1"""
-        if isinstance(v, list):
-            for i in v:
-                if abs(i) > 1:
-                    raise ValueError('all abs(control_weight) must be <= 1')
-        else:
-            if abs(v) > 1:
-                raise ValueError('abs(control_weight) must be <= 1')
-        return v
-    class Config:
-        schema_extra = {
-            "required": ["image", "control_model", "control_weight", "begin_step_percent", "end_step_percent"],
-            "ui": {
-                "type_hints": {
-                    "control_weight": "float",
-                    # "control_weight": "number",
-                }
-            }
-        }
-
-
-class ControlOutput(BaseInvocationOutput):
-    """node output for ControlNet info"""
-    # fmt: off
-    type: Literal["control_output"] = "control_output"
-    control: ControlField = Field(default=None, description="The control info")
-    # fmt: on
-
-
-class ControlNetInvocation(BaseInvocation):
-    """Collects ControlNet info to pass to other nodes"""
-    # fmt: off
-    type: Literal["controlnet"] = "controlnet"
-    # Inputs
-    image: ImageField = Field(default=None, description="The control image")
-    control_model: CONTROLNET_NAME_VALUES = Field(default="lllyasviel/sd-controlnet-canny",
-                                                  description="control model used")
-    control_weight: Union[float, List[float]] = Field(default=1.0, description="The weight given to the ControlNet")
-    begin_step_percent: float = Field(default=0, ge=0, le=1,
-                                      description="When the ControlNet is first applied (% of total steps)")
-    end_step_percent: float = Field(default=1, ge=0, le=1,
-                                    description="When the ControlNet is last applied (% of total steps)")
-    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode used")
-    # fmt: on
-
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents"],
-                "type_hints": {
-                  "model": "model",
-                  "control": "control",
-                  # "cfg_scale": "float",
-                  "cfg_scale": "number",
-                  "control_weight": "float",
-                }
-            },
-        }
-
-    def invoke(self, context: InvocationContext) -> ControlOutput:
-        return ControlOutput(
-            control=ControlField(
-                image=self.image,
-                control_model=self.control_model,
-                control_weight=self.control_weight,
-                begin_step_percent=self.begin_step_percent,
-                end_step_percent=self.end_step_percent,
-                control_mode=self.control_mode,
-            ),
-        )
-
-
-class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
-    """Base class for invocations that preprocess images for ControlNet"""
-
-    # fmt: off
-    type: Literal["image_processor"] = "image_processor"
-    # Inputs
-    image: ImageField = Field(default=None, description="The image to process")
-    # fmt: on
-
-
-    def run_processor(self, image):
-        # superclass just passes through image without processing
-        return image
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        raw_image = context.services.images.get_pil_image(self.image.image_name)
-        # image type should be PIL.PngImagePlugin.PngImageFile ?
-        processed_image = self.run_processor(raw_image)
-
-        # FIXME: what happened to image metadata?
-        # metadata = context.services.metadata.build_metadata(
-        #     session_id=context.graph_execution_state_id, node=self
-        # )
-
-        # currently can't see processed image in node UI without a showImage node,
-        #    so for now setting image_type to RESULT instead of INTERMEDIATE so will get saved in gallery
-        image_dto = context.services.images.create(
-            image=processed_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.CONTROL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate
-        )
-
-        """Builds an ImageOutput and its ImageField"""
-        processed_image_field = ImageField(image_name=image_dto.image_name)
-        return ImageOutput(
-            image=processed_image_field,
-            # width=processed_image.width,
-            width = image_dto.width,
-            # height=processed_image.height,
-            height = image_dto.height,
-            # mode=processed_image.mode,
-        )
-
-
-class CannyImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Canny edge detection for ControlNet"""
-    # fmt: off
-    type: Literal["canny_image_processor"] = "canny_image_processor"
-    # Input
-    low_threshold: int = Field(default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)")
-    high_threshold: int = Field(default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)")
-    # fmt: on
-
-    def run_processor(self, image):
-        canny_processor = CannyDetector()
-        processed_image = canny_processor(image, self.low_threshold, self.high_threshold)
-        return processed_image
-
-
-class HedImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies HED edge detection to image"""
-    # fmt: off
-    type: Literal["hed_image_processor"] = "hed_image_processor"
-    # Inputs
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    # safe not supported in controlnet_aux v0.0.3
-    # safe: bool = Field(default=False, description="whether to use safe mode")
-    scribble: bool = Field(default=False, description="Whether to use scribble mode")
-    # fmt: on
-
-    def run_processor(self, image):
-        hed_processor = HEDdetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = hed_processor(image,
-                                        detect_resolution=self.detect_resolution,
-                                        image_resolution=self.image_resolution,
-                                        # safe not supported in controlnet_aux v0.0.3
-                                        # safe=self.safe,
-                                        scribble=self.scribble,
-                                        )
-        return processed_image
-
-
-class LineartImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies line art processing to image"""
-    # fmt: off
-    type: Literal["lineart_image_processor"] = "lineart_image_processor"
-    # Inputs
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    coarse: bool = Field(default=False, description="Whether to use coarse mode")
-    # fmt: on
-
-    def run_processor(self, image):
-        lineart_processor = LineartDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = lineart_processor(image,
-                                            detect_resolution=self.detect_resolution,
-                                            image_resolution=self.image_resolution,
-                                            coarse=self.coarse)
-        return processed_image
-
-
-class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies line art anime processing to image"""
-    # fmt: off
-    type: Literal["lineart_anime_image_processor"] = "lineart_anime_image_processor"
-    # Inputs
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    # fmt: on
-
-    def run_processor(self, image):
-        processor = LineartAnimeDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = processor(image,
-                                    detect_resolution=self.detect_resolution,
-                                    image_resolution=self.image_resolution,
-                                    )
-        return processed_image
-
-
-class OpenposeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies Openpose processing to image"""
-    # fmt: off
-    type: Literal["openpose_image_processor"] = "openpose_image_processor"
-    # Inputs
-    hand_and_face: bool = Field(default=False, description="Whether to use hands and face mode")
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    # fmt: on
-
-    def run_processor(self, image):
-        openpose_processor = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = openpose_processor(image,
-                                             detect_resolution=self.detect_resolution,
-                                             image_resolution=self.image_resolution,
-                                             hand_and_face=self.hand_and_face,
-                                             )
-        return processed_image
-
-
-class MidasDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies Midas depth processing to image"""
-    # fmt: off
-    type: Literal["midas_depth_image_processor"] = "midas_depth_image_processor"
-    # Inputs
-    a_mult: float = Field(default=2.0, ge=0, description="Midas parameter `a_mult` (a = a_mult * PI)")
-    bg_th: float = Field(default=0.1, ge=0, description="Midas parameter `bg_th`")
-    # depth_and_normal not supported in controlnet_aux v0.0.3
-    # depth_and_normal: bool = Field(default=False, description="whether to use depth and normal mode")
-    # fmt: on
-
-    def run_processor(self, image):
-        midas_processor = MidasDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = midas_processor(image,
-                                          a=np.pi * self.a_mult,
-                                          bg_th=self.bg_th,
-                                          # dept_and_normal not supported in controlnet_aux v0.0.3
-                                          # depth_and_normal=self.depth_and_normal,
-                                          )
-        return processed_image
-
-
-class NormalbaeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies NormalBae processing to image"""
-    # fmt: off
-    type: Literal["normalbae_image_processor"] = "normalbae_image_processor"
-    # Inputs
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    # fmt: on
-
-    def run_processor(self, image):
-        normalbae_processor = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = normalbae_processor(image,
-                                              detect_resolution=self.detect_resolution,
-                                              image_resolution=self.image_resolution)
-        return processed_image
-
-
-class MlsdImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies MLSD processing to image"""
-    # fmt: off
-    type: Literal["mlsd_image_processor"] = "mlsd_image_processor"
-    # Inputs
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    thr_v: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_v`")
-    thr_d: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_d`")
-    # fmt: on
-
-    def run_processor(self, image):
-        mlsd_processor = MLSDdetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = mlsd_processor(image,
-                                         detect_resolution=self.detect_resolution,
-                                         image_resolution=self.image_resolution,
-                                         thr_v=self.thr_v,
-                                         thr_d=self.thr_d)
-        return processed_image
-
-
-class PidiImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies PIDI processing to image"""
-    # fmt: off
-    type: Literal["pidi_image_processor"] = "pidi_image_processor"
-    # Inputs
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    safe: bool = Field(default=False, description="Whether to use safe mode")
-    scribble: bool = Field(default=False, description="Whether to use scribble mode")
-    # fmt: on
-
-    def run_processor(self, image):
-        pidi_processor = PidiNetDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = pidi_processor(image,
-                                         detect_resolution=self.detect_resolution,
-                                         image_resolution=self.image_resolution,
-                                         safe=self.safe,
-                                         scribble=self.scribble)
-        return processed_image
-
-
-class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies content shuffle processing to image"""
-    # fmt: off
-    type: Literal["content_shuffle_image_processor"] = "content_shuffle_image_processor"
-    # Inputs
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    h: Union[int, None] = Field(default=512, ge=0, description="Content shuffle `h` parameter")
-    w: Union[int, None] = Field(default=512, ge=0, description="Content shuffle `w` parameter")
-    f: Union[int, None] = Field(default=256, ge=0, description="Content shuffle `f` parameter")
-    # fmt: on
-
-    def run_processor(self, image):
-        content_shuffle_processor = ContentShuffleDetector()
-        processed_image = content_shuffle_processor(image,
-                                                    detect_resolution=self.detect_resolution,
-                                                    image_resolution=self.image_resolution,
-                                                    h=self.h,
-                                                    w=self.w,
-                                                    f=self.f
-                                                    )
-        return processed_image
-
-
-# should work with controlnet_aux >= 0.0.4 and timm <= 0.6.13
-class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies Zoe depth processing to image"""
-    # fmt: off
-    type: Literal["zoe_depth_image_processor"] = "zoe_depth_image_processor"
-    # fmt: on
-
-    def run_processor(self, image):
-        zoe_depth_processor = ZoeDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = zoe_depth_processor(image)
-        return processed_image
-
-
-class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies mediapipe face processing to image"""
-    # fmt: off
-    type: Literal["mediapipe_face_processor"] = "mediapipe_face_processor"
-    # Inputs
-    max_faces: int = Field(default=1, ge=1, description="Maximum number of faces to detect")
-    min_confidence: float = Field(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
-    # fmt: on
-
-    def run_processor(self, image):
-        # 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
-
-class LeresImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies leres processing to image"""
-    # fmt: off
-    type: Literal["leres_image_processor"] = "leres_image_processor"
-    # Inputs
-    thr_a: float = Field(default=0, description="Leres parameter `thr_a`")
-    thr_b: float = Field(default=0, description="Leres parameter `thr_b`")
-    boost: bool = Field(default=False, description="Whether to use boost mode")
-    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
-    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    # fmt: on
-
-    def run_processor(self, image):
-        leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = leres_processor(image,
-                                          thr_a=self.thr_a,
-                                          thr_b=self.thr_b,
-                                          boost=self.boost,
-                                          detect_resolution=self.detect_resolution,
-                                          image_resolution=self.image_resolution)
-        return processed_image
-
-
-class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-
-    # fmt: off
-    type: Literal["tile_image_processor"] = "tile_image_processor"
-    # Inputs
-    #res: int = Field(default=512, ge=0, le=1024, description="The pixel resolution for each tile")
-    down_sampling_rate: float = Field(default=1.0, ge=1.0, le=8.0, description="Down sampling rate")
-    # fmt: on
-
-    # tile_resample copied from sd-webui-controlnet/scripts/processor.py
-    def tile_resample(self,
-                      np_img: np.ndarray,
-                      res=512,   # never used?
-                      down_sampling_rate=1.0,
-                      ):
-        np_img = HWC3(np_img)
-        if down_sampling_rate < 1.1:
-            return np_img
-        H, W, C = np_img.shape
-        H = int(float(H) / float(down_sampling_rate))
-        W = int(float(W) / float(down_sampling_rate))
-        np_img = cv2.resize(np_img, (W, H), interpolation=cv2.INTER_AREA)
-        return np_img
-
-    def run_processor(self, img):
-        np_img = np.array(img, dtype=np.uint8)
-        processed_np_image = self.tile_resample(np_img,
-                                                #res=self.tile_size,
-                                                down_sampling_rate=self.down_sampling_rate
-                                                )
-        processed_image = Image.fromarray(processed_np_image)
-        return processed_image
-
-
-
-
-class SegmentAnythingProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
-    """Applies segment anything processing to image"""
-    # fmt: off
-    type: Literal["segment_anything_processor"] = "segment_anything_processor"
-    # fmt: on
-
-    def run_processor(self, image):
-        # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
-        segment_anything_processor = SamDetectorReproducibleColors.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
-        np_img = np.array(image, dtype=np.uint8)
-        processed_image = segment_anything_processor(np_img)
-        return processed_image
-
-class SamDetectorReproducibleColors(SamDetector):
-
-    # overriding SamDetector.show_anns() method to use reproducible colors for segmentation image
-    #     base class show_anns() method randomizes colors,
-    #     which seems to also lead to non-reproducible image generation
-    # so using ADE20k color palette instead
-    def show_anns(self, anns: List[Dict]):
-        if len(anns) == 0:
-            return
-        sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
-        h, w = anns[0]['segmentation'].shape
-        final_img = Image.fromarray(np.zeros((h, w, 3), dtype=np.uint8), mode="RGB")
-        palette = ade_palette()
-        for i, ann in enumerate(sorted_anns):
-            m = ann['segmentation']
-            img = np.empty((m.shape[0], m.shape[1], 3), dtype=np.uint8)
-            # doing modulo just in case number of annotated regions exceeds number of colors in palette
-            ann_color = palette[i % len(palette)]
-            img[:, :] = ann_color
-            final_img.paste(Image.fromarray(img, mode="RGB"), (0, 0), Image.fromarray(np.uint8(m * 255)))
-        return np.array(final_img, dtype=np.uint8)

invokeai/app/invocations/cv.py

@@ -7,9 +7,10 @@ import numpy
 from PIL import Image, ImageOps
 from pydantic import BaseModel, Field
 
-from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
+from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.modules.metadata import MetadataModule
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput
+from .image import ImageOutput, build_image_output
 
 
 class CvInvocationConfig(BaseModel):
@@ -26,23 +27,24 @@ class CvInvocationConfig(BaseModel):
 
 class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
     """Simple inpaint using opencv."""
-
-    # fmt: off
+    #fmt: off
     type: Literal["cv_inpaint"] = "cv_inpaint"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to inpaint")
     mask: ImageField = Field(default=None, description="The mask to use when inpainting")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        mask = context.services.images.get_pil_image(self.mask.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
+        mask = context.services.images.get(self.mask.image_type, self.mask.image_name)
 
         # Convert to cv image/mask
         # TODO: consider making these utility functions
         cv_image = cv.cvtColor(numpy.array(image.convert("RGB")), cv.COLOR_RGB2BGR)
-        cv_mask = numpy.array(ImageOps.invert(mask.convert("L")))
+        cv_mask = numpy.array(ImageOps.invert(mask))
 
         # Inpaint
         cv_inpainted = cv.inpaint(cv_image, cv_mask, 3, cv.INPAINT_TELEA)
@@ -51,17 +53,18 @@ class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
         # TODO: consider making a utility function
         image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
 
-        image_dto = context.services.images.create(
-            image=image_inpainted,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
+        image_type = ImageType.INTERMEDIATE
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
         )
+        
+        context.services.images.save(image_type, image_name, image_inpainted, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image_inpainted,
+        )

invokeai/app/invocations/generate.py

@@ -1,79 +1,122 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 from functools import partial
-from typing import Literal, Optional, Union, get_args
+from typing import Literal, Optional, Union
+
+import numpy as np
+from torch import Tensor
 
-import torch
-from diffusers import ControlNetModel
 from pydantic import BaseModel, Field
 
-from invokeai.app.models.image import (ColorField, ImageCategory, ImageField,
-                                       ResourceOrigin)
-from invokeai.app.util.misc import SEED_MAX, get_random_seed
-from invokeai.backend.generator.inpaint import infill_methods
-
-from ...backend.generator import Inpaint, InvokeAIGenerator
+from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.invocations.util.choose_model import choose_model
+from invokeai.app.modules.metadata import MetadataModule
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
+from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ..util.step_callback import stable_diffusion_step_callback
-from .baseinvocation import BaseInvocation, InvocationConfig, InvocationContext
-from .image import ImageOutput
-
-import re
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
-from .model import UNetField, VaeField
-from .compel import ConditioningField
-from contextlib import contextmanager, ExitStack, ContextDecorator
 
 SAMPLER_NAME_VALUES = Literal[tuple(InvokeAIGenerator.schedulers())]
-INFILL_METHODS = Literal[tuple(infill_methods())]
-DEFAULT_INFILL_METHOD = (
-    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
-)
 
 
-from .latent import get_scheduler
+class SDImageInvocation(BaseModel):
+    """Helper class to provide all Stable Diffusion raster image invocations with additional config"""
 
-class OldModelContext(ContextDecorator):
-    model: StableDiffusionGeneratorPipeline
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["stable-diffusion", "image"],
+                "type_hints": {
+                    "model": "model",
+                },
+            },
+        }
 
-    def __init__(self, model):
-        self.model = model
 
-    def __enter__(self):
-        return self.model
+# Text to image
+class TextToImageInvocation(BaseInvocation, SDImageInvocation):
+    """Generates an image using text2img."""
 
-    def __exit__(self, *exc):
-        return False
+    type: Literal["txt2img"] = "txt2img"
 
-class OldModelInfo:
-    name: str
-    hash: str
-    context: OldModelContext
+    # Inputs
+    # TODO: consider making prompt optional to enable providing prompt through a link
+    # fmt: off
+    prompt: Optional[str] = Field(description="The prompt to generate an image from")
+    seed:        int = Field(default=-1,ge=-1, le=np.iinfo(np.uint32).max, description="The seed to use (-1 for a random seed)", )
+    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
+    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting image", )
+    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting image", )
+    cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
+    seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    model:       str = Field(default="", description="The model to use (currently ignored)")
+    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
+    # fmt: on
 
-    def __init__(self, name: str, hash: str, model: StableDiffusionGeneratorPipeline):
-        self.name = name
-        self.hash = hash
-        self.context = OldModelContext(
-            model=model,
+    # TODO: pass this an emitter method or something? or a session for dispatching?
+    def dispatch_progress(
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            invocation_dict=self.dict(),
+            source_node_id=source_node_id,
+        )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Handle invalid model parameter
+        model = choose_model(context.services.model_manager, self.model)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id
+        )
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        outputs = Txt2Img(model).generate(
+            prompt=self.prompt,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            **self.dict(
+                exclude={"prompt"}
+            ),  # Shorthand for passing all of the parameters above manually
+        )
+        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
+        # each time it is called. We only need the first one.
+        generate_output = next(outputs)
+
+        # Results are image and seed, unwrap for now and ignore the seed
+        # TODO: pre-seed?
+        # TODO: can this return multiple results? Should it?
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
+        )
+
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
+        )
+
+        context.services.images.save(
+            image_type, image_name, generate_output.image, metadata
+        )
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=generate_output.image,
         )
 
 
-class InpaintInvocation(BaseInvocation):
-    """Generates an image using inpaint."""
+class ImageToImageInvocation(TextToImageInvocation):
+    """Generates an image using img2img."""
 
-    type: Literal["inpaint"] = "inpaint"
-
-    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
-    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
-    seed:        int = Field(ge=0, le=SEED_MAX, description="The seed to use (omit for random)", default_factory=get_random_seed)
-    steps:       int = Field(default=30, gt=0, description="The number of steps to use to generate the image")
-    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting image", )
-    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting image", )
-    cfg_scale: float = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
-    unet: UNetField = Field(default=None, description="UNet model")
-    vae: VaeField = Field(default=None, description="Vae model")
+    type: Literal["img2img"] = "img2img"
 
     # Inputs
     image: Union[ImageField, None] = Field(description="The input image")
@@ -85,41 +128,81 @@ class InpaintInvocation(BaseInvocation):
         description="Whether or not the result should be fit to the aspect ratio of the input image",
     )
 
+    def dispatch_progress(
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            invocation_dict=self.dict(),
+            source_node_id=source_node_id,
+        )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = (
+            None
+            if self.image is None
+            else context.services.images.get(
+                self.image.image_type, self.image.image_name
+            )
+        )
+        mask = None
+
+        # Handle invalid model parameter
+        model = choose_model(context.services.model_manager, self.model)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id
+        )
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        outputs = Img2Img(model).generate(
+            prompt=self.prompt,
+            init_image=image,
+            init_mask=mask,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            **self.dict(
+                exclude={"prompt", "image", "mask"}
+            ),  # Shorthand for passing all of the parameters above manually
+        )
+
+        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
+        # each time it is called. We only need the first one.
+        generator_output = next(outputs)
+
+        result_image = generator_output.image
+
+        # Results are image and seed, unwrap for now and ignore the seed
+        # TODO: pre-seed?
+        # TODO: can this return multiple results? Should it?
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
+        )
+
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
+        )
+
+        context.services.images.save(image_type, image_name, result_image, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=result_image,
+        )
+
+
+class InpaintInvocation(ImageToImageInvocation):
+    """Generates an image using inpaint."""
+
+    type: Literal["inpaint"] = "inpaint"
+
     # Inputs
     mask: Union[ImageField, None] = Field(description="The mask")
-    seam_size: int = Field(default=96, ge=1, description="The seam inpaint size (px)")
-    seam_blur: int = Field(
-        default=16, ge=0, description="The seam inpaint blur radius (px)"
-    )
-    seam_strength: float = Field(
-        default=0.75, gt=0, le=1, description="The seam inpaint strength"
-    )
-    seam_steps: int = Field(
-        default=30, ge=1, description="The number of steps to use for seam inpaint"
-    )
-    tile_size: int = Field(
-        default=32, ge=1, description="The tile infill method size (px)"
-    )
-    infill_method: INFILL_METHODS = Field(
-        default=DEFAULT_INFILL_METHOD,
-        description="The method used to infill empty regions (px)",
-    )
-    inpaint_width: Optional[int] = Field(
-        default=None,
-        multiple_of=8,
-        gt=0,
-        description="The width of the inpaint region (px)",
-    )
-    inpaint_height: Optional[int] = Field(
-        default=None,
-        multiple_of=8,
-        gt=0,
-        description="The height of the inpaint region (px)",
-    )
-    inpaint_fill: Optional[ColorField] = Field(
-        default=ColorField(r=127, g=127, b=127, a=255),
-        description="The solid infill method color",
-    )
     inpaint_replace: float = Field(
         default=0.0,
         ge=0.0,
@@ -127,14 +210,6 @@ class InpaintInvocation(BaseInvocation):
         description="The amount by which to replace masked areas with latent noise",
     )
 
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["stable-diffusion", "image"],
-            },
-        }
-
     def dispatch_progress(
         self,
         context: InvocationContext,
@@ -144,105 +219,64 @@ class InpaintInvocation(BaseInvocation):
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
-            node=self.dict(),
+            invocation_dict=self.dict(),
             source_node_id=source_node_id,
         )
 
-    def get_conditioning(self, context):
-        c, extra_conditioning_info = context.services.latents.get(self.positive_conditioning.conditioning_name)
-        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
-
-        return (uc, c, extra_conditioning_info)
-
-    @contextmanager
-    def load_model_old_way(self, context, scheduler):
-        unet_info = context.services.model_manager.get_model(**self.unet.unet.dict())
-        vae_info = context.services.model_manager.get_model(**self.vae.vae.dict())
-
-        #unet = unet_info.context.model
-        #vae = vae_info.context.model
-
-        with ExitStack() as stack:
-            loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
-
-            with vae_info as vae,\
-                 unet_info as unet,\
-                 ModelPatcher.apply_lora_unet(unet, loras):
-
-                device = context.services.model_manager.mgr.cache.execution_device
-                dtype = context.services.model_manager.mgr.cache.precision
-
-                pipeline = StableDiffusionGeneratorPipeline(
-                    vae=vae,
-                    text_encoder=None,
-                    tokenizer=None,
-                    unet=unet,
-                    scheduler=scheduler,
-                    safety_checker=None,
-                    feature_extractor=None,
-                    requires_safety_checker=False,
-                    precision="float16" if dtype == torch.float16 else "float32",
-                    execution_device=device,
-                )
-
-                yield OldModelInfo(
-                    name=self.unet.unet.model_name,
-                    hash="<NO-HASH>",
-                    model=pipeline,
-                )
-
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
             None
             if self.image is None
-            else context.services.images.get_pil_image(self.image.image_name)
+            else context.services.images.get(
+                self.image.image_type, self.image.image_name
+            )
         )
         mask = (
             None
             if self.mask is None
-            else context.services.images.get_pil_image(self.mask.image_name)
+            else context.services.images.get(self.mask.image_type, self.mask.image_name)
         )
 
+        # Handle invalid model parameter
+        model = choose_model(context.services.model_manager, self.model)
+
         # Get the source node id (we are invoking the prepared node)
         graph_execution_state = context.services.graph_execution_manager.get(
             context.graph_execution_state_id
         )
         source_node_id = graph_execution_state.prepared_source_mapping[self.id]
 
-        conditioning = self.get_conditioning(context)
-        scheduler = get_scheduler(
-            context=context,
-            scheduler_info=self.unet.scheduler,
-            scheduler_name=self.scheduler,
+        outputs = Inpaint(model).generate(
+            prompt=self.prompt,
+            init_img=image,
+            init_mask=mask,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            **self.dict(
+                exclude={"prompt", "image", "mask"}
+            ),  # Shorthand for passing all of the parameters above manually
         )
 
-        with self.load_model_old_way(context, scheduler) as model:
-            outputs = Inpaint(model).generate(
-                conditioning=conditioning,
-                scheduler=scheduler,
-                init_image=image,
-                mask_image=mask,
-                step_callback=partial(self.dispatch_progress, context, source_node_id),
-                **self.dict(
-                    exclude={"positive_conditioning", "negative_conditioning", "scheduler", "image", "mask"}
-                ),  # Shorthand for passing all of the parameters above manually
-            )
-
         # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
         # each time it is called. We only need the first one.
         generator_output = next(outputs)
 
-        image_dto = context.services.images.create(
-            image=generator_output.image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
+        result_image = generator_output.image
+
+        # Results are image and seed, unwrap for now and ignore the seed
+        # TODO: pre-seed?
+        # TODO: can this return multiple results? Should it?
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
+        )
+
+        context.services.images.save(image_type, image_name, result_image, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=result_image,
         )

invokeai/app/invocations/image.py

@@ -1,13 +1,14 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-import io
-from typing import Literal, Optional, Union
+from typing import Literal, Optional
 
 import numpy
-from PIL import Image, ImageFilter, ImageOps, ImageChops
+from PIL import Image, ImageFilter, ImageOps
 from pydantic import BaseModel, Field
 
-from ..models.image import ImageCategory, ImageField, ResourceOrigin
+from invokeai.app.modules.metadata import MetadataModule
+
+from ..models.image import ImageField, ImageType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -31,14 +32,33 @@ class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
 
     # fmt: off
-    type: Literal["image_output"] = "image_output"
+    type: Literal["image"] = "image"
     image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
+    width:   Optional[int] = Field(default=None, description="The width of the image in pixels")
+    height:  Optional[int] = Field(default=None, description="The height of the image in pixels")
+    mode:    Optional[str] = Field(default=None, description="The image mode (ie pixel format)")
     # fmt: on
 
     class Config:
-        schema_extra = {"required": ["type", "image", "width", "height"]}
+        schema_extra = {
+            "required": ["type", "image", "width", "height", "mode"]
+        }
+
+
+def build_image_output(
+    image_type: ImageType, image_name: str, image: Image.Image
+) -> ImageOutput:
+    """Builds an ImageOutput and its ImageField"""
+    image_field = ImageField(
+        image_name=image_name,
+        image_type=image_type,
+    )
+    return ImageOutput(
+        image=image_field,
+        width=image.width,
+        height=image.height,
+        mode=image.mode,
+    )
 
 
 class MaskOutput(BaseInvocationOutput):
@@ -47,8 +67,6 @@ class MaskOutput(BaseInvocationOutput):
     # fmt: off
     type: Literal["mask"] = "mask"
     mask:      ImageField = Field(default=None, description="The output mask")
-    width:            int = Field(description="The width of the mask in pixels")
-    height:           int = Field(description="The height of the mask in pixels")
     # fmt: on
 
     class Config:
@@ -67,17 +85,16 @@ class LoadImageInvocation(BaseInvocation):
     type: Literal["load_image"] = "load_image"
 
     # Inputs
-    image: Union[ImageField, None] = Field(
-        default=None, description="The image to load"
-    )
+    image_type: ImageType = Field(description="The type of the image")
+    image_name:       str = Field(description="The name of the image")
     # fmt: on
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(self.image_type, self.image_name)
 
-        return ImageOutput(
-            image=ImageField(image_name=self.image.image_name),
-            width=image.width,
-            height=image.height,
+        return build_image_output(
+            image_type=self.image_type,
+            image_name=self.image_name,
+            image=image,
         )
 
 
@@ -87,32 +104,32 @@ class ShowImageInvocation(BaseInvocation):
     type: Literal["show_image"] = "show_image"
 
     # Inputs
-    image: Union[ImageField, None] = Field(
-        default=None, description="The image to show"
-    )
+    image: ImageField = Field(default=None, description="The image to show")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
         if image:
             image.show()
 
         # TODO: how to handle failure?
 
-        return ImageOutput(
-            image=ImageField(image_name=self.image.image_name),
-            width=image.width,
-            height=image.height,
+        return build_image_output(
+            image_type=self.image.image_type,
+            image_name=self.image.image_name,
+            image=image,
         )
 
 
-class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
+class CropImageInvocation(BaseInvocation, PILInvocationConfig):
     """Crops an image to a specified box. The box can be outside of the image."""
 
     # fmt: off
-    type: Literal["img_crop"] = "img_crop"
+    type: Literal["crop"] = "crop"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to crop")
+    image: ImageField = Field(default=None, description="The image to crop")
     x:      int = Field(default=0, description="The left x coordinate of the crop rectangle")
     y:      int = Field(default=0, description="The top y coordinate of the crop rectangle")
     width:  int = Field(default=512, gt=0, description="The width of the crop rectangle")
@@ -120,51 +137,58 @@ class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
 
         image_crop = Image.new(
             mode="RGBA", size=(self.width, self.height), color=(0, 0, 0, 0)
         )
         image_crop.paste(image, (-self.x, -self.y))
 
-        image_dto = context.services.images.create(
+        image_type = ImageType.INTERMEDIATE
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
+        )
+
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
+        )
+        
+        context.services.images.save(image_type, image_name, image_crop, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
             image=image_crop,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
         )
 
 
-class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
+class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
     """Pastes an image into another image."""
 
     # fmt: off
-    type: Literal["img_paste"] = "img_paste"
+    type: Literal["paste"] = "paste"
 
     # Inputs
-    base_image:     Union[ImageField, None]  = Field(default=None, description="The base image")
-    image:          Union[ImageField, None]  = Field(default=None, description="The image to paste")
+    base_image:     ImageField = Field(default=None, description="The base image")
+    image:          ImageField = Field(default=None, description="The image to paste")
     mask: Optional[ImageField] = Field(default=None, description="The mask to use when pasting")
     x:                     int = Field(default=0, description="The left x coordinate at which to paste the image")
     y:                     int = Field(default=0, description="The top y coordinate at which to paste the image")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        base_image = context.services.images.get_pil_image(self.base_image.image_name)
-        image = context.services.images.get_pil_image(self.image.image_name)
+        base_image = context.services.images.get(
+            self.base_image.image_type, self.base_image.image_name
+        )
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
         mask = (
             None
             if self.mask is None
             else ImageOps.invert(
-                context.services.images.get_pil_image(self.mask.image_name)
+                context.services.images.get(self.mask.image_type, self.mask.image_name)
             )
         )
         # TODO: probably shouldn't invert mask here... should user be required to do it?
@@ -180,19 +204,20 @@ class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
         new_image.paste(base_image, (abs(min_x), abs(min_y)))
         new_image.paste(image, (max(0, self.x), max(0, self.y)), mask=mask)
 
-        image_dto = context.services.images.create(
-            image=new_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
+        )
+        
+        context.services.images.save(image_type, image_name, new_image, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=new_image,
         )
 
 
@@ -203,150 +228,48 @@ class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["tomask"] = "tomask"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to create the mask from")
+    image: ImageField = Field(default=None, description="The image to create the mask from")
     invert:      bool = Field(default=False, description="Whether or not to invert the mask")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> MaskOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
 
         image_mask = image.split()[-1]
         if self.invert:
             image_mask = ImageOps.invert(image_mask)
 
-        image_dto = context.services.images.create(
-            image=image_mask,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
+        image_type = ImageType.INTERMEDIATE
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return MaskOutput(
-            mask=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
         )
 
-
-class ImageMultiplyInvocation(BaseInvocation, PILInvocationConfig):
-    """Multiplies two images together using `PIL.ImageChops.multiply()`."""
-
-    # fmt: off
-    type: Literal["img_mul"] = "img_mul"
-
-    # Inputs
-    image1: Union[ImageField, None]  = Field(default=None, description="The first image to multiply")
-    image2: Union[ImageField, None]  = Field(default=None, description="The second image to multiply")
-    # fmt: on
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image1 = context.services.images.get_pil_image(self.image1.image_name)
-        image2 = context.services.images.get_pil_image(self.image2.image_name)
-
-        multiply_image = ImageChops.multiply(image1, image2)
-
-        image_dto = context.services.images.create(
-            image=multiply_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        context.services.images.save(image_type, image_name, image_mask, metadata)
+        return MaskOutput(mask=ImageField(image_type=image_type, image_name=image_name))
 
 
-IMAGE_CHANNELS = Literal["A", "R", "G", "B"]
-
-
-class ImageChannelInvocation(BaseInvocation, PILInvocationConfig):
-    """Gets a channel from an image."""
-
-    # fmt: off
-    type: Literal["img_chan"] = "img_chan"
-
-    # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to get the channel from")
-    channel: IMAGE_CHANNELS  = Field(default="A", description="The channel to get")
-    # fmt: on
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        channel_image = image.getchannel(self.channel)
-
-        image_dto = context.services.images.create(
-            image=channel_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
-
-
-class ImageConvertInvocation(BaseInvocation, PILInvocationConfig):
-    """Converts an image to a different mode."""
-
-    # fmt: off
-    type: Literal["img_conv"] = "img_conv"
-
-    # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to convert")
-    mode: IMAGE_MODES  = Field(default="L", description="The mode to convert to")
-    # fmt: on
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        converted_image = image.convert(self.mode)
-
-        image_dto = context.services.images.create(
-            image=converted_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
+class BlurInvocation(BaseInvocation, PILInvocationConfig):
     """Blurs an image"""
 
     # fmt: off
-    type: Literal["img_blur"] = "img_blur"
+    type: Literal["blur"] = "blur"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to blur")
+    image: ImageField = Field(default=None, description="The image to blur")
     radius:     float = Field(default=8.0, ge=0, description="The blur radius")
     blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
 
         blur = (
             ImageFilter.GaussianBlur(self.radius)
@@ -355,171 +278,74 @@ class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
         )
         blur_image = image.filter(blur)
 
-        image_dto = context.services.images.create(
-            image=blur_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
+        image_type = ImageType.INTERMEDIATE
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
+        )
+
+        context.services.images.save(image_type, image_name, blur_image, metadata)
+        return build_image_output(
+            image_type=image_type, image_name=image_name, image=blur_image
         )
 
 
-PIL_RESAMPLING_MODES = Literal[
-    "nearest",
-    "box",
-    "bilinear",
-    "hamming",
-    "bicubic",
-    "lanczos",
-]
-
-
-PIL_RESAMPLING_MAP = {
-    "nearest": Image.Resampling.NEAREST,
-    "box": Image.Resampling.BOX,
-    "bilinear": Image.Resampling.BILINEAR,
-    "hamming": Image.Resampling.HAMMING,
-    "bicubic": Image.Resampling.BICUBIC,
-    "lanczos": Image.Resampling.LANCZOS,
-}
-
-
-class ImageResizeInvocation(BaseInvocation, PILInvocationConfig):
-    """Resizes an image to specific dimensions"""
-
-    # fmt: off
-    type: Literal["img_resize"] = "img_resize"
-
-    # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to resize")
-    width:                         int = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
-    height:                        int = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
-    resample_mode:  PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
-    # fmt: on
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
-
-        resize_image = image.resize(
-            (self.width, self.height),
-            resample=resample_mode,
-        )
-
-        image_dto = context.services.images.create(
-            image=resize_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-class ImageScaleInvocation(BaseInvocation, PILInvocationConfig):
-    """Scales an image by a factor"""
-
-    # fmt: off
-    type: Literal["img_scale"] = "img_scale"
-
-    # Inputs
-    image:       Union[ImageField, None] = Field(default=None, description="The image to scale")
-    scale_factor:                  float = Field(gt=0, description="The factor by which to scale the image")
-    resample_mode:  PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
-    # fmt: on
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
-        width = int(image.width * self.scale_factor)
-        height = int(image.height * self.scale_factor)
-
-        resize_image = image.resize(
-            (width, height),
-            resample=resample_mode,
-        )
-
-        image_dto = context.services.images.create(
-            image=resize_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-class ImageLerpInvocation(BaseInvocation, PILInvocationConfig):
+class LerpInvocation(BaseInvocation, PILInvocationConfig):
     """Linear interpolation of all pixels of an image"""
 
     # fmt: off
-    type: Literal["img_lerp"] = "img_lerp"
+    type: Literal["lerp"] = "lerp"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to lerp")
+    image: ImageField = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum output value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum output value")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
 
         image_arr = numpy.asarray(image, dtype=numpy.float32) / 255
         image_arr = image_arr * (self.max - self.min) + self.max
 
         lerp_image = Image.fromarray(numpy.uint8(image_arr))
 
-        image_dto = context.services.images.create(
-            image=lerp_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
+        image_type = ImageType.INTERMEDIATE
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
+        )
+
+        context.services.images.save(image_type, image_name, lerp_image, metadata)
+        return build_image_output(
+            image_type=image_type, image_name=image_name, image=lerp_image
         )
 
 
-class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
+class InverseLerpInvocation(BaseInvocation, PILInvocationConfig):
     """Inverse linear interpolation of all pixels of an image"""
 
     # fmt: off
-    type: Literal["img_ilerp"] = "img_ilerp"
+    type: Literal["ilerp"] = "ilerp"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to lerp")
+    image: ImageField = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum input value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum input value")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
 
         image_arr = numpy.asarray(image, dtype=numpy.float32)
         image_arr = (
@@ -531,17 +357,16 @@ class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
 
         ilerp_image = Image.fromarray(numpy.uint8(image_arr))
 
-        image_dto = context.services.images.create(
-            image=ilerp_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
+        image_type = ImageType.INTERMEDIATE
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
+        )
+
+        context.services.images.save(image_type, image_name, ilerp_image, metadata)
+        return build_image_output(
+            image_type=image_type, image_name=image_name, image=ilerp_image
         )

invokeai/app/invocations/infill.py

@@ -1,230 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
-
-from typing import Literal, Union, get_args
-
-import numpy as np
-import math
-from PIL import Image, ImageOps
-from pydantic import Field
-
-from invokeai.app.invocations.image import ImageOutput
-from invokeai.app.util.misc import SEED_MAX, get_random_seed
-from invokeai.backend.image_util.patchmatch import PatchMatch
-
-from ..models.image import ColorField, ImageCategory, ImageField, ResourceOrigin
-from .baseinvocation import (
-    BaseInvocation,
-    InvocationContext,
-)
-
-
-def infill_methods() -> list[str]:
-    methods = [
-        "tile",
-        "solid",
-    ]
-    if PatchMatch.patchmatch_available():
-        methods.insert(0, "patchmatch")
-    return methods
-
-
-INFILL_METHODS = Literal[tuple(infill_methods())]
-DEFAULT_INFILL_METHOD = (
-    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
-)
-
-
-def infill_patchmatch(im: Image.Image) -> Image.Image:
-    if im.mode != "RGBA":
-        return im
-
-    # Skip patchmatch if patchmatch isn't available
-    if not PatchMatch.patchmatch_available():
-        return im
-
-    # Patchmatch (note, we may want to expose patch_size? Increasing it significantly impacts performance though)
-    im_patched_np = PatchMatch.inpaint(
-        im.convert("RGB"), ImageOps.invert(im.split()[-1]), patch_size=3
-    )
-    im_patched = Image.fromarray(im_patched_np, mode="RGB")
-    return im_patched
-
-
-def get_tile_images(image: np.ndarray, width=8, height=8):
-    _nrows, _ncols, depth = image.shape
-    _strides = image.strides
-
-    nrows, _m = divmod(_nrows, height)
-    ncols, _n = divmod(_ncols, width)
-    if _m != 0 or _n != 0:
-        return None
-
-    return np.lib.stride_tricks.as_strided(
-        np.ravel(image),
-        shape=(nrows, ncols, height, width, depth),
-        strides=(height * _strides[0], width * _strides[1], *_strides),
-        writeable=False,
-    )
-
-
-def tile_fill_missing(
-    im: Image.Image, tile_size: int = 16, seed: Union[int, None] = None
-) -> Image.Image:
-    # Only fill if there's an alpha layer
-    if im.mode != "RGBA":
-        return im
-
-    a = np.asarray(im, dtype=np.uint8)
-
-    tile_size_tuple = (tile_size, tile_size)
-
-    # Get the image as tiles of a specified size
-    tiles = get_tile_images(a, *tile_size_tuple).copy()
-
-    # Get the mask as tiles
-    tiles_mask = tiles[:, :, :, :, 3]
-
-    # Find any mask tiles with any fully transparent pixels (we will be replacing these later)
-    tmask_shape = tiles_mask.shape
-    tiles_mask = tiles_mask.reshape(math.prod(tiles_mask.shape))
-    n, ny = (math.prod(tmask_shape[0:2])), math.prod(tmask_shape[2:])
-    tiles_mask = tiles_mask > 0
-    tiles_mask = tiles_mask.reshape((n, ny)).all(axis=1)
-
-    # Get RGB tiles in single array and filter by the mask
-    tshape = tiles.shape
-    tiles_all = tiles.reshape((math.prod(tiles.shape[0:2]), *tiles.shape[2:]))
-    filtered_tiles = tiles_all[tiles_mask]
-
-    if len(filtered_tiles) == 0:
-        return im
-
-    # Find all invalid tiles and replace with a random valid tile
-    replace_count = (tiles_mask == False).sum()
-    rng = np.random.default_rng(seed=seed)
-    tiles_all[np.logical_not(tiles_mask)] = filtered_tiles[
-        rng.choice(filtered_tiles.shape[0], replace_count), :, :, :
-    ]
-
-    # Convert back to an image
-    tiles_all = tiles_all.reshape(tshape)
-    tiles_all = tiles_all.swapaxes(1, 2)
-    st = tiles_all.reshape(
-        (
-            math.prod(tiles_all.shape[0:2]),
-            math.prod(tiles_all.shape[2:4]),
-            tiles_all.shape[4],
-        )
-    )
-    si = Image.fromarray(st, mode="RGBA")
-
-    return si
-
-
-class InfillColorInvocation(BaseInvocation):
-    """Infills transparent areas of an image with a solid color"""
-
-    type: Literal["infill_rgba"] = "infill_rgba"
-    image: Union[ImageField, None] = Field(
-        default=None, description="The image to infill"
-    )
-    color: ColorField = Field(
-        default=ColorField(r=127, g=127, b=127, a=255),
-        description="The color to use to infill",
-    )
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        solid_bg = Image.new("RGBA", image.size, self.color.tuple())
-        infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
-
-        infilled.paste(image, (0, 0), image.split()[-1])
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-class InfillTileInvocation(BaseInvocation):
-    """Infills transparent areas of an image with tiles of the image"""
-
-    type: Literal["infill_tile"] = "infill_tile"
-
-    image: Union[ImageField, None] = Field(
-        default=None, description="The image to infill"
-    )
-    tile_size: int = Field(default=32, ge=1, description="The tile size (px)")
-    seed: int = Field(
-        ge=0,
-        le=SEED_MAX,
-        description="The seed to use for tile generation (omit for random)",
-        default_factory=get_random_seed,
-    )
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        infilled = tile_fill_missing(
-            image.copy(), seed=self.seed, tile_size=self.tile_size
-        )
-        infilled.paste(image, (0, 0), image.split()[-1])
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-class InfillPatchMatchInvocation(BaseInvocation):
-    """Infills transparent areas of an image using the PatchMatch algorithm"""
-
-    type: Literal["infill_patchmatch"] = "infill_patchmatch"
-
-    image: Union[ImageField, None] = Field(
-        default=None, description="The image to infill"
-    )
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        if PatchMatch.patchmatch_available():
-            infilled = infill_patchmatch(image.copy())
-        else:
-            raise ValueError("PatchMatch is not available on this system")
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )

invokeai/app/invocations/latent.py

@@ -1,133 +1,170 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-from contextlib import ExitStack
-from typing import List, Literal, Optional, Union
-
-import einops
-
-from pydantic import BaseModel, Field, validator
+import random
+from typing import Literal, Optional
+from pydantic import BaseModel, Field
 import torch
-from diffusers import ControlNetModel, DPMSolverMultistepScheduler
-from diffusers.image_processor import VaeImageProcessor
-from diffusers.schedulers import SchedulerMixin as Scheduler
 
-from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.app.invocations.util.choose_model import choose_model
+from invokeai.app.modules.metadata import MetadataModule
+
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
 
-from ..models.image import ImageCategory, ImageField, ResourceOrigin
+from ...backend.model_management.model_manager import ModelManager
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
 from ...backend.image_util.seamless import configure_model_padding
+from ...backend.prompting.conditioning import get_uc_and_c_and_ec
+from ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+import numpy as np
+from ..services.image_storage import ImageType
+from .baseinvocation import BaseInvocation, InvocationContext
+from .image import ImageField, ImageOutput, build_image_output
 from ...backend.stable_diffusion import PipelineIntermediateState
-from ...backend.stable_diffusion.diffusers_pipeline import (
-    ConditioningData, ControlNetData, StableDiffusionGeneratorPipeline,
-    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 torch_dtype
-from ...backend.model_management.lora import ModelPatcher
-from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
-                             InvocationConfig, InvocationContext)
-from .compel import ConditioningField
-from .controlnet_image_processors import ControlField
-from .image import ImageOutput
-from .model import ModelInfo, UNetField, VaeField
+from diffusers.schedulers import SchedulerMixin as Scheduler
+import diffusers
+from diffusers import DiffusionPipeline
+
 
 class LatentsField(BaseModel):
     """A latents field used for passing latents between invocations"""
 
     latents_name: Optional[str] = Field(default=None, description="The name of the latents")
 
-    class Config:
-        schema_extra = {"required": ["latents_name"]}
 
 class LatentsOutput(BaseInvocationOutput):
     """Base class for invocations that output latents"""
     #fmt: off
-    type: Literal["latents_output"] = "latents_output"
+    type: Literal["latent_output"] = "latent_output"
+    latents: LatentsField            = Field(default=None, description="The output latents")
+    #fmt: on
 
-    # Inputs
-    latents: LatentsField          = Field(default=None, description="The output latents")
-    width:                     int = Field(description="The width of the latents in pixels")
-    height:                    int = Field(description="The height of the latents in pixels")
+class NoiseOutput(BaseInvocationOutput):
+    """Invocation noise output"""
+    #fmt: off
+    type: Literal["noise_output"] = "noise_output"
+    noise: LatentsField            = Field(default=None, description="The output noise")
     #fmt: on
 
 
-def build_latents_output(latents_name: str, latents: torch.Tensor):
-      return LatentsOutput(
-          latents=LatentsField(latents_name=latents_name),
-          width=latents.size()[3] * 8,
-          height=latents.size()[2] * 8,
-      )
+# TODO: this seems like a hack
+scheduler_map = dict(
+    ddim=diffusers.DDIMScheduler,
+    dpmpp_2=diffusers.DPMSolverMultistepScheduler,
+    k_dpm_2=diffusers.KDPM2DiscreteScheduler,
+    k_dpm_2_a=diffusers.KDPM2AncestralDiscreteScheduler,
+    k_dpmpp_2=diffusers.DPMSolverMultistepScheduler,
+    k_euler=diffusers.EulerDiscreteScheduler,
+    k_euler_a=diffusers.EulerAncestralDiscreteScheduler,
+    k_heun=diffusers.HeunDiscreteScheduler,
+    k_lms=diffusers.LMSDiscreteScheduler,
+    plms=diffusers.PNDMScheduler,
+)
 
 
 SAMPLER_NAME_VALUES = Literal[
-    tuple(list(SCHEDULER_MAP.keys()))
+    tuple(list(scheduler_map.keys()))
 ]
 
 
-def get_scheduler(
-    context: InvocationContext,
-    scheduler_info: ModelInfo,
-    scheduler_name: str,
-) -> Scheduler:
-    scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
-    orig_scheduler_info = context.services.model_manager.get_model(**scheduler_info.dict())
-    with orig_scheduler_info as orig_scheduler:
-        scheduler_config = orig_scheduler.config
-        
-    if "_backup" in scheduler_config:
-        scheduler_config = scheduler_config["_backup"]
-    scheduler_config = {**scheduler_config, **scheduler_extra_config, "_backup": scheduler_config}
-    scheduler = scheduler_class.from_config(scheduler_config)
-    
+def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
+    scheduler_class = scheduler_map.get(scheduler_name,'ddim')
+    scheduler = scheduler_class.from_config(model.scheduler.config)
     # hack copied over from generate.py
     if not hasattr(scheduler, 'uses_inpainting_model'):
         scheduler.uses_inpainting_model = lambda: False
     return scheduler
 
 
-# Text to image
-class TextToLatentsInvocation(BaseInvocation):
-    """Generates latents from conditionings."""
+def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_channels:int=4, use_mps_noise:bool=False, downsampling_factor:int = 8):
+    # limit noise to only the diffusion image channels, not the mask channels
+    input_channels = min(latent_channels, 4)
+    use_device = "cpu" if (use_mps_noise or device.type == "mps") else device
+    generator = torch.Generator(device=use_device).manual_seed(seed)
+    x = torch.randn(
+        [
+            1,
+            input_channels,
+            height // downsampling_factor,
+            width //  downsampling_factor,
+        ],
+        dtype=torch_dtype(device),
+        device=use_device,
+        generator=generator,
+    ).to(device)
+    # if self.perlin > 0.0:
+    #     perlin_noise = self.get_perlin_noise(
+    #         width // self.downsampling_factor, height // self.downsampling_factor
+    #     )
+    #     x = (1 - self.perlin) * x + self.perlin * perlin_noise
+    return x
 
-    type: Literal["t2l"] = "t2l"
+
+def random_seed():
+    return random.randint(0, np.iinfo(np.uint32).max)
+
+
+class NoiseInvocation(BaseInvocation):
+    """Generates latent noise."""
+
+    type: Literal["noise"] = "noise"
 
     # Inputs
-    # fmt: off
-    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
-    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
-    noise: Optional[LatentsField] = Field(description="The noise to use")
-    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
-    cfg_scale: Union[float, List[float]] = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
-    unet: UNetField = Field(default=None, description="UNet submodel")
-    control: Union[ControlField, list[ControlField]] = Field(default=None, description="The control to use")
-    #seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
-    #seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
-    # fmt: on
+    seed:        int = Field(ge=0, le=np.iinfo(np.uint32).max, description="The seed to use", default_factory=random_seed)
+    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting noise", )
+    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting noise", )
 
-    @validator("cfg_scale")
-    def ge_one(cls, v):
-        """validate that all cfg_scale values are >= 1"""
-        if isinstance(v, list):
-            for i in v:
-                if i < 1:
-                    raise ValueError('cfg_scale must be greater than 1')
-        else:
-            if v < 1:
-                raise ValueError('cfg_scale must be greater than 1')
-        return v
 
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
             "ui": {
-                "tags": ["latents"],
+                "tags": ["latents", "noise"],
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> NoiseOutput:
+        device = torch.device(choose_torch_device())
+        noise = get_noise(self.width, self.height, device, self.seed)
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.set(name, noise)
+        return NoiseOutput(
+            noise=LatentsField(latents_name=name)
+        )
+
+
+# Text to image
+class TextToLatentsInvocation(BaseInvocation):
+    """Generates latents from a prompt."""
+
+    type: Literal["t2l"] = "t2l"
+
+    # Inputs
+    # TODO: consider making prompt optional to enable providing prompt through a link
+    # fmt: off
+    prompt: Optional[str] = Field(description="The prompt to generate an image from")
+    seed:        int = Field(default=-1,ge=-1, le=np.iinfo(np.uint32).max, description="The seed to use (-1 for a random seed)", )
+    noise: Optional[LatentsField] = Field(description="The noise to use")
+    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
+    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting image", )
+    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting image", )
+    cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
+    seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
+    model:       str = Field(default="", description="The model to use (currently ignored)")
+    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
+    # fmt: on
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
                 "type_hints": {
-                  "model": "model",
-                  "control": "control",
-                  # "cfg_scale": "float",
-                  "cfg_scale": "number"
+                  "model": "model"
                 }
             },
         }
@@ -139,140 +176,51 @@ class TextToLatentsInvocation(BaseInvocation):
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
-            node=self.dict(),
+            invocation_dict=self.dict(),
             source_node_id=source_node_id,
         )
 
-    def get_conditioning_data(self, context: InvocationContext, scheduler) -> ConditioningData:
-        c, extra_conditioning_info = context.services.latents.get(self.positive_conditioning.conditioning_name)
-        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
+    def get_model(self, model_manager: ModelManager) -> StableDiffusionGeneratorPipeline:
+        model_info = choose_model(model_manager, self.model)
+        model_name = model_info['model_name']
+        model_hash = model_info['hash']
+        model: StableDiffusionGeneratorPipeline = model_info['model']
+        model.scheduler = get_scheduler(
+            model=model,
+            scheduler_name=self.scheduler
+        )
 
+        if isinstance(model, DiffusionPipeline):
+            for component in [model.unet, model.vae]:
+                configure_model_padding(component,
+                                        self.seamless,
+                                        self.seamless_axes
+                                        )
+        else:
+            configure_model_padding(model,
+                                    self.seamless,
+                                    self.seamless_axes
+                                    )
+
+        return model
+
+
+    def get_conditioning_data(self, model: StableDiffusionGeneratorPipeline) -> ConditioningData:
+        uc, c, extra_conditioning_info = get_uc_and_c_and_ec(self.prompt, model=model)
         conditioning_data = ConditioningData(
-            unconditioned_embeddings=uc,
-            text_embeddings=c,
-            guidance_scale=self.cfg_scale,
-            extra=extra_conditioning_info,
+            uc,
+            c,
+            self.cfg_scale,
+            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
-            generator=torch.Generator(device=uc.device).manual_seed(0),
-        )
+        ).add_scheduler_args_if_applicable(model.scheduler, eta=None)#ddim_eta)
         return conditioning_data
 
-    def create_pipeline(self, unet, scheduler) -> StableDiffusionGeneratorPipeline:
-        # TODO:
-        #configure_model_padding(
-        #    unet,
-        #    self.seamless,
-        #    self.seamless_axes,
-        #)
-
-        class FakeVae:
-            class FakeVaeConfig:
-                def __init__(self):
-                    self.block_out_channels = [0]
-            
-            def __init__(self):
-                self.config = FakeVae.FakeVaeConfig()
-
-        return StableDiffusionGeneratorPipeline(
-            vae=FakeVae(), # TODO: oh...
-            text_encoder=None,
-            tokenizer=None,
-            unet=unet,
-            scheduler=scheduler,
-            safety_checker=None,
-            feature_extractor=None,
-            requires_safety_checker=False,
-            precision="float16" if unet.dtype == torch.float16 else "float32",
-        )
-    
-    def prep_control_data(
-        self,
-        context: InvocationContext,
-        model: StableDiffusionGeneratorPipeline, # really only need model for dtype and device
-        control_input: List[ControlField],
-        latents_shape: List[int],
-        do_classifier_free_guidance: bool = True,
-    ) -> List[ControlNetData]:
-
-        # assuming fixed dimensional scaling of 8:1 for image:latents
-        control_height_resize = latents_shape[2] * 8
-        control_width_resize = latents_shape[3] * 8
-        if control_input is None:
-            control_list = None
-        elif isinstance(control_input, list) and len(control_input) == 0:
-            control_list = None
-        elif isinstance(control_input, ControlField):
-            control_list = [control_input]
-        elif isinstance(control_input, list) and len(control_input) > 0 and isinstance(control_input[0], ControlField):
-            control_list = control_input
-        else:
-            control_list = None
-        if (control_list is None):
-            control_data = None
-            # from above handling, any control that is not None should now be of type list[ControlField]
-        else:
-            # FIXME: add checks to skip entry if model or image is None
-            #        and if weight is None, populate with default 1.0?
-            control_data = []
-            control_models = []
-            for control_info in control_list:
-                # handle control models
-                if ("," in control_info.control_model):
-                    control_model_split = control_info.control_model.split(",")
-                    control_name = control_model_split[0]
-                    control_subfolder = control_model_split[1]
-                    print("Using HF model subfolders")
-                    print("    control_name: ", control_name)
-                    print("    control_subfolder: ", control_subfolder)
-                    control_model = ControlNetModel.from_pretrained(control_name,
-                                                                    subfolder=control_subfolder,
-                                                                    torch_dtype=model.unet.dtype).to(model.device)
-                else:
-                    control_model = ControlNetModel.from_pretrained(control_info.control_model,
-                                                                    torch_dtype=model.unet.dtype).to(model.device)
-                control_models.append(control_model)
-                control_image_field = control_info.image
-                input_image = context.services.images.get_pil_image(control_image_field.image_name)
-                # self.image.image_type, self.image.image_name
-                # FIXME: still need to test with different widths, heights, devices, dtypes
-                #        and add in batch_size, num_images_per_prompt?
-                #        and do real check for classifier_free_guidance?
-                # prepare_control_image should return torch.Tensor of shape(batch_size, 3, height, width)
-                control_image = model.prepare_control_image(
-                    image=input_image,
-                    do_classifier_free_guidance=do_classifier_free_guidance,
-                    width=control_width_resize,
-                    height=control_height_resize,
-                    # batch_size=batch_size * num_images_per_prompt,
-                    # num_images_per_prompt=num_images_per_prompt,
-                    device=control_model.device,
-                    dtype=control_model.dtype,
-                    control_mode=control_info.control_mode,
-                )
-                control_item = ControlNetData(model=control_model,
-                                              image_tensor=control_image,
-                                              weight=control_info.control_weight,
-                                              begin_step_percent=control_info.begin_step_percent,
-                                              end_step_percent=control_info.end_step_percent,
-                                              control_mode=control_info.control_mode,
-                                              )
-                control_data.append(control_item)
-                # MultiControlNetModel has been refactored out, just need list[ControlNetData]
-        return control_data
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         noise = context.services.latents.get(self.noise.latents_name)
@@ -284,67 +232,49 @@ class TextToLatentsInvocation(BaseInvocation):
         def step_callback(state: PipelineIntermediateState):
             self.dispatch_progress(context, source_node_id, state)
 
-        unet_info = context.services.model_manager.get_model(**self.unet.unet.dict())
-        with unet_info as unet:
+        model = self.get_model(context.services.model_manager)
+        conditioning_data = self.get_conditioning_data(model)
 
-            scheduler = get_scheduler(
-                context=context,
-                scheduler_info=self.unet.scheduler,
-                scheduler_name=self.scheduler,
-            )
-            
-            pipeline = self.create_pipeline(unet, scheduler)
-            conditioning_data = self.get_conditioning_data(context, scheduler)
+        # TODO: Verify the noise is the right size
 
-            loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.unet.loras]
-
-            control_data = self.prep_control_data(
-                model=pipeline, context=context, control_input=self.control,
-                latents_shape=noise.shape,
-                # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
-                do_classifier_free_guidance=True,
-            )
-
-            with ModelPatcher.apply_lora_unet(pipeline.unet, loras):
-                # TODO: Verify the noise is the right size
-                result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
-                    latents=torch.zeros_like(noise, dtype=torch_dtype(unet.device)),
-                    noise=noise,
-                    num_inference_steps=self.steps,
-                    conditioning_data=conditioning_data,
-                    control_data=control_data, # list[ControlNetData]
-                    callback=step_callback,
-                )
+        result_latents, result_attention_map_saver = model.latents_from_embeddings(
+            latents=torch.zeros_like(noise, dtype=torch_dtype(model.device)),
+            noise=noise,
+            num_inference_steps=self.steps,
+            conditioning_data=conditioning_data,
+            callback=step_callback
+        )
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         torch.cuda.empty_cache()
 
         name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.save(name, result_latents)
-        return build_latents_output(latents_name=name, latents=result_latents)
+        context.services.latents.set(name, result_latents)
+        return LatentsOutput(
+            latents=LatentsField(latents_name=name)
+        )
+
 
 class LatentsToLatentsInvocation(TextToLatentsInvocation):
     """Generates latents using latents as base image."""
 
     type: Literal["l2l"] = "l2l"
 
-    # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
-    strength: float = Field(default=0.7, ge=0, le=1, description="The strength of the latents to use")
-
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
             "ui": {
                 "tags": ["latents"],
                 "type_hints": {
-                    "model": "model",
-                    "control": "control",
-                    "cfg_scale": "number",
+                    "model": "model"
                 }
             },
         }
 
+    # Inputs
+    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
+    strength: float = Field(default=0.5, description="The strength of the latents to use")
+
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         noise = context.services.latents.get(self.noise.latents_name)
         latent = context.services.latents.get(self.latents.latents_name)
@@ -356,58 +286,38 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
         def step_callback(state: PipelineIntermediateState):
             self.dispatch_progress(context, source_node_id, state)
 
-        unet_info = context.services.model_manager.get_model(
-            **self.unet.unet.dict(),
+        model = self.get_model(context.services.model_manager)
+        conditioning_data = self.get_conditioning_data(model)
+
+        # TODO: Verify the noise is the right size
+
+        initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
+            latent, device=model.device, dtype=latent.dtype
         )
 
-        with unet_info as unet:
+        timesteps, _ = model.get_img2img_timesteps(
+            self.steps,
+            self.strength,
+            device=model.device,
+        )
 
-            scheduler = get_scheduler(
-                context=context,
-                scheduler_info=self.unet.scheduler,
-                scheduler_name=self.scheduler,
-            )
-
-            pipeline = self.create_pipeline(unet, scheduler)
-            conditioning_data = self.get_conditioning_data(context, scheduler)
-            
-            control_data = self.prep_control_data(
-                model=pipeline, context=context, control_input=self.control,
-                latents_shape=noise.shape,
-                # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
-                do_classifier_free_guidance=True,
-            )
-
-            # TODO: Verify the noise is the right size
-            initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
-                latent, device=unet.device, dtype=latent.dtype
-            )
-
-            timesteps, _ = pipeline.get_img2img_timesteps(
-                self.steps,
-                self.strength,
-                device=unet.device,
-            )
-
-            loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.unet.loras]
-
-            with ModelPatcher.apply_lora_unet(pipeline.unet, loras):
-                result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
-                    latents=initial_latents,
-                    timesteps=timesteps,
-                    noise=noise,
-                    num_inference_steps=self.steps,
-                    conditioning_data=conditioning_data,
-                    control_data=control_data,  # list[ControlNetData]
-                    callback=step_callback
-                )
+        result_latents, result_attention_map_saver = model.latents_from_embeddings(
+            latents=initial_latents,
+            timesteps=timesteps,
+            noise=noise,
+            num_inference_steps=self.steps,
+            conditioning_data=conditioning_data,
+            callback=step_callback
+        )
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         torch.cuda.empty_cache()
 
         name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.save(name, result_latents)
-        return build_latents_output(latents_name=name, latents=result_latents)
+        context.services.latents.set(name, result_latents)
+        return LatentsOutput(
+            latents=LatentsField(latents_name=name)
+        )
 
 
 # Latent to image
@@ -418,14 +328,16 @@ class LatentsToImageInvocation(BaseInvocation):
 
     # Inputs
     latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
-    vae: VaeField = Field(default=None, description="Vae submodel")
-    tiled: bool = Field(default=False, description="Decode latents by overlaping tiles(less memory consumption)")
+    model: str = Field(default="", description="The model to use")
 
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
             "ui": {
                 "tags": ["latents", "image"],
+                "type_hints": {
+                  "model": "model"
+                }
             },
         }
 
@@ -433,164 +345,26 @@ class LatentsToImageInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.dict(),
-        )
+        # TODO: this only really needs the vae
+        model_info = choose_model(context.services.model_manager, self.model)
+        model: StableDiffusionGeneratorPipeline = model_info['model']
 
-        with vae_info as vae:
-            if self.tiled or context.services.configuration.tiled_decode:
-                vae.enable_tiling()
-            else:
-                vae.disable_tiling()
+        with torch.inference_mode():
+            np_image = model.decode_latents(latents)
+            image = model.numpy_to_pil(np_image)[0]
 
-            # clear memory as vae decode can request a lot
-            torch.cuda.empty_cache()
+            image_type = ImageType.RESULT
+            image_name = context.services.images.create_name(
+                context.graph_execution_state_id, self.id
+            )
 
-            with torch.inference_mode():
-                # copied from diffusers pipeline
-                latents = latents / vae.config.scaling_factor
-                image = vae.decode(latents, return_dict=False)[0]
-                image = (image / 2 + 0.5).clamp(0, 1) # denormalize
-                # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
-                np_image = image.cpu().permute(0, 2, 3, 1).float().numpy()
+            metadata = MetadataModule.build_metadata(
+                session_id=context.graph_execution_state_id, invocation=self
+            )
 
-                image = VaeImageProcessor.numpy_to_pil(np_image)[0]
-
-        torch.cuda.empty_cache()
-
-        image_dto = context.services.images.create(
-            image=image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-LATENTS_INTERPOLATION_MODE = Literal[
-    "nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"
-]
-
-
-class ResizeLatentsInvocation(BaseInvocation):
-    """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
-
-    type: Literal["lresize"] = "lresize"
-
-    # Inputs
-    latents:    Optional[LatentsField] = Field(description="The latents to resize")
-    width:                         int = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
-    height:                        int = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
-    mode:   LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
-    antialias:                    bool = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
-
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
-
-        resized_latents = torch.nn.functional.interpolate(
-            latents,
-            size=(self.height // 8, self.width // 8),
-            mode=self.mode,
-            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
-        )
-
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        torch.cuda.empty_cache()
-
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, resized_latents)
-        return build_latents_output(latents_name=name, latents=resized_latents)
-
-
-class ScaleLatentsInvocation(BaseInvocation):
-    """Scales latents by a given factor."""
-
-    type: Literal["lscale"] = "lscale"
-
-    # Inputs
-    latents:   Optional[LatentsField] = Field(description="The latents to scale")
-    scale_factor:               float = Field(gt=0, description="The factor by which to scale the latents")
-    mode:  LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
-    antialias:                   bool = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
-
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
-
-        # resizing
-        resized_latents = torch.nn.functional.interpolate(
-            latents,
-            scale_factor=self.scale_factor,
-            mode=self.mode,
-            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
-        )
-
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        torch.cuda.empty_cache()
-
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, resized_latents)
-        return build_latents_output(latents_name=name, latents=resized_latents)
-
-
-class ImageToLatentsInvocation(BaseInvocation):
-    """Encodes an image into latents."""
-
-    type: Literal["i2l"] = "i2l"
-
-    # Inputs
-    image: Union[ImageField, None] = Field(description="The image to encode")
-    vae: VaeField = Field(default=None, description="Vae submodel")
-    tiled: bool = Field(default=False, description="Encode latents by overlaping tiles(less memory consumption)")
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "image"],
-            },
-        }
-
-    @torch.no_grad()
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        # image = context.services.images.get(
-        #     self.image.image_type, self.image.image_name
-        # )
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        #vae_info = context.services.model_manager.get_model(**self.vae.vae.dict())
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.dict(),
-        )
-
-        image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
-        if image_tensor.dim() == 3:
-            image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
-
-        with vae_info as vae:
-            if self.tiled:
-                vae.enable_tiling()
-            else:
-                vae.disable_tiling()
-
-            # non_noised_latents_from_image
-            image_tensor = image_tensor.to(device=vae.device, dtype=vae.dtype)
-            with torch.inference_mode():
-                image_tensor_dist = vae.encode(image_tensor).latent_dist
-                latents = image_tensor_dist.sample().to(
-                    dtype=vae.dtype
-                )  # FIXME: uses torch.randn. make reproducible!
-
-            latents = 0.18215 * latents
-
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, latents)
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=latents)
+            context.services.images.save(image_type, image_name, image, metadata)
+            return build_image_output(
+                image_type=image_type,
+                image_name=image_name,
+                image=image
+            )

invokeai/app/invocations/math.py

@@ -3,14 +3,8 @@
 from typing import Literal
 
 from pydantic import BaseModel, Field
-import numpy as np
 
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    InvocationContext,
-    InvocationConfig,
-)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
 
 
 class MathInvocationConfig(BaseModel):
@@ -27,30 +21,19 @@ class MathInvocationConfig(BaseModel):
 
 class IntOutput(BaseInvocationOutput):
     """An integer output"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["int_output"] = "int_output"
     a: int = Field(default=None, description="The output integer")
-    # fmt: on
-
-
-class FloatOutput(BaseInvocationOutput):
-    """A float output"""
-
-    # fmt: off
-    type: Literal["float_output"] = "float_output"
-    param: float = Field(default=None, description="The output float")
-    # fmt: on
+    #fmt: on
 
 
 class AddInvocation(BaseInvocation, MathInvocationConfig):
     """Adds two numbers"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["add"] = "add"
     a: int = Field(default=0, description="The first number")
     b: int = Field(default=0, description="The second number")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a + self.b)
@@ -58,12 +41,11 @@ class AddInvocation(BaseInvocation, MathInvocationConfig):
 
 class SubtractInvocation(BaseInvocation, MathInvocationConfig):
     """Subtracts two numbers"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["sub"] = "sub"
     a: int = Field(default=0, description="The first number")
     b: int = Field(default=0, description="The second number")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a - self.b)
@@ -71,12 +53,11 @@ class SubtractInvocation(BaseInvocation, MathInvocationConfig):
 
 class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
     """Multiplies two numbers"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["mul"] = "mul"
     a: int = Field(default=0, description="The first number")
     b: int = Field(default=0, description="The second number")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a * self.b)
@@ -84,26 +65,11 @@ class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
 
 class DivideInvocation(BaseInvocation, MathInvocationConfig):
     """Divides two numbers"""
-
-    # fmt: off
+    #fmt: off
     type: Literal["div"] = "div"
     a: int = Field(default=0, description="The first number")
     b: int = Field(default=0, description="The second number")
-    # fmt: on
+    #fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=int(self.a / self.b))
-
-
-class RandomIntInvocation(BaseInvocation):
-    """Outputs a single random integer."""
-
-    # fmt: off
-    type: Literal["rand_int"] = "rand_int"
-    low: int = Field(default=0, description="The inclusive low value")
-    high: int = Field(
-        default=np.iinfo(np.int32).max, description="The exclusive high value"
-    )
-    # fmt: on
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=np.random.randint(self.low, self.high))

invokeai/app/invocations/model.py

@@ -1,223 +0,0 @@
-from typing import Literal, Optional, Union, List
-from pydantic import BaseModel, Field
-import copy
-
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
-
-from ...backend.util.devices import choose_torch_device, torch_dtype
-from ...backend.model_management import BaseModelType, ModelType, SubModelType
-
-class ModelInfo(BaseModel):
-    model_name: str = Field(description="Info to load submodel")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Info to load submodel")
-    submodel: Optional[SubModelType] = Field(description="Info to load submodel")
-
-class LoraInfo(ModelInfo):
-    weight: float = Field(description="Lora's weight which to use when apply to model")
-
-class UNetField(BaseModel):
-    unet: ModelInfo = Field(description="Info to load unet submodel")
-    scheduler: ModelInfo = Field(description="Info to load scheduler submodel")
-    loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
-
-class ClipField(BaseModel):
-    tokenizer: ModelInfo = Field(description="Info to load tokenizer submodel")
-    text_encoder: ModelInfo = Field(description="Info to load text_encoder submodel")
-    loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
-
-class VaeField(BaseModel):
-    # TODO: better naming?
-    vae: ModelInfo = Field(description="Info to load vae submodel")
-
-
-class ModelLoaderOutput(BaseInvocationOutput):
-    """Model loader output"""
-
-    #fmt: off
-    type: Literal["model_loader_output"] = "model_loader_output"
-
-    unet: UNetField = Field(default=None, description="UNet submodel")
-    clip: ClipField = Field(default=None, description="Tokenizer and text_encoder submodels")
-    vae: VaeField = Field(default=None, description="Vae submodel")
-    #fmt: on
-
-
-class PipelineModelField(BaseModel):
-    """Pipeline model field"""
-
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-
-
-class PipelineModelLoaderInvocation(BaseInvocation):
-    """Loads a pipeline model, outputting its submodels."""
-
-    type: Literal["pipeline_model_loader"] = "pipeline_model_loader"
-
-    model: PipelineModelField = Field(description="The model to load")
-    # TODO: precision?
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["model", "loader"],
-                "type_hints": {
-                  "model": "model"
-                }
-            },
-        }
-
-    def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
-
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.Main
-
-        # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
-
-        """
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.Tokenizer,
-        ):
-            raise Exception(
-                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.TextEncoder,
-        ):
-            raise Exception(
-                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.UNet,
-        ):
-            raise Exception(
-                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
-            )
-        """
-
-
-        return ModelLoaderOutput(
-            unet=UNetField(
-                unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
-                ),
-                scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
-                ),
-                loras=[],
-            ),
-            clip=ClipField(
-                tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
-                ),
-                text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
-                ),
-                loras=[],
-            ),
-            vae=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Vae,
-                ),
-            )
-        )
-
-class LoraLoaderOutput(BaseInvocationOutput):
-    """Model loader output"""
-
-    #fmt: off
-    type: Literal["lora_loader_output"] = "lora_loader_output"
-
-    unet: Optional[UNetField] = Field(default=None, description="UNet submodel")
-    clip: Optional[ClipField] = Field(default=None, description="Tokenizer and text_encoder submodels")
-    #fmt: on
-
-class LoraLoaderInvocation(BaseInvocation):
-    """Apply selected lora to unet and text_encoder."""
-
-    type: Literal["lora_loader"] = "lora_loader"
-
-    lora_name: str = Field(description="Lora model name")
-    weight: float = Field(default=0.75, description="With what weight to apply lora")
-
-    unet: Optional[UNetField] = Field(description="UNet model for applying lora")
-    clip: Optional[ClipField] = Field(description="Clip model for applying lora")
-
-    def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
-
-        # TODO: ui rewrite
-        base_model = BaseModelType.StableDiffusion1
-
-        if not context.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=self.lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unkown lora name: {self.lora_name}!")
-
-        if self.unet is not None and any(lora.model_name == self.lora_name for lora in self.unet.loras):
-            raise Exception(f"Lora \"{self.lora_name}\" already applied to unet")
-
-        if self.clip is not None and any(lora.model_name == self.lora_name for lora in self.clip.loras):
-            raise Exception(f"Lora \"{self.lora_name}\" already applied to clip")
-
-        output = LoraLoaderOutput()
-
-        if self.unet is not None:
-            output.unet = copy.deepcopy(self.unet)
-            output.unet.loras.append(
-                LoraInfo(
-                    base_model=base_model,
-                    model_name=self.lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
-                    weight=self.weight,
-                )
-            )
-
-        if self.clip is not None:
-            output.clip = copy.deepcopy(self.clip)
-            output.clip.loras.append(
-                LoraInfo(
-                    base_model=base_model,
-                    model_name=self.lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
-                    weight=self.weight,
-                )
-            )
-
-        return output
-

invokeai/app/invocations/noise.py

@@ -1,134 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) & the InvokeAI Team
-
-import math
-from typing import Literal
-
-from pydantic import Field, validator
-import torch
-from invokeai.app.invocations.latent import LatentsField
-
-from invokeai.app.util.misc import SEED_MAX, get_random_seed
-from ...backend.util.devices import choose_torch_device, torch_dtype
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    InvocationConfig,
-    InvocationContext,
-)
-
-"""
-Utilities
-"""
-
-
-def get_noise(
-    width: int,
-    height: int,
-    device: torch.device,
-    seed: int = 0,
-    latent_channels: int = 4,
-    downsampling_factor: int = 8,
-    use_cpu: bool = True,
-    perlin: float = 0.0,
-):
-    """Generate noise for a given image size."""
-    noise_device_type = "cpu" if (use_cpu or device.type == "mps") else device.type
-
-    # limit noise to only the diffusion image channels, not the mask channels
-    input_channels = min(latent_channels, 4)
-    generator = torch.Generator(device=noise_device_type).manual_seed(seed)
-
-    noise_tensor = torch.randn(
-        [
-            1,
-            input_channels,
-            height // downsampling_factor,
-            width // downsampling_factor,
-        ],
-        dtype=torch_dtype(device),
-        device=noise_device_type,
-        generator=generator,
-    ).to(device)
-
-    return noise_tensor
-
-
-"""
-Nodes
-"""
-
-
-class NoiseOutput(BaseInvocationOutput):
-    """Invocation noise output"""
-
-    # fmt: off
-    type:  Literal["noise_output"] = "noise_output"
-
-    # Inputs
-    noise: LatentsField            = Field(default=None, description="The output noise")
-    width:                     int = Field(description="The width of the noise in pixels")
-    height:                    int = Field(description="The height of the noise in pixels")
-    # fmt: on
-
-
-def build_noise_output(latents_name: str, latents: torch.Tensor):
-    return NoiseOutput(
-        noise=LatentsField(latents_name=latents_name),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
-
-
-class NoiseInvocation(BaseInvocation):
-    """Generates latent noise."""
-
-    type: Literal["noise"] = "noise"
-
-    # Inputs
-    seed: int = Field(
-        ge=0,
-        le=SEED_MAX,
-        description="The seed to use",
-        default_factory=get_random_seed,
-    )
-    width: int = Field(
-        default=512,
-        multiple_of=8,
-        gt=0,
-        description="The width of the resulting noise",
-    )
-    height: int = Field(
-        default=512,
-        multiple_of=8,
-        gt=0,
-        description="The height of the resulting noise",
-    )
-    use_cpu: bool = Field(
-        default=True,
-        description="Use CPU for noise generation (for reproducible results across platforms)",
-    )
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "noise"],
-            },
-        }
-
-    @validator("seed", pre=True)
-    def modulo_seed(cls, v):
-        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
-        return v % SEED_MAX
-
-    def invoke(self, context: InvocationContext) -> NoiseOutput:
-        noise = get_noise(
-            width=self.width,
-            height=self.height,
-            device=choose_torch_device(),
-            seed=self.seed,
-            use_cpu=self.use_cpu,
-        )
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, noise)
-        return build_noise_output(latents_name=name, latents=noise)

invokeai/app/invocations/param_easing.py

@@ -1,236 +0,0 @@
-import io
-from typing import Literal, Optional, Any
-
-# from PIL.Image import Image
-import PIL.Image
-from matplotlib.ticker import MaxNLocator
-from matplotlib.figure import Figure
-
-from pydantic import BaseModel, Field
-import numpy as np
-import matplotlib.pyplot as plt
-
-from easing_functions import (
-    LinearInOut,
-    QuadEaseInOut, QuadEaseIn, QuadEaseOut,
-    CubicEaseInOut, CubicEaseIn, CubicEaseOut,
-    QuarticEaseInOut, QuarticEaseIn, QuarticEaseOut,
-    QuinticEaseInOut, QuinticEaseIn, QuinticEaseOut,
-    SineEaseInOut, SineEaseIn, SineEaseOut,
-    CircularEaseIn, CircularEaseInOut, CircularEaseOut,
-    ExponentialEaseInOut, ExponentialEaseIn, ExponentialEaseOut,
-    ElasticEaseIn, ElasticEaseInOut, ElasticEaseOut,
-    BackEaseIn, BackEaseInOut, BackEaseOut,
-    BounceEaseIn, BounceEaseInOut, BounceEaseOut)
-
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    InvocationContext,
-    InvocationConfig,
-)
-from ...backend.util.logging import InvokeAILogger
-from .collections import FloatCollectionOutput
-
-
-class FloatLinearRangeInvocation(BaseInvocation):
-    """Creates a range"""
-
-    type: Literal["float_range"] = "float_range"
-
-    # Inputs
-    start: float = Field(default=5, description="The first value of the range")
-    stop: float = Field(default=10, description="The last value of the range")
-    steps: int = Field(default=30, description="number of values to interpolate over (including start and stop)")
-
-    def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
-        param_list = list(np.linspace(self.start, self.stop, self.steps))
-        return FloatCollectionOutput(
-            collection=param_list
-        )
-
-
-EASING_FUNCTIONS_MAP = {
-    "Linear": LinearInOut,
-    "QuadIn": QuadEaseIn,
-    "QuadOut": QuadEaseOut,
-    "QuadInOut": QuadEaseInOut,
-    "CubicIn": CubicEaseIn,
-    "CubicOut": CubicEaseOut,
-    "CubicInOut": CubicEaseInOut,
-    "QuarticIn": QuarticEaseIn,
-    "QuarticOut": QuarticEaseOut,
-    "QuarticInOut": QuarticEaseInOut,
-    "QuinticIn": QuinticEaseIn,
-    "QuinticOut": QuinticEaseOut,
-    "QuinticInOut": QuinticEaseInOut,
-    "SineIn": SineEaseIn,
-    "SineOut": SineEaseOut,
-    "SineInOut": SineEaseInOut,
-    "CircularIn": CircularEaseIn,
-    "CircularOut": CircularEaseOut,
-    "CircularInOut": CircularEaseInOut,
-    "ExponentialIn": ExponentialEaseIn,
-    "ExponentialOut": ExponentialEaseOut,
-    "ExponentialInOut": ExponentialEaseInOut,
-    "ElasticIn": ElasticEaseIn,
-    "ElasticOut": ElasticEaseOut,
-    "ElasticInOut": ElasticEaseInOut,
-    "BackIn": BackEaseIn,
-    "BackOut": BackEaseOut,
-    "BackInOut": BackEaseInOut,
-    "BounceIn": BounceEaseIn,
-    "BounceOut": BounceEaseOut,
-    "BounceInOut": BounceEaseInOut,
-}
-
-EASING_FUNCTION_KEYS: Any = Literal[
-    tuple(list(EASING_FUNCTIONS_MAP.keys()))
-]
-
-
-# actually I think for now could just use CollectionOutput (which is list[Any]
-class StepParamEasingInvocation(BaseInvocation):
-    """Experimental per-step parameter easing for denoising steps"""
-
-    type: Literal["step_param_easing"] = "step_param_easing"
-
-    # Inputs
-    # fmt: off
-    easing: EASING_FUNCTION_KEYS = Field(default="Linear", description="The easing function to use")
-    num_steps: int = Field(default=20, description="number of denoising steps")
-    start_value: float = Field(default=0.0, description="easing starting value")
-    end_value: float = Field(default=1.0, description="easing ending value")
-    start_step_percent: float = Field(default=0.0, description="fraction of steps at which to start easing")
-    end_step_percent: float = Field(default=1.0, description="fraction of steps after which to end easing")
-    # if None, then start_value is used prior to easing start
-    pre_start_value: Optional[float] = Field(default=None, description="value before easing start")
-    # if None, then end value is used prior to easing end
-    post_end_value: Optional[float] = Field(default=None, description="value after easing end")
-    mirror: bool = Field(default=False, description="include mirror of easing function")
-    # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
-    # alt_mirror: bool = Field(default=False, description="alternative mirroring by dual easing")
-    show_easing_plot: bool = Field(default=False, description="show easing plot")
-    # fmt: on
-
-
-    def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
-        log_diagnostics = False
-        # convert from start_step_percent to nearest step <= (steps * start_step_percent)
-        # start_step = int(np.floor(self.num_steps * self.start_step_percent))
-        start_step = int(np.round(self.num_steps * self.start_step_percent))
-        # convert from end_step_percent to nearest step >= (steps * end_step_percent)
-        # end_step = int(np.ceil((self.num_steps - 1) * self.end_step_percent))
-        end_step = int(np.round((self.num_steps - 1) * self.end_step_percent))
-
-        # end_step = int(np.ceil(self.num_steps * self.end_step_percent))
-        num_easing_steps = end_step - start_step + 1
-
-        # num_presteps = max(start_step - 1, 0)
-        num_presteps = start_step
-        num_poststeps = self.num_steps - (num_presteps + num_easing_steps)
-        prelist = list(num_presteps * [self.pre_start_value])
-        postlist = list(num_poststeps * [self.post_end_value])
-
-        if log_diagnostics:
-            context.services.logger.debug("start_step: " + str(start_step))
-            context.services.logger.debug("end_step: " + str(end_step))
-            context.services.logger.debug("num_easing_steps: " + str(num_easing_steps))
-            context.services.logger.debug("num_presteps: " + str(num_presteps))
-            context.services.logger.debug("num_poststeps: " + str(num_poststeps))
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
-            context.services.logger.debug("prelist: " + str(prelist))
-            context.services.logger.debug("postlist: " + str(postlist))
-
-        easing_class = EASING_FUNCTIONS_MAP[self.easing]
-        if log_diagnostics:
-            context.services.logger.debug("easing class: " + str(easing_class))
-        easing_list = list()
-        if self.mirror:  # "expected" mirroring
-            # if number of steps is even, squeeze duration down to (number_of_steps)/2
-            # and create reverse copy of list to append
-            # if number of steps is odd, squeeze duration down to ceil(number_of_steps/2)
-            # and create reverse copy of list[1:end-1]
-            # but if even then number_of_steps/2 === ceil(number_of_steps/2), so can just use ceil always
-
-            base_easing_duration = int(np.ceil(num_easing_steps/2.0))
-            if log_diagnostics: context.services.logger.debug("base easing duration: " + str(base_easing_duration))
-            even_num_steps = (num_easing_steps % 2 == 0)  # even number of steps
-            easing_function = easing_class(start=self.start_value,
-                                           end=self.end_value,
-                                           duration=base_easing_duration - 1)
-            base_easing_vals = list()
-            for step_index in range(base_easing_duration):
-                easing_val = easing_function.ease(step_index)
-                base_easing_vals.append(easing_val)
-                if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
-            if even_num_steps:
-                mirror_easing_vals = list(reversed(base_easing_vals))
-            else:
-                mirror_easing_vals = list(reversed(base_easing_vals[0:-1]))
-            if log_diagnostics:
-                context.services.logger.debug("base easing vals: " + str(base_easing_vals))
-                context.services.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
-            easing_list = base_easing_vals + mirror_easing_vals
-
-        # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
-        # elif self.alt_mirror:  # function mirroring (unintuitive behavior (at least to me))
-        #     # half_ease_duration = round(num_easing_steps - 1 / 2)
-        #     half_ease_duration = round((num_easing_steps - 1) / 2)
-        #     easing_function = easing_class(start=self.start_value,
-        #                                    end=self.end_value,
-        #                                    duration=half_ease_duration,
-        #                                    )
-        #
-        #     mirror_function = easing_class(start=self.end_value,
-        #                                    end=self.start_value,
-        #                                    duration=half_ease_duration,
-        #                                    )
-        #     for step_index in range(num_easing_steps):
-        #         if step_index <= half_ease_duration:
-        #             step_val = easing_function.ease(step_index)
-        #         else:
-        #             step_val = mirror_function.ease(step_index - half_ease_duration)
-        #         easing_list.append(step_val)
-        #         if log_diagnostics: logger.debug(step_index, step_val)
-        #
-
-        else:  # no mirroring (default)
-            easing_function = easing_class(start=self.start_value,
-                                           end=self.end_value,
-                                           duration=num_easing_steps - 1)
-            for step_index in range(num_easing_steps):
-                step_val = easing_function.ease(step_index)
-                easing_list.append(step_val)
-                if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
-
-        if log_diagnostics:
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("easing_list size: " + str(len(easing_list)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
-
-        param_list = prelist + easing_list + postlist
-
-        if self.show_easing_plot:
-            plt.figure()
-            plt.xlabel("Step")
-            plt.ylabel("Param Value")
-            plt.title("Per-Step Values Based On Easing: " + self.easing)
-            plt.bar(range(len(param_list)), param_list)
-            # plt.plot(param_list)
-            ax = plt.gca()
-            ax.xaxis.set_major_locator(MaxNLocator(integer=True))
-            buf = io.BytesIO()
-            plt.savefig(buf, format='png')
-            buf.seek(0)
-            im = PIL.Image.open(buf)
-            im.show()
-            buf.close()
-
-        # output array of size steps, each entry list[i] is param value for step i
-        return FloatCollectionOutput(
-            collection=param_list
-        )

invokeai/app/invocations/params.py

@@ -3,7 +3,7 @@
 from typing import Literal
 from pydantic import Field
 from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
-from .math import IntOutput, FloatOutput
+from .math import IntOutput
 
 # Pass-through parameter nodes - used by subgraphs
 
@@ -16,13 +16,3 @@ class ParamIntInvocation(BaseInvocation):
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a)
-
-class ParamFloatInvocation(BaseInvocation):
-    """A float parameter"""
-    #fmt: off
-    type: Literal["param_float"] = "param_float"
-    param: float = Field(default=0.0, description="The float value")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> FloatOutput:
-        return FloatOutput(param=self.param)

invokeai/app/invocations/prompt.py

@@ -2,8 +2,8 @@ from typing import Literal
 
 from pydantic.fields import Field
 
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
-from dynamicprompts.generators import RandomPromptGenerator, CombinatorialPromptGenerator
+from .baseinvocation import BaseInvocationOutput
+
 
 class PromptOutput(BaseInvocationOutput):
     """Base class for invocations that output a prompt"""
@@ -20,38 +20,3 @@ class PromptOutput(BaseInvocationOutput):
                 'prompt',
             ]
         }
-
-
-class PromptCollectionOutput(BaseInvocationOutput):
-    """Base class for invocations that output a collection of prompts"""
-
-    # fmt: off
-    type: Literal["prompt_collection_output"] = "prompt_collection_output"
-
-    prompt_collection: list[str] = Field(description="The output prompt collection")
-    count: int = Field(description="The size of the prompt collection")
-    # fmt: on
-
-    class Config:
-        schema_extra = {"required": ["type", "prompt_collection", "count"]}
-
-
-class DynamicPromptInvocation(BaseInvocation):
-    """Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator"""
-
-    type: Literal["dynamic_prompt"] = "dynamic_prompt"
-    prompt: str = Field(description="The prompt to parse with dynamicprompts")
-    max_prompts: int = Field(default=1, description="The number of prompts to generate")
-    combinatorial: bool = Field(
-        default=False, description="Whether to use the combinatorial generator"
-    )
-
-    def invoke(self, context: InvocationContext) -> PromptCollectionOutput:
-        if self.combinatorial:
-            generator = CombinatorialPromptGenerator()
-            prompts = generator.generate(self.prompt, max_prompts=self.max_prompts)
-        else:
-            generator = RandomPromptGenerator()
-            prompts = generator.generate(self.prompt, num_images=self.max_prompts)
-
-        return PromptCollectionOutput(prompt_collection=prompts, count=len(prompts))

invokeai/app/invocations/reconstruct.py

@@ -2,23 +2,22 @@ from typing import Literal, Union
 
 from pydantic import Field
 
-from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
+from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.modules.metadata import MetadataModule
 
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput
-
+from .image import ImageOutput, build_image_output
 
 class RestoreFaceInvocation(BaseInvocation):
     """Restores faces in an image."""
-
-    # fmt: off
+    #fmt: off
     type:  Literal["restore_face"] = "restore_face"
 
     # Inputs
     image: Union[ImageField, None] = Field(description="The input image")
     strength:                float = Field(default=0.75, gt=0, le=1, description="The strength of the restoration"  )
-    # fmt: on
-
+    #fmt: on
+    
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
@@ -28,7 +27,9 @@ class RestoreFaceInvocation(BaseInvocation):
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
         results = context.services.restoration.upscale_and_reconstruct(
             image_list=[[image, 0]],
             upscale=None,
@@ -39,17 +40,18 @@ class RestoreFaceInvocation(BaseInvocation):
 
         # Results are image and seed, unwrap for now
         # TODO: can this return multiple results?
-        image_dto = context.services.images.create(
-            image=results[0][0],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
         )
+
+        context.services.images.save(image_type, image_name, results[0][0], metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=results[0][0]
+        )

invokeai/app/invocations/upscale.py

@@ -4,22 +4,23 @@ from typing import Literal, Union
 
 from pydantic import Field
 
-from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
+from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.modules.metadata import MetadataModule
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput
+from .image import ImageOutput, build_image_output
 
 
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
-
-    # fmt: off
+    #fmt: off
     type: Literal["upscale"] = "upscale"
 
     # Inputs
     image: Union[ImageField, None] = Field(description="The input image", default=None)
     strength: float = Field(default=0.75, gt=0, le=1, description="The strength")
     level: Literal[2, 4] = Field(default=2, description="The upscale level")
-    # fmt: on
+    #fmt: on
+
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -30,7 +31,9 @@ class UpscaleInvocation(BaseInvocation):
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
         results = context.services.restoration.upscale_and_reconstruct(
             image_list=[[image, 0]],
             upscale=(self.level, self.strength),
@@ -41,17 +44,18 @@ class UpscaleInvocation(BaseInvocation):
 
         # Results are image and seed, unwrap for now
         # TODO: can this return multiple results?
-        image_dto = context.services.images.create(
-            image=results[0][0],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
         )
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+        metadata = MetadataModule.build_metadata(
+            session_id=context.graph_execution_state_id, invocation=self
         )
+
+        context.services.images.save(image_type, image_name, results[0][0], metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=results[0][0]
+        )

invokeai/app/invocations/util/choose_model.py

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

invokeai/app/models/image.py

@@ -1,90 +1,23 @@
 from enum import Enum
-from typing import Optional, Tuple
+from typing import Optional
 from pydantic import BaseModel, Field
 
-from invokeai.app.util.metaenum import MetaEnum
 
-
-class ResourceOrigin(str, Enum, metaclass=MetaEnum):
-    """The origin of a resource (eg image).
-
-    - INTERNAL: The resource was created by the application.
-    - EXTERNAL: The resource was not created by the application.
-    This may be a user-initiated upload, or an internal application upload (eg Canvas init image).
-    """
-
-    INTERNAL = "internal"
-    """The resource was created by the application."""
-    EXTERNAL = "external"
-    """The resource was not created by the application.
-    This may be a user-initiated upload, or an internal application upload (eg Canvas init image).
-    """
-
-
-class InvalidOriginException(ValueError):
-    """Raised when a provided value is not a valid ResourceOrigin.
-
-    Subclasses `ValueError`.
-    """
-
-    def __init__(self, message="Invalid resource origin."):
-        super().__init__(message)
-
-
-class ImageCategory(str, Enum, metaclass=MetaEnum):
-    """The category of an image.
-
-    - GENERAL: The image is an output, init image, or otherwise an image without a specialized purpose.
-    - MASK: The image is a mask image.
-    - CONTROL: The image is a ControlNet control image.
-    - USER: The image is a user-provide image.
-    - OTHER: The image is some other type of image with a specialized purpose. To be used by external nodes.
-    """
-
-    GENERAL = "general"
-    """GENERAL: The image is an output, init image, or otherwise an image without a specialized purpose."""
-    MASK = "mask"
-    """MASK: The image is a mask image."""
-    CONTROL = "control"
-    """CONTROL: The image is a ControlNet control image."""
-    USER = "user"
-    """USER: The image is a user-provide image."""
-    OTHER = "other"
-    """OTHER: The image is some other type of image with a specialized purpose. To be used by external nodes."""
-
-
-class InvalidImageCategoryException(ValueError):
-    """Raised when a provided value is not a valid ImageCategory.
-
-    Subclasses `ValueError`.
-    """
-
-    def __init__(self, message="Invalid image category."):
-        super().__init__(message)
+class ImageType(str, Enum):
+    RESULT = "results"
+    INTERMEDIATE = "intermediates"
+    UPLOAD = "uploads"
 
 
 class ImageField(BaseModel):
     """An image field used for passing image objects between invocations"""
 
+    image_type: ImageType = Field(
+        default=ImageType.RESULT, description="The type of the image"
+    )
     image_name: Optional[str] = Field(default=None, description="The name of the image")
 
     class Config:
-        schema_extra = {"required": ["image_name"]}
-
-
-class ColorField(BaseModel):
-    r: int = Field(ge=0, le=255, description="The red component")
-    g: int = Field(ge=0, le=255, description="The green component")
-    b: int = Field(ge=0, le=255, description="The blue component")
-    a: int = Field(ge=0, le=255, description="The alpha component")
-
-    def tuple(self) -> Tuple[int, int, int, int]:
-        return (self.r, self.g, self.b, self.a)
-
-
-class ProgressImage(BaseModel):
-    """The progress image sent intermittently during processing"""
-
-    width: int = Field(description="The effective width of the image in pixels")
-    height: int = Field(description="The effective height of the image in pixels")
-    dataURL: str = Field(description="The image data as a b64 data URL")
+        schema_extra = {
+            "required": ["image_type", "image_name"]
+        }

invokeai/app/models/metadata.py

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

invokeai/app/modules/metadata.py

@@ -0,0 +1,180 @@
+import json
+from typing import Any, Dict, Literal, Optional
+from PIL import Image, PngImagePlugin
+from pydantic import (
+    BaseModel,
+    Extra,
+    Field,
+    StrictBool,
+    StrictInt,
+    StrictStr,
+    ValidationError,
+    root_validator,
+)
+
+from invokeai.app.models.image import ImageType
+
+
+class MetadataImageField(BaseModel):
+    """A non-nullable version of ImageField"""
+
+    image_type: Literal[tuple([t.value for t in ImageType])]  # type: ignore
+    image_name: StrictStr
+
+
+class MetadataLatentsField(BaseModel):
+    """A non-nullable version of LatentsField"""
+
+    latents_name: StrictStr
+
+
+# Union of all valid metadata field types - use mostly strict types
+NodeMetadataFieldTypes = (
+    StrictStr | StrictInt | float | StrictBool  # we want to cast ints to floats here
+)
+
+
+class NodeMetadataField(BaseModel):
+    """Helper class used as a hack for arbitrary metadata field keys."""
+
+    __root__: Dict[StrictStr, NodeMetadataFieldTypes]
+
+
+# `extra=Extra.allow` allows this to model any potential node with `id` and `type` fields
+class NodeMetadata(BaseModel, extra=Extra.allow):
+    """Node metadata model, used for validation of metadata."""
+
+    @root_validator
+    def validate_node_metadata(cls, values: dict[str, Any]) -> dict[str, Any]:
+        """Parses the node metadata, ignoring invalid values"""
+        parsed: dict[str, Any] = {}
+
+        # Conditionally build the parsed metadata, silently skipping invalid values
+        for name, value in values.items():
+            # explicitly parse `id` and `type` as strings
+            if name == "id":
+                if type(value) is not str:
+                    continue
+                parsed[name] = value
+            elif name == "type":
+                if type(value) is not str:
+                    continue
+                parsed[name] = value
+            else:
+                try:
+                    if type(value) is dict:
+                        # we only allow certain dicts, else just ignore the value entirely
+                        if "image_name" in value or "image_type" in value:
+                            # parse as an ImageField
+                            parsed[name] = MetadataImageField.parse_obj(value)
+                        elif "latents_name" in value:
+                            # this is a LatentsField
+                            parsed[name] = MetadataLatentsField.parse_obj(value)
+                    else:
+                        # hack to get parse and validate arbitrary keys
+                        NodeMetadataField.parse_obj({name: value})
+                        parsed[name] = value
+                except ValidationError:
+                    # TODO: do we want to somehow alert when metadata is not fully valid?
+                    continue
+        return parsed
+
+
+class InvokeAIMetadata(BaseModel):
+    session_id: Optional[StrictStr] = Field(
+        description="The session in which this image was created"
+    )
+    node: Optional[NodeMetadata] = Field(description="The node that created this image")
+
+    @root_validator(pre=True)
+    def validate_invokeai_metadata(cls, values: dict[str, Any]) -> dict[str, Any]:
+        parsed: dict[str, Any] = {}
+        # Conditionally build the parsed metadata, silently skipping invalid values
+        for name, value in values.items():
+            if name == "session_id":
+                if type(value) is not str:
+                    continue
+                parsed[name] = value
+            elif name == "node":
+                try:
+                    p = NodeMetadata.parse_obj(value)
+                    # check for empty NodeMetadata object
+                    if len(p.dict().items()) == 0:
+                        continue
+                except ValidationError:
+                    continue
+                parsed[name] = value
+
+        return parsed
+
+
+class ImageMetadata(BaseModel):
+    """An image's metadata. Used only in HTTP responses."""
+
+    created: int = Field(description="The creation timestamp of the image")
+    width: int = Field(description="The width of the image in pixels")
+    height: int = Field(description="The height of the image in pixels")
+    mode: str = Field(description="The color mode of the image")
+    invokeai: Optional[InvokeAIMetadata] = Field(
+        description="The image's InvokeAI-specific metadata"
+    )
+
+
+class MetadataModule:
+    """Handles loading metadata from images and parsing it."""
+
+    # TODO: Support parsing old format metadata **hurk**
+
+    @staticmethod
+    def _load_metadata(image: Image.Image, key="invokeai") -> Any:
+        """Loads a specific info entry from a PIL Image."""
+
+        raw_metadata = image.info.get(key)
+
+        # metadata should always be a dict
+        if type(raw_metadata) is not str:
+            return None
+
+        loaded_metadata = json.loads(raw_metadata)
+
+        return loaded_metadata
+
+    @staticmethod
+    def _parse_invokeai_metadata(
+        metadata: Any,
+    ) -> InvokeAIMetadata | None:
+        """Parses an object as InvokeAI metadata."""
+        if type(metadata) is not dict:
+            return None
+
+        parsed_metadata = InvokeAIMetadata.parse_obj(metadata)
+
+        return parsed_metadata
+
+    @staticmethod
+    def get_metadata(image: Image.Image) -> InvokeAIMetadata | None:
+        """Gets the InvokeAI metadata from a PIL Image, skipping invalid values"""
+        loaded_metadata = MetadataModule._load_metadata(image)
+        parsed_metadata = MetadataModule._parse_invokeai_metadata(loaded_metadata)
+
+        return parsed_metadata
+
+    @staticmethod
+    def build_metadata(
+        session_id: StrictStr, invocation: BaseModel
+    ) -> InvokeAIMetadata:
+        """Builds an InvokeAIMetadata object"""
+        metadata = InvokeAIMetadata(
+            session_id=session_id, node=NodeMetadata(**invocation.dict())
+        )
+
+        return metadata
+
+    @staticmethod
+    def build_png_info(metadata: InvokeAIMetadata | None):
+        png_info = PngImagePlugin.PngInfo()
+
+        if metadata is not None:
+            png_info.add_text("invokeai", metadata.json())
+
+        return png_info

invokeai/app/services/board_image_record_storage.py

@@ -1,254 +0,0 @@
-from abc import ABC, abstractmethod
-import sqlite3
-import threading
-from typing import Union, cast
-from invokeai.app.services.board_record_storage import BoardRecord
-
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.image_record import (
-    ImageRecord,
-    deserialize_image_record,
-)
-
-
-class BoardImageRecordStorageBase(ABC):
-    """Abstract base class for the one-to-many board-image relationship record storage."""
-
-    @abstractmethod
-    def add_image_to_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        """Adds an image to a board."""
-        pass
-
-    @abstractmethod
-    def remove_image_from_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        """Removes an image from a board."""
-        pass
-
-    @abstractmethod
-    def get_images_for_board(
-        self,
-        board_id: str,
-    ) -> OffsetPaginatedResults[ImageRecord]:
-        """Gets images for a board."""
-        pass
-
-    @abstractmethod
-    def get_board_for_image(
-        self,
-        image_name: str,
-    ) -> Union[str, None]:
-        """Gets an image's board id, if it has one."""
-        pass
-
-    @abstractmethod
-    def get_image_count_for_board(
-        self,
-        board_id: str,
-    ) -> int:
-        """Gets the number of images for a board."""
-        pass
-
-
-class SqliteBoardImageRecordStorage(BoardImageRecordStorageBase):
-    _filename: str
-    _conn: sqlite3.Connection
-    _cursor: sqlite3.Cursor
-    _lock: threading.Lock
-
-    def __init__(self, filename: str) -> None:
-        super().__init__()
-        self._filename = filename
-        self._conn = sqlite3.connect(filename, check_same_thread=False)
-        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
-        self._conn.row_factory = sqlite3.Row
-        self._cursor = self._conn.cursor()
-        self._lock = threading.Lock()
-
-        try:
-            self._lock.acquire()
-            # Enable foreign keys
-            self._conn.execute("PRAGMA foreign_keys = ON;")
-            self._create_tables()
-            self._conn.commit()
-        finally:
-            self._lock.release()
-
-    def _create_tables(self) -> None:
-        """Creates the `board_images` junction table."""
-
-        # Create the `board_images` junction table.
-        self._cursor.execute(
-            """--sql
-            CREATE TABLE IF NOT EXISTS board_images (
-                board_id TEXT NOT NULL,
-                image_name TEXT NOT NULL,
-                created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                -- updated via trigger
-                updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                -- Soft delete, currently unused
-                deleted_at DATETIME,
-                -- enforce one-to-many relationship between boards and images using PK
-                -- (we can extend this to many-to-many later)
-                PRIMARY KEY (image_name),
-                FOREIGN KEY (board_id) REFERENCES boards (board_id) ON DELETE CASCADE,
-                FOREIGN KEY (image_name) REFERENCES images (image_name) ON DELETE CASCADE
-            );
-            """
-        )
-
-        # Add index for board id
-        self._cursor.execute(
-            """--sql
-            CREATE INDEX IF NOT EXISTS idx_board_images_board_id ON board_images (board_id);
-            """
-        )
-
-        # Add index for board id, sorted by created_at
-        self._cursor.execute(
-            """--sql
-            CREATE INDEX IF NOT EXISTS idx_board_images_board_id_created_at ON board_images (board_id, created_at);
-            """
-        )
-
-        # Add trigger for `updated_at`.
-        self._cursor.execute(
-            """--sql
-            CREATE TRIGGER IF NOT EXISTS tg_board_images_updated_at
-            AFTER UPDATE
-            ON board_images FOR EACH ROW
-            BEGIN
-                UPDATE board_images SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
-                    WHERE board_id = old.board_id AND image_name = old.image_name;
-            END;
-            """
-        )
-
-    def add_image_to_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                INSERT INTO board_images (board_id, image_name)
-                VALUES (?, ?)
-                ON CONFLICT (image_name) DO UPDATE SET board_id = ?;
-                """,
-                (board_id, image_name, board_id),
-            )
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()
-
-    def remove_image_from_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                DELETE FROM board_images
-                WHERE board_id = ? AND image_name = ?;
-                """,
-                (board_id, image_name),
-            )
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()
-
-    def get_images_for_board(
-        self,
-        board_id: str,
-        offset: int = 0,
-        limit: int = 10,
-    ) -> OffsetPaginatedResults[ImageRecord]:
-        # TODO: this isn't paginated yet?
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                SELECT images.*
-                FROM board_images
-                INNER JOIN images ON board_images.image_name = images.image_name
-                WHERE board_images.board_id = ?
-                ORDER BY board_images.updated_at DESC;
-                """,
-                (board_id,),
-            )
-            result = cast(list[sqlite3.Row], self._cursor.fetchall())
-            images = list(map(lambda r: deserialize_image_record(dict(r)), result))
-
-            self._cursor.execute(
-                """--sql
-                SELECT COUNT(*) FROM images WHERE 1=1;
-                """
-            )
-            count = cast(int, self._cursor.fetchone()[0])
-
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()
-        return OffsetPaginatedResults(
-            items=images, offset=offset, limit=limit, total=count
-        )
-
-    def get_board_for_image(
-        self,
-        image_name: str,
-    ) -> Union[str, None]:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                SELECT board_id
-                FROM board_images
-                WHERE image_name = ?;
-                """,
-                (image_name,),
-            )
-            result = self._cursor.fetchone()
-            if result is None:
-                return None
-            return cast(str, result[0])
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()
-
-    def get_image_count_for_board(self, board_id: str) -> int:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                SELECT COUNT(*) FROM board_images WHERE board_id = ?;
-                """,
-                (board_id,),
-            )
-            count = cast(int, self._cursor.fetchone()[0])
-            return count
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()

invokeai/app/services/board_images.py

@@ -1,142 +0,0 @@
-from abc import ABC, abstractmethod
-from logging import Logger
-from typing import List, Union
-from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
-from invokeai.app.services.board_record_storage import (
-    BoardRecord,
-    BoardRecordStorageBase,
-)
-
-from invokeai.app.services.image_record_storage import (
-    ImageRecordStorageBase,
-    OffsetPaginatedResults,
-)
-from invokeai.app.services.models.board_record import BoardDTO
-from invokeai.app.services.models.image_record import ImageDTO, image_record_to_dto
-from invokeai.app.services.urls import UrlServiceBase
-
-
-class BoardImagesServiceABC(ABC):
-    """High-level service for board-image relationship management."""
-
-    @abstractmethod
-    def add_image_to_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        """Adds an image to a board."""
-        pass
-
-    @abstractmethod
-    def remove_image_from_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        """Removes an image from a board."""
-        pass
-
-    @abstractmethod
-    def get_images_for_board(
-        self,
-        board_id: str,
-    ) -> OffsetPaginatedResults[ImageDTO]:
-        """Gets images for a board."""
-        pass
-
-    @abstractmethod
-    def get_board_for_image(
-        self,
-        image_name: str,
-    ) -> Union[str, None]:
-        """Gets an image's board id, if it has one."""
-        pass
-
-
-class BoardImagesServiceDependencies:
-    """Service dependencies for the BoardImagesService."""
-
-    board_image_records: BoardImageRecordStorageBase
-    board_records: BoardRecordStorageBase
-    image_records: ImageRecordStorageBase
-    urls: UrlServiceBase
-    logger: Logger
-
-    def __init__(
-        self,
-        board_image_record_storage: BoardImageRecordStorageBase,
-        image_record_storage: ImageRecordStorageBase,
-        board_record_storage: BoardRecordStorageBase,
-        url: UrlServiceBase,
-        logger: Logger,
-    ):
-        self.board_image_records = board_image_record_storage
-        self.image_records = image_record_storage
-        self.board_records = board_record_storage
-        self.urls = url
-        self.logger = logger
-
-
-class BoardImagesService(BoardImagesServiceABC):
-    _services: BoardImagesServiceDependencies
-
-    def __init__(self, services: BoardImagesServiceDependencies):
-        self._services = services
-
-    def add_image_to_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        self._services.board_image_records.add_image_to_board(board_id, image_name)
-
-    def remove_image_from_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        self._services.board_image_records.remove_image_from_board(board_id, image_name)
-
-    def get_images_for_board(
-        self,
-        board_id: str,
-    ) -> OffsetPaginatedResults[ImageDTO]:
-        image_records = self._services.board_image_records.get_images_for_board(
-            board_id
-        )
-        image_dtos = list(
-            map(
-                lambda r: image_record_to_dto(
-                    r,
-                    self._services.urls.get_image_url(r.image_name),
-                    self._services.urls.get_image_url(r.image_name, True),
-                    board_id,
-                ),
-                image_records.items,
-            )
-        )
-        return OffsetPaginatedResults[ImageDTO](
-            items=image_dtos,
-            offset=image_records.offset,
-            limit=image_records.limit,
-            total=image_records.total,
-        )
-
-    def get_board_for_image(
-        self,
-        image_name: str,
-    ) -> Union[str, None]:
-        board_id = self._services.board_image_records.get_board_for_image(image_name)
-        return board_id
-
-
-def board_record_to_dto(
-    board_record: BoardRecord, cover_image_name: str | None, image_count: int
-) -> BoardDTO:
-    """Converts a board record to a board DTO."""
-    return BoardDTO(
-        **board_record.dict(exclude={'cover_image_name'}),
-        cover_image_name=cover_image_name,
-        image_count=image_count,
-    )

invokeai/app/services/board_record_storage.py

@@ -1,329 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import Optional, cast
-import sqlite3
-import threading
-from typing import Optional, Union
-import uuid
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.board_record import (
-    BoardRecord,
-    deserialize_board_record,
-)
-
-from pydantic import BaseModel, Field, Extra
-
-
-class BoardChanges(BaseModel, extra=Extra.forbid):
-    board_name: Optional[str] = Field(description="The board's new name.")
-    cover_image_name: Optional[str] = Field(
-        description="The name of the board's new cover image."
-    )
-
-
-class BoardRecordNotFoundException(Exception):
-    """Raised when an board record is not found."""
-
-    def __init__(self, message="Board record not found"):
-        super().__init__(message)
-
-
-class BoardRecordSaveException(Exception):
-    """Raised when an board record cannot be saved."""
-
-    def __init__(self, message="Board record not saved"):
-        super().__init__(message)
-
-
-class BoardRecordDeleteException(Exception):
-    """Raised when an board record cannot be deleted."""
-
-    def __init__(self, message="Board record not deleted"):
-        super().__init__(message)
-
-
-class BoardRecordStorageBase(ABC):
-    """Low-level service responsible for interfacing with the board record store."""
-
-    @abstractmethod
-    def delete(self, board_id: str) -> None:
-        """Deletes a board record."""
-        pass
-
-    @abstractmethod
-    def save(
-        self,
-        board_name: str,
-    ) -> BoardRecord:
-        """Saves a board record."""
-        pass
-
-    @abstractmethod
-    def get(
-        self,
-        board_id: str,
-    ) -> BoardRecord:
-        """Gets a board record."""
-        pass
-
-    @abstractmethod
-    def update(
-        self,
-        board_id: str,
-        changes: BoardChanges,
-    ) -> BoardRecord:
-        """Updates a board record."""
-        pass
-
-    @abstractmethod
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-    ) -> OffsetPaginatedResults[BoardRecord]:
-        """Gets many board records."""
-        pass
-
-    @abstractmethod
-    def get_all(
-        self,
-    ) -> list[BoardRecord]:
-        """Gets all board records."""
-        pass
-
-
-class SqliteBoardRecordStorage(BoardRecordStorageBase):
-    _filename: str
-    _conn: sqlite3.Connection
-    _cursor: sqlite3.Cursor
-    _lock: threading.Lock
-
-    def __init__(self, filename: str) -> None:
-        super().__init__()
-        self._filename = filename
-        self._conn = sqlite3.connect(filename, check_same_thread=False)
-        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
-        self._conn.row_factory = sqlite3.Row
-        self._cursor = self._conn.cursor()
-        self._lock = threading.Lock()
-
-        try:
-            self._lock.acquire()
-            # Enable foreign keys
-            self._conn.execute("PRAGMA foreign_keys = ON;")
-            self._create_tables()
-            self._conn.commit()
-        finally:
-            self._lock.release()
-
-    def _create_tables(self) -> None:
-        """Creates the `boards` table and `board_images` junction table."""
-
-        # Create the `boards` table.
-        self._cursor.execute(
-            """--sql
-            CREATE TABLE IF NOT EXISTS boards (
-                board_id TEXT NOT NULL PRIMARY KEY,
-                board_name TEXT NOT NULL,
-                cover_image_name TEXT,
-                created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                -- Updated via trigger
-                updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                -- Soft delete, currently unused
-                deleted_at DATETIME,
-                FOREIGN KEY (cover_image_name) REFERENCES images (image_name) ON DELETE SET NULL
-            );
-            """
-        )
-
-        self._cursor.execute(
-            """--sql
-            CREATE INDEX IF NOT EXISTS idx_boards_created_at ON boards (created_at);
-            """
-        )
-
-        # Add trigger for `updated_at`.
-        self._cursor.execute(
-            """--sql
-            CREATE TRIGGER IF NOT EXISTS tg_boards_updated_at
-            AFTER UPDATE
-            ON boards FOR EACH ROW
-            BEGIN
-                UPDATE boards SET updated_at = current_timestamp
-                    WHERE board_id = old.board_id;
-            END;
-            """
-        )
-
-    def delete(self, board_id: str) -> None:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                DELETE FROM boards
-                WHERE board_id = ?;
-                """,
-                (board_id,),
-            )
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise BoardRecordDeleteException from e
-        except Exception as e:
-            self._conn.rollback()
-            raise BoardRecordDeleteException from e
-        finally:
-            self._lock.release()
-
-    def save(
-        self,
-        board_name: str,
-    ) -> BoardRecord:
-        try:
-            board_id = str(uuid.uuid4())
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                INSERT OR IGNORE INTO boards (board_id, board_name)
-                VALUES (?, ?);
-                """,
-                (board_id, board_name),
-            )
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise BoardRecordSaveException from e
-        finally:
-            self._lock.release()
-        return self.get(board_id)
-
-    def get(
-        self,
-        board_id: str,
-    ) -> BoardRecord:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                SELECT *
-                FROM boards
-                WHERE board_id = ?;
-                """,
-                (board_id,),
-            )
-
-            result = cast(Union[sqlite3.Row, None], self._cursor.fetchone())
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise BoardRecordNotFoundException from e
-        finally:
-            self._lock.release()
-        if result is None:
-            raise BoardRecordNotFoundException
-        return BoardRecord(**dict(result))
-
-    def update(
-        self,
-        board_id: str,
-        changes: BoardChanges,
-    ) -> BoardRecord:
-        try:
-            self._lock.acquire()
-
-            # Change the name of a board
-            if changes.board_name is not None:
-                self._cursor.execute(
-                    f"""--sql
-                    UPDATE boards
-                    SET board_name = ?
-                    WHERE board_id = ?;
-                    """,
-                    (changes.board_name, board_id),
-                )
-
-            # Change the cover image of a board
-            if changes.cover_image_name is not None:
-                self._cursor.execute(
-                    f"""--sql
-                    UPDATE boards
-                    SET cover_image_name = ?
-                    WHERE board_id = ?;
-                    """,
-                    (changes.cover_image_name, board_id),
-                )
-
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise BoardRecordSaveException from e
-        finally:
-            self._lock.release()
-        return self.get(board_id)
-
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-    ) -> OffsetPaginatedResults[BoardRecord]:
-        try:
-            self._lock.acquire()
-
-            # Get all the boards
-            self._cursor.execute(
-                """--sql
-                SELECT *
-                FROM boards
-                ORDER BY created_at DESC
-                LIMIT ? OFFSET ?;
-                """,
-                (limit, offset),
-            )
-
-            result = cast(list[sqlite3.Row], self._cursor.fetchall())
-            boards = list(map(lambda r: deserialize_board_record(dict(r)), result))
-
-            # Get the total number of boards
-            self._cursor.execute(
-                """--sql
-                SELECT COUNT(*)
-                FROM boards
-                WHERE 1=1;
-                """
-            )
-
-            count = cast(int, self._cursor.fetchone()[0])
-
-            return OffsetPaginatedResults[BoardRecord](
-                items=boards, offset=offset, limit=limit, total=count
-            )
-
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()
-
-    def get_all(
-        self,
-    ) -> list[BoardRecord]:
-        try:
-            self._lock.acquire()
-
-            # Get all the boards
-            self._cursor.execute(
-                """--sql
-                SELECT *
-                FROM boards
-                ORDER BY created_at DESC
-                """
-            )
-
-            result = cast(list[sqlite3.Row], self._cursor.fetchall())
-            boards = list(map(lambda r: deserialize_board_record(dict(r)), result))
-
-            return boards
-
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()

invokeai/app/services/boards.py

@@ -1,185 +0,0 @@
-from abc import ABC, abstractmethod
-
-from logging import Logger
-from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
-from invokeai.app.services.board_images import board_record_to_dto
-
-from invokeai.app.services.board_record_storage import (
-    BoardChanges,
-    BoardRecordStorageBase,
-)
-from invokeai.app.services.image_record_storage import (
-    ImageRecordStorageBase,
-    OffsetPaginatedResults,
-)
-from invokeai.app.services.models.board_record import BoardDTO
-from invokeai.app.services.urls import UrlServiceBase
-
-
-class BoardServiceABC(ABC):
-    """High-level service for board management."""
-
-    @abstractmethod
-    def create(
-        self,
-        board_name: str,
-    ) -> BoardDTO:
-        """Creates a board."""
-        pass
-
-    @abstractmethod
-    def get_dto(
-        self,
-        board_id: str,
-    ) -> BoardDTO:
-        """Gets a board."""
-        pass
-
-    @abstractmethod
-    def update(
-        self,
-        board_id: str,
-        changes: BoardChanges,
-    ) -> BoardDTO:
-        """Updates a board."""
-        pass
-
-    @abstractmethod
-    def delete(
-        self,
-        board_id: str,
-    ) -> None:
-        """Deletes a board."""
-        pass
-
-    @abstractmethod
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-    ) -> OffsetPaginatedResults[BoardDTO]:
-        """Gets many boards."""
-        pass
-
-    @abstractmethod
-    def get_all(
-        self,
-    ) -> list[BoardDTO]:
-        """Gets all boards."""
-        pass
-
-
-class BoardServiceDependencies:
-    """Service dependencies for the BoardService."""
-
-    board_image_records: BoardImageRecordStorageBase
-    board_records: BoardRecordStorageBase
-    image_records: ImageRecordStorageBase
-    urls: UrlServiceBase
-    logger: Logger
-
-    def __init__(
-        self,
-        board_image_record_storage: BoardImageRecordStorageBase,
-        image_record_storage: ImageRecordStorageBase,
-        board_record_storage: BoardRecordStorageBase,
-        url: UrlServiceBase,
-        logger: Logger,
-    ):
-        self.board_image_records = board_image_record_storage
-        self.image_records = image_record_storage
-        self.board_records = board_record_storage
-        self.urls = url
-        self.logger = logger
-
-
-class BoardService(BoardServiceABC):
-    _services: BoardServiceDependencies
-
-    def __init__(self, services: BoardServiceDependencies):
-        self._services = services
-
-    def create(
-        self,
-        board_name: str,
-    ) -> BoardDTO:
-        board_record = self._services.board_records.save(board_name)
-        return board_record_to_dto(board_record, None, 0)
-
-    def get_dto(self, board_id: str) -> BoardDTO:
-        board_record = self._services.board_records.get(board_id)
-        cover_image = self._services.image_records.get_most_recent_image_for_board(
-            board_record.board_id
-        )
-        if cover_image:
-            cover_image_name = cover_image.image_name
-        else:
-            cover_image_name = None
-        image_count = self._services.board_image_records.get_image_count_for_board(
-            board_id
-        )
-        return board_record_to_dto(board_record, cover_image_name, image_count)
-
-    def update(
-        self,
-        board_id: str,
-        changes: BoardChanges,
-    ) -> BoardDTO:
-        board_record = self._services.board_records.update(board_id, changes)
-        cover_image = self._services.image_records.get_most_recent_image_for_board(
-            board_record.board_id
-        )
-        if cover_image:
-            cover_image_name = cover_image.image_name
-        else:
-            cover_image_name = None
-
-        image_count = self._services.board_image_records.get_image_count_for_board(
-            board_id
-        )
-        return board_record_to_dto(board_record, cover_image_name, image_count)
-
-    def delete(self, board_id: str) -> None:
-        self._services.board_records.delete(board_id)
-
-    def get_many(
-        self, offset: int = 0, limit: int = 10
-    ) -> OffsetPaginatedResults[BoardDTO]:
-        board_records = self._services.board_records.get_many(offset, limit)
-        board_dtos = []
-        for r in board_records.items:
-            cover_image = self._services.image_records.get_most_recent_image_for_board(
-                r.board_id
-            )
-            if cover_image:
-                cover_image_name = cover_image.image_name
-            else:
-                cover_image_name = None
-
-            image_count = self._services.board_image_records.get_image_count_for_board(
-                r.board_id
-            )
-            board_dtos.append(board_record_to_dto(r, cover_image_name, image_count))
-
-        return OffsetPaginatedResults[BoardDTO](
-            items=board_dtos, offset=offset, limit=limit, total=len(board_dtos)
-        )
-
-    def get_all(self) -> list[BoardDTO]:
-        board_records = self._services.board_records.get_all()
-        board_dtos = []
-        for r in board_records:
-            cover_image = self._services.image_records.get_most_recent_image_for_board(
-                r.board_id
-            )
-            if cover_image:
-                cover_image_name = cover_image.image_name
-            else:
-                cover_image_name = None
-
-            image_count = self._services.board_image_records.get_image_count_for_board(
-                r.board_id
-            )
-            board_dtos.append(board_record_to_dto(r, cover_image_name, image_count))
-
-        return board_dtos

invokeai/app/services/config.py

@@ -1,542 +0,0 @@
-# Copyright (c) 2023 Lincoln Stein (https://github.com/lstein) and the InvokeAI Development Team
-
-'''Invokeai configuration system.
-
-Arguments and fields are taken from the pydantic definition of the
-model.  Defaults can be set by creating a yaml configuration file that
-has a top-level key of "InvokeAI" and subheadings for each of the
-categories returned by `invokeai --help`. The file looks like this:
-
-[file: invokeai.yaml]
-
-InvokeAI:
-  Paths:
-    root: /home/lstein/invokeai-main
-    conf_path: configs/models.yaml
-    legacy_conf_dir: configs/stable-diffusion
-    outdir: outputs
-    autoimport_dir: null
-  Models:
-    model: stable-diffusion-1.5
-    embeddings: true
-  Memory/Performance:
-    xformers_enabled: false
-    sequential_guidance: false
-    precision: float16
-    max_loaded_models: 4
-    always_use_cpu: false
-    free_gpu_mem: false
-  Features:
-    nsfw_checker: true
-    restore: true
-    esrgan: true
-    patchmatch: true
-    internet_available: true
-    log_tokenization: false
-  Web Server:
-    host: 127.0.0.1
-    port: 8081
-    allow_origins: []
-    allow_credentials: true
-    allow_methods:
-    - '*'
-    allow_headers:
-    - '*'
-
-The default name of the configuration file is `invokeai.yaml`, located
-in INVOKEAI_ROOT. You can replace supersede this by providing any
-OmegaConf dictionary object initialization time:
-
- omegaconf = OmegaConf.load('/tmp/init.yaml')
- conf = InvokeAIAppConfig()
- conf.parse_args(conf=omegaconf)
-
-InvokeAIAppConfig.parse_args() will parse the contents of `sys.argv`
-at initialization time. You may pass a list of strings in the optional
-`argv` argument to use instead of the system argv:
-
- conf.parse_args(argv=['--xformers_enabled'])
-
-It is also possible to set a value at initialization time. However, if
-you call parse_args() it may be overwritten.
-
- conf = InvokeAIAppConfig(xformers_enabled=True)
- conf.parse_args(argv=['--no-xformers'])
- conf.xformers_enabled
- # False
-
-
-To avoid this, use `get_config()` to retrieve the application-wide
-configuration object. This will retain any properties set at object
-creation time:
-
- conf = InvokeAIAppConfig.get_config(xformers_enabled=True)
- conf.parse_args(argv=['--no-xformers'])
- conf.xformers_enabled
- # True
-
-Any setting can be overwritten by setting an environment variable of
-form: "INVOKEAI_<setting>", as in:
-
-  export INVOKEAI_port=8080
-
-Order of precedence (from highest):
-   1) initialization options
-   2) command line options
-   3) environment variable options
-   4) config file options
-   5) pydantic defaults
-
-Typical usage at the top level file:
-
- from invokeai.app.services.config import InvokeAIAppConfig
-
- # get global configuration and print its nsfw_checker value
- conf = InvokeAIAppConfig.get_config()
- conf.parse_args()
- print(conf.nsfw_checker)
-
-Typical usage in a backend module:
-
- from invokeai.app.services.config import InvokeAIAppConfig
-
- # get global configuration and print its nsfw_checker value
- conf = InvokeAIAppConfig.get_config()
- print(conf.nsfw_checker)
-
-
-Computed properties:
-
-The InvokeAIAppConfig object has a series of properties that
-resolve paths relative to the runtime root directory. They each return
-a Path object:
-
- root_path          - path to InvokeAI root
- output_path        - path to default outputs directory
- model_conf_path    - path to models.yaml
- conf               - alias for the above
- embedding_path     - path to the embeddings directory
- lora_path          - path to the LoRA directory
-
-In most cases, you will want to create a single InvokeAIAppConfig
-object for the entire application. The InvokeAIAppConfig.get_config() function
-does this:
-
-  config = InvokeAIAppConfig.get_config()
-  config.parse_args()   # read values from the command line/config file
-  print(config.root)
-
-# Subclassing
-
-If you wish to create a similar class, please subclass the
-`InvokeAISettings` class and define a Literal field named "type",
-which is set to the desired top-level name.  For example, to create a
-"InvokeBatch" configuration, define like this:
-
-  class InvokeBatch(InvokeAISettings):
-     type: Literal["InvokeBatch"] = "InvokeBatch"
-     node_count : int = Field(default=1, description="Number of nodes to run on", category='Resources')
-     cpu_count  : int = Field(default=8, description="Number of GPUs to run on per node", category='Resources')
-
-This will now read and write from the "InvokeBatch" section of the
-config file, look for environment variables named INVOKEBATCH_*, and
-accept the command-line arguments `--node_count` and `--cpu_count`. The
-two configs are kept in separate sections of the config file:
-
-  # invokeai.yaml
-
-  InvokeBatch:
-     Resources:
-        node_count: 1
-        cpu_count: 8
-
-  InvokeAI:
-     Paths:
-        root: /home/lstein/invokeai-main
-        conf_path: configs/models.yaml
-        legacy_conf_dir: configs/stable-diffusion
-        outdir: outputs
-     ...
-
-'''
-from __future__ import annotations
-import argparse
-import pydoc
-import os
-import sys
-from argparse import ArgumentParser
-from omegaconf import OmegaConf, DictConfig
-from pathlib import Path
-from pydantic import BaseSettings, Field, parse_obj_as
-from typing import ClassVar, Dict, List, Literal, Union, get_origin, get_type_hints, get_args
-
-INIT_FILE = Path('invokeai.yaml')
-DB_FILE   = Path('invokeai.db')
-LEGACY_INIT_FILE = Path('invokeai.init')
-
-class InvokeAISettings(BaseSettings):
-    '''
-    Runtime configuration settings in which default values are
-    read from an omegaconf .yaml file.
-    '''
-    initconf             : ClassVar[DictConfig] = None
-    argparse_groups      : ClassVar[Dict] = {}
-
-    def parse_args(self, argv: list=sys.argv[1:]):
-        parser = self.get_parser()
-        opt = parser.parse_args(argv)
-        for name in self.__fields__:
-            if name not in self._excluded():
-                setattr(self, name, getattr(opt,name))
-
-    def to_yaml(self)->str:
-        """
-        Return a YAML string representing our settings. This can be used
-        as the contents of `invokeai.yaml` to restore settings later.
-        """
-        cls = self.__class__
-        type = get_args(get_type_hints(cls)['type'])[0]
-        field_dict = dict({type:dict()})
-        for name,field in self.__fields__.items():
-            if name in cls._excluded():
-                continue
-            category = field.field_info.extra.get("category") or "Uncategorized"
-            value = getattr(self,name)
-            if category not in field_dict[type]:
-                field_dict[type][category] = dict()
-            # keep paths as strings to make it easier to read
-            field_dict[type][category][name] = str(value) if isinstance(value,Path) else value
-        conf = OmegaConf.create(field_dict)
-        return OmegaConf.to_yaml(conf)
-
-    @classmethod
-    def add_parser_arguments(cls, parser):
-        if 'type' in get_type_hints(cls):
-            settings_stanza = get_args(get_type_hints(cls)['type'])[0]
-        else:
-            settings_stanza = "Uncategorized"
-
-        env_prefix = cls.Config.env_prefix if hasattr(cls.Config,'env_prefix') else settings_stanza.upper()
-
-        initconf = cls.initconf.get(settings_stanza) \
-            if cls.initconf and settings_stanza in cls.initconf \
-               else OmegaConf.create()
-
-        # create an upcase version of the environment in
-        # order to achieve case-insensitive environment
-        # variables (the way Windows does)
-        upcase_environ = dict()
-        for key,value in os.environ.items():
-            upcase_environ[key.upper()] = value
-        
-        fields = cls.__fields__
-        cls.argparse_groups = {}
-        
-        for name, field in fields.items():
-            if name not in cls._excluded():
-                current_default = field.default
-
-                category = field.field_info.extra.get("category","Uncategorized")
-                env_name = env_prefix + '_' + name
-                if category in initconf and name in initconf.get(category):
-                    field.default = initconf.get(category).get(name)
-                if env_name.upper() in upcase_environ:
-                    field.default = upcase_environ[env_name.upper()]
-                cls.add_field_argument(parser, name, field)
-
-                field.default = current_default
-
-    @classmethod
-    def cmd_name(self, command_field: str='type')->str:
-        hints = get_type_hints(self)
-        if command_field in hints:
-            return get_args(hints[command_field])[0]
-        else:
-            return 'Uncategorized'
-
-    @classmethod
-    def get_parser(cls)->ArgumentParser:
-        parser = PagingArgumentParser(
-            prog=cls.cmd_name(),
-            description=cls.__doc__,
-        )
-        cls.add_parser_arguments(parser)
-        return parser
-
-    @classmethod
-    def add_subparser(cls, parser: argparse.ArgumentParser):
-        parser.add_parser(cls.cmd_name(), help=cls.__doc__)
-
-    @classmethod
-    def _excluded(self)->List[str]:
-        return ['type','initconf']
-
-    class Config:
-        env_file_encoding = 'utf-8'
-        arbitrary_types_allowed = True
-        case_sensitive = True
-
-    @classmethod
-    def add_field_argument(cls, command_parser, name: str, field, default_override = None):
-        field_type = get_type_hints(cls).get(name)
-        default = default_override if default_override is not None else field.default if field.default_factory is None else field.default_factory()
-        if category := field.field_info.extra.get("category"):
-            if category not in cls.argparse_groups:
-                cls.argparse_groups[category] = command_parser.add_argument_group(category)
-            argparse_group = cls.argparse_groups[category]
-        else:
-            argparse_group = command_parser
-
-        if get_origin(field_type) == Literal:
-            allowed_values = get_args(field.type_)
-            allowed_types = set()
-            for val in allowed_values:
-                allowed_types.add(type(val))
-            allowed_types_list = list(allowed_types)
-            field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
-
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                type=field_type,
-                default=default,
-                choices=allowed_values,
-                help=field.field_info.description,
-            )
-
-        elif get_origin(field_type) == list:
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                nargs='*',
-                type=field.type_,
-                default=default,
-                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
-                help=field.field_info.description,
-            )
-        else:
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                type=field.type_,
-                default=default,
-                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
-                help=field.field_info.description,
-            )
-def _find_root()->Path:
-    if os.environ.get("INVOKEAI_ROOT"):
-        root = Path(os.environ.get("INVOKEAI_ROOT")).resolve()
-    elif (
-            os.environ.get("VIRTUAL_ENV")
-            and (Path(os.environ.get("VIRTUAL_ENV"), "..", INIT_FILE).exists()
-                 or
-                 Path(os.environ.get("VIRTUAL_ENV"), "..", LEGACY_INIT_FILE).exists()
-                 )
-    ):
-        root = Path(os.environ.get("VIRTUAL_ENV"), "..").resolve()
-    else:
-        root = Path("~/invokeai").expanduser().resolve()
-    return root
-
-class InvokeAIAppConfig(InvokeAISettings):
-    '''
-Generate images using Stable Diffusion. Use "invokeai" to launch
-the command-line client (recommended for experts only), or
-"invokeai-web" to launch the web server. Global options
-can be changed by editing the file "INVOKEAI_ROOT/invokeai.yaml" or by
-setting environment variables INVOKEAI_<setting>.
-     '''
-    singleton_config: ClassVar[InvokeAIAppConfig] = None
-    singleton_init: ClassVar[Dict] = None
-    
-    #fmt: off
-    type: Literal["InvokeAI"] = "InvokeAI"
-    host                : str = Field(default="127.0.0.1", description="IP address to bind to", category='Web Server')
-    port                : int = Field(default=9090, description="Port to bind to", category='Web Server')
-    allow_origins       : List[str] = Field(default=[], description="Allowed CORS origins", category='Web Server')
-    allow_credentials   : bool = Field(default=True, description="Allow CORS credentials", category='Web Server')
-    allow_methods       : List[str] = Field(default=["*"], description="Methods allowed for CORS", category='Web Server')
-    allow_headers       : List[str] = Field(default=["*"], description="Headers allowed for CORS", category='Web Server')
-
-    esrgan              : bool = Field(default=True, description="Enable/disable upscaling code", category='Features')
-    internet_available  : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", category='Features')
-    log_tokenization    : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", category='Features')
-    nsfw_checker        : bool = Field(default=True, description="Enable/disable the NSFW checker", category='Features')
-    patchmatch          : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", category='Features')
-    restore             : bool = Field(default=True, description="Enable/disable face restoration code", category='Features')
-
-    always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
-    free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
-    max_loaded_models   : int = Field(default=3, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
-    precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
-    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
-    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
-    tiled_decode        : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category='Memory/Performance')
-
-    root                : Path = Field(default=_find_root(), description='InvokeAI runtime root directory', category='Paths')
-    autoimport_dir      : Path = Field(default='autoimport/main', description='Path to a directory of models files to be imported on startup.', category='Paths')
-    lora_dir            : Path = Field(default='autoimport/lora', description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', category='Paths')
-    embedding_dir       : Path = Field(default='autoimport/embedding', description='Path to a directory of Textual Inversion embeddings to be imported on startup.', category='Paths')
-    controlnet_dir      : Path = Field(default='autoimport/controlnet', description='Path to a directory of ControlNet embeddings to be imported on startup.', category='Paths')
-    conf_path           : Path = Field(default='configs/models.yaml', description='Path to models definition file', category='Paths')
-    models_dir          : Path = Field(default='models', description='Path to the models directory', category='Paths')
-    legacy_conf_dir     : Path = Field(default='configs/stable-diffusion', description='Path to directory of legacy checkpoint config files', category='Paths')
-    db_dir              : Path = Field(default='databases', description='Path to InvokeAI databases directory', category='Paths')
-    outdir              : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
-    from_file           : Path = Field(default=None, description='Take command input from the indicated file (command-line client only)', category='Paths')
-    use_memory_db       : bool = Field(default=False, description='Use in-memory database for storing image metadata', category='Paths')
-    
-    model               : str = Field(default='stable-diffusion-1.5', description='Initial model name', category='Models')
-    
-    log_handlers        : List[str] = Field(default=["console"], description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>"', category="Logging")
-    # note - would be better to read the log_format values from logging.py, but this creates circular dependencies issues
-    log_format          : Literal[tuple(['plain','color','syslog','legacy'])] = Field(default="color", description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style', category="Logging")
-    log_level           : Literal[tuple(["debug","info","warning","error","critical"])] = Field(default="debug", description="Emit logging messages at this level or  higher", category="Logging")
-    #fmt: on
-
-    def parse_args(self, argv: List[str]=None, conf: DictConfig = None, clobber=False):
-        '''
-        Update settings with contents of init file, environment, and 
-        command-line settings.
-        :param conf: alternate Omegaconf dictionary object
-        :param argv: aternate sys.argv list
-        :param clobber: ovewrite any initialization parameters passed during initialization
-        '''
-        # Set the runtime root directory. We parse command-line switches here
-        # in order to pick up the --root_dir option.
-        super().parse_args(argv)
-        if conf is None:
-            try:
-                conf = OmegaConf.load(self.root_dir / INIT_FILE)
-            except:
-                pass
-        InvokeAISettings.initconf = conf
-        
-        # parse args again in order to pick up settings in configuration file
-        super().parse_args(argv)
-
-        if self.singleton_init and not clobber:
-            hints = get_type_hints(self.__class__)
-            for k in self.singleton_init:
-                setattr(self,k,parse_obj_as(hints[k],self.singleton_init[k]))
-
-    @classmethod
-    def get_config(cls,**kwargs)->InvokeAIAppConfig:
-        '''
-        This returns a singleton InvokeAIAppConfig configuration object.
-        '''
-        if cls.singleton_config is None \
-           or type(cls.singleton_config)!=cls \
-           or (kwargs and cls.singleton_init != kwargs):
-            cls.singleton_config = cls(**kwargs)
-            cls.singleton_init = kwargs
-        return cls.singleton_config
-        
-    @property
-    def root_path(self)->Path:
-        '''
-        Path to the runtime root directory
-        '''
-        if self.root:
-            return Path(self.root).expanduser()
-        else:
-            return self.find_root()
-
-    @property
-    def root_dir(self)->Path:
-        '''
-        Alias for above.
-        '''
-        return self.root_path
-
-    def _resolve(self,partial_path:Path)->Path:
-        return (self.root_path / partial_path).resolve()
-
-    @property
-    def init_file_path(self)->Path:
-        '''
-        Path to invokeai.yaml
-        '''
-        return self._resolve(INIT_FILE)
-
-    @property
-    def output_path(self)->Path:
-        '''
-        Path to defaults outputs directory.
-        '''
-        return self._resolve(self.outdir)
-
-    @property
-    def db_path(self)->Path:
-        '''
-        Path to the invokeai.db file.
-        '''
-        return self._resolve(self.db_dir) / DB_FILE
-
-    @property
-    def model_conf_path(self)->Path:
-        '''
-        Path to models configuration file.
-        '''
-        return self._resolve(self.conf_path)
-
-    @property
-    def legacy_conf_path(self)->Path:
-        '''
-        Path to directory of legacy configuration files (e.g. v1-inference.yaml)
-        '''
-        return self._resolve(self.legacy_conf_dir)
-
-    @property
-    def models_path(self)->Path:
-        '''
-        Path to the models directory
-        '''
-        return self._resolve(self.models_dir)
-
-    @property
-    def autoconvert_path(self)->Path:
-        '''
-        Path to the directory containing models to be imported automatically at startup.
-        '''
-        return self._resolve(self.autoconvert_dir) if self.autoconvert_dir else None
-
-    # the following methods support legacy calls leftover from the Globals era
-    @property
-    def full_precision(self)->bool:
-        """Return true if precision set to float32"""
-        return self.precision=='float32'
-
-    @property
-    def disable_xformers(self)->bool:
-        """Return true if xformers_enabled is false"""
-        return not self.xformers_enabled
-
-    @property
-    def try_patchmatch(self)->bool:
-        """Return true if patchmatch true"""
-        return self.patchmatch
-
-    @staticmethod
-    def find_root()->Path:
-        '''
-        Choose the runtime root directory when not specified on command line or
-        init file.
-        '''
-        return _find_root()
-
-
-class PagingArgumentParser(argparse.ArgumentParser):
-    '''
-    A custom ArgumentParser that uses pydoc to page its output.
-    It also supports reading defaults from an init file.
-    '''
-    def print_help(self, file=None):
-        text = self.format_help()
-        pydoc.pager(text)
-
-def get_invokeai_config(**kwargs)->InvokeAIAppConfig:
-    '''
-    Legacy function which returns InvokeAIAppConfig.get_config()
-    '''
-    return InvokeAIAppConfig.get_config(**kwargs)

invokeai/app/services/default_graphs.py

@@ -1,6 +1,4 @@
-from ..invocations.latent import LatentsToImageInvocation, TextToLatentsInvocation
-from ..invocations.noise import NoiseInvocation
-from ..invocations.compel import CompelInvocation
+from ..invocations.latent import LatentsToImageInvocation, NoiseInvocation, TextToLatentsInvocation
 from ..invocations.params import ParamIntInvocation
 from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph
 from .item_storage import ItemStorageABC
@@ -18,45 +16,38 @@ def create_text_to_image() -> LibraryGraph:
             nodes={
                 'width': ParamIntInvocation(id='width', a=512),
                 'height': ParamIntInvocation(id='height', a=512),
-                'seed': ParamIntInvocation(id='seed', a=-1),
                 '3': NoiseInvocation(id='3'),
-                '4': CompelInvocation(id='4'),
-                '5': CompelInvocation(id='5'),
-                '6': TextToLatentsInvocation(id='6'),
-                '7': LatentsToImageInvocation(id='7'),
+                '4': TextToLatentsInvocation(id='4'),
+                '5': LatentsToImageInvocation(id='5')
             },
             edges=[
                 Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='3', field='width')),
                 Edge(source=EdgeConnection(node_id='height', field='a'), destination=EdgeConnection(node_id='3', field='height')),
-                Edge(source=EdgeConnection(node_id='seed', field='a'), destination=EdgeConnection(node_id='3', field='seed')),
-                Edge(source=EdgeConnection(node_id='3', field='noise'), destination=EdgeConnection(node_id='6', field='noise')),
-                Edge(source=EdgeConnection(node_id='6', field='latents'), destination=EdgeConnection(node_id='7', field='latents')),
-                Edge(source=EdgeConnection(node_id='4', field='conditioning'), destination=EdgeConnection(node_id='6', field='positive_conditioning')),
-                Edge(source=EdgeConnection(node_id='5', field='conditioning'), destination=EdgeConnection(node_id='6', field='negative_conditioning')),
+                Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='4', field='width')),
+                Edge(source=EdgeConnection(node_id='height', field='a'), destination=EdgeConnection(node_id='4', field='height')),
+                Edge(source=EdgeConnection(node_id='3', field='noise'), destination=EdgeConnection(node_id='4', field='noise')),
+                Edge(source=EdgeConnection(node_id='4', field='latents'), destination=EdgeConnection(node_id='5', field='latents')),
             ]
         ),
         exposed_inputs=[
-            ExposedNodeInput(node_path='4', field='prompt', alias='positive_prompt'),
-            ExposedNodeInput(node_path='5', field='prompt', alias='negative_prompt'),
+            ExposedNodeInput(node_path='4', field='prompt', alias='prompt'),
             ExposedNodeInput(node_path='width', field='a', alias='width'),
-            ExposedNodeInput(node_path='height', field='a', alias='height'),
-            ExposedNodeInput(node_path='seed', field='a', alias='seed'),
+            ExposedNodeInput(node_path='height', field='a', alias='height')
         ],
         exposed_outputs=[
-            ExposedNodeOutput(node_path='7', field='image', alias='image')
+            ExposedNodeOutput(node_path='5', field='image', alias='image')
         ])
 
 
 def create_system_graphs(graph_library: ItemStorageABC[LibraryGraph]) -> list[LibraryGraph]:
     """Creates the default system graphs, or adds new versions if the old ones don't match"""
-    
-    # TODO: Uncomment this when we are ready to fix this up to prevent breaking changes
+
     graphs: list[LibraryGraph] = list()
 
-    # text_to_image = graph_library.get(default_text_to_image_graph_id)
+    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:
+    # 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)
 

invokeai/app/services/events.py

@@ -1,10 +1,9 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 from typing import Any
-from invokeai.app.models.image import ProgressImage
-from invokeai.app.util.misc import get_timestamp
-from invokeai.app.services.model_manager_service import BaseModelType, ModelType, SubModelType, ModelInfo
-from invokeai.app.models.exceptions import CanceledException
+from invokeai.app.api.models.images import ProgressImage
+from invokeai.app.util.get_timestamp import get_timestamp
+
 
 class EventServiceBase:
     session_event: str = "session_event"
@@ -15,7 +14,6 @@ class EventServiceBase:
         pass
 
     def __emit_session_event(self, event_name: str, payload: dict) -> None:
-        payload["timestamp"] = get_timestamp()
         self.dispatch(
             event_name=EventServiceBase.session_event,
             payload=dict(event=event_name, data=payload),
@@ -26,7 +24,7 @@ class EventServiceBase:
     def emit_generator_progress(
         self,
         graph_execution_state_id: str,
-        node: dict,
+        invocation_dict: dict,
         source_node_id: str,
         progress_image: ProgressImage | None,
         step: int,
@@ -37,11 +35,12 @@ class EventServiceBase:
             event_name="generator_progress",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                node=node,
+                invocation=invocation_dict,
                 source_node_id=source_node_id,
                 progress_image=progress_image.dict() if progress_image is not None else None,
                 step=step,
                 total_steps=total_steps,
+                timestamp=get_timestamp(),
             ),
         )
 
@@ -49,24 +48,26 @@ class EventServiceBase:
         self,
         graph_execution_state_id: str,
         result: dict,
-        node: dict,
+        invocation_dict: dict,
         source_node_id: str,
     ) -> None:
         """Emitted when an invocation has completed"""
+        print(result)
         self.__emit_session_event(
             event_name="invocation_complete",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                node=node,
+                invocation=invocation_dict,
                 source_node_id=source_node_id,
                 result=result,
+                timestamp=get_timestamp(),
             ),
         )
 
     def emit_invocation_error(
         self,
         graph_execution_state_id: str,
-        node: dict,
+        invocation_dict: dict,
         source_node_id: str,
         error: str,
     ) -> None:
@@ -75,22 +76,24 @@ class EventServiceBase:
             event_name="invocation_error",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                node=node,
+                invocation=invocation_dict,
                 source_node_id=source_node_id,
                 error=error,
+                timestamp=get_timestamp(),
             ),
         )
 
     def emit_invocation_started(
-        self, graph_execution_state_id: str, node: dict, source_node_id: str
+        self, graph_execution_state_id: str, invocation_dict: dict, source_node_id: str
     ) -> None:
         """Emitted when an invocation has started"""
         self.__emit_session_event(
             event_name="invocation_started",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                node=node,
+                invocation=invocation_dict,
                 source_node_id=source_node_id,
+                timestamp=get_timestamp(),
             ),
         )
 
@@ -100,55 +103,6 @@ class EventServiceBase:
             event_name="graph_execution_state_complete",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-            ),
-        )
-
-    def emit_model_load_started (
-            self,
-            graph_execution_state_id: str,
-            node: dict,
-            source_node_id: str,
-            model_name: str,
-            base_model: BaseModelType,
-            model_type: ModelType,
-            submodel: SubModelType,
-    ) -> None:
-        """Emitted when a model is requested"""
-        self.__emit_session_event(
-            event_name="model_load_started",
-            payload=dict(
-                graph_execution_state_id=graph_execution_state_id,
-                node=node,
-                source_node_id=source_node_id,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-            ),
-        )
-
-    def emit_model_load_completed(
-            self,
-            graph_execution_state_id: str,
-            node: dict,
-            source_node_id: str,
-            model_name: str,
-            base_model: BaseModelType,
-            model_type: ModelType,
-            submodel: SubModelType,
-            model_info: ModelInfo,
-    ) -> None:
-        """Emitted when a model is correctly loaded (returns model info)"""
-        self.__emit_session_event(
-            event_name="model_load_completed",
-            payload=dict(
-                graph_execution_state_id=graph_execution_state_id,
-                node=node,
-                source_node_id=source_node_id,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-                model_info=model_info,
+                timestamp=get_timestamp(),
             ),
         )

invokeai/app/services/graph.py

@@ -60,33 +60,6 @@ def get_input_field(node: BaseInvocation, field: str) -> Any:
     node_input_field = node_inputs.get(field) or None
     return node_input_field
 
-from typing import Optional, Union, List, get_args
-
-def is_union_subtype(t1, t2):
-    t1_args = get_args(t1)
-    t2_args = get_args(t2)
-    if not t1_args:
-        # t1 is a single type
-        return t1 in t2_args
-    else:
-        # t1 is a Union, check that all of its types are in t2_args
-        return all(arg in t2_args for arg in t1_args)
-
-def is_list_or_contains_list(t):
-    t_args = get_args(t)
-
-    # If the type is a List
-    if get_origin(t) is list:
-        return True
-
-    # If the type is a Union
-    elif t_args:
-        # Check if any of the types in the Union is a List
-        for arg in t_args:
-            if get_origin(arg) is list:
-                return True
-    return False
-
 
 def are_connection_types_compatible(from_type: Any, to_type: Any) -> bool:
     if not from_type:
@@ -112,8 +85,7 @@ def are_connection_types_compatible(from_type: Any, to_type: Any) -> bool:
         if to_type in get_args(from_type):
             return True
 
-        # if not issubclass(from_type, to_type):
-        if not is_union_subtype(from_type, to_type):
+        if not issubclass(from_type, to_type):
             return False
     else:
         return False
@@ -163,7 +135,6 @@ class GraphInvocationOutput(BaseInvocationOutput):
 
 # TODO: Fill this out and move to invocations
 class GraphInvocation(BaseInvocation):
-    """Execute a graph"""
     type: Literal["graph"] = "graph"
 
     # TODO: figure out how to create a default here
@@ -191,7 +162,6 @@ class IterateInvocationOutput(BaseInvocationOutput):
 
 # TODO: Fill this out and move to invocations
 class IterateInvocation(BaseInvocation):
-    """Iterates over a list of items"""
     type: Literal["iterate"] = "iterate"
 
     collection: list[Any] = Field(
@@ -391,7 +361,7 @@ class Graph(BaseModel):
             from_node = self.get_node(edge.source.node_id)
             to_node = self.get_node(edge.destination.node_id)
         except NodeNotFoundError:
-            raise InvalidEdgeError("One or both nodes don't exist: {edge.source.node_id} -> {edge.destination.node_id}")
+            raise InvalidEdgeError("One or both nodes don't exist")
 
         # Validate that an edge to this node+field doesn't already exist
         input_edges = self._get_input_edges(edge.destination.node_id, edge.destination.field)
@@ -402,41 +372,41 @@ class Graph(BaseModel):
         g = self.nx_graph_flat()
         g.add_edge(edge.source.node_id, edge.destination.node_id)
         if not nx.is_directed_acyclic_graph(g):
-            raise InvalidEdgeError(f'Edge creates a cycle in the graph: {edge.source.node_id} -> {edge.destination.node_id}')
+            raise InvalidEdgeError(f'Edge creates a cycle in the graph')
 
         # Validate that the field types are compatible
         if not are_connections_compatible(
             from_node, edge.source.field, to_node, edge.destination.field
         ):
-            raise InvalidEdgeError(f'Fields are incompatible: cannot connect {edge.source.node_id}.{edge.source.field} to {edge.destination.node_id}.{edge.destination.field}')
+            raise InvalidEdgeError(f'Fields are incompatible')
 
         # Validate if iterator output type matches iterator input type (if this edge results in both being set)
         if isinstance(to_node, IterateInvocation) and edge.destination.field == "collection":
             if not self._is_iterator_connection_valid(
                 edge.destination.node_id, new_input=edge.source
             ):
-                raise InvalidEdgeError(f'Iterator input type does not match iterator output type: {edge.source.node_id}.{edge.source.field} to {edge.destination.node_id}.{edge.destination.field}')
+                raise InvalidEdgeError(f'Iterator input type does not match iterator output type')
 
         # Validate if iterator input type matches output type (if this edge results in both being set)
         if isinstance(from_node, IterateInvocation) and edge.source.field == "item":
             if not self._is_iterator_connection_valid(
                 edge.source.node_id, new_output=edge.destination
             ):
-                raise InvalidEdgeError(f'Iterator output type does not match iterator input type:, {edge.source.node_id}.{edge.source.field} to {edge.destination.node_id}.{edge.destination.field}')
+                raise InvalidEdgeError(f'Iterator output type does not match iterator input type')
 
         # Validate if collector input type matches output type (if this edge results in both being set)
         if isinstance(to_node, CollectInvocation) and edge.destination.field == "item":
             if not self._is_collector_connection_valid(
                 edge.destination.node_id, new_input=edge.source
             ):
-                raise InvalidEdgeError(f'Collector output type does not match collector input type: {edge.source.node_id}.{edge.source.field} to {edge.destination.node_id}.{edge.destination.field}')
+                raise InvalidEdgeError(f'Collector output type does not match collector input type')
 
         # Validate if collector output type matches input type (if this edge results in both being set)
         if isinstance(from_node, CollectInvocation) and edge.source.field == "collection":
             if not self._is_collector_connection_valid(
                 edge.source.node_id, new_output=edge.destination
             ):
-                raise InvalidEdgeError(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}')
+                raise InvalidEdgeError(f'Collector input type does not match collector output type')
 
 
     def has_node(self, node_path: str) -> bool:
@@ -722,11 +692,7 @@ class Graph(BaseModel):
         input_root_type = next(t[0] for t in type_degrees if t[1] == 0)  # type: ignore
 
         # Verify that all outputs are lists
-        # if not all((get_origin(f) == list for f in output_fields)):
-        #     return False
-
-        # Verify that all outputs are lists
-        if not all(is_list_or_contains_list(f) for f in output_fields):
+        if not all((get_origin(f) == list for f in output_fields)):
             return False
 
         # Verify that all outputs match the input type (are a base class or the same class)
@@ -745,13 +711,6 @@ class Graph(BaseModel):
         g.add_edges_from(set([(e.source.node_id, e.destination.node_id) for e in self.edges]))
         return g
 
-    def nx_graph_with_data(self) -> nx.DiGraph:
-        """Returns a NetworkX DiGraph representing the data and layout of this graph"""
-        g = nx.DiGraph()
-        g.add_nodes_from([n for n in self.nodes.items()])
-        g.add_edges_from(set([(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, prefix: Optional[str] = None
     ) -> nx.DiGraph:
@@ -857,9 +816,11 @@ class GraphExecutionState(BaseModel):
         if next_node is None:
             prepared_id = self._prepare()
 
-            # Prepare as many nodes as we can
-            while prepared_id is not None:
-                prepared_id = self._prepare()
+            # TODO: prepare multiple nodes at once?
+            # while prepared_id is not None and not isinstance(self.graph.nodes[prepared_id], IterateInvocation):
+            #     prepared_id = self._prepare()
+
+            if prepared_id is not None:
                 next_node = self._get_next_node()
 
         # Get values from edges
@@ -1006,30 +967,14 @@ class GraphExecutionState(BaseModel):
         # Get flattened source graph
         g = self.graph.nx_graph_flat()
 
-        # Find next node that:
-        # - was not already prepared
-        # - is not an iterate node whose inputs have not been executed
-        # - does not have an unexecuted iterate ancestor
+        # Find next unprepared node where all source nodes are executed
         sorted_nodes = nx.topological_sort(g)
         next_node_id = next(
             (
                 n
                 for n in sorted_nodes
-                # exclude nodes that have already been prepared
                 if n not in self.source_prepared_mapping
-                # exclude iterate nodes whose inputs have not been executed
-                and not (
-                    isinstance(self.graph.get_node(n), IterateInvocation)  # `n` is an iterate node...
-                    and not all((e[0] in self.executed for e in g.in_edges(n)))  # ...that has unexecuted inputs
-                )
-                # exclude nodes who have unexecuted iterate ancestors
-                and not any(
-                    (
-                        isinstance(self.graph.get_node(a), IterateInvocation)  # `a` is an iterate ancestor of `n`...
-                        and a not in self.executed  # ...that is not executed
-                        for a in nx.ancestors(g, n)  # for all ancestors `a` of node `n`
-                    )
-                )
+                and all((e[0] in self.executed for e in g.in_edges(n)))
             ),
             None,
         )
@@ -1126,22 +1071,9 @@ class GraphExecutionState(BaseModel):
         )
 
     def _get_next_node(self) -> Optional[BaseInvocation]:
-        """Gets the deepest node that is ready to be executed"""
         g = self.execution_graph.nx_graph()
-
-        # Depth-first search with pre-order traversal is a depth-first topological sort
-        sorted_nodes = nx.dfs_preorder_nodes(g)
-        
-        next_node = next(
-            (
-                n
-                for n in sorted_nodes
-                if n not in self.executed # the node must not already be executed...
-                and all((e[0] in self.executed for e in g.in_edges(n))) # ...and all its inputs must be executed
-            ),
-            None,
-        )
-
+        sorted_nodes = nx.topological_sort(g)
+        next_node = next((n for n in sorted_nodes if n not in self.executed), None)
         if next_node is None:
             return None
 

invokeai/app/services/image_file_storage.py

@@ -1,190 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
-from abc import ABC, abstractmethod
-from pathlib import Path
-from queue import Queue
-from typing import Dict, Optional
-
-from PIL.Image import Image as PILImageType
-from PIL import Image, PngImagePlugin
-from send2trash import send2trash
-
-from invokeai.app.models.image import ResourceOrigin
-from invokeai.app.models.metadata import ImageMetadata
-from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
-
-
-# TODO: Should these excpetions subclass existing python exceptions?
-class ImageFileNotFoundException(Exception):
-    """Raised when an image file is not found in storage."""
-
-    def __init__(self, message="Image file not found"):
-        super().__init__(message)
-
-
-class ImageFileSaveException(Exception):
-    """Raised when an image cannot be saved."""
-
-    def __init__(self, message="Image file not saved"):
-        super().__init__(message)
-
-
-class ImageFileDeleteException(Exception):
-    """Raised when an image cannot be deleted."""
-
-    def __init__(self, message="Image file not deleted"):
-        super().__init__(message)
-
-
-class ImageFileStorageBase(ABC):
-    """Low-level service responsible for storing and retrieving image files."""
-
-    @abstractmethod
-    def get(self, image_name: str) -> PILImageType:
-        """Retrieves an image as PIL Image."""
-        pass
-
-    @abstractmethod
-    def get_path(self, image_name: str, thumbnail: bool = False) -> str:
-        """Gets the internal path to an image or thumbnail."""
-        pass
-
-    # TODO: We need to validate paths before starlette makes the FileResponse, else we get a
-    # 500 internal server error. I don't like having this method on the service.
-    @abstractmethod
-    def validate_path(self, path: str) -> bool:
-        """Validates the path given for an image or thumbnail."""
-        pass
-
-    @abstractmethod
-    def save(
-        self,
-        image: PILImageType,
-        image_name: str,
-        metadata: Optional[ImageMetadata] = None,
-        thumbnail_size: int = 256,
-    ) -> None:
-        """Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image name, thumbnail name, and created timestamp."""
-        pass
-
-    @abstractmethod
-    def delete(self, image_name: str) -> None:
-        """Deletes an image and its thumbnail (if one exists)."""
-        pass
-
-
-class DiskImageFileStorage(ImageFileStorageBase):
-    """Stores images on disk"""
-
-    __output_folder: Path
-    __cache_ids: Queue  # TODO: this is an incredibly naive cache
-    __cache: Dict[Path, PILImageType]
-    __max_cache_size: int
-
-    def __init__(self, output_folder: str | Path):
-        self.__cache = dict()
-        self.__cache_ids = Queue()
-        self.__max_cache_size = 10  # TODO: get this from config
-
-        self.__output_folder: Path = (
-            output_folder if isinstance(output_folder, Path) else Path(output_folder)
-        )
-        self.__thumbnails_folder = self.__output_folder / "thumbnails"
-
-        # Validate required output folders at launch
-        self.__validate_storage_folders()
-
-    def get(self, image_name: str) -> PILImageType:
-        try:
-            image_path = self.get_path(image_name)
-
-            cache_item = self.__get_cache(image_path)
-            if cache_item:
-                return cache_item
-
-            image = Image.open(image_path)
-            self.__set_cache(image_path, image)
-            return image
-        except FileNotFoundError as e:
-            raise ImageFileNotFoundException from e
-
-    def save(
-        self,
-        image: PILImageType,
-        image_name: str,
-        metadata: Optional[ImageMetadata] = None,
-        thumbnail_size: int = 256,
-    ) -> None:
-        try:
-            self.__validate_storage_folders()
-            image_path = self.get_path(image_name)
-
-            if metadata is not None:
-                pnginfo = PngImagePlugin.PngInfo()
-                pnginfo.add_text("invokeai", metadata.json())
-                image.save(image_path, "PNG", pnginfo=pnginfo)
-            else:
-                image.save(image_path, "PNG")
-
-            thumbnail_name = get_thumbnail_name(image_name)
-            thumbnail_path = self.get_path(thumbnail_name, thumbnail=True)
-            thumbnail_image = make_thumbnail(image, thumbnail_size)
-            thumbnail_image.save(thumbnail_path)
-
-            self.__set_cache(image_path, image)
-            self.__set_cache(thumbnail_path, thumbnail_image)
-        except Exception as e:
-            raise ImageFileSaveException from e
-
-    def delete(self, image_name: str) -> None:
-        try:
-            image_path = self.get_path(image_name)
-
-            if image_path.exists():
-                send2trash(image_path)
-            if image_path in self.__cache:
-                del self.__cache[image_path]
-
-            thumbnail_name = get_thumbnail_name(image_name)
-            thumbnail_path = self.get_path(thumbnail_name, True)
-
-            if thumbnail_path.exists():
-                send2trash(thumbnail_path)
-            if thumbnail_path in self.__cache:
-                del self.__cache[thumbnail_path]
-        except Exception as e:
-            raise ImageFileDeleteException from e
-
-    # TODO: make this a bit more flexible for e.g. cloud storage
-    def get_path(self, image_name: str, thumbnail: bool = False) -> Path:
-        path = self.__output_folder / image_name
-
-        if thumbnail:
-            thumbnail_name = get_thumbnail_name(image_name)
-            path = self.__thumbnails_folder / thumbnail_name
-
-        return path
-
-    def validate_path(self, path: str | Path) -> bool:
-        """Validates the path given for an image or thumbnail."""
-        path = path if isinstance(path, Path) else Path(path)
-        return path.exists()
-
-    def __validate_storage_folders(self) -> None:
-        """Checks if the required output folders exist and create them if they don't"""
-        folders: list[Path] = [self.__output_folder, self.__thumbnails_folder]
-        for folder in folders:
-            folder.mkdir(parents=True, exist_ok=True)
-
-    def __get_cache(self, image_name: Path) -> PILImageType | None:
-        return None if image_name not in self.__cache else self.__cache[image_name]
-
-    def __set_cache(self, image_name: Path, image: PILImageType):
-        if not image_name in self.__cache:
-            self.__cache[image_name] = image
-            self.__cache_ids.put(
-                image_name
-            )  # TODO: this should refresh position for LRU cache
-            if len(self.__cache) > self.__max_cache_size:
-                cache_id = self.__cache_ids.get()
-                if cache_id in self.__cache:
-                    del self.__cache[cache_id]

invokeai/app/services/image_record_storage.py

@@ -1,499 +0,0 @@
-from abc import ABC, abstractmethod
-from datetime import datetime
-from typing import Generic, Optional, TypeVar, cast
-import sqlite3
-import threading
-from typing import Optional, Union
-
-from pydantic import BaseModel, Field
-from pydantic.generics import GenericModel
-
-from invokeai.app.models.metadata import ImageMetadata
-from invokeai.app.models.image import (
-    ImageCategory,
-    ResourceOrigin,
-)
-from invokeai.app.services.models.image_record import (
-    ImageRecord,
-    ImageRecordChanges,
-    deserialize_image_record,
-)
-
-T = TypeVar("T", bound=BaseModel)
-
-
-class OffsetPaginatedResults(GenericModel, Generic[T]):
-    """Offset-paginated results"""
-
-    # fmt: off
-    items: list[T] = Field(description="Items")
-    offset: int = Field(description="Offset from which to retrieve items")
-    limit: int = Field(description="Limit of items to get")
-    total: int = Field(description="Total number of items in result")
-    # fmt: on
-
-
-# TODO: Should these excpetions subclass existing python exceptions?
-class ImageRecordNotFoundException(Exception):
-    """Raised when an image record is not found."""
-
-    def __init__(self, message="Image record not found"):
-        super().__init__(message)
-
-
-class ImageRecordSaveException(Exception):
-    """Raised when an image record cannot be saved."""
-
-    def __init__(self, message="Image record not saved"):
-        super().__init__(message)
-
-
-class ImageRecordDeleteException(Exception):
-    """Raised when an image record cannot be deleted."""
-
-    def __init__(self, message="Image record not deleted"):
-        super().__init__(message)
-
-
-class ImageRecordStorageBase(ABC):
-    """Low-level service responsible for interfacing with the image record store."""
-
-    # TODO: Implement an `update()` method
-
-    @abstractmethod
-    def get(self, image_name: str) -> ImageRecord:
-        """Gets an image record."""
-        pass
-
-    @abstractmethod
-    def update(
-        self,
-        image_name: str,
-        changes: ImageRecordChanges,
-    ) -> None:
-        """Updates an image record."""
-        pass
-
-    @abstractmethod
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-        image_origin: Optional[ResourceOrigin] = None,
-        categories: Optional[list[ImageCategory]] = None,
-        is_intermediate: Optional[bool] = None,
-        board_id: Optional[str] = None,
-    ) -> OffsetPaginatedResults[ImageRecord]:
-        """Gets a page of image records."""
-        pass
-
-    # TODO: The database has a nullable `deleted_at` column, currently unused.
-    # Should we implement soft deletes? Would need coordination with ImageFileStorage.
-    @abstractmethod
-    def delete(self, image_name: str) -> None:
-        """Deletes an image record."""
-        pass
-
-    @abstractmethod
-    def delete_many(self, image_names: list[str]) -> None:
-        """Deletes many image records."""
-        pass
-
-    @abstractmethod
-    def save(
-        self,
-        image_name: str,
-        image_origin: ResourceOrigin,
-        image_category: ImageCategory,
-        width: int,
-        height: int,
-        session_id: Optional[str],
-        node_id: Optional[str],
-        metadata: Optional[ImageMetadata],
-        is_intermediate: bool = False,
-    ) -> datetime:
-        """Saves an image record."""
-        pass
-
-    @abstractmethod
-    def get_most_recent_image_for_board(self, board_id: str) -> ImageRecord | None:
-        """Gets the most recent image for a board."""
-        pass
-
-
-class SqliteImageRecordStorage(ImageRecordStorageBase):
-    _filename: str
-    _conn: sqlite3.Connection
-    _cursor: sqlite3.Cursor
-    _lock: threading.Lock
-
-    def __init__(self, filename: str) -> None:
-        super().__init__()
-        self._filename = filename
-        self._conn = sqlite3.connect(filename, check_same_thread=False)
-        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
-        self._conn.row_factory = sqlite3.Row
-        self._cursor = self._conn.cursor()
-        self._lock = threading.Lock()
-
-        try:
-            self._lock.acquire()
-            # Enable foreign keys
-            self._conn.execute("PRAGMA foreign_keys = ON;")
-            self._create_tables()
-            self._conn.commit()
-        finally:
-            self._lock.release()
-
-    def _create_tables(self) -> None:
-        """Creates the `images` table."""
-
-        # Create the `images` table.
-        self._cursor.execute(
-            """--sql
-            CREATE TABLE IF NOT EXISTS images (
-                image_name TEXT NOT NULL PRIMARY KEY,
-                -- This is an enum in python, unrestricted string here for flexibility
-                image_origin TEXT NOT NULL,
-                -- This is an enum in python, unrestricted string here for flexibility
-                image_category TEXT NOT NULL,
-                width INTEGER NOT NULL,
-                height INTEGER NOT NULL,
-                session_id TEXT,
-                node_id TEXT,
-                metadata TEXT,
-                is_intermediate BOOLEAN DEFAULT FALSE,
-                board_id TEXT,
-                created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                -- Updated via trigger
-                updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                -- Soft delete, currently unused
-                deleted_at DATETIME
-            );
-            """
-        )
-
-        # Create the `images` table indices.
-        self._cursor.execute(
-            """--sql
-            CREATE UNIQUE INDEX IF NOT EXISTS idx_images_image_name ON images(image_name);
-            """
-        )
-        self._cursor.execute(
-            """--sql
-            CREATE INDEX IF NOT EXISTS idx_images_image_origin ON images(image_origin);
-            """
-        )
-        self._cursor.execute(
-            """--sql
-            CREATE INDEX IF NOT EXISTS idx_images_image_category ON images(image_category);
-            """
-        )
-        self._cursor.execute(
-            """--sql
-            CREATE INDEX IF NOT EXISTS idx_images_created_at ON images(created_at);
-            """
-        )
-
-        # Add trigger for `updated_at`.
-        self._cursor.execute(
-            """--sql
-            CREATE TRIGGER IF NOT EXISTS tg_images_updated_at
-            AFTER UPDATE
-            ON images FOR EACH ROW
-            BEGIN
-                UPDATE images SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
-                    WHERE image_name = old.image_name;
-            END;
-            """
-        )
-
-    def get(self, image_name: str) -> Union[ImageRecord, None]:
-        try:
-            self._lock.acquire()
-
-            self._cursor.execute(
-                f"""--sql
-                SELECT * FROM images
-                WHERE image_name = ?;
-                """,
-                (image_name,),
-            )
-
-            result = cast(Union[sqlite3.Row, None], self._cursor.fetchone())
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise ImageRecordNotFoundException from e
-        finally:
-            self._lock.release()
-
-        if not result:
-            raise ImageRecordNotFoundException
-
-        return deserialize_image_record(dict(result))
-
-    def update(
-        self,
-        image_name: str,
-        changes: ImageRecordChanges,
-    ) -> None:
-        try:
-            self._lock.acquire()
-            # Change the category of the image
-            if changes.image_category is not None:
-                self._cursor.execute(
-                    f"""--sql
-                    UPDATE images
-                    SET image_category = ?
-                    WHERE image_name = ?;
-                    """,
-                    (changes.image_category, image_name),
-                )
-
-            # Change the session associated with the image
-            if changes.session_id is not None:
-                self._cursor.execute(
-                    f"""--sql
-                    UPDATE images
-                    SET session_id = ?
-                    WHERE image_name = ?;
-                    """,
-                    (changes.session_id, image_name),
-                )
-
-            # Change the image's `is_intermediate`` flag
-            if changes.is_intermediate is not None:
-                self._cursor.execute(
-                    f"""--sql
-                    UPDATE images
-                    SET is_intermediate = ?
-                    WHERE image_name = ?;
-                    """,
-                    (changes.is_intermediate, image_name),
-                )
-
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise ImageRecordSaveException from e
-        finally:
-            self._lock.release()
-
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-        image_origin: Optional[ResourceOrigin] = None,
-        categories: Optional[list[ImageCategory]] = None,
-        is_intermediate: Optional[bool] = None,
-        board_id: Optional[str] = None,
-    ) -> OffsetPaginatedResults[ImageRecord]:
-        try:
-            self._lock.acquire()
-
-            # Manually build two queries - one for the count, one for the records
-            count_query = """--sql
-            SELECT COUNT(*)
-            FROM images
-            LEFT JOIN board_images ON board_images.image_name = images.image_name
-            WHERE 1=1
-            """
-
-            images_query = """--sql
-            SELECT images.*
-            FROM images
-            LEFT JOIN board_images ON board_images.image_name = images.image_name
-            WHERE 1=1
-            """
-
-            query_conditions = ""
-            query_params = []
-
-            if image_origin is not None:
-                query_conditions += """--sql
-                AND images.image_origin = ?
-                """
-                query_params.append(image_origin.value)
-
-            if categories is not None:
-                # Convert the enum values to unique list of strings
-                category_strings = list(map(lambda c: c.value, set(categories)))
-                # Create the correct length of placeholders
-                placeholders = ",".join("?" * len(category_strings))
-
-                query_conditions += f"""--sql
-                AND images.image_category IN ( {placeholders} )
-                """
-
-                # Unpack the included categories into the query params
-                for c in category_strings:
-                    query_params.append(c)
-
-            if is_intermediate is not None:
-                query_conditions += """--sql
-                AND images.is_intermediate = ?
-                """
-
-                query_params.append(is_intermediate)
-
-            if board_id is not None:
-                query_conditions += """--sql
-                AND board_images.board_id = ?
-                """
-
-                query_params.append(board_id)
-
-            query_pagination = """--sql
-            ORDER BY images.created_at DESC LIMIT ? OFFSET ?
-            """
-
-            # Final images query with pagination
-            images_query += query_conditions + query_pagination + ";"
-            # Add all the parameters
-            images_params = query_params.copy()
-            images_params.append(limit)
-            images_params.append(offset)
-            # Build the list of images, deserializing each row
-            self._cursor.execute(images_query, images_params)
-            result = cast(list[sqlite3.Row], self._cursor.fetchall())
-            images = list(map(lambda r: deserialize_image_record(dict(r)), result))
-
-            # Set up and execute the count query, without pagination
-            count_query += query_conditions + ";"
-            count_params = query_params.copy()
-            self._cursor.execute(count_query, count_params)
-            count = cast(int, self._cursor.fetchone()[0])
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()
-
-        return OffsetPaginatedResults(
-            items=images, offset=offset, limit=limit, total=count
-        )
-
-    def delete(self, image_name: str) -> None:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                DELETE FROM images
-                WHERE image_name = ?;
-                """,
-                (image_name,),
-            )
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise ImageRecordDeleteException from e
-        finally:
-            self._lock.release()
-
-    def delete_many(self, image_names: list[str]) -> None:
-        try:
-            placeholders = ",".join("?" for _ in image_names)
-
-            self._lock.acquire()
-
-            # Construct the SQLite query with the placeholders
-            query = f"DELETE FROM images WHERE image_name IN ({placeholders})"
-
-            # Execute the query with the list of IDs as parameters
-            self._cursor.execute(query, image_names)
-
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise ImageRecordDeleteException from e
-        finally:
-            self._lock.release()
-
-    def save(
-        self,
-        image_name: str,
-        image_origin: ResourceOrigin,
-        image_category: ImageCategory,
-        session_id: Optional[str],
-        width: int,
-        height: int,
-        node_id: Optional[str],
-        metadata: Optional[ImageMetadata],
-        is_intermediate: bool = False,
-    ) -> datetime:
-        try:
-            metadata_json = (
-                None if metadata is None else metadata.json(exclude_none=True)
-            )
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                INSERT OR IGNORE INTO images (
-                    image_name,
-                    image_origin,
-                    image_category,
-                    width,
-                    height,
-                    node_id,
-                    session_id,
-                    metadata,
-                    is_intermediate
-                    )
-                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?);
-                """,
-                (
-                    image_name,
-                    image_origin.value,
-                    image_category.value,
-                    width,
-                    height,
-                    node_id,
-                    session_id,
-                    metadata_json,
-                    is_intermediate,
-                ),
-            )
-            self._conn.commit()
-
-            self._cursor.execute(
-                """--sql
-                SELECT created_at
-                FROM images
-                WHERE image_name = ?;
-                """,
-                (image_name,),
-            )
-
-            created_at = datetime.fromisoformat(self._cursor.fetchone()[0])
-
-            return created_at
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise ImageRecordSaveException from e
-        finally:
-            self._lock.release()
-
-    def get_most_recent_image_for_board(
-        self, board_id: str
-    ) -> Union[ImageRecord, None]:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                SELECT images.*
-                FROM images
-                JOIN board_images ON images.image_name = board_images.image_name
-                WHERE board_images.board_id = ?
-                ORDER BY images.created_at DESC
-                LIMIT 1;
-                """,
-                (board_id,),
-            )
-
-            result = cast(Union[sqlite3.Row, None], self._cursor.fetchone())
-        finally:
-            self._lock.release()
-        if result is None:
-            return None
-
-        return deserialize_image_record(dict(result))

invokeai/app/services/image_storage.py

@@ -0,0 +1,229 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import datetime
+import os
+import json
+from glob import glob
+from abc import ABC, abstractmethod
+from pathlib import Path
+from queue import Queue
+from typing import Any, Dict, List, Tuple
+
+from PIL.Image import Image
+import PIL.Image as PILImage
+from PIL import PngImagePlugin
+from invokeai.app.api.models.images import ImageResponse
+from invokeai.app.models.image import  ImageType
+from invokeai.app.modules.metadata import ImageMetadata, InvokeAIMetadata, MetadataModule
+from invokeai.app.services.item_storage import PaginatedResults
+from invokeai.app.util.get_timestamp import get_timestamp
+from invokeai.app.util.image_paths import build_image_path
+from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
+
+from invokeai.backend.image_util import PngWriter
+
+
+class ImageStorageBase(ABC):
+    """Responsible for storing and retrieving images."""
+
+    @abstractmethod
+    def get(self, image_type: ImageType, image_name: str) -> Image:
+        """Retrieves an image as PIL Image."""
+        pass
+
+    @abstractmethod
+    def list(
+        self, image_type: ImageType, page: int = 0, per_page: int = 10
+    ) -> PaginatedResults[ImageResponse]:
+        """Gets a paginated list of images."""
+        pass
+
+    # TODO: make this a bit more flexible for e.g. cloud storage
+    @abstractmethod
+    def get_path(
+        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
+    ) -> str:
+        """Gets the path to an image or its thumbnail."""
+        pass
+
+    # TODO: make this a bit more flexible for e.g. cloud storage
+    @abstractmethod
+    def validate_path(
+        self, path: str
+    ) -> bool:
+        """Validates an image path."""
+        pass
+
+    @abstractmethod
+    def save(self, image_type: ImageType, image_name: str, image: Image, metadata: InvokeAIMetadata | None = None) -> Tuple[str, str, int]:
+        """Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image path, thumbnail path, and created timestamp."""
+        pass
+
+    @abstractmethod
+    def delete(self, image_type: ImageType, image_name: str) -> None:
+        """Deletes an image and its thumbnail (if one exists)."""
+        pass
+
+    def create_name(self, context_id: str, node_id: str) -> str:
+        """Creates a unique contextual image filename."""
+        return f"{context_id}_{node_id}_{str(get_timestamp())}.png"
+
+
+class DiskImageStorage(ImageStorageBase):
+    """Stores images on disk"""
+
+    __output_folder: str
+    __cache_ids: Queue  # TODO: this is an incredibly naive cache
+    __cache: Dict[str, Image]
+    __max_cache_size: int
+
+    def __init__(self, output_folder: str):
+        self.__output_folder = output_folder
+        self.__cache = dict()
+        self.__cache_ids = Queue()
+        self.__max_cache_size = 10  # TODO: get this from config
+
+        Path(output_folder).mkdir(parents=True, exist_ok=True)
+
+        # TODO: don't hard-code. get/save/delete should maybe take subpath?
+        for image_type in ImageType:
+            Path(os.path.join(output_folder, image_type)).mkdir(
+                parents=True, exist_ok=True
+            )
+            Path(os.path.join(output_folder, image_type, "thumbnails")).mkdir(
+                parents=True, exist_ok=True
+            )
+
+    def list(
+        self, image_type: ImageType, page: int = 0, per_page: int = 10
+    ) -> PaginatedResults[ImageResponse]:
+        dir_path = os.path.join(self.__output_folder, image_type)
+        image_paths = glob(f"{dir_path}/*.png")
+        count = len(image_paths)
+
+        sorted_image_paths = sorted(
+            glob(f"{dir_path}/*.png"), key=os.path.getctime, reverse=True
+        )
+
+        page_of_image_paths = sorted_image_paths[
+            page * per_page : (page + 1) * per_page
+        ]
+
+        page_of_images: List[ImageResponse] = []
+
+        for path in page_of_image_paths:
+            filename = os.path.basename(path)
+            img = PILImage.open(path)
+            
+            invokeai_metadata = MetadataModule.get_metadata(img)
+
+            page_of_images.append(
+                ImageResponse(
+                    image_type=image_type.value,
+                    image_name=filename,
+                    image_url=build_image_path(image_type.value, filename),
+                    thumbnail_url = build_image_path(image_type.value, filename, True),
+                    # TODO: Creation of this object should happen elsewhere (?), just making it fit here so it works
+                    metadata=ImageMetadata(
+                        created=int(os.path.getctime(path)),
+                        width=img.width,
+                        height=img.height,
+                        mode=img.mode,
+                        invokeai=invokeai_metadata
+                    ),
+                )
+            )
+
+        page_count_trunc = int(count / per_page)
+        page_count_mod = count % per_page
+        page_count = page_count_trunc if page_count_mod == 0 else page_count_trunc + 1
+
+        return PaginatedResults[ImageResponse](
+            items=page_of_images,
+            page=page,
+            pages=page_count,
+            per_page=per_page,
+            total=count,
+        )
+
+    def get(self, image_type: ImageType, image_name: str) -> Image:
+        image_path = self.get_path(image_type, image_name)
+        cache_item = self.__get_cache(image_path)
+        if cache_item:
+            return cache_item
+
+        image = PILImage.open(image_path)
+        self.__set_cache(image_path, image)
+        return image
+
+    # TODO: make this a bit more flexible for e.g. cloud storage
+    def get_path(
+        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
+    ) -> str:
+        # strip out any relative path shenanigans
+        basename = os.path.basename(image_name)
+
+        if is_thumbnail:
+            path = os.path.join(
+                self.__output_folder, image_type, "thumbnails", basename
+            )
+        else:
+            path = os.path.join(self.__output_folder, image_type, basename)
+
+        return path
+
+    def validate_path(
+        self, path: str
+    ) -> bool:
+        try:
+            os.stat(path)
+            return True
+        except Exception:
+            return False
+
+
+    def save(self, image_type: ImageType, image_name: str, image: Image, metadata: InvokeAIMetadata | None = None) -> Tuple[str, str, int]:
+        image_path = self.get_path(image_type, image_name)
+
+        thumbnail_name = get_thumbnail_name(image_name)
+        thumbnail_path = self.get_path(image_type, thumbnail_name, is_thumbnail=True)
+
+        png_info = MetadataModule.build_png_info(metadata=metadata)
+
+        image.save(image_path, "PNG", pnginfo=png_info)
+
+        thumbnail_image = make_thumbnail(image)
+        thumbnail_image.save(thumbnail_path)
+
+        self.__set_cache(image_path, image)
+        self.__set_cache(thumbnail_path, thumbnail_image)
+
+        return (image_path, thumbnail_path, int(os.path.getctime(image_path)))
+
+    def delete(self, image_type: ImageType, image_name: str) -> None:
+        image_path = self.get_path(image_type, image_name)
+        thumbnail_path = self.get_path(image_type, image_name, True)
+        if os.path.exists(image_path):
+            os.remove(image_path)
+
+        if image_path in self.__cache:
+            del self.__cache[image_path]
+
+        if os.path.exists(thumbnail_path):
+            os.remove(thumbnail_path)
+
+        if thumbnail_path in self.__cache:
+            del self.__cache[thumbnail_path]
+
+    def __get_cache(self, image_name: str) -> Image:
+        return None if image_name not in self.__cache else self.__cache[image_name]
+
+    def __set_cache(self, image_name: str, image: Image):
+        if not image_name in self.__cache:
+            self.__cache[image_name] = image
+            self.__cache_ids.put(
+                image_name
+            )  # TODO: this should refresh position for LRU cache
+            if len(self.__cache) > self.__max_cache_size:
+                cache_id = self.__cache_ids.get()
+                del self.__cache[cache_id]

invokeai/app/services/images.py

@@ -1,381 +0,0 @@
-from abc import ABC, abstractmethod
-from logging import Logger
-from typing import Optional, TYPE_CHECKING, Union
-from PIL.Image import Image as PILImageType
-
-from invokeai.app.models.image import (
-    ImageCategory,
-    ResourceOrigin,
-    InvalidImageCategoryException,
-    InvalidOriginException,
-)
-from invokeai.app.models.metadata import ImageMetadata
-from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
-from invokeai.app.services.image_record_storage import (
-    ImageRecordDeleteException,
-    ImageRecordNotFoundException,
-    ImageRecordSaveException,
-    ImageRecordStorageBase,
-    OffsetPaginatedResults,
-)
-from invokeai.app.services.models.image_record import (
-    ImageRecord,
-    ImageDTO,
-    ImageRecordChanges,
-    image_record_to_dto,
-)
-from invokeai.app.services.image_file_storage import (
-    ImageFileDeleteException,
-    ImageFileNotFoundException,
-    ImageFileSaveException,
-    ImageFileStorageBase,
-)
-from invokeai.app.services.item_storage import ItemStorageABC, PaginatedResults
-from invokeai.app.services.metadata import MetadataServiceBase
-from invokeai.app.services.resource_name import NameServiceBase
-from invokeai.app.services.urls import UrlServiceBase
-
-if TYPE_CHECKING:
-    from invokeai.app.services.graph import GraphExecutionState
-
-
-class ImageServiceABC(ABC):
-    """High-level service for image management."""
-
-    @abstractmethod
-    def create(
-        self,
-        image: PILImageType,
-        image_origin: ResourceOrigin,
-        image_category: ImageCategory,
-        node_id: Optional[str] = None,
-        session_id: Optional[str] = None,
-        is_intermediate: bool = False,
-    ) -> ImageDTO:
-        """Creates an image, storing the file and its metadata."""
-        pass
-
-    @abstractmethod
-    def update(
-        self,
-        image_name: str,
-        changes: ImageRecordChanges,
-    ) -> ImageDTO:
-        """Updates an image."""
-        pass
-
-    @abstractmethod
-    def get_pil_image(self, image_name: str) -> PILImageType:
-        """Gets an image as a PIL image."""
-        pass
-
-    @abstractmethod
-    def get_record(self, image_name: str) -> ImageRecord:
-        """Gets an image record."""
-        pass
-
-    @abstractmethod
-    def get_dto(self, image_name: str) -> ImageDTO:
-        """Gets an image DTO."""
-        pass
-
-    @abstractmethod
-    def get_path(self, image_name: str, thumbnail: bool = False) -> str:
-        """Gets an image's path."""
-        pass
-
-    @abstractmethod
-    def validate_path(self, path: str) -> bool:
-        """Validates an image's path."""
-        pass
-
-    @abstractmethod
-    def get_url(self, image_name: str, thumbnail: bool = False) -> str:
-        """Gets an image's or thumbnail's URL."""
-        pass
-
-    @abstractmethod
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-        image_origin: Optional[ResourceOrigin] = None,
-        categories: Optional[list[ImageCategory]] = None,
-        is_intermediate: Optional[bool] = None,
-        board_id: Optional[str] = None,
-    ) -> OffsetPaginatedResults[ImageDTO]:
-        """Gets a paginated list of image DTOs."""
-        pass
-
-    @abstractmethod
-    def delete(self, image_name: str):
-        """Deletes an image."""
-        pass
-
-    @abstractmethod
-    def delete_images_on_board(self, board_id: str):
-        """Deletes all images on a board."""
-        pass
-
-
-class ImageServiceDependencies:
-    """Service dependencies for the ImageService."""
-
-    image_records: ImageRecordStorageBase
-    image_files: ImageFileStorageBase
-    board_image_records: BoardImageRecordStorageBase
-    metadata: MetadataServiceBase
-    urls: UrlServiceBase
-    logger: Logger
-    names: NameServiceBase
-    graph_execution_manager: ItemStorageABC["GraphExecutionState"]
-
-    def __init__(
-        self,
-        image_record_storage: ImageRecordStorageBase,
-        image_file_storage: ImageFileStorageBase,
-        board_image_record_storage: BoardImageRecordStorageBase,
-        metadata: MetadataServiceBase,
-        url: UrlServiceBase,
-        logger: Logger,
-        names: NameServiceBase,
-        graph_execution_manager: ItemStorageABC["GraphExecutionState"],
-    ):
-        self.image_records = image_record_storage
-        self.image_files = image_file_storage
-        self.board_image_records = board_image_record_storage
-        self.metadata = metadata
-        self.urls = url
-        self.logger = logger
-        self.names = names
-        self.graph_execution_manager = graph_execution_manager
-
-
-class ImageService(ImageServiceABC):
-    _services: ImageServiceDependencies
-
-    def __init__(self, services: ImageServiceDependencies):
-        self._services = services
-
-    def create(
-        self,
-        image: PILImageType,
-        image_origin: ResourceOrigin,
-        image_category: ImageCategory,
-        node_id: Optional[str] = None,
-        session_id: Optional[str] = None,
-        is_intermediate: bool = False,
-    ) -> ImageDTO:
-        if image_origin not in ResourceOrigin:
-            raise InvalidOriginException
-
-        if image_category not in ImageCategory:
-            raise InvalidImageCategoryException
-
-        image_name = self._services.names.create_image_name()
-
-        metadata = self._get_metadata(session_id, node_id)
-
-        (width, height) = image.size
-
-        try:
-            # TODO: Consider using a transaction here to ensure consistency between storage and database
-            self._services.image_records.save(
-                # Non-nullable fields
-                image_name=image_name,
-                image_origin=image_origin,
-                image_category=image_category,
-                width=width,
-                height=height,
-                # Meta fields
-                is_intermediate=is_intermediate,
-                # Nullable fields
-                node_id=node_id,
-                session_id=session_id,
-                metadata=metadata,
-            )
-
-            self._services.image_files.save(
-                image_name=image_name,
-                image=image,
-                metadata=metadata,
-            )
-
-            image_dto = self.get_dto(image_name)
-
-            return image_dto
-        except ImageRecordSaveException:
-            self._services.logger.error("Failed to save image record")
-            raise
-        except ImageFileSaveException:
-            self._services.logger.error("Failed to save image file")
-            raise
-        except Exception as e:
-            self._services.logger.error("Problem saving image record and file")
-            raise e
-
-    def update(
-        self,
-        image_name: str,
-        changes: ImageRecordChanges,
-    ) -> ImageDTO:
-        try:
-            self._services.image_records.update(image_name, changes)
-            return self.get_dto(image_name)
-        except ImageRecordSaveException:
-            self._services.logger.error("Failed to update image record")
-            raise
-        except Exception as e:
-            self._services.logger.error("Problem updating image record")
-            raise e
-
-    def get_pil_image(self, image_name: str) -> PILImageType:
-        try:
-            return self._services.image_files.get(image_name)
-        except ImageFileNotFoundException:
-            self._services.logger.error("Failed to get image file")
-            raise
-        except Exception as e:
-            self._services.logger.error("Problem getting image file")
-            raise e
-
-    def get_record(self, image_name: str) -> ImageRecord:
-        try:
-            return self._services.image_records.get(image_name)
-        except ImageRecordNotFoundException:
-            self._services.logger.error("Image record not found")
-            raise
-        except Exception as e:
-            self._services.logger.error("Problem getting image record")
-            raise e
-
-    def get_dto(self, image_name: str) -> ImageDTO:
-        try:
-            image_record = self._services.image_records.get(image_name)
-
-            image_dto = image_record_to_dto(
-                image_record,
-                self._services.urls.get_image_url(image_name),
-                self._services.urls.get_image_url(image_name, True),
-                self._services.board_image_records.get_board_for_image(image_name),
-            )
-
-            return image_dto
-        except ImageRecordNotFoundException:
-            self._services.logger.error("Image record not found")
-            raise
-        except Exception as e:
-            self._services.logger.error("Problem getting image DTO")
-            raise e
-
-    def get_path(self, image_name: str, thumbnail: bool = False) -> str:
-        try:
-            return self._services.image_files.get_path(image_name, thumbnail)
-        except Exception as e:
-            self._services.logger.error("Problem getting image path")
-            raise e
-
-    def validate_path(self, path: str) -> bool:
-        try:
-            return self._services.image_files.validate_path(path)
-        except Exception as e:
-            self._services.logger.error("Problem validating image path")
-            raise e
-
-    def get_url(self, image_name: str, thumbnail: bool = False) -> str:
-        try:
-            return self._services.urls.get_image_url(image_name, thumbnail)
-        except Exception as e:
-            self._services.logger.error("Problem getting image path")
-            raise e
-
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-        image_origin: Optional[ResourceOrigin] = None,
-        categories: Optional[list[ImageCategory]] = None,
-        is_intermediate: Optional[bool] = None,
-        board_id: Optional[str] = None,
-    ) -> OffsetPaginatedResults[ImageDTO]:
-        try:
-            results = self._services.image_records.get_many(
-                offset,
-                limit,
-                image_origin,
-                categories,
-                is_intermediate,
-                board_id,
-            )
-
-            image_dtos = list(
-                map(
-                    lambda r: image_record_to_dto(
-                        r,
-                        self._services.urls.get_image_url(r.image_name),
-                        self._services.urls.get_image_url(r.image_name, True),
-                        self._services.board_image_records.get_board_for_image(
-                            r.image_name
-                        ),
-                    ),
-                    results.items,
-                )
-            )
-
-            return OffsetPaginatedResults[ImageDTO](
-                items=image_dtos,
-                offset=results.offset,
-                limit=results.limit,
-                total=results.total,
-            )
-        except Exception as e:
-            self._services.logger.error("Problem getting paginated image DTOs")
-            raise e
-
-    def delete(self, image_name: str):
-        try:
-            self._services.image_files.delete(image_name)
-            self._services.image_records.delete(image_name)
-        except ImageRecordDeleteException:
-            self._services.logger.error(f"Failed to delete image record")
-            raise
-        except ImageFileDeleteException:
-            self._services.logger.error(f"Failed to delete image file")
-            raise
-        except Exception as e:
-            self._services.logger.error("Problem deleting image record and file")
-            raise e
-
-    def delete_images_on_board(self, board_id: str):
-        try:
-            images = self._services.board_image_records.get_images_for_board(board_id)
-            image_name_list = list(
-                map(
-                    lambda r: r.image_name,
-                    images.items,
-                )
-            )
-            for image_name in image_name_list:
-                self._services.image_files.delete(image_name)
-            self._services.image_records.delete_many(image_name_list)
-        except ImageRecordDeleteException:
-            self._services.logger.error(f"Failed to delete image records")
-            raise
-        except ImageFileDeleteException:
-            self._services.logger.error(f"Failed to delete image files")
-            raise
-        except Exception as e:
-            self._services.logger.error("Problem deleting image records and files")
-            raise e
-
-    def _get_metadata(
-        self, session_id: Optional[str] = None, node_id: Optional[str] = None
-    ) -> Union[ImageMetadata, None]:
-        """Get the metadata for a node."""
-        metadata = None
-
-        if node_id is not None and session_id is not None:
-            session = self._services.graph_execution_manager.get(session_id)
-            metadata = self._services.metadata.create_image_metadata(session, node_id)
-
-        return metadata

invokeai/app/services/invocation_services.py

@@ -1,67 +1,46 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
-from __future__ import annotations
-from typing import TYPE_CHECKING
-
-if TYPE_CHECKING:
-    from logging import Logger
-    from invokeai.app.services.board_images import BoardImagesServiceABC
-    from invokeai.app.services.boards import BoardServiceABC
-    from invokeai.app.services.images import ImageServiceABC
-    from invokeai.backend import ModelManager
-    from invokeai.app.services.events import EventServiceBase
-    from invokeai.app.services.latent_storage import LatentsStorageBase
-    from invokeai.app.services.restoration_services import RestorationServices
-    from invokeai.app.services.invocation_queue import InvocationQueueABC
-    from invokeai.app.services.item_storage import ItemStorageABC
-    from invokeai.app.services.config import InvokeAISettings
-    from invokeai.app.services.graph import GraphExecutionState, LibraryGraph
-    from invokeai.app.services.invoker import InvocationProcessorABC
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+from invokeai.backend import ModelManager
 
+from .events import EventServiceBase
+from .latent_storage import LatentsStorageBase
+from .image_storage import ImageStorageBase
+from .restoration_services import RestorationServices
+from .invocation_queue import InvocationQueueABC
+from .item_storage import ItemStorageABC
 
 class InvocationServices:
     """Services that can be used by invocations"""
 
-    # TODO: Just forward-declared everything due to circular dependencies. Fix structure.
-    events: "EventServiceBase"
-    latents: "LatentsStorageBase"
-    queue: "InvocationQueueABC"
-    model_manager: "ModelManager"
-    restoration: "RestorationServices"
-    configuration: "InvokeAISettings"
-    images: "ImageServiceABC"
-    boards: "BoardServiceABC"
-    board_images: "BoardImagesServiceABC"
-    graph_library: "ItemStorageABC"["LibraryGraph"]
-    graph_execution_manager: "ItemStorageABC"["GraphExecutionState"]
+    events: EventServiceBase
+    latents: LatentsStorageBase
+    images: ImageStorageBase
+    queue: InvocationQueueABC
+    model_manager: ModelManager
+    restoration: RestorationServices
+
+    # NOTE: we must forward-declare any types that include invocations, since invocations can use services
+    graph_library: ItemStorageABC["LibraryGraph"]
+    graph_execution_manager: ItemStorageABC["GraphExecutionState"]
     processor: "InvocationProcessorABC"
 
     def __init__(
-        self,
-        model_manager: "ModelManager",
-        events: "EventServiceBase",
-        logger: "Logger",
-        latents: "LatentsStorageBase",
-        images: "ImageServiceABC",
-        boards: "BoardServiceABC",
-        board_images: "BoardImagesServiceABC",
-        queue: "InvocationQueueABC",
-        graph_library: "ItemStorageABC"["LibraryGraph"],
-        graph_execution_manager: "ItemStorageABC"["GraphExecutionState"],
-        processor: "InvocationProcessorABC",
-        restoration: "RestorationServices",
-        configuration: "InvokeAISettings",
+            self,
+            model_manager: ModelManager,
+            events: EventServiceBase,
+            latents: LatentsStorageBase,
+            images: ImageStorageBase,
+            queue: InvocationQueueABC,
+            graph_library: ItemStorageABC["LibraryGraph"],
+            graph_execution_manager: ItemStorageABC["GraphExecutionState"],
+            processor: "InvocationProcessorABC",
+            restoration: RestorationServices,
     ):
         self.model_manager = model_manager
         self.events = events
-        self.logger = logger
         self.latents = latents
         self.images = images
-        self.boards = boards
-        self.board_images = board_images
         self.queue = queue
         self.graph_library = graph_library
         self.graph_execution_manager = graph_execution_manager
         self.processor = processor
         self.restoration = restoration
-        self.configuration = configuration
-        self.boards = boards

invokeai/app/services/invoker.py

@@ -22,8 +22,7 @@ class Invoker:
     def invoke(
         self, graph_execution_state: GraphExecutionState, invoke_all: bool = False
     ) -> str | None:
-        """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."""
+        """Determines the next node to invoke and returns the id of the invoked node, or None if there are no nodes to execute"""
 
         # Get the next invocation
         invocation = graph_execution_state.next()
@@ -50,7 +49,7 @@ class Invoker:
         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)
@@ -72,12 +71,18 @@ class Invoker:
         for service in vars(self.services):
             self.__start_service(getattr(self.services, service))
 
+        for service in vars(self.services):
+            self.__start_service(getattr(self.services, service))
+
     def stop(self) -> None:
         """Stops the invoker. A new invoker will have to be created to execute further."""
         # First stop all services
         for service in vars(self.services):
             self.__stop_service(getattr(self.services, service))
 
+        for service in vars(self.services):
+            self.__stop_service(getattr(self.services, service))
+
         self.services.queue.put(None)
 
 

invokeai/app/services/latent_storage.py

@@ -1,5 +1,6 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
+import os
 from abc import ABC, abstractmethod
 from pathlib import Path
 from queue import Queue
@@ -15,7 +16,7 @@ class LatentsStorageBase(ABC):
         pass
 
     @abstractmethod
-    def save(self, name: str, data: torch.Tensor) -> None:
+    def set(self, name: str, data: torch.Tensor) -> None:
         pass
 
     @abstractmethod
@@ -46,8 +47,8 @@ class ForwardCacheLatentsStorage(LatentsStorageBase):
         self.__set_cache(name, latent)
         return latent
 
-    def save(self, name: str, data: torch.Tensor) -> None:
-        self.__underlying_storage.save(name, data)
+    def set(self, name: str, data: torch.Tensor) -> None:
+        self.__underlying_storage.set(name, data)
         self.__set_cache(name, data)
 
     def delete(self, name: str) -> None:
@@ -69,26 +70,24 @@ class ForwardCacheLatentsStorage(LatentsStorageBase):
 class DiskLatentsStorage(LatentsStorageBase):
     """Stores latents in a folder on disk without caching"""
 
-    __output_folder: str | Path
+    __output_folder: str
 
-    def __init__(self, output_folder: str | Path):
-        self.__output_folder = output_folder if isinstance(output_folder, Path) else Path(output_folder)
-        self.__output_folder.mkdir(parents=True, exist_ok=True)
+    def __init__(self, output_folder: str):
+        self.__output_folder = output_folder
+        Path(output_folder).mkdir(parents=True, exist_ok=True)
 
     def get(self, name: str) -> torch.Tensor:
         latent_path = self.get_path(name)
         return torch.load(latent_path)
 
-    def save(self, name: str, data: torch.Tensor) -> None:
-        self.__output_folder.mkdir(parents=True, exist_ok=True)
+    def set(self, name: str, data: torch.Tensor) -> None:
         latent_path = self.get_path(name)
         torch.save(data, latent_path)
 
     def delete(self, name: str) -> None:
         latent_path = self.get_path(name)
-        latent_path.unlink()
-        
+        os.remove(latent_path)
 
-    def get_path(self, name: str) -> Path:
-        return self.__output_folder / name
+    def get_path(self, name: str) -> str:
+        return os.path.join(self.__output_folder, name)
     

invokeai/app/services/metadata.py

@@ -1,142 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import Any, Union
-import networkx as nx
-
-from invokeai.app.models.metadata import ImageMetadata
-from invokeai.app.services.graph import Graph, GraphExecutionState
-
-
-class MetadataServiceBase(ABC):
-    """Handles building metadata for nodes, images, and outputs."""
-
-    @abstractmethod
-    def create_image_metadata(
-        self, session: GraphExecutionState, node_id: str
-    ) -> ImageMetadata:
-        """Builds an ImageMetadata object for a node."""
-        pass
-
-
-class CoreMetadataService(MetadataServiceBase):
-    _ANCESTOR_TYPES = ["t2l", "l2l"]
-    """The ancestor types that contain the core metadata"""
-
-    _ANCESTOR_PARAMS = ["type", "steps", "model", "cfg_scale", "scheduler", "strength"]
-    """The core metadata parameters in the ancestor types"""
-
-    _NOISE_FIELDS = ["seed", "width", "height"]
-    """The core metadata parameters in the noise node"""
-
-    def create_image_metadata(
-        self, session: GraphExecutionState, node_id: str
-    ) -> ImageMetadata:
-        metadata = self._build_metadata_from_graph(session, node_id)
-
-        return metadata
-
-    def _find_nearest_ancestor(self, G: nx.DiGraph, node_id: str) -> Union[str, None]:
-        """
-        Finds the id of the nearest ancestor (of a valid type) of a given node.
-
-        Parameters:
-        G (nx.DiGraph): The execution graph, converted in to a networkx DiGraph. Its nodes must
-        have the same data as the execution graph.
-        node_id (str): The ID of the node.
-
-        Returns:
-        str | None: The ID of the nearest ancestor, or None if there are no valid ancestors.
-        """
-
-        # Retrieve the node from the graph
-        node = G.nodes[node_id]
-
-        # If the node type is one of the core metadata node types, return its id
-        if node.get("type") in self._ANCESTOR_TYPES:
-            return node.get("id")
-
-        # Else, look for the ancestor in the predecessor nodes
-        for predecessor in G.predecessors(node_id):
-            result = self._find_nearest_ancestor(G, predecessor)
-            if result:
-                return result
-
-        # If there are no valid ancestors, return None
-        return None
-
-    def _get_additional_metadata(
-        self, graph: Graph, node_id: str
-    ) -> Union[dict[str, Any], None]:
-        """
-        Returns additional metadata for a given node.
-
-        Parameters:
-        graph (Graph): The execution graph.
-        node_id (str): The ID of the node.
-
-        Returns:
-        dict[str, Any] | None: A dictionary of additional metadata.
-        """
-
-        metadata = {}
-
-        # Iterate over all edges in the graph
-        for edge in graph.edges:
-            dest_node_id = edge.destination.node_id
-            dest_field = edge.destination.field
-            source_node_dict = graph.nodes[edge.source.node_id].dict()
-
-            # If the destination node ID matches the given node ID, gather necessary metadata
-            if dest_node_id == node_id:
-                # Prompt
-                if dest_field == "positive_conditioning":
-                    metadata["positive_conditioning"] = source_node_dict.get("prompt")
-                # Negative prompt
-                if dest_field == "negative_conditioning":
-                    metadata["negative_conditioning"] = source_node_dict.get("prompt")
-                # Seed, width and height
-                if dest_field == "noise":
-                    for field in self._NOISE_FIELDS:
-                        metadata[field] = source_node_dict.get(field)
-        return metadata
-
-    def _build_metadata_from_graph(
-        self, session: GraphExecutionState, node_id: str
-    ) -> ImageMetadata:
-        """
-        Builds an ImageMetadata object for a node.
-
-        Parameters:
-        session (GraphExecutionState): The session.
-        node_id (str): The ID of the node.
-
-        Returns:
-        ImageMetadata: The metadata for the node.
-        """
-
-        # We need to do all the traversal on the execution graph
-        graph = session.execution_graph
-
-        # Find the nearest `t2l`/`l2l` ancestor of the given node
-        ancestor_id = self._find_nearest_ancestor(graph.nx_graph_with_data(), node_id)
-
-        # If no ancestor was found, return an empty ImageMetadata object
-        if ancestor_id is None:
-            return ImageMetadata()
-
-        ancestor_node = graph.get_node(ancestor_id)
-
-        # Grab all the core metadata from the ancestor node
-        ancestor_metadata = {
-            param: val
-            for param, val in ancestor_node.dict().items()
-            if param in self._ANCESTOR_PARAMS
-        }
-
-        # Get this image's prompts and noise parameters
-        addl_metadata = self._get_additional_metadata(graph, ancestor_id)
-
-        # If additional metadata was found, add it to the main metadata
-        if addl_metadata is not None:
-            ancestor_metadata.update(addl_metadata)
-
-        return ImageMetadata(**ancestor_metadata)

invokeai/app/services/model_manager_initializer.py

@@ -0,0 +1,120 @@
+import os
+import sys
+import torch
+from argparse import Namespace
+from invokeai.backend import Args
+from omegaconf import OmegaConf
+from pathlib import Path
+
+import invokeai.version
+from ...backend import ModelManager
+from ...backend.util import choose_precision, choose_torch_device
+from ...backend import Globals
+
+# TODO: Replace with an abstract class base ModelManagerBase
+def get_model_manager(config: Args) -> ModelManager:
+    if not config.conf:
+        config_file = os.path.join(Globals.root, "configs", "models.yaml")
+        if not os.path.exists(config_file):
+            report_model_error(
+                config, FileNotFoundError(f"The file {config_file} could not be found.")
+            )
+
+    print(f">> {invokeai.version.__app_name__}, version {invokeai.version.__version__}")
+    print(f'>> InvokeAI runtime directory is "{Globals.root}"')
+
+    # these two lines prevent a horrible warning message from appearing
+    # when the frozen CLIP tokenizer is imported
+    import transformers  # type: ignore
+
+    transformers.logging.set_verbosity_error()
+    import diffusers
+
+    diffusers.logging.set_verbosity_error()
+
+    # normalize the config directory relative to root
+    if not os.path.isabs(config.conf):
+        config.conf = os.path.normpath(os.path.join(Globals.root, config.conf))
+
+    if config.embeddings:
+        if not os.path.isabs(config.embedding_path):
+            embedding_path = os.path.normpath(
+                os.path.join(Globals.root, config.embedding_path)
+            )
+        else:
+            embedding_path = config.embedding_path
+    else:
+        embedding_path = None
+
+    # migrate legacy models
+    ModelManager.migrate_models()
+
+    # creating the model manager
+    try:
+        device = torch.device(choose_torch_device())
+        precision = 'float16' if config.precision=='float16' \
+        else 'float32' if config.precision=='float32' \
+        else choose_precision(device)
+        
+        model_manager = ModelManager(
+            OmegaConf.load(config.conf),
+            precision=precision,
+            device_type=device,
+            max_loaded_models=config.max_loaded_models,
+            embedding_path = Path(embedding_path),
+        )
+    except (FileNotFoundError, TypeError, AssertionError) as e:
+        report_model_error(config, e)
+    except (IOError, KeyError) as e:
+        print(f"{e}. Aborting.")
+        sys.exit(-1)
+
+    # try to autoconvert new models
+    # autoimport new .ckpt files
+    if path := config.autoconvert:
+        model_manager.autoconvert_weights(
+            conf_path=config.conf,
+            weights_directory=path,
+        )
+
+    return model_manager
+
+def report_model_error(opt: Namespace, e: Exception):
+    print(f'** An error occurred while attempting to initialize the model: "{str(e)}"')
+    print(
+        "** This can be caused by a missing or corrupted models file, and can sometimes be fixed by (re)installing the models."
+    )
+    yes_to_all = os.environ.get("INVOKE_MODEL_RECONFIGURE")
+    if yes_to_all:
+        print(
+            "** Reconfiguration is being forced by environment variable INVOKE_MODEL_RECONFIGURE"
+        )
+    else:
+        response = input(
+            "Do you want to run invokeai-configure script to select and/or reinstall models? [y] "
+        )
+        if response.startswith(("n", "N")):
+            return
+
+    print("invokeai-configure is launching....\n")
+
+    # Match arguments that were set on the CLI
+    # only the arguments accepted by the configuration script are parsed
+    root_dir = ["--root", opt.root_dir] if opt.root_dir is not None else []
+    config = ["--config", opt.conf] if opt.conf is not None else []
+    previous_config = sys.argv
+    sys.argv = ["invokeai-configure"]
+    sys.argv.extend(root_dir)
+    sys.argv.extend(config.to_dict())
+    if yes_to_all is not None:
+        for arg in yes_to_all.split():
+            sys.argv.append(arg)
+
+    from invokeai.frontend.install import invokeai_configure
+
+    invokeai_configure()
+    # TODO: Figure out how to restart
+    # print('** InvokeAI will now restart')
+    # sys.argv = previous_args
+    # main() # would rather do a os.exec(), but doesn't exist?
+    # sys.exit(0)