Gitignore aider

# Aider chat conversation:

USER: `invokeai/backend/model_manager/convert_ckpt_to_diffusers.py` Im having issues with cpu memory, not gpu memory

ASSISTANT: To address CPU memory issues, we can make the following changes:

1. Use `del` to explicitly delete large objects when they are no longer needed.
2. Use `gc.collect()` to force garbage collection after deleting large objects.

Here are the *SEARCH/REPLACE* blocks:

invokeai/backend/model_manager/convert_ckpt_to_diffusers.py
```python
<<<<<<< SEARCH
    vae = AutoencoderKL(**vae_config)
    with torch.no_grad():
        vae.load_state_dict(converted_vae_checkpoint)
        vae.to(precision)
        torch.cuda.empty_cache()
=======
    vae = AutoencoderKL(**vae_config)
    with torch.no_grad():
        vae.load_state_dict(converted_vae_checkpoint)
        del converted_vae_checkpoint  # Free memory
        import gc
        gc.collect()
        vae.to(precision)
>>>>>>> REPLACE
```

invokeai/backend/model_manager/convert_ckpt_to_diffusers.py
```python
<<<<<<< SEARCH
    pipe = download_from_original_stable_diffusion_ckpt(Path(checkpoint_path).as_posix(), **kwargs)
    with torch.no_grad():
        pipe = pipe.to(precision)
        torch.cuda.empty_cache()
=======
    pipe = download_from_original_stable_diffusion_ckpt(Path(checkpoint_path).as_posix(), **kwargs)
    with torch.no_grad():
        del kwargs  # Free memory
        import gc
        gc.collect()
        pipe = pipe.to(precision)
>>>>>>> REPLACE
```

invokeai/backend/model_manager/convert_ckpt_to_diffusers.py
```python
<<<<<<< SEARCH
    pipe = download_controlnet_from_original_ckpt(checkpoint_path.as_posix(), **kwargs)
    with torch.no_grad():
        pipe = pipe.to(precision)
        torch.cuda.empty_cache()
=======
    pipe = download_controlnet_from_original_ckpt(checkpoint_path.as_posix(), **kwargs)
    with torch.no_grad():
        del kwargs  # Free memory
        import gc
        gc.collect()
        pipe = pipe.to(precision)
>>>>>>> REPLACE
```

.github/workflows/build-installer.yml

@@ -41,5 +41,5 @@ jobs:
       - name: upload installer artifact
         uses: actions/upload-artifact@v4
         with:
-          name: ${{ steps.create_installer.outputs.INSTALLER_FILENAME }}
+          name: installer
           path: ${{ steps.create_installer.outputs.INSTALLER_PATH }}

.gitignore

@@ -188,3 +188,4 @@ installer/install.sh
 installer/update.bat
 installer/update.sh
 installer/InvokeAI-Installer/
+.aider*

README.md

@@ -2,21 +2,102 @@
 
 ![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/6e3728c7-e90e-4711-905c-3b55844ff5be)
 
-# Invoke - Professional Creative AI Tools for Visual Media 
-##  To learn more about Invoke, or implement our Business solutions, visit [invoke.com](https://www.invoke.com/about)
-  
+# Invoke - Professional Creative AI Tools for Visual Media
 
+#### To learn more about Invoke, or implement our Business solutions, visit [invoke.com]
 
-[![discord badge]][discord link]
+[![discord badge]][discord link] [![latest release badge]][latest release link] [![github stars badge]][github stars link] [![github forks badge]][github forks link] [![CI checks on main badge]][CI checks on main link] [![latest commit to main badge]][latest commit to main link] [![github open issues badge]][github open issues link] [![github open prs badge]][github open prs link] [![translation status badge]][translation status link]
 
-[![latest release badge]][latest release link] [![github stars badge]][github stars link] [![github forks badge]][github forks link]
+</div>
 
-[![CI checks on main badge]][CI checks on main link] [![latest commit to main badge]][latest commit to main link]
+Invoke is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. Invoke offers an industry leading web-based UI, and serves as the foundation for multiple commercial products.
 
-[![github open issues badge]][github open issues link] [![github open prs badge]][github open prs link] [![translation status badge]][translation status link]
+[Installation and Updates][installation docs] - [Documentation and Tutorials][docs home] - [Bug Reports][github issues] - [Contributing][contributing docs]
 
+<div align="center">
+
+![Highlighted Features - Canvas and Workflows](https://github.com/invoke-ai/InvokeAI/assets/31807370/708f7a82-084f-4860-bfbe-e2588c53548d)
+
+</div>
+
+## Quick Start
+
+1. Download and unzip the installer from the bottom of the [latest release][latest release link].
+2. Run the installer script.
+
+   - **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 enter.
+   - **Linux**: Run `install.sh`.
+
+3. When prompted, enter a location for the install and select your GPU type.
+4. Once the install finishes, find the directory you selected during install. The default location is `C:\Users\Username\invokeai` for Windows or `~/invokeai` for Linux/macOS.
+5. Run the launcher script (`invoke.bat` for Windows, `invoke.sh` for macOS and Linux) the same way you ran the installer script in step 2.
+6. Select option 1 to start the application. Once it starts up, open your browser and go to <http://localhost:9090>.
+7. Open the model manager tab to install a starter model and then you'll be ready to generate.
+
+More detail, including hardware requirements and manual install instructions, are available in the [installation documentation][installation docs].
+
+## Troubleshooting, FAQ and Support
+
+Please review our [FAQ][faq] for solutions to common installation problems and other issues.
+
+For more help, please join our [Discord][discord link].
+
+## Features
+
+Full details on features can be found in [our documentation][features docs].
+
+### Web Server & UI
+
+Invoke runs a locally hosted web server & React UI with an industry-leading user experience.
+
+### Unified Canvas
+
+The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/out-painting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.
+
+### Workflows & Nodes
+
+Invoke offers a fully featured workflow management solution, enabling users to combine the power of node-based workflows with the easy of a UI. This allows for customizable generation pipelines to be developed and shared by users looking to create specific workflows to support their production use-cases.
+
+### Board & Gallery Management
+
+Invoke features an organized gallery system for easily storing, accessing, and remixing your content in the Invoke workspace. Images can be dragged/dropped onto any Image-base UI element in the application, and rich metadata within the Image allows for easy recall of key prompts or settings used in your workflow.
+
+### Other features
+
+- Support for both ckpt and diffusers models
+- SD1.5, SD2.0, and SDXL support
+- Upscaling Tools
+- Embedding Manager & Support
+- Model Manager & Support
+- Workflow creation & management
+- Node-Based Architecture
+
+## 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.
+
+Get started with contributing by reading our [contribution documentation][contributing docs], joining the [#dev-chat] or the GitHub discussion board.
+
+We hope you enjoy using Invoke as much as we enjoy creating it, and we hope you will elect to become part of our community.
+
+## Thanks
+
+Invoke is a combined effort of [passionate and talented people from across the world][contributors]. We thank them for their time, hard work and effort.
+
+Original portions of the software are Copyright © 2024 by respective contributors.
+
+[features docs]: https://invoke-ai.github.io/InvokeAI/features/
+[faq]: https://invoke-ai.github.io/InvokeAI/help/FAQ/
+[contributors]: https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/
+[invoke.com]: https://www.invoke.com/about
+[github issues]: https://github.com/invoke-ai/InvokeAI/issues
+[docs home]: https://invoke-ai.github.io/InvokeAI
+[installation docs]: https://invoke-ai.github.io/InvokeAI/installation/INSTALLATION/
+[#dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939
+[contributing docs]: https://invoke-ai.github.io/InvokeAI/contributing/CONTRIBUTING/
 [CI checks on main badge]: https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
-[CI checks on main link]:https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Amain
+[CI checks on main link]: https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Amain
 [discord badge]: https://flat.badgen.net/discord/members/ZmtBAhwWhy?icon=discord
 [discord link]: https://discord.gg/ZmtBAhwWhy
 [github forks badge]: https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
@@ -30,402 +111,6 @@
 [latest commit to main badge]: https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/main?icon=github&color=yellow&label=last%20dev%20commit&cache=900
 [latest commit to main link]: https://github.com/invoke-ai/InvokeAI/commits/main
 [latest release badge]: https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
-[latest release link]: https://github.com/invoke-ai/InvokeAI/releases
+[latest release link]: https://github.com/invoke-ai/InvokeAI/releases/latest
 [translation status badge]: https://hosted.weblate.org/widgets/invokeai/-/svg-badge.svg
 [translation status link]: https://hosted.weblate.org/engage/invokeai/
-
-</div>
-
-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/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/issues">Bug Reports</a>]
-  [<a
-  href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion,
-  Ideas & Q&A</a>] 
-   [<a
-  href="https://invoke-ai.github.io/InvokeAI/contributing/CONTRIBUTING/">Contributing</a>] 
-
-<div align="center">
-
-
-![Highlighted Features - Canvas and Workflows](https://github.com/invoke-ai/InvokeAI/assets/31807370/708f7a82-084f-4860-bfbe-e2588c53548d)
-
-
-</div>
-
-## Table of Contents
-
-Table of Contents 📝
-
-**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
-
-For full installation and upgrade instructions, please see:
-[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/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)
-
-2. Download the .zip file for your OS (Windows/macOS/Linux).
-
-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`.
-
-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
-location with at least 15 GB of free memory. More if you plan on
-installing lots of models.
-
-6. Wait while the installer does its thing. After installing the software,
-the installer will launch a script that lets you configure InvokeAI and
-select a set of starting image generation models.
-
-7. Find the folder that InvokeAI was installed into (it is not the
-same as the unpacked zip file directory!) The default location of this
-folder (if you didn't change it in step 5) is `~/invokeai` on
-Linux/Mac systems, and `C:\Users\YourName\invokeai` on Windows. This directory will contain launcher scripts named `invoke.sh` and `invoke.bat`.
-
-8. On Windows systems, double-click on the `invoke.bat` file. On
-macOS, open a Terminal window, drag `invoke.sh` from the folder into
-the Terminal, and press return. On Linux, run `invoke.sh`
-
-9. Press 2 to open the "browser-based UI", press enter/return, wait a
-minute or two for Stable Diffusion to start up, then open your browser
-and go to http://localhost:9090.
-
-10. Type `banana sushi` in the box on the top left and click `Invoke`
-
-### Command-Line Installation (for developers and users familiar with Terminals)
-
-You must have Python 3.10 through 3.11 installed on your machine. Earlier or
-later versions are not supported.
-Node.js also needs to be installed along with `pnpm` (can be installed with
-the command `npm install -g pnpm` if needed)
-
-1. Open a command-line window on your machine. The PowerShell is recommended for Windows.
-2. Create a directory to install InvokeAI into. You'll need at least 15 GB of free space:
-
-    ```terminal
-    mkdir invokeai
-    ````
-
-3. Create a virtual environment named `.venv` inside this directory and activate it:
-
-    ```terminal
-    cd invokeai
-    python -m venv .venv --prompt InvokeAI
-    ```
-
-4. Activate the virtual environment (do it every time you run InvokeAI)
-
-    _For Linux/Mac users:_
-
-    ```sh
-    source .venv/bin/activate
-    ```
-
-    _For Windows users:_
-
-    ```ps
-    .venv\Scripts\activate
-    ```
-
-5. Install the InvokeAI module and its dependencies. Choose the command suited for your platform & GPU.
-
-    _For Windows/Linux with an NVIDIA GPU:_
-
-    ```terminal
-    pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-    ```
-
-    _For Linux with an AMD GPU:_
-
-    ```sh
-    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
-    ```
-
-    _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/M3:_
-
-    ```sh
-    pip install InvokeAI --use-pep517
-    ```
-
-6. Configure InvokeAI and install a starting set of image generation models (you only need to do this once):
-
-    ```terminal
-    invokeai-configure --root .
-    ```
-	Don't miss the dot at the end!
-
-7. Launch the web server (do it every time you run InvokeAI):
-
-    ```terminal
-    invokeai-web
-    ```
-
-8. Point your browser to http://localhost:9090 to bring up the web interface.
-
-9. Type `banana sushi` in the box on the top left and click `Invoke`.
-
-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
-
-This fork is supported across Linux, Windows and Macintosh. Linux
-users can use either an Nvidia-based card (with CUDA support) or an
-AMD card (using the ROCm driver). For full installation and upgrade
-instructions, please see:
-[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_SOURCE/)
-
-<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.
-
- If you wish, you can pass the 2.3 root directory to both `--from` and
-`--to` in order to update in place. Warning: this directory will no
-longer be usable with InvokeAI 2.3.
-
-#### Migrating in place
-
-For the adventurous, you may do an in-place upgrade from 2.3 to 3.0
-without touching the command line. ***This recipe does not work on
-Windows platforms due to a bug in the Windows version of the 2.3
-upgrade script.** See the next section for a Windows recipe.
-
-##### For Mac and Linux Users:
-
-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.
-
-3. Select option [1] to upgrade to the latest release.
-
-4. Once the upgrade is finished you will be returned to the launcher
-menu. Select option [6] "Re-run the configure script to fix a broken
-install or to complete a major upgrade".
-
-This will run the configure script against the v2.3 directory and
-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.
-
-##### For Windows Users:
-
-Windows Users can upgrade with the
-
-1. Enter the 2.3 root directory you wish to upgrade
-2. Launch `invoke.sh` or `invoke.bat`
-3. Select the "Developer's console" option [8]
-4. Type the following commands
-
-```
-pip install "invokeai @ https://github.com/invoke-ai/InvokeAI/archive/refs/tags/v3.0.0" --use-pep517 --upgrade
-invokeai-configure --root .
-```
-(Replace `v3.0.0` with the current release number if this document is out of date).
-
-The first command will install and upgrade new software to run
-InvokeAI. The second will prepare the 2.3 directory for use with 3.0.
-You may now launch the WebUI in the usual way, by selecting option [1]
-from the launcher script
-
-#### Migrating Images
-
-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. To do this, you 
-need to run an additional step:
-
-1. From a working InvokeAI 3.0 root directory, start the launcher and
-enter menu option [8] to open the "developer's console".
-
-2. At the developer's console command line, type the command:
-
-```bash
-invokeai-import-images
-```
-
-3. This will lead you through the process of confirming the desired
-   source and destination for the imported images. The images will
-   appear in the gallery board of your choice, and contain the
-   original prompt, model name, and other parameters used to generate
-   the image.
-   
-(Many kudos to **techjedi** for contributing this script.)
-
-## Hardware Requirements
-
-InvokeAI is supported across Linux, Windows and macOS. Linux
-users can use either an Nvidia-based card (with CUDA support) or an
-AMD card (using the ROCm driver).
-
-### System
-
-You will need one of the following:
-
-- An NVIDIA-based graphics card with 4 GB or more VRAM memory. 6-8 GB
-  of VRAM is highly recommended for rendering using the Stable
-  Diffusion XL models
-- An Apple computer with an M1 chip.
-- An AMD-based graphics card with 4GB or more VRAM memory (Linux
-  only), 6-8 GB for XL rendering.
-
-We do not recommend the GTX 1650 or 1660 series video cards. They are
-unable to run in half-precision mode and do not have sufficient VRAM
-to render 512x512 images.
-
-**Memory** - At least 12 GB Main Memory RAM.
-
-**Disk** - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
-
-## Features
-
-Feature documentation can be reviewed by navigating to [the InvokeAI Documentation page](https://invoke-ai.github.io/InvokeAI/features/)
-
-### *Web Server & UI*
-
-InvokeAI offers a locally hosted Web Server & React Frontend, with an industry leading user experience. The Web-based UI allows for simple and intuitive workflows, and is responsive for use on mobile devices and tablets accessing the web server.
-
-### *Unified Canvas*
-
-The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/outpainting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.
-
-### *Workflows & Nodes*
-
-InvokeAI offers a fully featured workflow management solution, enabling users to combine the power of nodes based workflows with the easy of a UI. This allows for customizable generation pipelines to be developed and shared by users looking to create specific workflows to support their production use-cases.
-
-### *Board & Gallery Management*
-
-Invoke AI provides an organized gallery system for easily storing, accessing, and remixing your content in the Invoke workspace. Images can be dragged/dropped onto any Image-base UI element in the application, and rich metadata within the Image allows for easy recall of key prompts or settings used in your workflow. 
-
-### Other features
-
-- *Support for both ckpt and diffusers models*
-- *SD 2.0, 2.1, XL support*
-- *Upscaling Tools*
-- *Embedding Manager & Support*
-- *Model Manager & Support*
-- *Workflow creation & management*
-- *Node-Based Architecture*
-
-
-### Latest Changes
-
-For our latest changes, view our [Release
-Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
-[CHANGELOG](docs/CHANGELOG.md).
-
-### Troubleshooting
-
-Please check out our **[Troubleshooting Guide](https://invoke-ai.github.io/InvokeAI/installation/010_INSTALL_AUTOMATED/#troubleshooting)** to get solutions for common installation
-problems and other issues. For more help, please join our [Discord][discord link]
-
-## 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.
-
-Get started with contributing by reading our [Contribution documentation](https://invoke-ai.github.io/InvokeAI/contributing/CONTRIBUTING/), joining the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) or the GitHub discussion board.
-
-If you are unfamiliar with how
-to contribute to GitHub projects, we have a new contributor checklist you can follow to get started contributing: 
-[New Contributor Checklist](https://invoke-ai.github.io/InvokeAI/contributing/contribution_guides/newContributorChecklist/).
-
-We hope you enjoy using our software as much as we enjoy creating it,
-and we hope that some of those of you who are reading this will elect
-to become part of our community.
-
-Welcome to InvokeAI!
-
-### Contributors
-
-This fork is a combined effort of various people from across the world.
-[Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
-their time, hard work and effort.
-
-### Support
-
-For support, please use this repository's GitHub Issues tracking service, or join the [Discord][discord link].
-
-Original portions of the software are Copyright (c) 2023 by respective contributors.
-

docker/README.md

@@ -64,7 +64,7 @@ GPU_DRIVER=nvidia
 
 Any environment variables supported by InvokeAI can be set here - please see the [Configuration docs](https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/) for further detail.
 
-## Even Moar Customizing!
+## Even More Customizing!
 
 See the `docker-compose.yml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
 

docs/RELEASE.md

@@ -61,11 +61,33 @@ This sets up both python and frontend dependencies and builds the python package
 
 #### Sanity Check & Smoke Test
 
-At this point, the release workflow pauses as the remaining publish jobs require approval.
+At this point, the release workflow pauses as the remaining publish jobs require approval. Time to test the installer.
 
-A maintainer should go to the **Summary** tab of the workflow, download the installer and test it. Ensure the app loads and generates.
+Because the installer pulls from PyPI, and we haven't published to PyPI yet, you will need to install from the wheel:
 
-> The same wheel file is bundled in the installer and in the `dist` artifact, which is uploaded to PyPI. You should end up with the exactly the same installation of the `invokeai` package from any of these methods.
+- Download and unzip `dist.zip` and the installer from the **Summary** tab of the workflow
+- Run the installer script using the `--wheel` CLI arg, pointing at the wheel:
+
+  ```sh
+  ./install.sh --wheel ../InvokeAI-4.0.0rc6-py3-none-any.whl
+  ```
+
+- Install to a temporary directory so you get the new user experience
+- Download a model and generate
+
+> The same wheel file is bundled in the installer and in the `dist` artifact, which is uploaded to PyPI. You should end up with the exactly the same installation as if the installer got the wheel from PyPI.
+
+##### Something isn't right
+
+If testing reveals any issues, no worries. Cancel the workflow, which will cancel the pending publish jobs (you didn't approve them prematurely, right?).
+
+Now you can start from the top:
+
+- Fix the issues and PR the fixes per usual
+- Get the PR approved and merged per usual
+- Switch to `main` and pull in the fixes
+- Run `make tag-release` to move the tag to `HEAD` (which has the fixes) and kick off the release workflow again
+- Re-do the sanity check
 
 #### PyPI Publish Jobs
 
@@ -81,6 +103,12 @@ Both jobs require a maintainer to approve them from the workflow's **Summary** t
 
 > **If the version already exists on PyPI, the publish jobs will fail.** PyPI only allows a given version to be published once - you cannot change it. If version published on PyPI has a problem, you'll need to "fail forward" by bumping the app version and publishing a followup release.
 
+##### Failing PyPI Publish
+
+Check the [python infrastructure status page] for incidents.
+
+If there are no incidents, contact @hipsterusername or @lstein, who have owner access to GH and PyPI, to see if access has expired or something like that.
+
 #### `publish-testpypi` Job
 
 Publishes the distribution on the [Test PyPI] index, using the `testpypi` GitHub environment.
@@ -110,11 +138,13 @@ Publishes the distribution on the production PyPI index, using the `pypi` GitHub
 Once the release is published to PyPI, it's time to publish the GitHub release.
 
 1. [Draft a new release] on GitHub, choosing the tag that triggered the release.
-2. Write the release notes, describing important changes. The **Generate release notes** button automatically inserts the changelog and new contributors, and you can copy/paste the intro from previous releases.
-3. Upload the zip file created in **`build`** job into the Assets section of the release notes. You can also upload the zip into the body of the release notes, since it can be hard for users to find the Assets section.
-4. Check the **Set as a pre-release** and **Create a discussion for this release** checkboxes at the bottom of the release page.
-5. Publish the pre-release.
-6. Announce the pre-release in Discord.
+1. Write the release notes, describing important changes. The **Generate release notes** button automatically inserts the changelog and new contributors, and you can copy/paste the intro from previous releases.
+1. Use `scripts/get_external_contributions.py` to get a list of external contributions to shout out in the release notes.
+1. Upload the zip file created in **`build`** job into the Assets section of the release notes.
+1. Check **Set as a pre-release** if it's a pre-release.
+1. Check **Create a discussion for this release**.
+1. Publish the release.
+1. Announce the release in Discord.
 
 > **TODO** Workflows can create a GitHub release from a template and upload release assets. One popular action to handle this is [ncipollo/release-action]. A future enhancement to the release process could set this up.
 
@@ -140,3 +170,4 @@ This functionality is available as a fallback in case something goes wonky. Typi
 [trusted publishers]: https://docs.pypi.org/trusted-publishers/
 [samuelcolvin/check-python-version]: https://github.com/samuelcolvin/check-python-version
 [manually]: #manual-release
+[python infrastructure status page]: https://status.python.org/

docs/contributing/MODEL_MANAGER.md

@@ -840,22 +840,6 @@ and directories at regular intervals when the size of the cache
 exceeds the value specified in Invoke's `convert_cache` configuration
 variable.
 
-#### List[str]=installer.scan_directory(scan_dir: Path, install: bool)
-
-This method will recursively scan the directory indicated in
-`scan_dir` for new models and either install them in the models
-directory or register them in place, depending on the setting of
-`install` (default False).
-
-The return value is the list of keys of the new installed/registered
-models.
-
-#### installer.sync_to_config()
-
-This method synchronizes models in the models directory and autoimport
-directory to those in the `ModelConfigRecordService` database. New
-models are registered and orphan models are unregistered.
-
 #### installer.start(invoker)
 
 The `start` method is called by the API intialization routines when

docs/contributing/frontend/WORKFLOWS.md

@@ -117,13 +117,13 @@ Stateless fields do not store their value in the node, so their field instances
 
 "Custom" fields will always be treated as stateless fields.
 
-##### Collection and Scalar Fields
+##### Single and Collection Fields
 
-Field types have a name and two flags which may identify it as a **collection** or **collection or scalar** field.
+Field types have a name and cardinality property which may identify it as a **SINGLE**, **COLLECTION** or **SINGLE_OR_COLLECTION** field.
 
-If a field is annotated in python as a list, its field type is parsed and flagged as a **collection** type (e.g. `list[int]`).
-
-If it is annotated as a union of a type and list, the type will be flagged as a **collection or scalar** type (e.g. `Union[int, list[int]]`). Fields may not be unions of different types (e.g. `Union[int, list[str]]` and `Union[int, str]` are not allowed).
+- If a field is annotated in python as a singular value or class, its field type is parsed as a **SINGLE** type (e.g. `int`, `ImageField`, `str`).
+- If a field is annotated in python as a list, its field type is parsed as a **COLLECTION** type (e.g. `list[int]`).
+- If it is annotated as a union of a type and list, the type will be parsed as a **SINGLE_OR_COLLECTION** type (e.g. `Union[int, list[int]]`). Fields may not be unions of different types (e.g. `Union[int, list[str]]` and `Union[int, str]` are not allowed).
 
 ## Implementation
 
@@ -173,8 +173,7 @@ Field types are represented as structured objects:
 ```ts
 type FieldType = {
   name: string;
-  isCollection: boolean;
-  isCollectionOrScalar: boolean;
+  cardinality: 'SINGLE' | 'COLLECTION' | 'SINGLE_OR_COLLECTION';
 };
 ```
 
@@ -186,7 +185,7 @@ There are 4 general cases for field type parsing.
 
 When a field is annotated as a primitive values (e.g. `int`, `str`, `float`), the field type parsing is fairly straightforward. The field is represented by a simple OpenAPI **schema object**, which has a `type` property.
 
-We create a field type name from this `type` string (e.g. `string` -> `StringField`).
+We create a field type name from this `type` string (e.g. `string` -> `StringField`). The cardinality is `"SINGLE"`.
 
 ##### Complex Types
 
@@ -200,13 +199,13 @@ We need to **dereference** the schema to pull these out. Dereferencing may requi
 
 When a field is annotated as a list of a single type, the schema object has an `items` property. They may be a schema object or reference object and must be parsed to determine the item type.
 
-We use the item type for field type name, adding `isCollection: true` to the field type.
+We use the item type for field type name. The cardinality is `"COLLECTION"`.
 
-##### Collection or Scalar Types
+##### Single or Collection Types
 
 When a field is annotated as a union of a type and list of that type, the schema object has an `anyOf` property, which holds a list of valid types for the union.
 
-After verifying that the union has two members (a type and list of the same type), we use the type for field type name, adding `isCollectionOrScalar: true` to the field type.
+After verifying that the union has two members (a type and list of the same type), we use the type for field type name, with cardinality `"SINGLE_OR_COLLECTION"`.
 
 ##### Optional Fields
 

docs/deprecated/2to3.md

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

docs/deprecated/CLI.md

@@ -1,589 +0,0 @@
----
-title: Command-Line Interface
----
-
-# :material-bash: CLI
-
-## **Interactive Command Line Interface**
-
-The InvokeAI command line interface (CLI) provides scriptable access
-to InvokeAI's features.Some advanced features are only available
-through the CLI, though they eventually find their way into the WebUI.
-
-The CLI is accessible from the `invoke.sh`/`invoke.bat` launcher by
-selecting option (1). Alternatively, it can be launched directly from
-the command line by activating the InvokeAI environment and giving the
-command:
-
-```bash
-invokeai
-```
-
-After some startup messages, you will be presented with the `invoke> `
-prompt. Here you can type prompts to generate images and issue other
-commands to load and manipulate generative models. The CLI has a large
-number of command-line options that control its behavior. To get a
-concise summary of the options, call `invokeai` with the `--help` argument:
-
-```bash
-invokeai --help
-```
-
-The script uses the readline library to allow for in-line editing, command
-history (++up++ and ++down++), autocompletion, and more. To help keep track of
-which prompts generated which images, the script writes a log file of image
-names and prompts to the selected output directory.
-
-Here is a typical session
-
-```bash
-PS1:C:\Users\fred> invokeai
-* Initializing, be patient...
-* Initializing, be patient...
->> Initialization file /home/lstein/invokeai/invokeai.init found. Loading...
->> Internet connectivity is True
->> InvokeAI, version 2.3.0-rc5
->> InvokeAI runtime directory is "/home/lstein/invokeai"
->> GFPGAN Initialized
->> CodeFormer Initialized
->> ESRGAN Initialized
->> Using device_type cuda
->> xformers memory-efficient attention is available and enabled
-     (...more initialization messages...)
-* Initialization done! Awaiting your command (-h for help, 'q' to quit)
-invoke> ashley judd riding a camel -n2 -s150
-Outputs:
-   outputs/img-samples/00009.png: "ashley judd riding a camel" -n2 -s150 -S 416354203
-   outputs/img-samples/00010.png: "ashley judd riding a camel" -n2 -s150 -S 1362479620
-
-invoke> "there's a fly in my soup" -n6 -g
-    outputs/img-samples/00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
-    seeds for individual rows: [2685670268, 1216708065, 2335773498, 822223658, 714542046, 3395302430]
-invoke> q
-```
-
-![invoke-py-demo](../assets/dream-py-demo.png)
-
-## Arguments
-
-The script recognizes a series of command-line switches that will
-change important global defaults, such as the directory for image
-outputs and the location of the model weight files.
-
-### List of arguments recognized at the command line
-
-These command-line arguments can be passed to `invoke.py` when you first run it
-from the Windows, Mac or Linux command line. Some set defaults that can be
-overridden on a per-prompt basis (see
-[List of prompt arguments](#list-of-prompt-arguments). Others
-
-| Argument <img width="240" align="right"/> | Shortcut <img width="100" align="right"/> | Default <img width="320" align="right"/>       | Description                                                                                          |
-| ----------------------------------------- | ----------------------------------------- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
-| `--help`                                  | `-h`                                      |                                                | Print a concise help message.                                                                        |
-| `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                          | Location for generated images.                                                                       |
-| `--prompt_as_dir`                         | `-p`                                      | `False`                                        | Name output directories using the prompt text.                                                       |
-| `--from_file <path>`                      |                                           | `None`                                         | Read list of prompts from a file. Use `-` to read from standard input                                |
-| `--model <modelname>`                     |                                           | `stable-diffusion-1.5`                         | Loads the initial model specified in configs/models.yaml. |
-| `--ckpt_convert `           |                                                         | `False`                                        | If provided both .ckpt and .safetensors files will be auto-converted into diffusers format in memory |
-| `--autoconvert <path>`                    |                          | `None`                                        | On startup, scan the indicated directory for new .ckpt/.safetensor files and automatically convert and import them |
-| `--precision`                             |                                           | `fp16`                                         | Provide `fp32` for full precision mode, `fp16` for half-precision. `fp32` needed for Macintoshes and some NVidia cards. |
-| `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                            | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
-| `--safety-checker`                        |                                           | `False`                                        | Activate safety checker for NSFW and other potentially disturbing imagery                            |
-| `--patchmatch`, `--no-patchmatch`                 |                                   | `--patchmatch`                                        | Load/Don't load the PatchMatch inpainting extension    |
-| `--xformers`, `--no-xformers`                 |                                   | `--xformers`                                        | Load/Don't load the Xformers memory-efficient attention module (CUDA only)    |
-| `--web`                                   |                                           | `False`                                        | Start in web server mode                                                                             |
-| `--host <ip addr>`                        |                                           | `localhost`                                    | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any.                |
-| `--port <port>`                           |                                           | `9090`                                         | Which port web server should listen for requests on.                                                 |
-| `--config <path>`                         |                                           | `configs/models.yaml`                          | Configuration file for models and their weights.                                                     |
-| `--iterations <int>`                      | `-n<int>`                                 | `1`                                            | How many images to generate per prompt.                                                              |
-| `--width <int>`                           | `-W<int>`                                 | `512`                                    | Width of generated image                                                                                                                                                                                                                         |
-| `--height <int>`                          | `-H<int>`                                 | `512`                                    | Height of generated image                                                                                                        | `--steps <int>`                           | `-s<int>`                                 | `50`                                     | How many steps of refinement to apply                                                                                                                                                                                                            |
-| `--strength <float>`                      | `-s<float>` | `0.75`  | For img2img: how hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
-| `--fit`                                   | `-F`        | `False` | For img2img: scale the init image to fit into the specified -H and -W dimensions                                                                             |
-| `--grid`                                  | `-g`                                      | `False`                                        | Save all image series as a grid rather than individually.                                            |
-| `--sampler <sampler>`                     | `-A<sampler>`                             | `k_lms`                                        | Sampler to use. Use `-h` to get list of available samplers.                                          |
-| `--seamless`                              |                                           | `False`                                        | Create interesting effects by tiling elements of the image.                                          |
-| `--embedding_path <path>`                 |                                           | `None`                                         | Path to pre-trained embedding manager checkpoints, for custom models                                 |
-| `--gfpgan_model_path`                     |                                           | `experiments/pretrained_models/GFPGANv1.4.pth` | Path to GFPGAN model file.                                              |
-| `--free_gpu_mem`                          |                                           | `False`                                        | Free GPU memory after sampling, to allow image decoding and saving in low VRAM conditions            |
-| `--precision`                             |                                           | `auto`                                         | Set model precision, default is selected by device. Options: auto, float32, float16, autocast        |
-
-!!! warning "These arguments are deprecated but still work"
-
-    <div align="center" markdown>
-
-    | Argument           |  Shortcut  |  Default            |  Description |
-    |--------------------|------------|---------------------|--------------|
-    | `--full_precision`  |             | `False`                | Same as `--precision=fp32`|
-    | `--weights <path>`   |            | `None`                | Path to weights file; use `--model stable-diffusion-1.4` instead |
-    | `--laion400m`        | `-l`         | `False`               | Use older LAION400m weights; use `--model=laion400m` instead |
-
-    </div>
-
-!!! tip
-
-      On Windows systems, you may run into
-      problems when passing the invoke script standard backslashed path
-      names because the Python interpreter treats "\" as an escape.
-      You can either double your slashes (ick): `C:\\path\\to\\my\\file`, or
-      use Linux/Mac style forward slashes (better): `C:/path/to/my/file`.
-
-## The .invokeai initialization file
-
-To start up invoke.py with your preferred settings, place your desired
-startup options in a file in your home directory named `.invokeai` The
-file should contain the startup options as you would type them on the
-command line (`--steps=10 --grid`), one argument per line, or a
-mixture of both using any of the accepted command switch formats:
-
-!!! example "my unmodified initialization file"
-
-    ```bash title="~/.invokeai" linenums="1"
-    # InvokeAI initialization file
-    # This is the InvokeAI initialization file, which contains command-line default values.
-    # Feel free to edit. If anything goes wrong, you can re-initialize this file by deleting
-    # or renaming it and then running invokeai-configure again.
-
-    # The --root option below points to the folder in which InvokeAI stores its models, configs and outputs.
-    --root="/Users/mauwii/invokeai"
-
-    # the --outdir option controls the default location of image files.
-    --outdir="/Users/mauwii/invokeai/outputs"
-
-    # You may place other  frequently-used startup commands here, one or more per line.
-    # Examples:
-    # --web --host=0.0.0.0
-    # --steps=20
-    # -Ak_euler_a -C10.0
-    ```
-
-!!! note
-
-    The  initialization file only accepts the command line arguments.
-    There are additional arguments that you can provide on the `invoke>` command
-    line (such as `-n` or `--iterations`) that cannot be entered into this file.
-    Also be alert for empty blank lines at the end of the file, which will cause
-    an arguments error at startup time.
-
-## List of prompt arguments
-
-After the invoke.py script initializes, it will present you with a `invoke>`
-prompt. Here you can enter information to generate images from text
-([txt2img](#txt2img)), to embellish an existing image or sketch
-([img2img](#img2img)), or to selectively alter chosen regions of the image
-([inpainting](#inpainting)).
-
-### txt2img
-
-!!! example ""
-
-    ```bash
-    invoke> waterfall and rainbow -W640 -H480
-    ```
-
-    This will create the requested image with the dimensions 640 (width)
-    and 480 (height).
-
-Here are the invoke> command that apply to txt2img:
-
-| Argument <img width="680" align="right"/> | Shortcut <img width="420" align="right"/> | Default <img width="480" align="right"/> | Description                                                                                                                                                                                                                                      |
-| ----------------------------------------- | ----------------------------------------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| "my prompt"                               |                                           |                                          | Text prompt to use. The quotation marks are optional.                                                                                                                                                                                            |
-| `--width <int>`                           | `-W<int>`                                 | `512`                                    | Width of generated image                                                                                                                                                                                                                         |
-| `--height <int>`                          | `-H<int>`                                 | `512`                                    | Height of generated image                                                                                                                                                                                                                        |
-| `--iterations <int>`                      | `-n<int>`                                 | `1`                                      | How many images to generate from this prompt                                                                                                                                                                                                     |
-| `--steps <int>`                           | `-s<int>`                                 | `50`                                     | How many steps of refinement to apply                                                                                                                                                                                                            |
-| `--cfg_scale <float>`                     | `-C<float>`                               | `7.5`                                    | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0                                                                                                       |
-| `--seed <int>`                            | `-S<int>`                                 | `None`                                   | Set the random seed for the next series of images. This can be used to recreate an image generated previously.                                                                                                                                   |
-| `--sampler <sampler>`                     | `-A<sampler>`                             | `k_lms`                                  | Sampler to use. Use -h to get list of available samplers.                                                                                                                                                                                        |
-| `--karras_max <int>`                      |                                           | `29`                                     | When using k\_\* samplers, set the maximum number of steps before shifting from using the Karras noise schedule (good for low step counts) to the LatentDiffusion noise schedule (good for high step counts) This value is sticky. [29]          |
-| `--hires_fix`                             |                                           |                                          | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution                                                                          |
-| `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                      | Select level of compression for output files, from 0 (no compression) to 9 (max compression)                                                                                                                                                     |
-| `--grid`                                  | `-g`                                      | `False`                                  | Turn on grid mode to return a single image combining all the images generated by this prompt                                                                                                                                                     |
-| `--individual`                            | `-i`                                      | `True`                                   | Turn off grid mode (deprecated; leave off --grid instead)                                                                                                                                                                                        |
-| `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                    | Temporarily change the location of these images                                                                                                                                                                                                  |
-| `--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)                                                                                                                                                  |
-| `--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](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.)                                   |
-
-!!! note
-
-    the width and height of the image must be multiples of 64. You can
-    provide different values, but they will be rounded down to the nearest multiple
-    of 64.
-
-!!! example "This is a example of img2img"
-
-    ```bash
-    invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
-    ```
-
-This will modify the indicated vacation photograph by making it more like the
-prompt. Results will vary greatly depending on what is in the image. We also ask
-to --fit the image into a box no bigger than 640x480. Otherwise the image size
-will be identical to the provided photo and you may run out of memory if it is
-large.
-
-In addition to the command-line options recognized by txt2img, img2img accepts
-additional options:
-
-| Argument <img width="160" align="right"/> | Shortcut    | Default | Description                                                                                                                                |
-| ----------------------------------------- | ----------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
-| `--init_img <path>`                       | `-I<path>`  | `None`  | Path to the initialization image                                                                                                           |
-| `--fit`                                   | `-F`        | `False` | Scale the image to fit into the specified -H and -W dimensions                                                                             |
-| `--strength <float>`                      | `-s<float>` | `0.75`  | How hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
-
-### inpainting
-
-!!! example ""
-
-    ```bash
-    invoke> waterfall and rainbow -I./vacation-photo.png -M./vacation-mask.png -W640 -H480 --fit
-    ```
-
-    This will do the same thing as img2img, but image alterations will
-    only occur within transparent areas defined by the mask file specified
-    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 accepts all the arguments used for txt2img and img2img, as well as
-the --mask (-M) and --text_mask (-tm) arguments:
-
-| Argument <img width="100" align="right"/> | Shortcut                 | Default | Description                                                                                      |
-| ----------------------------------------- | ------------------------ | ------- | ------------------------------------------------------------------------------------------------ |
-| `--init_mask <path>`                      | `-M<path>`               | `None`  | Path to an image the same size as the initial_image, with areas for inpainting made transparent. |
-| `--invert_mask `                          |                          | False   | If true, invert the mask so that transparent areas are opaque and vice versa.                    |
-| `--text_mask <prompt> [<float>]`          | `-tm <prompt> [<float>]` | <none>  | Create a mask from a text prompt describing part of the image                                    |
-
-The mask may either be an image with transparent areas, in which case the
-inpainting will occur in the transparent areas only, or a black and white image,
-in which case all black areas will be painted into.
-
-`--text_mask` (short form `-tm`) is a way to generate a mask using a text
-description of the part of the image to replace. For example, if you have an
-image of a breakfast plate with a bagel, toast and scrambled eggs, you can
-selectively mask the bagel and replace it with a piece of cake this way:
-
-```bash
-invoke> a piece of cake -I /path/to/breakfast.png -tm bagel
-```
-
-The algorithm uses <a
-href="https://github.com/timojl/clipseg">clipseg</a> to classify different
-regions of the image. The classifier puts out a confidence score for each region
-it identifies. Generally regions that score above 0.5 are reliable, but if you
-are getting too much or too little masking you can adjust the threshold down (to
-get more mask), or up (to get less). In this example, by passing `-tm` a higher
-value, we are insisting on a more stringent classification.
-
-```bash
-invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
-```
-
-### Custom Styles and Subjects
-
-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.
-
-## Other Commands
-
-The CLI offers a number of commands that begin with "!".
-
-### Postprocessing images
-
-To postprocess a file using face restoration or upscaling, use the `!fix`
-command.
-
-#### `!fix`
-
-This command runs a post-processor on a previously-generated image. It takes a
-PNG filename or path and applies your choice of the `-U`, `-G`, or `--embiggen`
-switches in order to fix faces or upscale. If you provide a filename, the script
-will look for it in the current output directory. Otherwise you can provide a
-full or partial path to the desired file.
-
-Some examples:
-
-!!! example "Upscale to 4X its original size and fix faces using codeformer"
-
-    ```bash
-    invoke> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
-    ```
-
-!!! example "Use the GFPGAN algorithm to fix faces, then upscale to 3X using --embiggen"
-
-    ```bash
-    invoke> !fix 0000045.4829112.png -G0.8 -ft gfpgan
-    >> fixing outputs/img-samples/0000045.4829112.png
-    >> retrieved seed 4829112 and prompt "boy enjoying a banana split"
-    >> GFPGAN - Restoring Faces for image seed:4829112
-    Outputs:
-    [1] outputs/img-samples/000017.4829112.gfpgan-00.png: !fix "outputs/img-samples/0000045.4829112.png" -s 50 -S  -W 512 -H 512 -C 7.5 -A k_lms -G 0.8
-    ```
-
-#### `!mask`
-
-This command takes an image, a text prompt, and uses the `clipseg` algorithm to
-automatically generate a mask of the area that matches the text prompt. It is
-useful for debugging the text masking process prior to inpainting with the
-`--text_mask` argument. See [INPAINTING.md] for details.
-
-### Model selection and importation
-
-The CLI allows you to add new models on the fly, as well as to switch
-among them rapidly without leaving the script. There are several
-different model formats, each described in the [Model Installation
-Guide](../installation/050_INSTALLING_MODELS.md).
-
-#### `!models`
-
-This prints out a list of the models defined in `config/models.yaml'. The active
-model is bold-faced
-
-Example:
-
-<pre>
-inpainting-1.5            not loaded  Stable Diffusion inpainting model
-<b>stable-diffusion-1.5          active  Stable Diffusion v1.5</b>
-waifu-diffusion           not loaded  Waifu Diffusion v1.4
-</pre>
-
-#### `!switch <model>`
-
-This quickly switches from one model to another without leaving the CLI script.
-`invoke.py` uses a memory caching system; once a model has been loaded,
-switching back and forth is quick. The following example shows this in action.
-Note how the second column of the `!models` table changes to `cached` after a
-model is first loaded, and that the long initialization step is not needed when
-loading a cached model.
-
-#### `!import_model <hugging_face_repo_ID>`
-
-This imports and installs a `diffusers`-style model that is stored on
-the [HuggingFace Web Site](https://huggingface.co). You can look up
-any [Stable Diffusion diffusers
-model](https://huggingface.co/models?library=diffusers) and install it
-with a command like the following:
-
-```bash
-!import_model prompthero/openjourney
-```
-
-#### `!import_model <path/to/diffusers/directory>`
-
-If you have a copy of a `diffusers`-style model saved to disk, you can
-import it by passing the path to model's top-level directory.
-
-#### `!import_model <url>`
-
-For a `.ckpt` or `.safetensors` file, if you have a direct download
-URL for the file, you can provide it to `!import_model` and the file
-will be downloaded and installed for you.
-
-#### `!import_model <path/to/model/weights.ckpt>`
-
-This command imports a new model weights file into InvokeAI, makes it available
-for image generation within the script, and writes out the configuration for the
-model into `config/models.yaml` for use in subsequent sessions.
-
-Provide `!import_model` with the path to a weights file ending in `.ckpt`. If
-you type a partial path and press tab, the CLI will autocomplete. Although it
-will also autocomplete to `.vae` files, these are not currenty supported (but
-will be soon).
-
-When you hit return, the CLI will prompt you to fill in additional information
-about the model, including the short name you wish to use for it with the
-`!switch` command, a brief description of the model, the default image width and
-height to use with this model, and the model's configuration file. The latter
-three fields are automatically filled with reasonable defaults. In the example
-below, the bold-faced text shows what the user typed in with the exception of
-the width, height and configuration file paths, which were filled in
-automatically.
-
-#### `!import_model <path/to/directory_of_models>`
-
-If you provide the path of a directory that contains one or more
-`.ckpt` or `.safetensors` files, the CLI will scan the directory and
-interactively offer to import the models it finds there. Also see the
-`--autoconvert` command-line option.
-
-#### `!edit_model <name_of_model>`
-
-The `!edit_model` command can be used to modify a model that is already defined
-in `config/models.yaml`. Call it with the short name of the model you wish to
-modify, and it will allow you to modify the model's `description`, `weights` and
-other fields.
-
-Example:
-
-<pre>
-invoke> <b>!edit_model waifu-diffusion</b>
->> Editing model waifu-diffusion from configuration file ./configs/models.yaml
-description: <b>Waifu diffusion v1.4beta</b>
-weights: models/ldm/stable-diffusion-v1/<b>model-epoch10-float16.ckpt</b>
-config: configs/stable-diffusion/v1-inference.yaml
-width: 512
-height: 512
-
->> New configuration:
-waifu-diffusion:
-  config: configs/stable-diffusion/v1-inference.yaml
-  description: Waifu diffusion v1.4beta
-  weights: models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
-  height: 512
-  width: 512
-
-OK to import [n]? y
->> Caching model stable-diffusion-1.4 in system RAM
->> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
-...
-</pre>
-
-### History processing
-
-The CLI provides a series of convenient commands for reviewing previous actions,
-retrieving them, modifying them, and re-running them.
-
-#### `!history`
-
-The invoke script keeps track of all the commands you issue during a session,
-allowing you to re-run them. On Mac and Linux systems, it also writes the
-command-line history out to disk, giving you access to the most recent 1000
-commands issued.
-
-The `!history` command will return a numbered list of all the commands issued
-during the session (Windows), or the most recent 1000 commands (Mac|Linux). You
-can then repeat a command by using the command `!NNN`, where "NNN" is the
-history line number. For example:
-
-!!! example ""
-
-    ```bash
-    invoke> !history
-    ...
-    [14] happy woman sitting under tree wearing broad hat and flowing garment
-    [15] beautiful woman sitting under tree wearing broad hat and flowing garment
-    [18] beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6
-    [20] watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    [21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    ...
-    invoke> !20
-    invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    ```
-
-####`!fetch`
-
-This command retrieves the generation parameters from a previously generated
-image and either loads them into the command line (Linux|Mac), or prints them
-out in a comment for copy-and-paste (Windows). You may provide either the name
-of a file in the current output directory, or a full file path. Specify path to
-a folder with image png files, and wildcard \*.png to retrieve the dream command
-used to generate the images, and save them to a file commands.txt for further
-processing.
-
-!!! example "load the generation command for a single png file"
-
-    ```bash
-    invoke> !fetch 0000015.8929913.png
-    # the script returns the next line, ready for editing and running:
-    invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
-    ```
-
-!!! example "fetch the generation commands from a batch of files and store them into `selected.txt`"
-
-    ```bash
-    invoke> !fetch outputs\selected-imgs\*.png selected.txt
-    ```
-
-#### `!replay`
-
-This command replays a text file generated by !fetch or created manually
-
-!!! example
-
-    ```bash
-    invoke> !replay outputs\selected-imgs\selected.txt
-    ```
-
-!!! note
-
-    These commands may behave unexpectedly if given a PNG file that was
-    not generated by InvokeAI.
-
-#### `!search <search string>`
-
-This is similar to !history but it only returns lines that contain
-`search string`. For example:
-
-```bash
-invoke> !search surreal
-[21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-```
-
-#### `!clear`
-
-This clears the search history from memory and disk. Be advised that this
-operation is irreversible and does not issue any warnings!
-
-## Command-line editing and completion
-
-The command-line offers convenient history tracking, editing, and command
-completion.
-
-- To scroll through previous commands and potentially edit/reuse them, use the
-  ++up++ and ++down++ keys.
-- To edit the current command, use the ++left++ and ++right++ keys to position
-  the cursor, and then ++backspace++, ++delete++ or insert characters.
-- To move to the very beginning of the command, type ++ctrl+a++ (or
-  ++command+a++ on the Mac)
-- To move to the end of the command, type ++ctrl+e++.
-- To cut a section of the command, position the cursor where you want to start
-  cutting and type ++ctrl+k++
-- To paste a cut section back in, position the cursor where you want to paste,
-  and type ++ctrl+y++
-
-Windows users can get similar, but more limited, functionality if they launch
-`invoke.py` with the `winpty` program and have the `pyreadline3` library
-installed:
-
-```batch
-> winpty python scripts\invoke.py
-```
-
-On the Mac and Linux platforms, when you exit invoke.py, the last 1000 lines of
-your command-line history will be saved. When you restart `invoke.py`, you can
-access the saved history using the ++up++ key.
-
-In addition, limited command-line completion is installed. In various contexts,
-you can start typing your command and press ++tab++. A list of potential
-completions will be presented to you. You can then type a little more, hit
-++tab++ again, and eventually autocomplete what you want.
-
-When specifying file paths using the one-letter shortcuts, the CLI will attempt
-to complete pathnames for you. This is most handy for the `-I` (init image) and
-`-M` (init mask) paths. To initiate completion, start the path with a slash
-(`/`) or `./`. For example:
-
-```bash
-invoke> zebra with a mustache -I./test-pictures<TAB>
--I./test-pictures/Lincoln-and-Parrot.png  -I./test-pictures/zebra.jpg        -I./test-pictures/madonna.png
--I./test-pictures/bad-sketch.png          -I./test-pictures/man_with_eagle/
-```
-
-You can then type ++z++, hit ++tab++ again, and it will autofill to `zebra.jpg`.
-
-More text completion features (such as autocompleting seeds) are on their way.

docs/deprecated/EMBIGGEN.md

@@ -1,167 +0,0 @@
----
-title: Embiggen
----
-
-# :material-loupe: Embiggen
-
-**upscale your images on limited memory machines**
-
-GFPGAN and Real-ESRGAN are both memory intensive. In order to avoid
-crashes and memory overloads during the Stable Diffusion process,
-these effects are applied after Stable Diffusion has completed its
-work.
-
-In single image generations, you will see the output right away but
-when you are using multiple iterations, the images will first be
-generated and then upscaled and face restored after that 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.
-
-## Embiggen
-
-If you wanted to be able to do more (pixels) without running out of VRAM,
-or you want to upscale with details that couldn't possibly appear
-without the context of a prompt, this is the feature to try out.
-
-Embiggen automates the process of taking an init image, upscaling it,
-cutting it into smaller tiles that slightly overlap, running all the
-tiles through img2img to refine details with respect to the prompt,
-and "stitching" the tiles back together into a cohesive image.
-
-It automatically computes how many tiles are needed, and so it can be fed
-*ANY* size init image and perform Img2Img on it (though it will be run only
-one tile at a time, which can cause problems, see the Note at the end).
-
-If you're familiar with "GoBig" (ala [progrock-stable](https://github.com/lowfuel/progrock-stable))
-it's similar to that, except it can work up to an arbitrarily large size
-(instead of just 2x), with tile overlaps configurable as a ratio, and
-has extra logic to re-run any number of the tile sub-sections of the image
-if for example a small part of a huge run got messed up.
-
-### Usage
-
-`-embiggen <scaling_factor> <esrgan_strength> <overlap_ratio OR overlap_pixels>`
-
-Takes a scaling factor relative to the size of the `--init_img` (`-I`), followed by
-ESRGAN upscaling strength (0 - 1.0), followed by minimum amount of overlap
-between tiles as a decimal ratio (0 - 1.0) *OR* a number of pixels.
-
-The scaling factor is how much larger than the `--init_img` the output
-should be, and will multiply both x and y axis, so an image that is a
-scaling factor of 3.0 has 3*3= 9 times as many pixels, and will take
-(at least) 9 times as long (see overlap for why it might be
-longer). If the `--init_img` is already the right size `-embiggen 1`,
-and it can also be less than one if the init_img is too big.
-
-Esrgan_strength defaults to 0.75, and the overlap_ratio defaults to
-0.25, both are optional.
-
-Unlike Img2Img, the `--width` (`-W`) and `--height` (`-H`) arguments
-do not control the size of the image as a whole, but the size of the
-tiles used to Embiggen the image.
-
-ESRGAN is used to upscale the `--init_img` prior to cutting it into
-tiles/pieces to run through img2img and then stitch back
-together. Embiggen can be run without ESRGAN; just set the strength to
-zero (e.g. `-embiggen 1.75 0`). The output of Embiggen can also be
-upscaled after it's finished (`-U`).
-
-The overlap is the minimum that tiles will overlap with adjacent
-tiles, specified as either a ratio or a number of pixels. How much the
-tiles overlap determines the likelihood the tiling will be noticable,
-really small overlaps (e.g. a couple of pixels) may produce noticeable
-grid-like fuzzy distortions in the final stitched image. Though, as
-the overlapping space doesn't contribute to making the image bigger,
-and the larger the overlap the more tiles (and the more time) it will
-take to finish.
-
-Because the overlapping parts of tiles don't "contribute" to
-increasing size, every tile after the first in a row or column
-effectively only covers an extra `1 - overlap_ratio` on each axis. If
-the input/`--init_img` is same size as a tile, the ideal (for time)
-scaling factors with the default overlap (0.25) are 1.75, 2.5, 3.25,
-4.0, etc.
-
-`-embiggen_tiles <spaced list of tiles>`
-
-An advanced usage useful if you only want to alter parts of the image
-while running Embiggen. It takes a list of tiles by number to run and
-replace onto the initial image e.g. `1 3 5`. It's useful for either
-fixing problem spots from a previous Embiggen run, or selectively
-altering the prompt for sections of an image - for creative or
-coherency reasons.
-
-Tiles are numbered starting with one, and left-to-right,
-top-to-bottom.  So, if you are generating a 3x3 tiled image, the
-middle row would be `4 5 6`.
-
-`-embiggen_strength <strength>`
-
-Another advanced option if you want to experiment with the strength parameter
-that embiggen uses when it calls Img2Img. Values range from 0.0 to 1.0
-and lower values preserve more of the character of the initial image.
-Values that are too high will result in a completely different end image,
-while values that are too low will result in an image not dissimilar to one
-you would get with ESRGAN upscaling alone. The default value is 0.4.
-
-### Examples
-
-!!! example ""
-
-    Running Embiggen with 512x512 tiles on an existing image, scaling up by a factor of 2.5x;
-    and doing the same again (default ESRGAN strength is 0.75, default overlap between tiles is 0.25):
-
-    ```bash
-    invoke > a photo of a forest at sunset -s 100 -W 512 -H 512 -I outputs/forest.png -f 0.4 -embiggen 2.5
-    invoke > a photo of a forest at sunset -s 100 -W 512 -H 512 -I outputs/forest.png -f 0.4 -embiggen 2.5 0.75 0.25
-    ```
-
-    If your starting image was also 512x512 this should have taken 9 tiles.
-
-!!! example ""
-
-    If there weren't enough clouds in the sky of that forest you just made
-    (and that image is about 1280 pixels (512*2.5) wide A.K.A. three
-    512x512 tiles with 0.25 overlaps wide) we can replace that top row of
-    tiles:
-
-    ```bash
-    invoke> a photo of puffy clouds over a forest at sunset -s 100 -W 512 -H 512 -I outputs/000002.seed.png -f 0.5 -embiggen_tiles 1 2 3
-    ```
-
-## Fixing Previously-Generated Images
-
-It is easy to apply embiggen to any previously-generated file without having to
-look up the original prompt and provide an initial image. Just use the
-syntax `!fix path/to/file.png <embiggen>`. For example, you can rewrite the
-previous command to look like this:
-
-```bash
-invoke> !fix ./outputs/000002.seed.png -embiggen_tiles 1 2 3
-```
-
-A new file named `000002.seed.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.
-You do not need to provide the prompt, and `!fix` automatically selects a good strength for
-embiggen-ing.
-
-!!! note
-
-    Because the same prompt is used on all the tiled images, and the model
-    doesn't have the context of anything outside the tile being run - it
-    can end up creating repeated pattern (also called 'motifs') across all
-    the tiles based on that prompt. The best way to combat this is
-    lowering the `--strength` (`-f`) to stay more true to the init image,
-    and increasing the number of steps so there is more compute-time to
-    create the detail.  Anecdotally `--strength` 0.35-0.45 works pretty
-    well on most things. It may also work great in some examples even with
-    the `--strength` set high for patterns, landscapes, or subjects that
-    are more abstract. Because this is (relatively) fast, you can also
-    preserve the best parts from each.
-
-Author: [Travco](https://github.com/travco)

docs/deprecated/INPAINTING.md

@@ -1,310 +0,0 @@
----
-title: Inpainting
----
-
-# :octicons-paintbrush-16: Inpainting
-
-## **Creating Transparent Regions for Inpainting**
-
-Inpainting is really cool. To do it, you start with an initial image and use a
-photoeditor to make one or more regions transparent (i.e. they have a "hole" in
-them). You then provide the path to this image at the dream> command line using
-the `-I` switch. Stable Diffusion will only paint within the transparent region.
-
-There's a catch. In the current implementation, you have to prepare the initial
-image correctly so that the underlying colors are preserved under the
-transparent area. Many imaging editing applications will by default erase the
-color information under the transparent pixels and replace them with white or
-black, which will lead to suboptimal inpainting. It often helps to apply
-incomplete transparency, such as any value between 1 and 99%
-
-You also must take care to export the PNG file in such a way that the color
-information is preserved. There is often an option in the export dialog that
-lets you specify this.
-
-If your photoeditor is erasing the underlying color information, `dream.py` will
-give you a big fat warning. If you can't find a way to coax your photoeditor to
-retain color values under transparent areas, then you can combine the `-I` and
-`-M` switches to provide both the original unedited image and the masked
-(partially transparent) image:
-
-```bash
-invoke> "man with cat on shoulder" -I./images/man.png -M./images/man-transparent.png
-```
-
-## **Masking using Text**
-
-You can also create a mask using a text prompt to select the part of the image
-you want to alter, using the [clipseg](https://github.com/timojl/clipseg)
-algorithm. This works on any image, not just ones generated by InvokeAI.
-
-The `--text_mask` (short form `-tm`) option takes two arguments. The first
-argument is a text description of the part of the image you wish to mask (paint
-over). If the text description contains a space, you must surround it with
-quotation marks. The optional second argument is the minimum threshold for the
-mask classifier's confidence score, described in more detail below.
-
-To see how this works in practice, here's an image of a still life painting that
-I got off the web.
-
-<figure markdown>
-![still life scaled](../assets/still-life-scaled.jpg)
-</figure>
-
-You can selectively mask out the orange and replace it with a baseball in this
-way:
-
-```bash
-invoke> a baseball -I /path/to/still_life.png -tm orange
-```
-
-<figure markdown>
-![](../assets/still-life-inpainted.png)
-</figure>
-
-The clipseg classifier produces a confidence score for each region it
-identifies. Generally regions that score above 0.5 are reliable, but if you are
-getting too much or too little masking you can adjust the threshold down (to get
-more mask), or up (to get less). In this example, by passing `-tm` a higher
-value, we are insisting on a tigher mask. However, if you make it too high, the
-orange may not be picked up at all!
-
-```bash
-invoke> a baseball -I /path/to/breakfast.png -tm orange 0.6
-```
-
-The `!mask` command may be useful for debugging problems with the text2mask
-feature. The syntax is `!mask /path/to/image.png -tm <text> <threshold>`
-
-It will generate three files:
-
-- The image with the selected area highlighted.
-  - it will be named XXXXX.<imagename>.<prompt>.selected.png
-- The image with the un-selected area highlighted.
-  - it will be named XXXXX.<imagename>.<prompt>.deselected.png
-- The image with the selected area converted into a black and white image
-  according to the threshold level
-  - it will be named XXXXX.<imagename>.<prompt>.masked.png
-
-The `.masked.png` file can then be directly passed to the `invoke>` prompt in
-the CLI via the `-M` argument. Do not attempt this with the `selected.png` or
-`deselected.png` files, as they contain some transparency throughout the image
-and will not produce the desired results.
-
-Here is an example of how `!mask` works:
-
-```bash
-invoke> !mask ./test-pictures/curly.png -tm hair 0.5
->> generating masks from ./test-pictures/curly.png
->> Initializing clipseg model for text to mask inference
-Outputs:
-[941.1] outputs/img-samples/000019.curly.hair.deselected.png: !mask ./test-pictures/curly.png -tm hair 0.5
-[941.2] outputs/img-samples/000019.curly.hair.selected.png: !mask ./test-pictures/curly.png -tm hair 0.5
-[941.3] outputs/img-samples/000019.curly.hair.masked.png: !mask ./test-pictures/curly.png -tm hair 0.5
-```
-
-<figure markdown>
-![curly](../assets/outpainting/curly.png)
-<figcaption>Original image "curly.png"</figcaption>
-</figure>
-
-<figure markdown>
-![curly hair selected](../assets/inpainting/000019.curly.hair.selected.png)
-<figcaption>000019.curly.hair.selected.png</figcaption>
-</figure>
-
-<figure markdown>
-![curly hair deselected](../assets/inpainting/000019.curly.hair.deselected.png)
-<figcaption>000019.curly.hair.deselected.png</figcaption>
-</figure>
-
-<figure markdown>
-![curly hair masked](../assets/inpainting/000019.curly.hair.masked.png)
-<figcaption>000019.curly.hair.masked.png</figcaption>
-</figure>
-
-It looks like we selected the hair pretty well at the 0.5 threshold (which is
-the default, so we didn't actually have to specify it), so let's have some fun:
-
-```bash
-invoke> medusa with cobras -I ./test-pictures/curly.png -M 000019.curly.hair.masked.png -C20
->> loaded input image of size 512x512 from ./test-pictures/curly.png
-...
-Outputs:
-[946] outputs/img-samples/000024.801380492.png: "medusa with cobras" -s 50 -S 801380492 -W 512 -H 512 -C 20.0 -I ./test-pictures/curly.png -A k_lms -f 0.75
-```
-
-<figure markdown>
-![](../assets/inpainting/000024.801380492.png)
-</figure>
-
-You can also skip the `!mask` creation step and just select the masked
-
-region directly:
-
-```bash
-invoke> medusa with cobras -I ./test-pictures/curly.png -tm hair -C20
-```
-
-## Using the RunwayML inpainting model
-
-The
-[RunwayML Inpainting Model v1.5](https://huggingface.co/runwayml/stable-diffusion-inpainting)
-is a specialized version of
-[Stable Diffusion v1.5](https://huggingface.co/spaces/runwayml/stable-diffusion-v1-5)
-that contains extra channels specifically designed to enhance inpainting and
-outpainting. While it can do regular `txt2img` and `img2img`, it really shines
-when filling in missing regions. It has an almost uncanny ability to blend the
-new regions with existing ones in a semantically coherent way.
-
-To install the inpainting model, follow the
-[instructions](../installation/050_INSTALLING_MODELS.md) for installing a new model.
-You may use either the CLI (`invoke.py` script) or directly edit the
-`configs/models.yaml` configuration file to do this. The main thing to watch out
-for is that the the model `config` option must be set up to use
-`v1-inpainting-inference.yaml` rather than the `v1-inference.yaml` file that is
-used by Stable Diffusion 1.4 and 1.5.
-
-After installation, your `models.yaml` should contain an entry that looks like
-this one:
-
-```yml
-inpainting-1.5:
-  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
-  description: SD inpainting v1.5
-  config: configs/stable-diffusion/v1-inpainting-inference.yaml
-  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
-  width: 512
-  height: 512
-```
-
-As shown in the example, you may include a VAE fine-tuning weights file as well.
-This is strongly recommended.
-
-To use the custom inpainting model, launch `invoke.py` with the argument
-`--model inpainting-1.5` or alternatively from within the script use the
-`!switch inpainting-1.5` command to load and switch to the inpainting model.
-
-You can now do inpainting and outpainting exactly as described above, but there
-will (likely) be a noticeable improvement in coherence. Txt2img and Img2img will
-work as well.
-
-There are a few caveats to be aware of:
-
-1. The inpainting model is larger than the standard model, and will use nearly 4
-   GB of GPU VRAM. This makes it unlikely to run on a 4 GB graphics card.
-
-2. When operating in Img2img mode, the inpainting model is much less steerable
-   than the standard model. It is great for making small changes, such as
-   changing the pattern of a fabric, or slightly changing a subject's expression
-   or hair, but the model will resist making the dramatic alterations that the
-   standard model lets you do.
-
-3. While the `--hires` option works fine with the inpainting model, some special
-   features, such as `--embiggen` are disabled.
-
-4. Prompt weighting (`banana++ sushi`) and merging work well with the inpainting
-   model, but prompt swapping
-   (`a ("fluffy cat").swap("smiling dog") eating a hotdog`) will not have any
-   effect due to the way the model is set up. You may use text masking (with
-   `-tm thing-to-mask`) as an effective replacement.
-
-5. The model tends to oversharpen image if you use high step or CFG values. If
-   you need to do large steps, use the standard model.
-
-6. The `--strength` (`-f`) option has no effect on the inpainting model due to
-   its fundamental differences with the standard model. It will always take the
-   full number of steps you specify.
-
-## Troubleshooting
-
-Here are some troubleshooting tips for inpainting and outpainting.
-
-## Inpainting is not changing the masked region enough!
-
-One of the things to understand about how inpainting works is that it is
-equivalent to running img2img on just the masked (transparent) area. img2img
-builds on top of the existing image data, and therefore will attempt to preserve
-colors, shapes and textures to the best of its ability. Unfortunately this means
-that if you want to make a dramatic change in the inpainted region, for example
-replacing a red wall with a blue one, the algorithm will fight you.
-
-You have a couple of options. The first is to increase the values of the
-requested steps (`-sXXX`), strength (`-f0.XX`), and/or condition-free guidance
-(`-CXX.X`). If this is not working for you, a more extreme step is to provide
-the `--inpaint_replace 0.X` (`-r0.X`) option. This value ranges from 0.0 to 1.0.
-The higher it is the less attention the algorithm will pay to the data
-underneath the masked region. At high values this will enable you to replace
-colored regions entirely, but beware that the masked region mayl not blend in
-with the surrounding unmasked regions as well.
-
----
-
-## Recipe for GIMP
-
-[GIMP](https://www.gimp.org/) is a popular Linux photoediting tool.
-
-1. Open image in GIMP.
-2. Layer->Transparency->Add Alpha Channel
-3. Use lasso tool to select region to mask
-4. Choose Select -> Float to create a floating selection
-5. Open the Layers toolbar (^L) and select "Floating Selection"
-6. Set opacity to a value between 0% and 99%
-7. Export as PNG
-8. In the export dialogue, Make sure the "Save colour values from transparent
-   pixels" checkbox is selected.
-
----
-
-## Recipe for Adobe Photoshop
-
-1. Open image in Photoshop
-
-    <figure markdown>
-    ![step1](../assets/step1.png)
-    </figure>
-
-2. Use any of the selection tools (Marquee, Lasso, or Wand) to select the area
-   you desire to inpaint.
-
-    <figure markdown>
-    ![step2](../assets/step2.png)
-    </figure>
-
-3. Because we'll be applying a mask over the area we want to preserve, you
-   should now select the inverse by using the ++shift+ctrl+i++ shortcut, or
-   right clicking and using the "Select Inverse" option.
-
-4. You'll now create a mask by selecting the image layer, and Masking the
-   selection. Make sure that you don't delete any of the underlying image, or
-   your inpainting results will be dramatically impacted.
-
-    <figure markdown>
-    ![step4](../assets/step4.png)
-    </figure>
-
-5. Make sure to hide any background layers that are present. You should see the
-   mask applied to your image layer, and the image on your canvas should display
-   the checkered background.
-
-    <figure markdown>
-    ![step5](../assets/step5.png)
-    </figure>
-
-6. Save the image as a transparent PNG by using `File`-->`Save a Copy` from the
-   menu bar, or by using the keyboard shortcut ++alt+ctrl+s++
-
-    <figure markdown>
-    ![step6](../assets/step6.png)
-    </figure>
-
-7. After following the inpainting instructions above (either through the CLI or
-   the Web UI), marvel at your newfound ability to selectively invoke. Lookin'
-   good!
-
-    <figure markdown>
-   ![step7](../assets/step7.png)
-    </figure>
-
-8. In the export dialogue, Make sure the "Save colour values from transparent
-   pixels" checkbox is selected.

docs/deprecated/OUTPAINTING.md

@@ -1,171 +0,0 @@
----
-title: Outpainting
----
-
-# :octicons-paintbrush-16: Outpainting
-
-## Outpainting and outcropping
-
-Outpainting is a process by which the AI generates parts of the image that are
-outside its original frame. It can be used to fix up images in which the subject
-is off center, or when some detail (often the top of someone's head!) is cut
-off.
-
-InvokeAI supports two versions of outpainting, one called "outpaint" and the
-other "outcrop." They work slightly differently and each has its advantages and
-drawbacks.
-
-### Outpainting
-
-Outpainting is the same as inpainting, except that the painting occurs in the
-regions outside of the original image. To outpaint using the `invoke.py` command
-line script, prepare an image in which the borders to be extended are pure
-black. Add an alpha channel (if there isn't one already), and make the borders
-completely transparent and the interior completely opaque. If you wish to modify
-the interior as well, you may create transparent holes in the transparency
-layer, which `img2img` will paint into as usual.
-
-Pass the image as the argument to the `-I` switch as you would for regular
-inpainting:
-
-```bash
-invoke> a stream by a river -I /path/to/transparent_img.png
-```
-
-You'll likely be delighted by the results.
-
-### Tips
-
-1. Do not try to expand the image too much at once. Generally it is best to
-   expand the margins in 64-pixel increments. 128 pixels often works, but your
-   mileage may vary depending on the nature of the image you are trying to
-   outpaint into.
-
-2. There are a series of switches that can be used to adjust how the inpainting
-   algorithm operates. In particular, you can use these to minimize the seam
-   that sometimes appears between the original image and the extended part.
-   These switches are:
-
-| switch                     | default | description                                                            |
-| -------------------------- | ------- | ---------------------------------------------------------------------- |
-| `--seam_size SEAM_SIZE `   | `0`     | Size of the mask around the seam between original and outpainted image |
-| `--seam_blur SEAM_BLUR`    | `0`     | The amount to blur the seam inwards                                    |
-| `--seam_strength STRENGTH` | `0.7`   | The img2img strength to use when filling the seam                      |
-| `--seam_steps SEAM_STEPS`  | `10`    | The number of steps to use to fill the seam.                           |
-| `--tile_size TILE_SIZE`    | `32`    | The tile size to use for filling outpaint areas                        |
-
-### Outcrop
-
-The `outcrop` extension gives you a convenient `!fix` postprocessing command
-that allows you to extend a previously-generated image in 64 pixel increments in
-any direction. You can apply the module to any image previously-generated by
-InvokeAI. Note that it works with arbitrary PNG photographs, but not currently
-with JPG or other formats. Outcropping is particularly effective when combined
-with the
-[runwayML custom inpainting model](INPAINTING.md#using-the-runwayml-inpainting-model).
-
-Consider this image:
-
-<figure markdown>
-![curly_woman](../assets/outpainting/curly.png)
-</figure>
-
-Pretty nice, but it's annoying that the top of her head is cut off. She's also a
-bit off center. Let's fix that!
-
-```bash
-invoke> !fix images/curly.png --outcrop top 128 right 64 bottom 64
-```
-
-This is saying to apply the `outcrop` extension by extending the top of the
-image by 128 pixels, and the right and bottom of the image by 64 pixels. You can
-use any combination of top|left|right|bottom, and specify any number of pixels
-to extend. You can also abbreviate `--outcrop` to `-c`.
-
-The result looks like this:
-
-<figure markdown>
-![curly_woman_outcrop](../assets/outpainting/curly-outcrop-2.png)
-</figure>
-
-The new image is larger than the original (576x704) because 64 pixels were added
-to the top and right sides. You will need enough VRAM to process an image of
-this size.
-
-#### Outcropping non-InvokeAI images
-
-You can outcrop an arbitrary image that was not generated by InvokeAI,
-but your results will vary. The `inpainting-1.5` model is highly
-recommended, but if not feasible, then you may be able to improve the
-output by conditioning the outcropping with a text prompt that
-describes the scene using the `--new_prompt` argument:
-
-```bash
-invoke> !fix images/vacation.png --outcrop top 128 --new_prompt "family vacation"
-```
-
-You may also provide a different seed for outcropping to use by passing
-`-S<seed>`. A negative seed will generate a new random seed.
-
-A number of caveats:
-
-1. Although you can specify any pixel values, they will be rounded up to the
-   nearest multiple of 64. Smaller values are better. Larger extensions are more
-   likely to generate artefacts. However, if you wish you can run the !fix
-   command repeatedly to cautiously expand the image.
-
-2. The extension is stochastic, meaning that each time you run it you'll get a
-   slightly different result. You can run it repeatedly until you get an image
-   you like. Unfortunately `!fix` does not currently respect the `-n`
-   (`--iterations`) argument.
-
-3. Your results will be _much_ better if you use the `inpaint-1.5` model
-   released by runwayML and installed by default by `invokeai-configure`.
-   This model was trained specifically to harmoniously fill in image gaps. The
-   standard model will work as well, but you may notice color discontinuities at
-   the border.
-
-4. When using the `inpaint-1.5` model, you may notice subtle changes to the area
-   outside the masked region. This is because the model performs an
-   encoding/decoding on the image as a whole. This does not occur with the
-   standard model.
-
-## Outpaint
-
-The `outpaint` extension does the same thing, but with subtle differences.
-Starting with the same image, here is how we would add an additional 64 pixels
-to the top of the image:
-
-```bash
-invoke> !fix images/curly.png --out_direction top 64
-```
-
-(you can abbreviate `--out_direction` as `-D`.
-
-The result is shown here:
-
-<figure markdown>
-![curly_woman_outpaint](../assets/outpainting/curly-outpaint.png)
-</figure>
-
-Although the effect is similar, there are significant differences from
-outcropping:
-
-- You can only specify one direction to extend at a time.
-- The image is **not** resized. Instead, the image is shifted by the specified
-  number of pixels. If you look carefully, you'll see that less of the lady's
-  torso is visible in the image.
-- Because the image dimensions remain the same, there's no rounding to multiples
-  of 64.
-- Attempting to outpaint larger areas will frequently give rise to ugly ghosting
-  effects.
-- For best results, try increasing the step number.
-- If you don't specify a pixel value in `-D`, it will default to half of the
-  whole image, which is likely not what you want.
-
-!!! tip
-
-    Neither `outpaint` nor `outcrop` are perfect, but we continue to tune
-    and improve them. If one doesn't work, try the other. You may also
-    wish to experiment with other `img2img` arguments, such as `-C`, `-f`
-    and `-s`.

docs/deprecated/TRANSLATION.md

@@ -1,19 +0,0 @@
-# Translation
-
-InvokeAI uses [Weblate](https://weblate.org) for translation. Weblate is a FOSS project providing a scalable translation service. Weblate automates the tedious parts of managing translation of a growing project, and the service is generously provided at no cost to FOSS projects like InvokeAI.
-
-## Contributing
-
-If you'd like to contribute by adding or updating a translation, please visit our [Weblate project](https://hosted.weblate.org/engage/invokeai/). You'll need to sign in with your GitHub account (a number of other accounts are supported, including Google).
-
-Once signed in, select a language and then the Web UI component. From here you can Browse and Translate strings from English to your chosen language. Zen mode offers a simpler translation experience.
-
-Your changes will be attributed to you in the automated PR process; you don't need to do anything else.
-
-## Help & Questions
-
-Please check Weblate's [documentation](https://docs.weblate.org/en/latest/index.html) or ping @psychedelicious or @blessedcoolant on Discord if you have any questions.
-
-## Thanks
-
-Thanks to the InvokeAI community for their efforts to translate the project!

docs/deprecated/VARIATIONS.md

@@ -1,131 +0,0 @@
----
-title: Variations
----
-
-# :material-tune-variant: Variations
-
-## Intro
-
-InvokeAI's support for variations enables you 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.
-
-2. Given two or more variations that you like, you can combine them in a
-   weighted fashion.
-
-!!! Information ""
-
-    This cheat sheet provides a quick guide for how this works in practice, using
-    variations to create the desired image of Xena, Warrior Princess.
-
-## Step 1 -- Find a base image that you like
-
-The prompt we will use throughout is:
-
-`#!bash "lucy lawless as xena, warrior princess, character portrait, high resolution."`
-
-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.
-
-<figure markdown>
-![var1](../assets/variation_walkthru/000001.3357757885.png)
-<figcaption> Seed 3357757885 looks nice </figcaption>
-</figure>
-
----
-
-## 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.
-
-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.
-
-### **Variation Sub Seeding**
-
-Note that the output for each image has a `-V` option giving the "variant
-subseed" for that image, consisting of a seed followed by the variation amount
-used to generate it.
-
-This gives us a series of closely-related variations, including the two shown
-here.
-
-<figure markdown>
-![var2](../assets/variation_walkthru/000002.3647897225.png)
-<figcaption>subseed 3647897225</figcaption>
-</figure>
-
-<figure markdown>
-![var3](../assets/variation_walkthru/000002.1614299449.png)
-<figcaption>subseed 1614299449</figcaption>
-</figure>
-
-I like the expression on Xena's face in the first one (subseed 3647897225), and
-the armor on her shoulder in the second one (subseed 1614299449). Can we combine
-them to get the best of both worlds?
-
-We combine the two variations using `-V` (`--with_variations`). Again, we must
-provide the seed for the originally-chosen image in order for this to work.
-
-```bash
-invoke> "prompt"  -S3357757885 -V3647897225,0.1,1614299449,0.1
-Outputs:
-./outputs/Xena/000003.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1 -S3357757885
-```
-
-Here we are providing equal weights (0.1 and 0.1) for both the subseeds. The
-resulting image is close, but not exactly what I wanted:
-
-<figure markdown>
-![var4](../assets/variation_walkthru/000003.1614299449.png)
-<figcaption> subseed 1614299449 </figcaption>
-</figure>
-
-We could either try combining the images with different weights, or we can
-generate more variations around the almost-but-not-quite image. We do the
-latter, using both the `-V` (combining) and `-v` (variation strength) options.
-Note that we use `-n6` to generate 6 variations:
-
-```bash
-invoke> "prompt" -S3357757885 -V3647897225,0.1,1614299449,0.1 -v0.05 -n6
-Outputs:
-./outputs/Xena/000004.3279757577.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,3279757577:0.05 -S3357757885
-./outputs/Xena/000004.2853129515.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2853129515:0.05 -S3357757885
-./outputs/Xena/000004.3747154981.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,3747154981:0.05 -S3357757885
-./outputs/Xena/000004.2664260391.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2664260391:0.05 -S3357757885
-./outputs/Xena/000004.1642517170.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,1642517170:0.05 -S3357757885
-./outputs/Xena/000004.2183375608.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2183375608:0.05 -S3357757885
-```
-
-This produces six images, all slight variations on the combination of the chosen
-two images. Here's the one I like best:
-
-<figure markdown>
-![var5](../assets/variation_walkthru/000004.3747154981.png)
-<figcaption> subseed 3747154981 </figcaption>
-</figure>
-
-As you can see, this is a very powerful tool, which when combined with subprompt
-weighting, gives you great control over the content and quality of your
-generated images.
-
-## Variations and Samplers
-
-The sampler you choose has a strong effect on variation strength. Some
-samplers, such as `k_euler_a` are very "creative" and produce significant
-amounts of image-to-image variation even when the seed is fixed and the
-`-v` argument is very low. Others are more deterministic. Feel free to
-experiment until you find the combination that you like.
-
-Also be aware of the [Perlin Noise](../features/OTHER.md#thresholding-and-perlin-noise-initialization-options)
-feature, which provides another way of introducing variability into your
-image generation requests.

docs/features/CONFIGURATION.md

@@ -51,13 +51,11 @@ The settings in this file will override the defaults. You only need
 to change this file if the default for a particular setting doesn't
 work for you.
 
+You'll find an example file next to `invokeai.yaml` that shows the default values.
+
 Some settings, like [Model Marketplace API Keys], require the YAML
 to be formatted correctly. Here is a [basic guide to YAML files].
 
-You can fix a broken `invokeai.yaml` by deleting it and running the
-configuration script again -- option [6] in the launcher, "Re-run the
-configure script".
-
 #### Custom Config File Location
 
 You can use any config file with the `--config` CLI arg. Pass in the path to the `invokeai.yaml` file you want to use.
@@ -137,15 +135,7 @@ Most common algorithms are supported, like `md5`, `sha256`, and `sha512`. These
 
 #### Path Settings
 
-These options set the paths of various directories and files used by
-InvokeAI. Relative paths are interpreted relative to the root directory, so
-if root is `/home/fred/invokeai` and the path is
-`autoimport/main`, then the corresponding directory will be located at
-`/home/fred/invokeai/autoimport/main`.
-
-Note that the autoimport directory will be searched recursively,
-allowing you to organize the models into folders and subfolders in any
-way you wish.
+These options set the paths of various directories and files used by InvokeAI. Any user-defined paths should be absolute paths.
 
 #### Logging
 

docs/features/CONTROLNET.md

@@ -165,7 +165,7 @@ Additionally, each  section can be expanded with the "Show Advanced" button in o
 There are several ways to install IP-Adapter models with an existing InvokeAI installation:
 
 1. Through the command line interface launched from the invoke.sh / invoke.bat scripts, option [4] to download models.
-2. Through the Model Manager UI with models from the *Tools* section of [www.models.invoke.ai](https://www.models.invoke.ai). To do this, copy the repo ID from the desired model page, and paste it in the Add Model field of the model manager. **Note** Both the IP-Adapter and the Image Encoder must be installed for IP-Adapter to work. For example, the [SD 1.5 IP-Adapter](https://models.invoke.ai/InvokeAI/ip_adapter_plus_sd15) and [SD1.5 Image Encoder](https://models.invoke.ai/InvokeAI/ip_adapter_sd_image_encoder) must be installed to use IP-Adapter with SD1.5 based models.  
+2. Through the Model Manager UI with models from the *Tools* section of [models.invoke.ai](https://models.invoke.ai). To do this, copy the repo ID from the desired model page, and paste it in the Add Model field of the model manager. **Note** Both the IP-Adapter and the Image Encoder must be installed for IP-Adapter to work. For example, the [SD 1.5 IP-Adapter](https://models.invoke.ai/InvokeAI/ip_adapter_plus_sd15) and [SD1.5 Image Encoder](https://models.invoke.ai/InvokeAI/ip_adapter_sd_image_encoder) must be installed to use IP-Adapter with SD1.5 based models.  
 3. **Advanced -- Not recommended ** Manually downloading the IP-Adapter and Image Encoder files - Image Encoder folders shouid be placed in the `models\any\clip_vision` folders. IP Adapter Model folders should be placed in the relevant `ip-adapter` folder of relevant base model folder of Invoke root directory. For example, for the SDXL IP-Adapter, files should be added to the `model/sdxl/ip_adapter/` folder. 
 
 #### Using IP-Adapter

docs/features/GALLERY.md

@@ -0,0 +1,92 @@
+---
+title: InvokeAI Gallery Panel
+---
+
+# :material-web: InvokeAI Gallery Panel
+
+## Quick guided walkthrough of the Gallery Panel's features
+
+The Gallery Panel is a fast way to review, find, and make use of images you've
+generated and loaded. The Gallery is divided into Boards. The Uncategorized board is always 
+present but you can create your own for better organization.
+
+![image](../assets/gallery/gallery.png)
+
+### Board Display and Settings
+
+At the very top of the Gallery Panel are the boards disclosure and settings buttons.
+
+![image](../assets/gallery/top_controls.png)
+
+The disclosure button shows the name of the currently selected board and allows you to show and hide the board thumbnails (shown in the image below).
+
+![image](../assets/gallery/board_thumbnails.png)
+
+The settings button opens a list of options.
+
+![image](../assets/gallery/board_settings.png)
+
+- ***Image Size*** this slider lets you control the size of the image previews (images of three different sizes).
+- ***Auto-Switch to New Images*** if you turn this on, whenever a new image is generated, it will automatically be loaded into the current image panel on the Text to Image tab and into the result panel on the [Image to Image](IMG2IMG.md) tab. This will happen invisibly if you are on any other tab when the image is generated.
+- ***Auto-Assign Board on Click*** whenever an image is generated or saved, it always gets put in a board. The board it gets put into is marked with AUTO (image of board marked). Turning on Auto-Assign Board on Click will make whichever board you last selected be the destination when you click Invoke. That means you can click Invoke, select a different board, and then click Invoke again and the two images will be put in two different boards. (bold)It's the board selected when Invoke is clicked that's used, not the board that's selected when the image is finished generating.(bold) Turning this off, enables the Auto-Add Board drop down which lets you set one specific board to always put generated images into. This also enables and disables the Auto-add to this Board menu item described below.
+- ***Always Show Image Size Badge*** this toggles whether to show image sizes for each image preview (show two images, one with sizes shown, one without)
+
+Below these two buttons, you'll see the Search Boards text entry area. You use this to search for specific boards by the name of the board.
+Next to it is the Add Board (+) button which lets you add new boards. Boards can be renamed by clicking on the name of the board under its thumbnail and typing in the new name.
+
+### Board Thumbnail Menu
+
+Each board has a context menu (ctrl+click / right-click).
+
+![image](../assets/gallery/thumbnail_menu.png)
+
+- ***Auto-add to this Board*** if you've disabled Auto-Assign Board on Click in the board settings, you can use this option to set this board to be where new images are put.
+- ***Download Board*** this will add all the images in the board into a zip file and provide a link to it in a notification (image of notification)
+- ***Delete Board*** this will delete the board
+> [!CAUTION]
+> This will delete all the images in the board and the board itself.
+
+### Board Contents
+
+Every board is organized by two tabs, Images and Assets.
+
+![image](../assets/gallery/board_tabs.png)
+
+Images are the Invoke-generated images that are placed into the board. Assets are images that you upload into Invoke to be used as an [Image Prompt](https://support.invoke.ai/support/solutions/articles/151000159340-using-the-image-prompt-adapter-ip-adapter-) or in the [Image to Image](IMG2IMG.md) tab.
+
+### Image Thumbnail Menu
+
+Every image generated by Invoke has its generation information stored as text inside the image file itself. This can be read directly by selecting the image and clicking on the Info button ![image](../assets/gallery/info_button.png) in any of the image result panels. 
+
+Each image also has a context menu (ctrl+click / right-click).
+
+![image](../assets/gallery/image_menu.png)
+
+ The options are (items marked with an * will not work with images that lack generation information):
+- ***Open in New Tab*** this will open the image alone in a new browser tab, separate from the Invoke interface.
+- ***Download Image*** this will trigger your browser to download the image.
+- ***Load Workflow **** this will load any workflow settings into the Workflow tab and automatically open it.
+- ***Remix Image **** this will load all of the image's generation information, (bold)excluding its Seed, into the left hand control panel
+- ***Use Prompt **** this will load only the image's text prompts into the left-hand control panel
+- ***Use Seed **** this will load only the image's Seed into the left-hand control panel
+- ***Use All **** this will load all of the image's generation information into the left-hand control panel
+- ***Send to Image to Image*** this will put the image into the left-hand panel in the Image to Image tab ana automatically open it
+- ***Send to Unified Canvas*** This will (bold)replace whatever is already present(bold) in the Unified Canvas tab with the image and automatically open the tab
+- ***Change Board*** this will oipen a small window that will let you move the image to a different board. This is the same as dragging the image to that board's thumbnail.
+- ***Star Image*** this will add the image to the board's list of starred images that are always kept at the top of the gallery. This is the same as clicking on the star on the top right-hand side of the image that appears when you hover over the image with the mouse
+- ***Delete Image*** this will delete the image from the board
+> [!CAUTION] 
+> This will delete the image entirely from Invoke.
+
+## Summary
+
+This walkthrough only covers the Gallery interface and Boards. Actually generating images is handled by [Prompts](PROMPTS.md), the [Image to Image](IMG2IMG.md) tab, and the [Unified Canvas](UNIFIED_CANVAS.md).
+
+## Acknowledgements
+
+A huge shout-out to the core team working to make the Web GUI a reality,
+including [psychedelicious](https://github.com/psychedelicious),
+[Kyle0654](https://github.com/Kyle0654) and
+[blessedcoolant](https://github.com/blessedcoolant).
+[hipsterusername](https://github.com/hipsterusername) was the team's unofficial
+cheerleader and added tooltips/docs.

docs/features/LORAS.md

@@ -20,10 +20,7 @@ are applied to generate imagery. LoRAs may be supplied with a
 simply apply their effect without being triggered.
 
 LoRAs are typically stored in .safetensors files, which are the most
-secure way to store and transmit these types of weights. You may
-install any number of `.safetensors` LoRA files simply by copying them
-into the `autoimport/lora` directory of the corresponding InvokeAI models
-directory (usually `invokeai` in your home directory).
+secure way to store and transmit these types of weights.
 
 To use these when generating, open the LoRA menu item in the options
 panel, select the LoRAs you want to apply and ensure that they have

docs/features/PROMPTS.md

@@ -108,40 +108,6 @@ Can be used with .and():
 Each will give you different results - try them out and see what you prefer!
 
 
-
-### Cross-Attention Control ('prompt2prompt')
-
-Sometimes an image you generate is almost right, and you just want to change one
-detail without affecting the rest. You could use a photo editor and inpainting
-to overpaint the area, but that's a pain. Here's where `prompt2prompt` comes in
-handy.
-
-Generate an image with a given prompt, record the seed of the image, and then
-use the `prompt2prompt` syntax to substitute words in the original prompt for
-words in a new prompt. This works for `img2img` as well.
-
-For example, consider the prompt `a cat.swap(dog) playing with a ball in the forest`. Normally, because the words interact with each other when doing a stable diffusion image generation, these two prompts would generate different compositions:
-  - `a cat playing with a ball in the forest`
-  - `a dog playing with a ball in the forest`
-
-| `a cat playing with a ball in the forest` | `a dog playing with a ball in the forest` |
-| --- | --- |
-| img | img |
-
-
-      - For multiple word swaps, use parentheses: `a (fluffy cat).swap(barking dog) playing with a ball in the forest`.
-      - To swap a comma, use quotes: `a ("fluffy, grey cat").swap("big, barking dog") playing with a ball in the forest`.
-- Supports options `t_start` and `t_end` (each 0-1) loosely corresponding to (bloc97's)[(https://github.com/bloc97/CrossAttentionControl)] `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to
-  intuitively understand. `t_start` and `t_end` are used to control on which steps cross-attention control should run. With the default values `t_start=0` and `t_end=1`, cross-attention control is active on every step of image generation. Other values can be used to turn cross-attention control off for part of the image generation process.
-    - For example, if doing a diffusion with 10 steps for the prompt is `a cat.swap(dog, t_start=0.3, t_end=1.0) playing with a ball in the forest`, the first 3 steps will be run as `a cat playing with a ball in the forest`, while the last 7 steps will run as `a dog playing with a ball in the forest`, but the pixels that represent `dog` will be locked to the pixels that would have represented `cat` if the `cat` prompt had been used instead.
-    - Conversely, for `a cat.swap(dog, t_start=0, t_end=0.7) playing with a ball in the forest`, the first 7 steps will run as `a dog playing with a ball in the forest` with the pixels that represent `dog` locked to the same pixels that would have represented `cat` if the `cat` prompt was being used instead. The final 3 steps will just run `a cat playing with a ball in the forest`.
-    > For img2img, the step sequence does not start at 0 but instead at `(1.0-strength)` - so if the img2img `strength` is `0.7`, `t_start` and `t_end` must both be greater than `0.3` (`1.0-0.7`) to have any effect.
-
-Prompt2prompt `.swap()` is not compatible with xformers, which will be temporarily disabled when doing a `.swap()` - so you should expect to use more VRAM and run slower that with xformers enabled.
-
-The `prompt2prompt` code is based off
-[bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
-
 ### Escaping parentheses and speech marks 
 
 If the model you are using has parentheses () or speech marks "" as part of its

docs/features/TRAINING.md

@@ -4,278 +4,6 @@ title: Training
 
 # :material-file-document: Training
 
-# Textual Inversion Training
-## **Personalizing Text-to-Image Generation**
+Invoke Training has moved to its own repository, with a dedicated UI for accessing common scripts like Textual Inversion and LoRA training.
 
-You may personalize the generated images to provide your own styles or objects
-by training a new LDM checkpoint and introducing a new vocabulary to the fixed
-model as a (.pt) embeddings file. Alternatively, you may use or train
-HuggingFace Concepts embeddings files (.bin) from
-<https://huggingface.co/sd-concepts-library> and its associated
-notebooks.
-
-## **Hardware and Software Requirements**
-
-You will need a GPU to perform training in a reasonable length of
-time, and at least 12 GB of VRAM. We recommend using the [`xformers`
-library](../installation/070_INSTALL_XFORMERS.md) to accelerate the
-training process further. During training, about ~8 GB is temporarily
-needed in order to store intermediate models, checkpoints and logs.
-
-## **Preparing for Training**
-
-To train, prepare a folder that contains 3-5 images that illustrate
-the object or concept. It is good to provide a variety of examples or
-poses to avoid overtraining the system. Format these images as PNG
-(preferred) or JPG. You do not need to resize or crop the images in
-advance, but for more control you may wish to do so.
-
-Place the training images in a directory on the machine InvokeAI runs
-on. We recommend placing them in a subdirectory of the
-`text-inversion-training-data` folder located in the InvokeAI root
-directory, ordinarily `~/invokeai` (Linux/Mac), or
-`C:\Users\your_name\invokeai` (Windows). For example, to create an
-embedding for the "psychedelic" style, you'd place the training images
-into the directory
-`~invokeai/text-inversion-training-data/psychedelic`.
-
-## **Launching Training Using the Console Front End**
-
-InvokeAI 2.3 and higher comes with a text console-based training front
-end. From within the `invoke.sh`/`invoke.bat` Invoke launcher script,
-start training tool selecting choice (3):
-
-```sh
-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"
-```
-
-Alternatively, you can select option (8) or from the command line, with the InvokeAI virtual environment active,
-you can then launch the front end with the command `invokeai-ti --gui`.
-
-This will launch a text-based front end that will look like this:
-
-<figure markdown>
-![ti-frontend](../assets/textual-inversion/ti-frontend.png)
-</figure>
-
-The interface is keyboard-based. Move from field to field using
-control-N (^N) to move to the next field and control-P (^P) to the
-previous one. <Tab> and <shift-TAB> work as well. Once a field is
-active, use the cursor keys. In a checkbox group, use the up and down
-cursor keys to move from choice to choice, and <space> to select a
-choice. In a scrollbar, use the left and right cursor keys to increase
-and decrease the value of the scroll. In textfields, type the desired
-values.
-
-The number of parameters may look intimidating, but in most cases the
-predefined defaults work fine. The red circled fields in the above
-illustration are the ones you will adjust most frequently.
-
-### Model Name
-
-This will list all the diffusers models that are currently
-installed. Select the one you wish to use as the basis for your
-embedding. Be aware that if you use a SD-1.X-based model for your
-training, you will only be able to use this embedding with other
-SD-1.X-based models. Similarly, if you train on SD-2.X, you will only
-be able to use the embeddings with models based on SD-2.X.
-
-### Trigger Term
-
-This is the prompt term you will use to trigger the embedding. Type a
-single word or phrase you wish to use as the trigger, example
-"psychedelic" (without angle brackets). Within InvokeAI, you will then
-be able to activate the trigger using the syntax `<psychedelic>`.
-
-### Initializer
-
-This is a single character that is used internally during the training
-process as a placeholder for the trigger term. It defaults to "*" and
-can usually be left alone.
-
-### Resume from last saved checkpoint
-
-As training proceeds, textual inversion will write a series of
-intermediate files that can be used to resume training from where it
-was left off in the case of an interruption. This checkbox will be
-automatically selected if you provide a previously used trigger term
-and at least one checkpoint file is found on disk.
-
-Note that as of 20 January 2023, resume does not seem to be working
-properly due to an issue with the upstream code.
-
-### Data Training Directory
-
-This is the location of the images to be used for training. When you
-select a trigger term like "my-trigger", the frontend will prepopulate
-this field with `~/invokeai/text-inversion-training-data/my-trigger`,
-but you can change the path to wherever you want.
-
-### Output Destination Directory
-
-This is the location of the logs, checkpoint files, and embedding
-files created during training. When you select a trigger term like
-"my-trigger", the frontend will prepopulate this field with
-`~/invokeai/text-inversion-output/my-trigger`, but you can change the
-path to wherever you want.
-
-### Image resolution
-
-The images in the training directory will be automatically scaled to
-the value you use here. For best results, you will want to use the
-same default resolution of the underlying model (512 pixels for
-SD-1.5, 768 for the larger version of SD-2.1).
-
-### Center crop images
-
-If this is selected, your images will be center cropped to make them
-square before resizing them to the desired resolution. Center cropping
-can indiscriminately cut off the top of subjects' heads for portrait
-aspect images, so if you have images like this, you may wish to use a
-photoeditor to manually crop them to a square aspect ratio.
-
-### Mixed precision
-
-Select the floating point precision for the embedding. "no" will
-result in a full 32-bit precision, "fp16" will provide 16-bit
-precision, and "bf16" will provide mixed precision (only available
-when XFormers is used).
-
-### Max training steps
-
-How many steps the training will take before the model converges. Most
-training sets will converge with 2000-3000 steps.
-
-### Batch size
-
-This adjusts how many training images are processed simultaneously in
-each step. Higher values will cause the training process to run more
-quickly, but use more memory. The default size will run with GPUs with
-as little as 12 GB.
-
-### Learning rate
-
-The rate at which the system adjusts its internal weights during
-training. Higher values risk overtraining (getting the same image each
-time), and lower values will take more steps to train a good
-model. The default of 0.0005 is conservative; you may wish to increase
-it to 0.005 to speed up training.
-
-### Scale learning rate by number of GPUs, steps and batch size
-
-If this is selected (the default) the system will adjust the provided
-learning rate to improve performance.
-
-### Use xformers acceleration
-
-This will activate XFormers memory-efficient attention. You need to
-have XFormers installed for this to have an effect.
-
-### Learning rate scheduler
-
-This adjusts how the learning rate changes over the course of
-training. The default "constant" means to use a constant learning rate
-for the entire training session. The other values scale the learning
-rate according to various formulas.
-
-Only "constant" is supported by the XFormers library.
-
-### Gradient accumulation steps
-
-This is a parameter that allows you to use bigger batch sizes than
-your GPU's VRAM would ordinarily accommodate, at the cost of some
-performance.
-
-### Warmup steps
-
-If "constant_with_warmup" is selected in the learning rate scheduler,
-then this provides the number of warmup steps. Warmup steps have a
-very low learning rate, and are one way of preventing early
-overtraining.
-
-## The training run
-
-Start the training run by advancing to the OK button (bottom right)
-and pressing <enter>. A series of progress messages will be displayed
-as the training process proceeds. This may take an hour or two,
-depending on settings and the speed of your system. Various log and
-checkpoint files will be written into the output directory (ordinarily
-`~/invokeai/text-inversion-output/my-model/`)
-
-At the end of successful training, the system will copy the file
-`learned_embeds.bin` into the InvokeAI root directory's `embeddings`
-directory, using a subdirectory named after the trigger token. For
-example, if the trigger token was `psychedelic`, then look for the
-embeddings file in
-`~/invokeai/embeddings/psychedelic/learned_embeds.bin`
-
-You may now launch InvokeAI and try out a prompt that uses the trigger
-term. For example `a plate of banana sushi in <psychedelic> style`.
-
-## **Training with the Command-Line Script**
-
-Training can also be done using a traditional command-line script. It
-can be launched from within the "developer's console", or from the
-command line after activating InvokeAI's virtual environment.
-
-It accepts a large number of arguments, which can be summarized by
-passing the `--help` argument:
-
-```sh
-invokeai-ti --help
-```
-
-Typical usage is shown here:
-```sh
-invokeai-ti \
-       --model=stable-diffusion-1.5 \
-       --resolution=512 \
-       --learnable_property=style \
-       --initializer_token='*' \
-       --placeholder_token='<psychedelic>' \
-       --train_data_dir=/home/lstein/invokeai/training-data/psychedelic \
-       --output_dir=/home/lstein/invokeai/text-inversion-training/psychedelic \
-       --scale_lr \
-       --train_batch_size=8 \
-       --gradient_accumulation_steps=4 \
-       --max_train_steps=3000 \
-       --learning_rate=0.0005 \
-       --resume_from_checkpoint=latest \
-       --lr_scheduler=constant \
-       --mixed_precision=fp16 \
-       --only_save_embeds
-```
-
-## Troubleshooting
-
-### `Cannot load embedding for <trigger>. It was trained on a model with token dimension 1024, but the current model has token dimension 768`
-
-Messages like this indicate you trained the embedding on a different base model than the currently selected one.
-
-For example, in the error above, the training was done on SD2.1 (768x768) but it was used on SD1.5 (512x512).
-
-## Reading
-
-For more information on textual inversion, please see the following
-resources:
-
-* The [textual inversion repository](https://github.com/rinongal/textual_inversion) and
-  associated paper for details and limitations.
-* [HuggingFace's textual inversion training
-  page](https://huggingface.co/docs/diffusers/training/text_inversion)
-* [HuggingFace example script
-  documentation](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion)
-  (Note that this script is similar to, but not identical, to
-  `textual_inversion`, but produces embed files that are completely compatible.
-
----
-
-copyright (c) 2023, Lincoln Stein and the InvokeAI Development Team
+You can find more by visiting the repo at https://github.com/invoke-ai/invoke-training

docs/features/WEB.md

@@ -54,7 +54,7 @@ main sections:
    of buttons at the top lets you modify and manipulate the image in
    various ways.
 
-3. A **gallery** section on the left that contains a history of the images you
+3. A **gallery** section on the right that contains a history of the images you
    have generated. These images are read and written to the directory specified
    in the `INVOKEAIROOT/invokeai.yaml` initialization file, usually a directory
    named `outputs` in `INVOKEAIROOT`.

docs/help/FAQ.md

@@ -1,43 +1,232 @@
-# FAQs
+# FAQ
 
-**Where do I get started? How can I install Invoke?**
+!!! info "How to Reinstall"
 
-- You can download the latest installers [here](https://github.com/invoke-ai/InvokeAI/releases) - Note that any releases marked as *pre-release* are in a beta state. You may experience some issues, but we appreciate your help testing those! For stable/reliable installations, please install the **[Latest Release](https://github.com/invoke-ai/InvokeAI/releases/latest)**
+    Many issues can be resolved by re-installing the application. You won't lose any data by re-installing. We suggest downloading the [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest) and using it to re-install the application. Consult the [installer guide](../installation/010_INSTALL_AUTOMATED.md) for more information.
 
-**How can I download models? Can I use models I already have downloaded?**
+    When you run the installer, you'll have an option to select the version to install. If you aren't ready to upgrade, you choose the current version to fix a broken install.
 
-- Models can be downloaded through the model manager, or through option [4] in the invoke.bat/invoke.sh launcher script. To download a model through the Model Manager, use the HuggingFace Repo ID by pressing the “Copy” button next to the repository name. Alternatively, to download a model from CivitAi, use the download link in the Model Manager.
-- Models that are already downloaded can be used by creating a symlink to the model location in the `autoimport` folder or by using the Model Manger’s “Scan for Models” function.
+If the troubleshooting steps on this page don't get you up and running, please either [create an issue] or hop on [discord] for help.
 
-**My images are taking a long time to generate. How can I speed up generation?** 
+## How to Install
 
-- A common solution is to reduce the size of your RAM & VRAM cache to 0.25. This ensures your system has enough memory to generate images.
-- Additionally, check the [hardware requirements](https://invoke-ai.github.io/InvokeAI/#hardware-requirements) to ensure that your system is capable of generating images.
-- Lastly, double check your generations are happening on your GPU (if you have one). InvokeAI will log what is being used for generation upon startup. 
+You can download the latest installers [here](https://github.com/invoke-ai/InvokeAI/releases).
 
-**I’ve installed Python on Windows but the installer says it can’t find it?**
+Note that any releases marked as _pre-release_ are in a beta state. You may experience some issues, but we appreciate your help testing those! For stable/reliable installations, please install the [latest release].
 
-- Then ensure that you checked  **'Add python.exe to PATH'** when installing Python. This can be found at the bottom of the Python Installer window. If you already have Python installed, this can be done with the modify / repair feature of the installer.
+## Downloading models and using existing models
 
-**I’ve installed everything successfully but I still get an error about Triton when starting Invoke?**
+The Model Manager tab in the UI provides a few ways to install models, including using your already-downloaded models. You'll see a popup directing you there on first startup. For more information, see the [model install docs].
 
-- This can be safely ignored. InvokeAI doesn't use Triton, but if you are on Linux and wish to dismiss the error, you can install Triton.
+## Missing models after updating to v4
 
-**I updated to 3.4.0 and now xFormers can’t load C++/CUDA?**
+If you find some models are missing after updating to v4, it's likely they weren't correctly registered before the update and didn't get picked up in the migration.
 
-- An issue occurred with your PyTorch update. Follow these steps to fix :
-    1. Launch your invoke.bat / invoke.sh and select the option to open the developer console
-    2. Run:`pip install ".[xformers]" --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121`
-    - If you run into an error with `typing_extensions`, re-open the developer console and run:  `pip install -U typing-extensions`
+You can use the `Scan Folder` tab in the Model Manager UI to fix this. The models will either be in the old, now-unused `autoimport` folder, or your `models` folder.
 
-**It says my pip is out of date - is that why my install isn't working?**
-- An out of date won't cause an installation to fail. The cause of the error can likely be found above the message that says pip is out of date.
-- If you saw that warning but the install went well, don't worry about it (but you can update pip afterwards if you'd like).   
+- Find and copy your install's old `autoimport` folder path, install the main install folder.
+- Go to the Model Manager and click `Scan Folder`.
+- Paste the path and scan.
+- IMPORTANT: Uncheck `Inplace install`.
+- Click `Install All` to install all found models, or just install the models you want.
+
+Next, find and copy your install's `models` folder path (this could be your custom models folder path, or the `models` folder inside the main install folder).
+
+Follow the same steps to scan and import the missing models.
+
+## Slow generation
+
+- Check the [system requirements] to ensure that your system is capable of generating images.
+- Check the `ram` setting in `invokeai.yaml`. This setting tells Invoke how much of your system RAM can be used to cache models. Having this too high or too low can slow things down. That said, it's generally safest to not set this at all and instead let Invoke manage it.
+- Check the `vram` setting in `invokeai.yaml`. This setting tells Invoke how much of your GPU VRAM can be used to cache models. Counter-intuitively, if this setting is too high, Invoke will need to do a lot of shuffling of models as it juggles the VRAM cache and the currently-loaded model. The default value of 0.25 is generally works well for GPUs without 16GB or more VRAM. Even on a 24GB card, the default works well.
+- Check that your generations are happening on your GPU (if you have one). InvokeAI will log what is being used for generation upon startup. If your GPU isn't used, re-install to ensure the correct versions of torch get installed.
+- If you are on Windows, you may have exceeded your GPU's VRAM capacity and are using slower [shared GPU memory](#shared-gpu-memory-windows). There's a guide to opt out of this behaviour in the linked FAQ entry.
+
+## Shared GPU Memory (Windows)
+
+!!! tip "Nvidia GPUs with driver 536.40"
+
+    This only applies to current Nvidia cards with driver 536.40 or later, released in June 2023.
+
+When the GPU doesn't have enough VRAM for a task, Windows is able to allocate some of its CPU RAM to the GPU. This is much slower than VRAM, but it does allow the system to generate when it otherwise might no have enough VRAM.
+
+When shared GPU memory is used, generation slows down dramatically - but at least it doesn't crash.
+
+If you'd like to opt out of this behavior and instead get an error when you exceed your GPU's VRAM, follow [this guide from Nvidia](https://nvidia.custhelp.com/app/answers/detail/a_id/5490).
+
+Here's how to get the python path required in the linked guide:
+
+- Run `invoke.bat`.
+- Select option 2 for developer console.
+- At least one python path will be printed. Copy the path that includes your invoke installation directory (typically the first).
+
+## Installer cannot find python (Windows)
+
+Ensure that you checked **Add python.exe to PATH** when installing Python. This can be found at the bottom of the Python Installer window. If you already have Python installed, you can re-run the python installer, choose the Modify option and check the box.
+
+## Triton error on startup
+
+This can be safely ignored. InvokeAI doesn't use Triton, but if you are on Linux and wish to dismiss the error, you can install Triton.
+
+## Updated to 3.4.0 and xformers can’t load C++/CUDA
+
+An issue occurred with your PyTorch update. Follow these steps to fix :
+
+1. Launch your invoke.bat / invoke.sh and select the option to open the developer console
+2. Run:`pip install ".[xformers]" --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121`
+   - If you run into an error with `typing_extensions`, re-open the developer console and run: `pip install -U typing-extensions`
+
+Note that v3.4.0 is an old, unsupported version. Please upgrade to the [latest release].
+
+## Install failed and says `pip` is out of date
+
+An out of date `pip` typically won't cause an installation to fail. The cause of the error can likely be found above the message that says `pip` is out of date.
+
+If you saw that warning but the install went well, don't worry about it (but you can update `pip` afterwards if you'd like).
+
+## Replicate image found online
 
-**How can I generate the exact same that I found on the internet?**
 Most example images with prompts that you'll find on the internet have been generated using different software, so you can't expect to get identical results. In order to reproduce an image, you need to replicate the exact settings and processing steps, including (but not limited to) the model, the positive and negative prompts, the seed, the sampler, the exact image size, any upscaling steps, etc.
 
+## OSErrors on Windows while installing dependencies
 
-**Where can I get more help?** 
+During a zip file installation or an update, installation stops with an error like this:
 
-- Create an issue on [GitHub](https://github.com/invoke-ai/InvokeAI/issues) or post in the [#help channel](https://discord.com/channels/1020123559063990373/1149510134058471514) of the InvokeAI Discord
+![broken-dependency-screenshot](../assets/troubleshooting/broken-dependency.png){:width="800px"}
+
+To resolve this, re-install the application as described above.
+
+## HuggingFace install failed due to invalid access token
+
+Some HuggingFace models require you to authenticate using an [access token].
+
+Invoke doesn't manage this token for you, but it's easy to set it up:
+
+- Follow the instructions in the link above to create an access token. Copy it.
+- Run the launcher script.
+- Select option 2 (developer console).
+- Paste the following command:
+
+  ```sh
+  python -c "import huggingface_hub; huggingface_hub.login()"
+  ```
+
+- Paste your access token when prompted and press Enter. You won't see anything when you paste it.
+- Type `n` if prompted about git credentials.
+
+If you get an error, try the command again - maybe the token didn't paste correctly.
+
+Once your token is set, start Invoke and try downloading the model again. The installer will automatically use the access token.
+
+If the install still fails, you may not have access to the model.
+
+## Stable Diffusion XL generation fails after trying to load UNet
+
+InvokeAI is working in other respects, but when trying to generate
+images with Stable Diffusion XL you get a "Server Error". The text log
+in the launch window contains this log line above several more lines of
+error messages:
+
+`INFO --> Loading model:D:\LONG\PATH\TO\MODEL, type sdxl:main:unet`
+
+This failure mode occurs when there is a network glitch during
+downloading the very large SDXL model.
+
+To address this, first go to the Model Manager and delete the
+Stable-Diffusion-XL-base-1.X model. Then, click the HuggingFace tab,
+paste the Repo ID stabilityai/stable-diffusion-xl-base-1.0 and install
+the model.
+
+## Package dependency conflicts during installation or update
+
+If you have previously installed InvokeAI or another Stable Diffusion
+package, the installer may occasionally pick up outdated libraries and
+either the installer or `invoke` will fail with complaints about
+library conflicts.
+
+To resolve this, re-install the application as described above.
+
+## Invalid configuration file
+
+Everything seems to install ok, you get a `ValidationError` when starting up the app.
+
+This is caused by an invalid setting in the `invokeai.yaml` configuration file. The error message should tell you what is wrong.
+
+Check the [configuration docs] for more detail about the settings and how to specify them.
+
+## Out of Memory Issues
+
+The models are large, VRAM is expensive, and you may find yourself
+faced with Out of Memory errors when generating images. Here are some
+tips to reduce the problem:
+
+!!! info "Optimizing for GPU VRAM"
+
+    === "4GB VRAM GPU"
+
+        This should be adequate for 512x512 pixel images using Stable Diffusion 1.5
+        and derived models, provided that you do not use the NSFW checker. It won't be loaded unless you go into the UI settings and turn it on.
+
+        If you are on a CUDA-enabled GPU, we will automatically use xformers or torch-sdp to reduce VRAM requirements, though you can explicitly configure this. See the [configuration docs].
+
+    === "6GB VRAM GPU"
+
+        This is a border case. Using the SD 1.5 series you should be able to
+        generate images up to 640x640 with the NSFW checker enabled, and up to
+        1024x1024 with it disabled.
+
+        If you run into persistent memory issues there are a series of
+        environment variables that you can set before launching InvokeAI that
+        alter how the PyTorch machine learning library manages memory. See
+        <https://pytorch.org/docs/stable/notes/cuda.html#memory-management> for
+        a list of these tweaks.
+
+    === "12GB VRAM GPU"
+
+        This should be sufficient to generate larger images up to about 1280x1280.
+
+## Memory Leak (Linux)
+
+If you notice a memory leak, it could be caused to memory fragmentation as models are loaded and/or moved from CPU to GPU.
+
+A workaround is to tune memory allocation with an environment variable:
+
+```bash
+# Force blocks >1MB to be allocated with `mmap` so that they are released to the system immediately when they are freed.
+MALLOC_MMAP_THRESHOLD_=1048576
+```
+
+!!! warning "Speed vs Memory Tradeoff"
+
+    Your generations may be slower overall when setting this environment variable.
+
+!!! info "Possibly dependent on `libc` implementation"
+
+    It's not known if this issue occurs with other `libc` implementations such as `musl`.
+
+    If you encounter this issue and your system uses a different implementation, please try this environment variable and let us know if it fixes the issue.
+
+<h3>Detailed Discussion</h3>
+
+Python (and PyTorch) relies on the memory allocator from the C Standard Library (`libc`). On linux, with the GNU C Standard Library implementation (`glibc`), our memory access patterns have been observed to cause severe memory fragmentation.
+
+This fragmentation results in large amounts of memory that has been freed but can't be released back to the OS. Loading models from disk and moving them between CPU/CUDA seem to be the operations that contribute most to the fragmentation.
+
+This memory fragmentation issue can result in OOM crashes during frequent model switching, even if `ram` (the max RAM cache size) is set to a reasonable value (e.g. a OOM crash with `ram=16` on a system with 32GB of RAM).
+
+This problem may also exist on other OSes, and other `libc` implementations. But, at the time of writing, it has only been investigated on linux with `glibc`.
+
+To better understand how the `glibc` memory allocator works, see these references:
+
+- Basics: <https://www.gnu.org/software/libc/manual/html_node/The-GNU-Allocator.html>
+- Details: <https://sourceware.org/glibc/wiki/MallocInternals>
+
+Note the differences between memory allocated as chunks in an arena vs. memory allocated with `mmap`. Under `glibc`'s default configuration, most model tensors get allocated as chunks in an arena making them vulnerable to the problem of fragmentation.
+
+[model install docs]: ../installation/050_INSTALLING_MODELS.md
+[system requirements]: ../installation/INSTALL_REQUIREMENTS.md
+[latest release]: https://github.com/invoke-ai/InvokeAI/releases/latest
+[create an issue]: https://github.com/invoke-ai/InvokeAI/issues
+[discord]: https://discord.gg/ZmtBAhwWhy
+[configuration docs]: ../features/CONFIGURATION.md
+[access token]: https://huggingface.co/docs/hub/security-tokens#how-to-manage-user-access-tokens

docs/help/deprecated/TROUBLESHOOT.md

@@ -1,128 +0,0 @@
----
-title: F.A.Q.
----
-
-# :material-frequently-asked-questions: F.A.Q.
-
-## **Frequently-Asked-Questions**
-
-Here are a few common installation problems and their solutions. Often these are
-caused by incomplete installations or crashes during the install process.
-
----
-
-### During `conda env create`, conda hangs indefinitely
-
-If it is because of the last PIP step (usually stuck in the Git Clone step, you
-can check the detailed log by this method):
-
-```bash
-export PIP_LOG="/tmp/pip_log.txt"
-touch ${PIP_LOG}
-tail -f ${PIP_LOG} &
-conda env create -f environment-mac.yaml --debug --verbose
-killall tail
-rm ${PIP_LOG}
-```
-
-**SOLUTION**
-
-Conda sometimes gets stuck at the last PIP step, in which several git
-repositories are cloned and built.
-
-Enter the stable-diffusion directory and completely remove the `src` directory
-and all its contents. The safest way to do this is to enter the stable-diffusion
-directory and give the command `git clean -f`. If this still doesn't fix the
-problem, try "conda clean -all" and then restart at the `conda env create` step.
-
-To further understand the problem to checking the install lot using this method:
-
-```bash
-export PIP_LOG="/tmp/pip_log.txt"
-touch ${PIP_LOG}
-tail -f ${PIP_LOG} &
-conda env create -f environment-mac.yaml --debug --verbose
-killall tail
-rm ${PIP_LOG}
-```
-
----
-
-### `invoke.py` crashes with the complaint that it can't find `ldm.simplet2i.py`
-
-Or it complains that function is being passed incorrect parameters.
-
-**SOLUTION**
-
-Reinstall the stable diffusion modules. Enter the `stable-diffusion` directory
-and give the command `pip install -e .`
-
----
-
-### Missing modules
-
-`invoke.py` dies, complaining of various missing modules, none of which starts
-with `ldm`.
-
-**SOLUTION**
-
-From within the `InvokeAI` directory, run `conda env update` This is also
-frequently the solution to complaints about an unknown function in a module.
-
----
-
-### How can I try new features
-
-There's a feature or bugfix in the Stable Diffusion GitHub that you want to try
-out.
-
-**SOLUTIONS**
-
-#### **Main Branch**
-
-If the fix/feature is on the `main` branch, enter the stable-diffusion directory
-and do a `git pull`.
-
-Usually this will be sufficient, but if you start to see errors about missing or
-incorrect modules, use the command `pip install -e .` and/or `conda env update`
-(These commands won't break anything.)
-
-`pip install -e .` and/or `conda env update -f environment.yaml`
-
-(These commands won't break anything.)
-
-#### **Sub Branch**
-
-If the feature/fix is on a branch (e.g. "_foo-bugfix_"), the recipe is similar,
-but do a `git pull <name of branch>`.
-
-#### **Not Committed**
-
-If the feature/fix is in a pull request that has not yet been made part of the
-main branch or a feature/bugfix branch, then from the page for the desired pull
-request, look for the line at the top that reads "_xxxx wants to merge xx
-commits into lstein:main from YYYYYY_". Copy the URL in YYYY. It should have the
-format
-
-`https://github.com/<name of contributor>/stable-diffusion/tree/<name of branch>`
-
-Then **go to the directory above stable-diffusion** and rename the directory to
-"_stable-diffusion.lstein_", "_stable-diffusion.old_", or anything else. You can
-then git clone the branch that contains the pull request:
-
-`git clone https://github.com/<name of contributor>/stable-diffusion/tree/<name of branch>`
-
-You will need to go through the install procedure again, but it should be fast
-because all the dependencies are already loaded.
-
----
-
-### CUDA out of memory
-
-Image generation crashed with CUDA out of memory error after successful
-sampling.
-
-**SOLUTION**
-
-Try to run script with option `--free_gpu_mem` This will free memory before
-image decoding step.

docs/help/diffusion.md

@@ -20,7 +20,7 @@ When you generate an image using text-to-image, multiple steps occur in latent s
 4. The VAE decodes the final latent image from latent space into image space.
 
 Image-to-image is a similar process, with only step 1 being different:
-1. The input image is encoded from image space into latent space by the VAE. Noise is then added to the input latent image. Denoising Strength dictates how may noise steps are added, and the amount of noise added at each step. A Denoising Strength of 0 means there are 0 steps and no noise added, resulting in an unchanged image, while a Denoising Strength of 1 results in the image being completely replaced with noise and a full set of denoising steps are performance. The process is then the same as steps 2-4 in the text-to-image process. 
+1. The input image is encoded from image space into latent space by the VAE. Noise is then added to the input latent image. Denoising Strength dictates how many noise steps are added, and the amount of noise added at each step. A Denoising Strength of 0 means there are 0 steps and no noise added, resulting in an unchanged image, while a Denoising Strength of 1 results in the image being completely replaced with noise and a full set of denoising steps are performance. The process is then the same as steps 2-4 in the text-to-image process. 
 
 Furthermore, a model provides the CLIP prompt tokenizer, the VAE, and a U-Net (where noise prediction occurs given a prompt and initial noise tensor).
 

docs/index.md

@@ -153,8 +153,7 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 ## :material-target: Troubleshooting
 
 Please check out our **[:material-frequently-asked-questions:
-Troubleshooting
-Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)** to
+FAQ](help/FAQ/)** to
 get solutions for common installation problems and other issues.
 
 ## :octicons-repo-push-24: Contributing

docs/installation/010_INSTALL_AUTOMATED.md

@@ -1,424 +1,107 @@
----
-title: Installing with the Automated Installer
----
+# Automatic Install & Updates
 
-# InvokeAI Automated Installation
+**The same packaged installer file can be used for both new installs and updates.**
+Using the installer for updates will leave everything you've added since installation, and just update the core libraries used to run Invoke.
+Simply use the same path you installed to originally.
 
-## Introduction
+Both release and pre-release versions can be installed using the installer. It also supports install through a wheel if needed.
 
-The automated installer is a Python script that automates the steps
-needed to install and run InvokeAI on a stock computer running recent
-versions of Linux, MacOS or Windows. It will leave you with a version
-that runs a stable version of InvokeAI with the option to upgrade to
-experimental versions later.
+Be sure to review the [installation requirements] and ensure your system has everything it needs to install Invoke.
 
-## Walk through
+## Getting the Latest Installer
 
-1.  <a name="hardware_requirements">**Hardware Requirements**: </a>Make sure that your system meets the [hardware
-    requirements](../index.md#hardware-requirements) and has the
-    appropriate GPU drivers installed. For a system with an NVIDIA
-    card installed, you will need to install the CUDA driver, while
-    AMD-based cards require the ROCm driver. In most cases, if you've
-    already used the system for gaming or other graphics-intensive
-    tasks, the appropriate drivers will already be installed. If
-    unsure, check the [GPU Driver Guide](030_INSTALL_CUDA_AND_ROCM.md)
+Download the `InvokeAI-installer-vX.Y.Z.zip` file from the [latest release] page. It is at the bottom of the page, under **Assets**.
 
-    !!! info "Required Space"
+After unzipping the installer, you should have a `InvokeAI-Installer` folder with some files inside, including `install.bat` and `install.sh`.
 
-        Installation requires roughly 18G of free disk space to load
-        the libraries and recommended model weights files.
+## Running the Installer
 
-        Regardless of your destination disk, your *system drive*
-        (`C:\` on Windows, `/` on macOS/Linux) requires at least 6GB
-        of free disk space to download and cache python
-        dependencies.
+!!! tip
 
-	NOTE for Linux users: if your temporary directory is mounted
-        as a `tmpfs`, ensure it has sufficient space.
+    Windows users should first double-click the `WinLongPathsEnabled.reg` file to prevent a failed installation due to long file paths.
 
-2.  <a name="software_requirements">**Software Requirements**: </a>Check that your system has an up-to-date Python installed. To do
-    this, open up a command-line window ("Terminal" on Linux and
-    Macintosh, "Command" or "Powershell" on Windows) and type `python
-    --version`. If Python is installed, it will print out the version
-    number. If it is version `3.10.*` or `3.11.*` you meet
-    requirements.
+Double-click the install script:
 
-    !!! warning "What to do if you have an unsupported version"
+=== "Windows"
 
-        Go to [Python Downloads](https://www.python.org/downloads/)
-        and download the appropriate installer package for your
-        platform. We recommend [Version
-        3.10.12](https://www.python.org/downloads/release/python-3109/),
-        which has been extensively tested with InvokeAI.
-
-    _Please select your platform in the section below for platform-specific
-    setup requirements._
-
-    === "Windows"
-        During the Python configuration process, look out for a
-        checkbox to add Python to your PATH and select it. If the
-        install script complains that it can't find python, then open
-        the Python installer again and choose "Modify" existing
-        installation.
-
-        Installation requires an up to date version of the Microsoft
-        Visual C libraries. Please install the 2015-2022 libraries
-        available here:
-        https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170
-
-        Please double-click on the file `WinLongPathsEnabled.reg` and
-        accept the dialog box that asks you if you wish to modify your registry.
-        This activates long filename support on your system and will prevent
-        mysterious errors during installation.
-
-    === "Linux"
-         To install an appropriate version of Python on Ubuntu 22.04
-         and higher, run the following:
-
-         ```
-         sudo apt update
-         sudo apt install -y python3 python3-pip python3-venv
-         sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
-         ```
-
-         On Ubuntu 20.04, the process is slightly different:
-
-         ```
-         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 update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
-         ```
-
-         Both `python` and `python3` commands are now pointing at
-         Python3.10. You can still access older versions of Python by
-         calling `python2`, `python3.8`, etc.
-
-         Linux systems require a couple of additional graphics
-         libraries to be installed for proper functioning of
-         `python3-opencv`. Please run the following:
-
-         `sudo apt update && sudo apt install -y libglib2.0-0 libgl1-mesa-glx`
-
-    === "Mac"
-
-        After installing Python, you may need to run the
-        following command from the Terminal in order to install the Web
-        certificates needed to download model data from https sites. If
-        you see lots of CERTIFICATE ERRORS during the last part of the
-        install, this is the problem, and you can fix it with this command:
-
-            `/Applications/Python\ 3.10/Install\ Certificates.command`
-
-        You may need to install the Xcode command line tools. These
-        are a set of tools that are needed to run certain applications in a
-        Terminal, including InvokeAI. This package is provided
-        directly by Apple. To install, open a terminal window and run `xcode-select --install`. You will get a macOS system popup guiding you through the
-        install. If you already have them installed, you will instead see some
-        output in the Terminal advising you that the tools are already installed. More information can be found at [FreeCode Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
-
-3.  **Download the Installer**: The InvokeAI installer is distributed as a ZIP files. Go to the
-    [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest),
-    and look for a file named:
-
-    - InvokeAI-installer-v4.X.X.zip
-
-    where "4.X.X" is the latest released version. The file is located
-    at the very bottom of the release page, under **Assets**.
-
-4.  **Unpack the installer**: Unpack the zip file into a convenient directory. This will create a new
-    directory named "InvokeAI-Installer". When unpacked, the directory
-    will look like this:
-
-    <figure markdown>
-    ![zipfile-screenshot](../assets/installer-walkthrough/unpacked-zipfile.png)
-    </figure>
-
-5.  **Launch the installer script from the desktop**: If you are using a desktop GUI, double-click the installer file
-    appropriate for your platform. It will be named `install.bat` on
-    Windows systems and `install.sh` on Linux and Macintosh
-    systems. Be aware that your system's file browser may suppress the
-    display of the file extension.
-
-    On Windows systems if you get an "Untrusted Publisher" warning.
-    Click on "More Info" and then select "Run Anyway." You trust us, right?
-
-6.  **[Alternative] Launch the installer script from the command line**: Alternatively, from the command line, run the shell script or .bat file:
-
-    ```cmd
-    C:\Documents\Linco> cd InvokeAI-Installer
-    C:\Documents\Linco\invokeAI> .\install.bat
+    ```sh
+    install.bat
     ```
 
-7.  **Select the location to install InvokeAI**: The script will ask you to choose where to install InvokeAI. Select a
-    directory with at least 18G of free space for a full install. InvokeAI and
-    all its support files will be installed into a new directory named
-    `invokeai` located at the location you specify.
+=== "Linux/macOS"
 
-    <figure markdown>
-    ![confirm-install-directory-screenshot](../assets/installer-walkthrough/confirm-directory.png)
-    </figure>
-
-    - The default is to install the `invokeai` directory in your home directory,
-      usually `C:\Users\YourName\invokeai` on Windows systems,
-      `/home/YourName/invokeai` on Linux systems, and `/Users/YourName/invokeai`
-      on Macintoshes, where "YourName" is your login name.
-
-    -If you have previously installed InvokeAI, you will be asked to
-     confirm whether you want to reinstall into this directory.  You
-     may choose to reinstall, in which case your version will be upgraded,
-     or choose a different directory.
-
-    - The script uses tab autocompletion to suggest directory path completions.
-      Type part of the path (e.g. "C:\Users") and press ++tab++ repeatedly
-      to suggest completions.
-
-8.  **Select your GPU**: The installer will autodetect your platform and will request you to
-    confirm the type of GPU your graphics card has. On Linux systems,
-    you will have the choice of CUDA (NVidia cards), ROCm (AMD cards),
-    or CPU (no graphics acceleration). On Windows, you'll have the
-    choice of CUDA vs CPU, and on Macs you'll be offered CPU only. When
-    you select CPU on M1/M2/M3 Macintoshes, you will get MPS-based
-    graphics acceleration without installing additional drivers. If you
-    are unsure what GPU you are using, you can ask the installer to
-    guess.
-
-9.  **Watch it go!**: Sit back and let the install script work. It will install the third-party
-    libraries needed by InvokeAI and the application itself.
-
-    Be aware that some of the library download and install steps take a long
-    time. In particular, the `pytorch` package is quite large and often appears
-    to get "stuck" at 99.9%. Have patience and the installation step will
-    eventually resume. However, there are occasions when the library install
-    does legitimately get stuck. If you have been waiting for more than ten
-    minutes and nothing is happening, you can interrupt the script with ^C. You
-    may restart it and it will pick up where it left off.
-
-    <figure markdown>
-    ![initial-settings-screenshot](../assets/installer-walkthrough/settings-form.png)
-    </figure>
-
-10. **Running InvokeAI for the first time**: The script will now exit and you'll be ready to generate some images. Look
-    for the directory `invokeai` installed in the location you chose at the
-    beginning of the install session. Look for a shell script named `invoke.sh`
-    (Linux/Mac) or `invoke.bat` (Windows). Launch the script by double-clicking
-    it or typing its name at the command-line:
-
-    ```cmd
-    C:\Documents\Linco> cd invokeai
-    C:\Documents\Linco\invokeAI> invoke.bat
+    ```sh
+    install.sh
     ```
 
-    - The `invoke.bat` (`invoke.sh`) script will give you the choice
-      of starting (1) the command-line interface, (2) the web GUI, (3)
-      textual inversion training, and (4) model merging.
+!!! info "Running the Installer from the commandline"
 
-    - By default, the script will launch the web interface. When you
-      do this, you'll see a series of startup messages ending with
-      instructions to point your browser at
-      http://localhost:9090. Click on this link to open up a browser
-      and start exploring InvokeAI's features.
+    You can also run the install script from cmd/powershell (Windows) or terminal (Linux/macOS).
 
-12. **InvokeAI Options**: You can configure using the `invokeai.yaml` config file.
-    For example, you can change the location of the
-    image output directory or balance memory usage vs performance. See
-    [Configuration](../features/CONFIGURATION.md) for a full list of the options.
+!!! warning "Untrusted Publisher (Windows)"
 
-    - To set defaults that will take effect every time you launch InvokeAI,
-      use a text editor (e.g. Notepad) to exit the file
-      `invokeai\invokeai.yaml`. It contains a variety of examples that you can
-      follow to add and modify launch options.
+    You may get a popup saying the file comes from an `Untrusted Publisher`. Click `More Info` and `Run Anyway` to get past this.
 
-    - The launcher script also offers you an option labeled "open the developer
-      console". If you choose this option, you will be dropped into a
-      command-line interface in which you can run python commands directly,
-      access developer tools, and launch InvokeAI with customized options.
+The installation process is simple, with a few prompts:
 
+- Select the version to install. Unless you have a specific reason to install a specific version, select the default (the latest version).
+- Select location for the install. Be sure you have enough space in this folder for the base application, as described in the [installation requirements].
+- Select a GPU device.
 
-    !!! warning "Do not move or remove the `invokeai` directory"
-      
-        The `invokeai` directory contains the `invokeai` application, its
-        configuration files, the model weight files, and outputs of image generation.
-        Once InvokeAI is installed, do not move or remove this directory."
+!!! info "Slow Installation"
 
+    The installer needs to download several GB of data and install it all. It may appear to get stuck at 99.9% when installing `pytorch` or during a step labeled "Installing collected packages".
 
-<a name="troubleshooting"></a>
-## Troubleshooting
+    If it is stuck for over 10 minutes, something has probably gone wrong and you should close the window and restart.
 
-### _OSErrors on Windows while installing dependencies_
+## Running the Application
 
-During a zip file installation or an online update, installation stops
-with an error like this:
+Find the install location you selected earlier. Double-click the launcher script to run the app:
 
-![broken-dependency-screenshot](../assets/troubleshooting/broken-dependency.png){:width="800px"}
+=== "Windows"
 
-This seems to happen particularly often with the `pydantic` and
-`numpy` packages. The most reliable solution requires several manual
-steps to complete installation.
+    ```sh
+    invoke.bat
+    ```
 
-Open up a Powershell window and navigate to the `invokeai` directory
-created by the installer. Then give the following series of commands:
+=== "Linux/macOS"
 
-```cmd
-rm .\.venv -r -force
-python -mvenv .venv
-.\.venv\Scripts\activate
-pip install invokeai
+    ```sh
+    invoke.sh
+    ```
+
+Choose the first option to run the UI. After a series of startup messages, you'll see something like this:
+
+```
+Uvicorn running on http://127.0.0.1:9090 (Press CTRL+C to quit)
 ```
 
-If you see anything marked as an error during this process please stop
-and seek help on the Discord [installation support
-channel](https://discord.com/channels/1020123559063990373/1041391462190956654). A
-few warning messages are OK.
+Copy the URL into your browser and you should see the UI.
 
-If you are updating from a previous version, this should restore your
-system to a working state. If you are installing from scratch, there
-is one additional command to give:
+## First-time Setup
 
-```cmd
-wget -O invoke.bat https://raw.githubusercontent.com/invoke-ai/InvokeAI/main/installer/templates/invoke.bat.in
-```
+You will need to [install some models] before you can generate.
 
-This will create the `invoke.bat` script needed to launch InvokeAI and
-its related programs.
+Check the [configuration docs] for details on configuring the application.
 
+## Updating
 
-### _Stable Diffusion XL Generation Fails after Trying to Load unet_
+Updating is exactly the same as installing - download the latest installer, choose the latest version and off you go.
 
-InvokeAI is working in other respects, but when trying to generate
-images with Stable Diffusion XL you get a "Server Error". The text log
-in the launch window contains this log line above several more lines of
-error messages:
+!!! info "Dependency Resolution Issues"
 
-```INFO --> Loading model:D:\LONG\PATH\TO\MODEL, type sdxl:main:unet```
+    We've found that pip's dependency resolution can cause issues when upgrading packages. One very common problem was pip "downgrading" torch from CUDA to CPU, but things broke in other novel ways.
 
-This failure mode occurs when there is a network glitch during
-downloading the very large SDXL model.
+    The installer doesn't have this kind of problem, so we use it for updating as well.
 
-To address this, first go to the Model Manager and delete the
-Stable-Diffusion-XL-base-1.X model. Then, click the HuggingFace tab,
- paste the Repo ID stabilityai/stable-diffusion-xl-base-1.0 and install
- the model.
+## Installation Issues
 
-### _Package dependency conflicts_
+If you have installation issues, please review the [FAQ]. You can also [create an issue] or ask for help on [discord].
 
-If you have previously installed InvokeAI or another Stable Diffusion
-package, the installer may occasionally pick up outdated libraries and
-either the installer or `invoke` will fail with complaints about
-library conflicts. In this case, run the `invoke.sh`/`invoke.bat`
-command and enter the Developer's Console by picking option (5). This
-will take you to a command-line prompt.
-
-Then give this command:
-
-`pip install InvokeAI --force-reinstall`
-
-This should fix the issues.
-
-### InvokeAI runs extremely slowly on Linux or Windows systems
-
-The most frequent cause of this problem is when the installation
-process installed the CPU-only version of the torch machine-learning
-library, rather than a version that takes advantage of GPU
-acceleration. To confirm this issue, look at the InvokeAI startup
-messages. If you see a message saying ">> Using device CPU", then
-this is what happened.
-
-To fix this problem, first determine whether you have an NVidia or an
-AMD GPU. The former uses the CUDA driver, and the latter uses ROCm
-(only available on Linux). Then run the `invoke.sh`/`invoke.bat`
-command and enter the Developer's Console by picking option (5). This
-will take you to a command-line prompt.
-
-Then type the following commands:
-
-=== "NVIDIA System"
-    ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121
-    pip install xformers
-    ```
-
-=== "AMD System"
-    ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.6
-    ```
-
-### Corrupted configuration file
-
-Everything seems to install ok, but `invokeai` complains of a corrupted
-configuration file and goes back into the configuration process (asking you to
-download models, etc), but this doesn't fix the problem.
-
-This issue is often caused by a misconfigured configuration directive in the
-`invokeai\invokeai.init` initialization file that contains startup settings. The
-easiest way to fix the problem is to move the file out of the way and restart the app.
-
-_If none of these maneuvers fixes the problem_ then please report the problem to
-the [InvokeAI Issues](https://github.com/invoke-ai/InvokeAI/issues) section, or
-visit our [Discord Server](https://discord.gg/ZmtBAhwWhy) for interactive
-assistance.
-
-### Out of Memory Issues
-
-The models are large, VRAM is expensive, and you may find yourself
-faced with Out of Memory errors when generating images. Here are some
-tips to reduce the problem:
-
-* **4 GB of VRAM**
-
-This should be adequate for 512x512 pixel images using Stable Diffusion 1.5
-and derived models, provided that you **disable** the NSFW checker. To
-disable the filter, do one of the following:
-
-   * Select option (6) "_change InvokeAI startup options_" from the
-     launcher. This will bring up the console-based startup settings
-     dialogue and allow you to unselect the "NSFW Checker" option.
-   * Start the startup settings dialogue directly by running
-     `invokeai-configure --skip-sd-weights --skip-support-models`
-     from the command line.
-   * Find the `invokeai.init` initialization file in the InvokeAI root
-     directory, open it in a text editor, and change `--nsfw_checker`
-     to `--no-nsfw_checker`
-
-If you are on a CUDA system, you can realize significant memory
-savings by activating the `xformers` library as described above. The
-downside is `xformers` introduces non-deterministic behavior, such
-that images generated with exactly the same prompt and settings will
-be slightly different from each other. See above for more information.
-
-* **6 GB of VRAM**
-
-This is a border case. Using the SD 1.5 series you should be able to
-generate images up to 640x640 with the NSFW checker enabled, and up to
-1024x1024 with it disabled and `xformers` activated. 
-
-If you run into persistent memory issues there are a series of
-environment variables that you can set before launching InvokeAI that
-alter how the PyTorch machine learning library manages memory.  See
-https://pytorch.org/docs/stable/notes/cuda.html#memory-management for
-a list of these tweaks.
-
-* **12 GB of VRAM**
-
-This should be sufficient to generate larger images up to about
-1280x1280. If you wish to push further, consider activating
-`xformers`.
-
-### Other Problems
-
-If you run into problems during or after installation, the InvokeAI team is
-available to help you. Either create an
-[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub site, or
-make a request for help on the "bugs-and-support" channel of our
-[Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100% volunteer
-organization, but typically somebody will be available to help you within 24
-hours, and often much sooner.
-
-## Updating to newer versions
-
-This distribution is changing rapidly, and we add new features
-regularly. Releases are announced at
-http://github.com/invoke-ai/InvokeAI/releases, and at
-https://pypi.org/project/InvokeAI/ To update to the latest released
-version (recommended), download the latest release and run the installer.
+[installation requirements]: INSTALL_REQUIREMENTS.md
+[FAQ]: ../help/FAQ.md
+[install some models]: 050_INSTALLING_MODELS.md
+[configuration docs]: ../features/CONFIGURATION.md
+[latest release]: https://github.com/invoke-ai/InvokeAI/releases/latest
+[create an issue]: https://github.com/invoke-ai/InvokeAI/issues
+[discord]: https://discord.gg/ZmtBAhwWhy

docs/installation/020_INSTALL_MANUAL.md

@@ -1,122 +1,55 @@
----
-title: Installing Manually
----
-
-<figure markdown>
-
-# :fontawesome-brands-linux: Linux | :fontawesome-brands-apple: macOS | :fontawesome-brands-windows: Windows
-
-</figure>
+# Manual Install
 
 !!! warning "This is for Advanced Users"
 
-    **Python experience is mandatory**
+    **Python experience is mandatory.**
 
 ## Introduction
 
-!!! tip "Conda"
-    As of InvokeAI v2.3.0 installation using the `conda` package manager is no longer being supported. It will likely still work, but we are not testing this installation method.
+InvokeAI is distributed as a python package on PyPI, installable with `pip`. There are a few things that are handled by the installer and launcher that you'll need to manage manually, described in this guide.
 
-On Windows systems, you are encouraged to install and use the
-[PowerShell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.3),
-which provides compatibility with Linux and Mac shells and nice
-features such as command-line completion.
+### Requirements
 
-### Prerequisites
-
-Before you start, make sure you have the following preqrequisites
-installed.  These are described in more detail in [Automated
-Installation](010_INSTALL_AUTOMATED.md), and in many cases will
-already be installed (if, for example, you have used your system for
-gaming):
-
-* **Python**
-
-    version 3.10 through 3.11
-
-* **CUDA Tools**
-
-    For those with _NVidia GPUs_, you will need to
-    install the [CUDA toolkit and optionally the XFormers library](070_INSTALL_XFORMERS.md).
-
-* **ROCm Tools**
-
-    For _Linux users with AMD GPUs_, you will need
-    to install the [ROCm toolkit](./030_INSTALL_CUDA_AND_ROCM.md). Note that
-    InvokeAI does not support AMD GPUs on Windows systems due to
-    lack of a Windows ROCm library.
-
-* **Visual C++ Libraries**
-
-    _Windows users_ must install the free
-    [Visual C++ libraries from Microsoft](https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170)
-
-* **The Xcode command line tools**
-
-    for _Macintosh users_. Instructions are available at
-    [Free Code Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
-
-    * _Macintosh users_ may also need to run the `Install Certificates` command
-      if model downloads give lots of certificate errors. Run:
-      `/Applications/Python\ 3.10/Install\ Certificates.command`
+Before you start, go through the [installation requirements](./INSTALL_REQUIREMENTS.md).
 
 ### Installation Walkthrough
 
-To install InvokeAI with virtual environments and the PIP package
-manager, please follow these steps:
-
-1.  Please make sure you are using Python 3.10 through 3.11. The rest of the install
-    procedure depends on this and will not work with other versions:
-
-    ```bash
-    python -V
-    ```
-
-2.  Create a directory to contain your InvokeAI library, configuration
+1. Create a directory to contain your InvokeAI library, configuration
     files, and models. This is known as the "runtime" or "root"
     directory, and often lives in your home directory under the name `invokeai`.
 
-    Please keep in mind the disk space requirements - you will need at
-    least 20GB for the models and the virtual environment.  From now
-    on we will refer to this directory as `INVOKEAI_ROOT`. For convenience,
-    the steps below create a shell variable of that name which contains the
-    path to `HOME/invokeai`.
+    We will refer to this directory as `INVOKEAI_ROOT`. For convenience, create an environment variable pointing to the directory.
 
-    === "Linux/Mac"
+    === "Linux/macOS"
 
         ```bash
         export INVOKEAI_ROOT=~/invokeai
         mkdir $INVOKEAI_ROOT
         ```
 
-    === "Windows (Powershell)"
+    === "Windows (PowerShell)"
 
         ```bash
         Set-Variable -Name INVOKEAI_ROOT -Value $Home/invokeai
         mkdir $INVOKEAI_ROOT
         ```
 
-3. Enter the root (invokeai) directory and create a virtual Python
-   environment within it named `.venv`. If the command `python`
-   doesn't work, try `python3`. Note that while you may create the
-   virtual environment anywhere in the file system, we recommend that
-   you create it within the root directory as shown here. This makes
-   it possible for the InvokeAI applications to find the model data
-   and configuration. If you do not choose to install the virtual
-   environment inside the root directory, then you **must** set the
-   `INVOKEAI_ROOT` environment variable in your shell environment, for
-   example, by editing `~/.bashrc` or `~/.zshrc` files, or setting the
-   Windows environment variable using the Advanced System Settings dialogue.
-   Refer to your operating system documentation for details.
+1. Enter the root (invokeai) directory and create a virtual Python environment within it named `.venv`.
+
+    !!! warning "Virtual Environment Location"
+
+        While you may create the virtual environment anywhere in the file system, we recommend that you create it within the root directory as shown here. This allows the application to automatically detect its data directories.
+
+        If you choose a different location for the venv, then you _must_ set the `INVOKEAI_ROOT` environment variable or specify the root directory using the `--root` CLI arg.
 
     ```terminal
     cd $INVOKEAI_ROOT
-    python -m venv .venv --prompt InvokeAI
+    python3 -m venv .venv --prompt InvokeAI
     ```
 
-4.  Activate the new environment:
+1. Activate the new environment:
 
-    === "Linux/Mac"
+    === "Linux/macOS"
 
         ```bash
         source .venv/bin/activate
@@ -128,51 +61,43 @@ manager, please follow these steps:
         .venv\Scripts\activate
         ```
 
+    !!! info "Permissions Error (Windows)"
+
         If you get a permissions error at this point, run this command and try again
 
         `Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser`
 
-    The command-line prompt should change to to show `(InvokeAI)` at the
-    beginning of the prompt. Note that all the following steps should be
-    run while inside the INVOKEAI_ROOT directory
+    The command-line prompt should change to to show `(InvokeAI)` at the beginning of the prompt.
 
-5.  Make sure that pip is installed in your virtual environment and up to date:
+    The following steps should be run while inside the `INVOKEAI_ROOT` directory.
+
+1. Make sure that pip is installed in your virtual environment and up to date:
 
     ```bash
-    python -m pip install --upgrade pip
+    python3 -m pip install --upgrade pip
     ```
 
-6. Install the InvokeAI Package. The `--extra-index-url` option is used to select among
-   CUDA, ROCm and CPU/MPS drivers as shown below:
+1. Install the InvokeAI Package. The base command is `pip install InvokeAI --use-pep517`, but you may need to change this depending on your system and the desired features.
 
-    === "CUDA (NVidia)"
+    - You may need to provide an [extra index URL](https://pip.pypa.io/en/stable/cli/pip_install/#cmdoption-extra-index-url). Select your platform configuration using [this tool on the PyTorch website](https://pytorch.org/get-started/locally/). Copy the `--extra-index-url` string from this and append it to your install command.
 
-        ```bash
-        pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-        ```
+        !!! example "Install with an extra index URL"
 
-    === "ROCm (AMD)"
+            ```bash
+            pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
+            ```
 
-        ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
-        ```
+    - If you have a CUDA GPU and want to install with `xformers`, you need to add an option to the package name. Note that `xformers` is not necessary. PyTorch includes an implementation of the SDP attention algorithm with the same performance.
 
-    === "CPU (Intel Macs & non-GPU systems)"
+        !!! example "Install with `xformers`"
 
-        ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
-        ```
+            ```bash
+            pip install "InvokeAI[xformers]" --use-pep517
+            ```
 
-    === "MPS (M1 and M2 Macs)"
+1. Deactivate and reactivate your runtime directory so that the invokeai-specific commands become available in the environment:
 
-        ```bash
-        pip install InvokeAI --use-pep517
-        ```
-
-7.  Deactivate and reactivate your runtime directory so that the invokeai-specific commands
-    become available in the environment
-
-    === "Linux/Macintosh"
+    === "Linux/macOS"
 
         ```bash
         deactivate && source .venv/bin/activate
@@ -185,221 +110,10 @@ manager, please follow these steps:
         .venv\Scripts\activate
         ```
 
-8.  Set up the runtime directory
+1. Run the application:
 
-    In this step you will initialize your runtime directory with the downloaded
-    models, model config files, directory for textual inversion embeddings, and
-    your outputs.
-
-    ```terminal
-    invokeai-configure --root .
-    ```
-	
-	Don't miss the dot at the end of the command!
-
-    The script `invokeai-configure` will interactively guide you through the
-    process of downloading and installing the weights files needed for InvokeAI.
-    Note that the main Stable Diffusion weights file is protected by a license
-    agreement that you have to agree to. The script will list the steps you need
-    to take to create an account on the site that hosts the weights files,
-    accept the agreement, and provide an access token that allows InvokeAI to
-    legally download and install the weights files.
-
-    If you get an error message about a module not being installed, check that
-    the `invokeai` environment is active and if not, repeat step 5.
-
-    !!! tip
-
-        If you have already downloaded the weights file(s) for another Stable
-        Diffusion distribution, you may skip this step (by selecting "skip" when
-        prompted) and configure InvokeAI to use the previously-downloaded files. The
-        process for this is described in [Installing Models](050_INSTALLING_MODELS.md).
-
-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
-    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:
-
-    !!! example ""
-
-        !!! warning "Make sure that the virtual environment is activated, which should create `(.venv)` in front of your prompt!"
-
-        === "local Webserver"
-
-            ```bash
-            invokeai-web
-            ```
-
-        === "Public Webserver"
-
-            ```bash
-            invokeai-web --host 0.0.0.0
-            ```
-
-        === "CLI"
-
-            ```bash
-            invokeai
-            ```
-
-        If you choose the run the web interface, point your browser at
-        http://localhost:9090 in order to load the GUI.
-
-    !!! tip
-
-        You can permanently set the location of the runtime directory
-        by setting the environment variable `INVOKEAI_ROOT` to the
-        path of the directory. As mentioned previously, this is
-        *highly recommended** if your virtual environment is located outside of
-        your runtime directory.
-
-    !!! tip
-
-        On linux, it is recommended to run invokeai with the following env var: `MALLOC_MMAP_THRESHOLD_=1048576`. For example: `MALLOC_MMAP_THRESHOLD_=1048576 invokeai --web`. This helps to prevent memory fragmentation that can lead to memory accumulation over time. This env var is set automatically when running via `invoke.sh`.
-
-10.  Render away!
-
-    Browse the [features](../features/index.md) section to learn about all the
-    things you can do with InvokeAI.
-
-
-11.  Subsequently, to relaunch the script, activate the virtual environment, and
-    then launch `invokeai` command. If you forget to activate the virtual
-    environment you will most likeley receive a `command not found` error.
+    Run `invokeai-web` to start the UI. You must activate the virtual environment before running the app.
 
     !!! warning
 
-        Do not move the runtime directory after installation. The virtual environment will get confused if the directory is moved.
-
-12. Other scripts
-
-    The [Textual Inversion](../features/TRAINING.md) script can be launched with the command:
-
-    ```bash
-    invokeai-ti --gui
-    ```
-
-    Similarly, the [Model Merging](../features/MODEL_MERGING.md) script can be launched with the command:
-
-    ```bash
-    invokeai-merge --gui
-    ```
-
-    Leave off the `--gui` option to run the script using command-line arguments. Pass the `--help` argument
-    to get usage instructions.
-
-## Developer Install
-
-!!! warning
-
-    InvokeAI uses a SQLite database. By running on `main`, you accept responsibility for your database. This
-    means making regular backups (especially before pulling) and/or fixing it yourself in the event that a
-    PR introduces a schema change.
-    
-    If you don't need persistent backend storage, you can use an ephemeral in-memory database by setting
-    `use_memory_db: true` under `Path:` in your `invokeai.yaml` file.
-
-    If this is untenable, you should run the application via the official installer or a manual install of the
-    python package from pypi. These releases will not break your database.
-
-
-If you have an interest in how InvokeAI works, or you would like to
-add features or bugfixes, you are encouraged to install the source
-code for InvokeAI. For this to work, you will need to install the
-`git` source code management program. If it is not already installed
-on your system, please see the [Git Installation
-Guide](https://github.com/git-guides/install-git)
-
-You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md).
-
-If you have a "normal" installation, you should create a totally separate virtual environment for the git-based installation, else the two may interfere.
-
-> **Why do I need the frontend toolchain**?
->
-> The InvokeAI project uses trunk-based development. That means our `main` branch is the development branch, and releases are tags on that branch. Because development is very active, we don't keep an updated build of the UI in `main` - we only build it for production releases.
->
-> That means that between releases, to have a functioning application when running directly from the repo, you will need to run the UI in dev mode or build it regularly (any time the UI code changes).
-
-1. Create a fork of the InvokeAI repository through the GitHub UI or [this link](https://github.com/invoke-ai/InvokeAI/fork) 
-2. From the command line, run this command:
-   ```bash
-   git clone https://github.com/<your_github_username>/InvokeAI.git
-   ```
-
-    This will create a directory named `InvokeAI` and populate it with the
-    full source code from your fork of the InvokeAI repository.
-
-3. Activate the InvokeAI virtual environment as per step (4) of the manual
-installation protocol (important!)
-
-4. Enter the InvokeAI repository directory and run one of these
-   commands, based on your GPU:
-
-    === "CUDA (NVidia)"
-        ```bash
-        pip install -e .[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-        ```
-
-    === "ROCm (AMD)"
-        ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
-        ```
-
-    === "CPU (Intel Macs & non-GPU systems)"
-        ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
-        ```
-
-    === "MPS (M1 and M2 Macs)"
-        ```bash
-        pip install -e . --use-pep517
-        ```
-
-    Be sure to pass `-e` (for an editable install) and don't forget the
-    dot ("."). It is part of the command.
-
-5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md) and do a production build of the UI as described.
-
-6.  You can now run `invokeai` and its related commands. The code will be
-    read from the repository, so that you can edit the .py source files
-    and watch the code's behavior change.
-
-    When you pull in new changes to the repo, be sure to re-build the UI.
-
-7.  If you wish to contribute to the InvokeAI project, you are
-    encouraged to establish a GitHub account and "fork"
-    https://github.com/invoke-ai/InvokeAI into your own copy of the
-    repository. You can then use GitHub functions to create and submit
-    pull requests to contribute improvements to the project.
-
-    Please see [Contributing](../index.md#contributing) for hints
-    on getting started.
-
-### Unsupported Conda Install
-
-Congratulations, you found the "secret" Conda installation
-instructions. If you really **really** want to use Conda with InvokeAI
-you can do so using this unsupported recipe:
-
-```
-mkdir ~/invokeai
-conda create -n invokeai python=3.10
-conda activate invokeai
-pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-invokeai-configure --root ~/invokeai
-invokeai --root ~/invokeai --web
-```
-
-The `pip install` command shown in this recipe is for Linux/Windows
-systems with an NVIDIA GPU. See step (6) above for the command to use
-with other platforms/GPU combinations. If you don't wish to pass the
-`--root` argument to `invokeai` with each launch, you may set the
-environment variable INVOKEAI_ROOT to point to the installation directory.
-
-Note that if you run into problems with the Conda installation, the InvokeAI
-staff will **not** be able to help you out. Caveat Emptor!
-
-[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939
+        If the virtual environment is _not_ inside the root directory, then you _must_ specify the path to the root directory with `--root \path\to\invokeai` or the `INVOKEAI_ROOT` environment variable.

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -1,149 +0,0 @@
----
-title: NVIDIA Cuda / AMD ROCm
----
-
-<figure markdown>
-
-# :simple-nvidia: CUDA | :simple-amd: ROCm
-
-</figure>
-
-In order for InvokeAI to run at full speed, you will need a graphics
-card with a supported GPU. InvokeAI supports NVidia cards via the CUDA
-driver on Windows and Linux, and AMD cards via the ROCm driver on Linux.
-
-## :simple-nvidia: CUDA
-
-### Linux and Windows Install
-
-If you have used your system for other graphics-intensive tasks, such
-as gaming, you may very well already have the CUDA drivers
-installed. To confirm, open up a command-line window and type:
-
-```
-nvidia-smi
-```
-
-If this command produces a status report on the GPU(s) installed on
-your system, CUDA is installed and you have no more work to do. If
-instead you get "command not found", or similar, then the driver will
-need to be installed.
-
-We strongly recommend that you install the CUDA Toolkit package
-directly from NVIDIA. **Do not try to install Ubuntu's
-nvidia-cuda-toolkit package. It is out of date and will cause
-conflicts among the NVIDIA driver and binaries.**
-
-Go to [CUDA Toolkit
-Downloads](https://developer.nvidia.com/cuda-downloads), and use the
-target selection wizard to choose your operating system, hardware
-platform, and preferred installation method (e.g. "local" versus
-"network").
-
-This will provide you with a downloadable install file or, depending
-on your choices, a recipe for downloading and running a install shell
-script. Be sure to read and follow the full installation instructions.
-
-After an install that seems successful, you can confirm by again
-running `nvidia-smi` from the command line.
-
-### Linux Install with a Runtime Container
-
-On Linux systems, an alternative to installing CUDA Toolkit directly on
-your system is to run an NVIDIA software container that has the CUDA
-libraries already in place. This is recommended if you are already 
-familiar with containerization technologies such as Docker.
-
-For downloads and instructions, visit the [NVIDIA CUDA Container
-Runtime Site](https://developer.nvidia.com/nvidia-container-runtime)
-
-### cuDNN Installation for 40/30 Series Optimization* (Optional)
-
-1. Find the InvokeAI folder
-2. Click on .venv folder - e.g., YourInvokeFolderHere\\.venv
-3. Click on Lib folder - e.g., YourInvokeFolderHere\\.venv\Lib
-4. Click on site-packages folder - e.g., YourInvokeFolderHere\\.venv\Lib\site-packages
-5. Click on Torch directory - e.g., YourInvokeFolderHere\InvokeAI\\.venv\Lib\site-packages\torch
-6. Click on the lib folder - e.g., YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib
-7. Copy everything inside the folder and save it elsewhere as a backup.
-8. Go to __https://developer.nvidia.com/cudnn__
-9. Login or create an Account. 
-10. Choose the newer version of cuDNN. **Note:** 
-There are two versions, 11.x or 12.x for the differents architectures(Turing,Maxwell Etc...) of GPUs.
-You can find which version you should download from [this link](https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html).
-13. Download the latest version and extract it from the download location
-14. Find the bin folder E\cudnn-windows-x86_64-__Whatever Version__\bin
-15. Copy and paste the .dll files into YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib **Make sure to copy, and not move the files**
-16. If prompted, replace any existing files 
-
-**Notes:** 
-* If no change is seen or any issues are encountered, follow the same steps as above and paste the torch/lib backup folder you made earlier and replace it. If you didn't make a backup, you can also uninstall and reinstall torch through the command line to repair this folder. 
-* This optimization is  intended for the newer version of graphics card (40/30 series) but results have been seen with older graphics card.
-
-
-### Torch Installation
-
-When installing torch and torchvision manually with `pip`, remember to provide
-the argument `--extra-index-url
-https://download.pytorch.org/whl/cu121` as described in the [Manual
-Installation Guide](020_INSTALL_MANUAL.md).
-
-## :simple-amd: ROCm
-
-### Linux Install
-
-AMD GPUs are only supported on Linux platforms due to the lack of a
-Windows ROCm driver at the current time. Also be aware that support
-for newer AMD GPUs is spotty. Your mileage may vary.
-
-It is possible that the ROCm driver is already installed on your
-machine. To test, open up a terminal window and issue the following
-command:
-
-```
-rocm-smi
-```
-
-If you get a table labeled "ROCm System Management Interface" the
-driver is installed and you are done. If you get "command not found,"
-then the driver needs to be installed.
-
-Go to AMD's [ROCm Downloads
-Guide](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation_new.html#installation-methods)
-and scroll to the _Installation Methods_ section. Find the subsection
-for the install method for your preferred Linux distribution, and
-issue the commands given in the recipe.
-
-Annoyingly, the official AMD site does not have a recipe for the most
-recent version of Ubuntu, 22.04. However, this [community-contributed
-recipe](https://novaspirit.github.io/amdgpu-rocm-ubu22/) is reported
-to work well.
-
-After installation, please run `rocm-smi` a second time to confirm
-that the driver is present and the GPU is recognized. You may need to
-do a reboot in order to load the driver.
-
-### Linux Install with a ROCm-docker Container
-
-If you are comfortable with the Docker containerization system, then
-you can build a ROCm docker file. The source code and installation
-recipes are available
-[Here](https://github.com/RadeonOpenCompute/ROCm-docker/blob/master/quick-start.md)
-
-### Torch Installation
-
-When installing torch and torchvision manually with `pip`, remember to provide
-the argument `--extra-index-url
-https://download.pytorch.org/whl/rocm5.6` as described in the [Manual
-Installation Guide](020_INSTALL_MANUAL.md).
-
-This will be done automatically for you if you use the installer
-script.
-
-Be aware that the torch machine learning library does not seamlessly
-interoperate with all AMD GPUs and you may experience garbled images,
-black images, or long startup delays before rendering commences. Most
-of these issues can be solved by Googling for workarounds. If you have
-a problem and find a solution, please post an
-[Issue](https://github.com/invoke-ai/InvokeAI/issues) so that other
-users benefit and we can update this document.

docs/installation/050_INSTALLING_MODELS.md

@@ -1,186 +1,52 @@
----
-title: Installing Models
----
-
-# :octicons-paintbrush-16: Installing Models
+# Installing Models
 
 ## Checkpoint and Diffusers Models
 
-The model checkpoint files ('\*.ckpt') are the Stable Diffusion
-"secret sauce". They are the product of training the AI on millions of
-captioned images gathered from multiple sources.
+The model checkpoint files (`*.ckpt`) are the Stable Diffusion "secret sauce". They are the product of training the AI on millions of captioned images gathered from multiple sources.
 
-Originally there was only a single Stable Diffusion weights file,
-which many people named `model.ckpt`. Now there are dozens or more
-that have been fine tuned to provide particulary styles, genres, or
-other features. In addition, there are several new formats that
-improve on the original checkpoint format: a `.safetensors` format
-which prevents malware from masquerading as a model, and `diffusers`
-models, the most recent innovation.
+Originally there was only a single Stable Diffusion weights file, which many people named `model.ckpt`.
 
-InvokeAI supports all three formats but strongly prefers the
-`diffusers` format. These are distributed as directories containing
-multiple subfolders, each of which contains a different aspect of the
-model. The advantage of this is that the models load from disk really
-fast. Another advantage is that `diffusers` models are supported by a
-large and active set of open source developers working at and with
-HuggingFace organization, and improvements in both rendering quality
-and performance are being made at a rapid pace. Among other features
-is the ability to download and install a `diffusers` model just by
-providing its HuggingFace repository ID.
+Today, there are thousands of models, fine tuned to excel at specific styles, genres, or themes.
 
-While InvokeAI will continue to support `.ckpt` and `.safetensors`
-models for the near future, these are deprecated and support will
-likely be withdrawn at some point in the not-too-distant future.
+!!! tip "Model Formats"
 
-This manual will guide you through installing and configuring model
-weight files and converting legacy `.ckpt` and `.safetensors` files
-into performant `diffusers` models.
+    We also have two more popular model formats, both created [HuggingFace](https://huggingface.co/):
 
-## Base Models
+    - `safetensors`: Single file, like `.ckpt` files. Prevents malware from lurking in a model.
+    - `diffusers`: Splits the model components into separate files, allowing very fast loading.
 
-InvokeAI comes with support for a good set of starter models. You'll
-find them listed in the master models file
-`configs/INITIAL_MODELS.yaml` in the InvokeAI root directory. The
-subset that are currently installed are found in
-`configs/models.yaml`.
+    InvokeAI supports all three formats. Our backend will convert models to `diffusers` format before running them. This is a transparent process.
 
-Note that these files are covered by an "Ethical AI" license which
-forbids certain uses. When you initially download them, you are asked
-to accept the license terms. In addition, some of these models carry
-additional license terms that limit their use in commercial
-applications or on public servers. Be sure to familiarize yourself
-with the model terms by visiting the URLs in the table above.
+## Starter Models
 
-## Community-Contributed Models
+When you first start InvokeAI, you'll see a popup prompting you to install some starter models from the Model Manager. Click the `Starter Models` tab to see the list.
 
-[HuggingFace](https://huggingface.co/models?library=diffusers)
-is a great resource for diffusers models, and is also the home of a
-[fast-growing repository](https://huggingface.co/sd-concepts-library)
-of embedding (".bin") models that add subjects and/or styles to your
-images. The latter are automatically installed on the fly when you
-include the text `<concept-name>` in your prompt. See [Concepts
-Library](../features/CONCEPTS.md) for more information.
+You'll find a collection of popular and high-quality models available for easy download.
 
-Another popular site for community-contributed models is
-[CIVITAI](https://civitai.com). This extensive site currently supports
-only `.safetensors` and `.ckpt` models, but they can be easily loaded
-into InvokeAI and/or converted into optimized `diffusers` models. Be
-aware that CIVITAI hosts many models that generate NSFW content.
+Some models carry license terms that limit their use in commercial applications or on public servers. It's your responsibility to adhere to the license terms.
 
-## Installation
+## Other Models
 
-There are two ways to install and manage models:
+You can install other models using the Model Manager. You'll find tabs for the following install methods:
 
-1. The `invokeai-model-install` script which will download and install
-them for you.  In addition to supporting main models, you can install
-ControlNet, LoRA and Textual Inversion models.
+- **URL or Local Path**: Provide the path to a model on your computer, or a direct link to the model. Some sites require you to use an API token to download models, which you can [set up in the config file].
+- **HuggingFace**: Paste a HF Repo ID to install it. If there are multiple models in the repo, you'll get a list to choose from. Repo IDs look like this: `XpucT/Deliberate`. There is a copy button on each repo to copy the ID.
+- **Scan Folder**: Scan a local folder for models. You can install all of the detected models in one click.
 
-2. The web interface (WebUI) has a GUI for importing and managing
-   models.
+!!! tip "Autoimport"
 
-3. By placing models (or symbolic links to models) inside one of the
-InvokeAI root directory's `autoimport` folder.
+    The dedicated autoimport folder is removed as of v4.0.0. You can do the same thing on the **Scan Folder** tab - paste the folder you'd like to import from and then click `Install All`.
 
-### Installation via `invokeai-model-install`
+### Diffusers models in HF repo subfolders
 
-From the `invoke` launcher, choose option [4] "Download and install
-models." This will launch the same script that prompted you to select
-models at install time. You can use this to add models that you
-skipped the first time around. It is all right to specify a model that
-was previously downloaded; the script will just confirm that the files
-are complete.
+HuggingFace repos can be structured in any way. Some model authors include multiple models within the same folder.
 
-The installer has different panels for installing main models from
-HuggingFace, models from Civitai and other arbitrary web sites,
-ControlNet models, LoRA/LyCORIS models, and Textual Inversion
-embeddings. Each section has a text box in which you can enter a new
-model to install. You can refer to a model using its:
+In this situation, you may need to provide some additional information to identify the model you want, by adding `:subfolder_name` to the repo ID.
 
-1. Local path to the .ckpt, .safetensors or diffusers folder on your local machine
-2. A directory on your machine that contains multiple models
-3. A URL that points to a downloadable model
-4. A HuggingFace repo id
+!!! example
 
-Previously-installed models are shown with checkboxes. Uncheck a box
-to unregister the model from InvokeAI. Models that are physically
-installed inside the InvokeAI root directory will be deleted and
-purged (after a confirmation warning). Models that are located outside
-the InvokeAI root directory will be unregistered but not deleted.
+    Say you have a repo ID `monster-labs/control_v1p_sd15_qrcode_monster`, and the model you want is inside the `v2` subfolder.
 
-Note: The installer script uses a console-based text interface that requires
-significant amounts of horizontal and vertical space. If the display
-looks messed up, just enlarge the terminal window and/or relaunch the
-script.
+    Add `:v2` to the repo ID and use that when installing the model: `monster-labs/control_v1p_sd15_qrcode_monster:v2`
 
-If you wish you can script model addition and deletion, as well as
-listing installed models. Start the "developer's console" and give the
-command `invokeai-model-install --help`. This will give you a series
-of command-line parameters that will let you control model
-installation. Examples:
-
-```
-# (list all controlnet models)
-invokeai-model-install --list controlnet
-
-# (install the model at the indicated URL)
-invokeai-model-install --add https://civitai.com/api/download/models/128713
-
-# (delete the named model)
-invokeai-model-install --delete sd-1/main/analog-diffusion
-```
-
-### Installation via the Web GUI
-
-To install a new model using the Web GUI, do the following:
-
-1. Open the InvokeAI Model Manager (cube at the bottom of the
-left-hand panel) and navigate to *Import Models*
-
-2. In the field labeled *Location* type in the path to the model you
-wish to install. You may use a URL, HuggingFace repo id, or a path on
-your local disk.
-
-3. Alternatively, the *Scan for Models* button allows you to paste in
-the path to a folder somewhere on your machine. It will be scanned for
-importable models and prompt you to add the ones of your choice.
-
-4. Press *Add Model* and wait for confirmation that the model
-was added.
-
-To delete a model, Select *Model Manager* to list all the currently
-installed models. Press the trash can icons to delete any models you
-wish to get rid of. Models whose weights are located inside the
-InvokeAI `models` directory will be purged from disk, while those
-located outside will be unregistered from InvokeAI, but not deleted.
-
-You can see where model weights are located by clicking on the model name.
-This will bring up an editable info panel showing the model's characteristics,
-including the `Model Location` of its files.
-
-### Installation via the `autoimport` function
-
-In the InvokeAI root directory you will find a series of folders under
-`autoimport`, one each for main models, controlnets, embeddings and
-Loras.  Any models that you add to these directories will be scanned
-at startup time and registered automatically.
-
-You may create symbolic links from these folders to models located
-elsewhere on disk and they will be autoimported. You can also create
-subfolders and organize them as you wish.
-
-The location of the autoimport directories are controlled by settings
-in `invokeai.yaml`. See [Configuration](../features/CONFIGURATION.md).
-
-### Installing models that live in HuggingFace subfolders
-
-On rare occasions you may need to install a diffusers-style model that
-lives in a subfolder of a HuggingFace repo id. In this event, simply
-add ":_subfolder-name_" to the end of the repo id. For example, if the
-repo id is "monster-labs/control_v1p_sd15_qrcode_monster" and the model
-you wish to fetch lives in a subfolder named "v2", then the repo id to
-pass to the various model installers should be 
-
-```
-monster-labs/control_v1p_sd15_qrcode_monster:v2
-```
+[set up in the config file]: ../../features/CONFIGURATION#model-marketplace-api-keys

docs/installation/070_INSTALL_XFORMERS.md

@@ -1,204 +0,0 @@
----
-title: Installing xFormers
----
-
-# :material-image-size-select-large: Installing xformers
-
-xFormers is toolbox that integrates with the pyTorch and CUDA
-libraries to provide accelerated performance and reduced memory
-consumption for applications using the transformers machine learning
-architecture. After installing xFormers, InvokeAI users who have
-CUDA GPUs will see a noticeable decrease in GPU memory consumption and
-an increase in speed.
-
-xFormers can be installed into a working InvokeAI installation without
-any code changes or other updates. This document explains how to
-install xFormers.
-
-## Pip Install
-
-For both Windows and Linux, you can install `xformers` in just a
-couple of steps from the command line.
-
-If you are used to launching `invoke.sh` or `invoke.bat` to start
-InvokeAI, then run the launcher and select the "developer's console"
-to get to the command line. If you run invoke.py directly from the
-command line, then just be sure to activate it's virtual environment.
-
-Then run the following three commands:
-
-```sh
-pip install xformers~=0.0.22
-pip install triton    # WON'T WORK ON WINDOWS
-python -m xformers.info output
-```
-
-The first command installs `xformers`, the second installs the
-`triton` training accelerator, and the third prints out the `xformers`
-installation status. On Windows, please omit the `triton` package,
-which is not available on that platform.
-
-If all goes well, you'll see a report like the
-following:
-
-```sh
-xFormers 0.0.22
-memory_efficient_attention.cutlassF:               available
-memory_efficient_attention.cutlassB:               available
-memory_efficient_attention.flshattF:               available
-memory_efficient_attention.flshattB:               available
-memory_efficient_attention.smallkF:                available
-memory_efficient_attention.smallkB:                available
-memory_efficient_attention.tritonflashattF:        available
-memory_efficient_attention.tritonflashattB:        available
-indexing.scaled_index_addF:                        available
-indexing.scaled_index_addB:                        available
-indexing.index_select:                             available
-swiglu.dual_gemm_silu:                             available
-swiglu.gemm_fused_operand_sum:                     available
-swiglu.fused.p.cpp:                                available
-is_triton_available:                               True
-is_functorch_available:                            False
-pytorch.version:                                   2.1.0+cu121
-pytorch.cuda:                                      available
-gpu.compute_capability:                            8.9
-gpu.name:                                          NVIDIA GeForce RTX 4070
-build.info:                                        available
-build.cuda_version:                                1108
-build.python_version:                              3.10.11
-build.torch_version:                               2.1.0+cu121
-build.env.TORCH_CUDA_ARCH_LIST:                    5.0+PTX 6.0 6.1 7.0 7.5 8.0 8.6
-build.env.XFORMERS_BUILD_TYPE:                     Release
-build.env.XFORMERS_ENABLE_DEBUG_ASSERTIONS:        None
-build.env.NVCC_FLAGS:                              None
-build.env.XFORMERS_PACKAGE_FROM:                   wheel-v0.0.20
-build.nvcc_version:                                11.8.89
-source.privacy:                                    open source
-```
-
-## Source Builds
-
-`xformers` is currently under active development and at some point you
-may wish to build it from sourcce to get the latest features and
-bugfixes.
-
-### Source Build on Linux
-
-Note that xFormers only works with true NVIDIA GPUs and will not work
-properly with the ROCm driver for AMD acceleration.
-
-xFormers is not currently available as a pip binary wheel and must be
-installed from source. These instructions were written for a system
-running Ubuntu 22.04, but other Linux distributions should be able to
-adapt this recipe.
-
-#### 1. Install CUDA Toolkit 12.1
-
-You will need the CUDA developer's toolkit in order to compile and
-install xFormers. **Do not try to install Ubuntu's nvidia-cuda-toolkit
-package.** It is out of date and will cause conflicts among the NVIDIA
-driver and binaries. Instead install the CUDA Toolkit package provided
-by NVIDIA itself. Go to [CUDA Toolkit 12.1
-Downloads](https://developer.nvidia.com/cuda-12-1-0-download-archive)
-and use the target selection wizard to choose your platform and Linux
-distribution. Select an installer type of "runfile (local)" at the
-last step.
-
-This will provide you with a recipe for downloading and running a
-install shell script that will install the toolkit and drivers.
-
-#### 2. Confirm/Install pyTorch 2.1.0 with CUDA 12.1 support
-
-If you are using InvokeAI 3.0.2 or higher, these will already be
-installed. If not, you can check whether you have the needed libraries
-using a quick command. Activate the invokeai virtual environment,
-either by entering the "developer's console", or manually with a
-command similar to `source ~/invokeai/.venv/bin/activate` (depending
-on where your `invokeai` directory is.
-
-Then run the command:
-
-```sh
-python -c 'exec("import torch\nprint(torch.__version__)")'
-```
-
-If it prints __2.1.0+cu121__ you're good. If not, you can install the
-most up to date libraries with this command:
-
-```sh
-pip install --upgrade --force-reinstall torch torchvision
-```
-
-#### 3. Install the triton module
-
-This module isn't necessary for xFormers image inference optimization,
-but avoids a startup warning.
-
-```sh
-pip install triton
-```
-
-#### 4. Install source code build prerequisites
-
-To build xFormers from source, you will need the `build-essentials`
-package. If you don't have it installed already, run:
-
-```sh
-sudo apt install build-essential
-```
-
-#### 5. Build xFormers
-
-There is no pip wheel package for xFormers at this time (January
-2023). Although there is a conda package, InvokeAI no longer
-officially supports conda installations and you're on your own if you
-wish to try this route.
-
-Following the recipe provided at the [xFormers GitHub
-page](https://github.com/facebookresearch/xformers), and with the
-InvokeAI virtual environment active (see step 1) run the following
-commands:
-
-```sh
-pip install ninja
-export TORCH_CUDA_ARCH_LIST="6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6"
-pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers
-```
-
-The TORCH_CUDA_ARCH_LIST is a list of GPU architectures to compile
-xFormer support for. You can speed up compilation by selecting
-the architecture specific for your system. You'll find the list of
-GPUs and their architectures at NVIDIA's [GPU Compute
-Capability](https://developer.nvidia.com/cuda-gpus) table.
-
-If the compile and install completes successfully, you can check that
-xFormers is installed with this command:
-
-```sh
-python -m xformers.info
-```
-
-If suiccessful, the top of the listing should indicate "available" for
-each of the `memory_efficient_attention` modules, as shown here:
-
-```sh
-memory_efficient_attention.cutlassF:               available
-memory_efficient_attention.cutlassB:               available
-memory_efficient_attention.flshattF:               available
-memory_efficient_attention.flshattB:               available
-memory_efficient_attention.smallkF:                available
-memory_efficient_attention.smallkB:                available
-memory_efficient_attention.tritonflashattF:        available
-memory_efficient_attention.tritonflashattB:        available
-[...]
-```
-
-You can now launch InvokeAI and enjoy the benefits of xFormers.
-
-### Windows
-
-To come
-
-
----
-(c) Copyright 2023 Lincoln Stein and the InvokeAI Development Team

docs/installation/Developers_documentation/BUILDING_BINARY_INSTALLERS.md

@@ -1,89 +0,0 @@
----
-title: build binary installers
----
-
-# :simple-buildkite: How to build "binary" installers (InvokeAI-mac/windows/linux_on_*.zip)
-
-## 1. Ensure `installers/requirements.in` is correct
-
-and up to date on the branch to be installed.
-
-## <a name="step-2"></a> 2. Run `pip-compile` on each platform.
-
-On each target platform, in the branch that is to be installed, and
-inside the InvokeAI git root folder, run the following commands:
-
-```commandline
-conda activate invokeai # or however you activate python
-pip install pip-tools
-pip-compile --allow-unsafe --generate-hashes --output-file=binary_installer/<reqsfile>.txt binary_installer/requirements.in
-```
-where `<reqsfile>.txt` is whichever of
-```commandline
-py3.10-darwin-arm64-mps-reqs.txt
-py3.10-darwin-x86_64-reqs.txt
-py3.10-linux-x86_64-cuda-reqs.txt
-py3.10-windows-x86_64-cuda-reqs.txt
-```
-matches the current OS and architecture.
-> There is no way to cross-compile these. They must be done on a system matching the target OS and arch.
-
-## <a name="step-3"></a> 3. Set github repository and branch
-
-Once all reqs files have been collected and committed **to the branch
-to be installed**, edit `binary_installer/install.sh.in` and `binary_installer/install.bat.in` so that `RELEASE_URL`
-and `RELEASE_SOURCEBALL` point to the github repo and branch that is
-to be installed.
-
-For example, to install `main` branch of `InvokeAI`, they should be
-set as follows:
-
-`install.sh.in`:
-```commandline
-RELEASE_URL=https://github.com/invoke-ai/InvokeAI
-RELEASE_SOURCEBALL=/archive/refs/heads/main.tar.gz
-```
-
-`install.bat.in`:
-```commandline
-set RELEASE_URL=https://github.com/invoke-ai/InvokeAI
-set RELEASE_SOURCEBALL=/archive/refs/heads/main.tar.gz
-```
-
-Or, to install `damians-cool-feature` branch of `damian0815`, set them
-as follows:
-
-`install.sh.in`:
-```commandline
-RELEASE_URL=https://github.com/damian0815/InvokeAI
-RELEASE_SOURCEBALL=/archive/refs/heads/damians-cool-feature.tar.gz
-```
-
-`install.bat.in`:
-```commandline
-set RELEASE_URL=https://github.com/damian0815/InvokeAI
-set RELEASE_SOURCEBALL=/archive/refs/heads/damians-cool-feature.tar.gz
-```
-
-The branch and repo specified here **must** contain the correct reqs
-files. The installer zip files **do not** contain requirements files,
-they are pulled from the specified branch during the installation
-process.
-
-## 4. Create zip files.
-
-cd into the `installers/` folder and run
-`./create_installers.sh`. This will create
-`InvokeAI-mac_on_<branch>.zip`,
-`InvokeAI-windows_on_<branch>.zip` and
-`InvokeAI-linux_on_<branch>.zip`. These files can be distributed to end users.
-
-These zips will continue to function as installers for all future
-pushes to those branches, as long as necessary changes to
-`requirements.in` are propagated in a timely manner to the
-`py3.10-*-reqs.txt` files using pip-compile as outlined in [step
-2](#step-2).
-
-To actually install, users should unzip the appropriate zip file into an empty
-folder and run `install.sh` on macOS/Linux or `install.bat` on
-Windows.

docs/installation/INSTALLATION.md

@@ -1,88 +1,48 @@
-# Overview
+# Installation and Updating Overview
 
-We offer several ways to install InvokeAI, each one suited to your
-experience and preferences. We suggest that everyone start by
-reviewing the
-[hardware](010_INSTALL_AUTOMATED.md#hardware_requirements) and
-[software](010_INSTALL_AUTOMATED.md#software_requirements)
-requirements, as they are the same across each install method. Then
-pick the install method most suitable to your level of experience and
-needs.
+Before installing, review the [installation requirements] to ensure your system is set up properly.
 
-See the [troubleshooting
-section](010_INSTALL_AUTOMATED.md#troubleshooting) of the automated
-install guide for frequently-encountered installation issues.
+See the [FAQ] for frequently-encountered installation issues.
 
-This fork is supported across Linux, Windows and Macintosh. Linux users can use
-either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
-driver).
+If you need more help, join our [discord] or [create an issue].
 
+<h2>Automatic Install & Updates </h2>
 
-## **[Automated Installer (Recommended)](010_INSTALL_AUTOMATED.md)**
- ✅ This is the recommended installation method for first-time users. 
+✅ The automatic install is the best way to run InvokeAI. Check out the [installation guide] to get started.
 
-  This is a script that will install all of InvokeAI's essential
-  third party libraries and InvokeAI itself.
+⬆️ The same installer is also the best way to update InvokeAI - Simply rerun it for the same folder you installed to.
 
-🖥️ **Download the latest installer .zip file here** : https://github.com/invoke-ai/InvokeAI/releases/latest
-  
-- *Look for the file labelled "InvokeAI-installer-v4.X.X.zip" at the bottom of the page*
-- If you experience issues, read through the full [installation instructions](010_INSTALL_AUTOMATED.md) to make sure you have met all of the installation requirements. If you need more help, join the [Discord](discord.gg/invoke-ai) or create an issue on [Github](https://github.com/invoke-ai/InvokeAI).
+The installation process simply manages installation for the core libraries & application dependencies that run Invoke.
+Any models, images, or other assets in the Invoke root folder won't be affected by the installation process.
 
+<h2>Manual Install</h2>
 
+If you are familiar with python and want more control over the packages that are installed, you can [install InvokeAI manually via PyPI].
 
-## **[Manual Installation](020_INSTALL_MANUAL.md)**
-This method is recommended for experienced users and developers.
+Updates are managed by reinstalling the latest version through PyPi.
 
-  In this method you will manually run the commands needed to install
-  InvokeAI and its dependencies. We offer two recipes: one suited to
-  those who prefer the `conda` tool, and one suited to those who prefer
-  `pip` and Python virtual environments. In our hands the pip install
-  is faster and more reliable, but your mileage may vary.
-  Note that the conda installation method is currently deprecated and
-  will not be supported at some point in the future.
+<h2>Developer Install</h2>
+
+If you want to contribute to InvokeAI, consult the [developer install guide].
+
+<h2>Docker Install</h2>
 
-## **[Docker Installation](040_INSTALL_DOCKER.md)**
 This method is recommended for those familiar with running Docker containers.
 
 We offer a method for creating Docker containers containing InvokeAI and its dependencies. This method is recommended for individuals with experience with Docker containers and understand the pluses and minuses of a container-based install.
 
-## Other Installation Guides
-  - [PyPatchMatch](060_INSTALL_PATCHMATCH.md)
-  - [XFormers](070_INSTALL_XFORMERS.md)
-  - [CUDA and ROCm Drivers](030_INSTALL_CUDA_AND_ROCM.md)
-  - [Installing New Models](050_INSTALLING_MODELS.md)
+See the [docker installation guide].
 
-## :fontawesome-solid-computer: Hardware Requirements
+<h2>Other Installation Guides</h2>
 
-### :octicons-cpu-24: System
-
-You wil need one of the following:
-
-- :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
-- :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
-  only)
-- :fontawesome-brands-apple: An Apple computer with an M1 chip.
-
-** SDXL 1.0 Requirements*
-To use SDXL, user must have one of the following: 
-- :simple-nvidia: An NVIDIA-based graphics card with 8 GB or more VRAM memory.
-- :simple-amd: An AMD-based graphics card with 16 GB or more VRAM memory (Linux
-  only)
-- :fontawesome-brands-apple: An Apple computer with an M1 chip.
-
-
-### :fontawesome-solid-memory: Memory and Disk
-
-- At least 12 GB Main Memory RAM.
-- At least 18 GB of free disk space for the machine learning model, Python, and
-  all its dependencies.
-
-We do **not recommend** the following video cards due to issues with their
-running in half-precision mode and having insufficient VRAM to render 512x512
-images in full-precision mode:
-
-- NVIDIA 10xx series cards such as the 1080ti
-- GTX 1650 series cards
-- GTX 1660 series cards
+- [PyPatchMatch](060_INSTALL_PATCHMATCH.md)
+- [Installing Models](050_INSTALLING_MODELS.md)
 
+[install InvokeAI manually via PyPI]: 020_INSTALL_MANUAL.md
+[developer install guide]: INSTALL_DEVELOPMENT.md
+[docker installation guide]: 040_INSTALL_DOCKER.md
+[installation guide]: 010_INSTALL_AUTOMATED.md
+[FAQ]: ../help/FAQ.md
+[discord]: discord.gg/invoke-ai
+[create an issue]: https://github.com/invoke-ai/InvokeAI/issues
+[installation requirements]: INSTALL_REQUIREMENTS.md

docs/installation/INSTALL_DEVELOPMENT.md

@@ -0,0 +1,37 @@
+# Developer Install
+
+!!! warning
+
+    InvokeAI uses a SQLite database. By running on `main`, you accept responsibility for your database. This
+    means making regular backups (especially before pulling) and/or fixing it yourself in the event that a
+    PR introduces a schema change.
+
+    If you don't need persistent backend storage, you can use an ephemeral in-memory database by setting
+    `use_memory_db: true` in your `invokeai.yaml` file. You'll also want to set `scan_models_on_startup: true`
+    so that your models are registered on startup.
+
+    If this is untenable, you should run the application via the official installer or a manual install of the
+    python package from PyPI. These releases will not break your database.
+
+If you have an interest in how InvokeAI works, or you would like to add features or bugfixes, you are encouraged to install the source code for InvokeAI.
+
+!!! info "Why do I need the frontend toolchain?"
+
+    The repo doesn't contain a build of the frontend. You'll be responsible for rebuilding it (or running it in dev mode) to use the app, as described in the [frontend dev toolchain] docs.
+
+<h2> Installation </h2>
+
+1. [Fork and clone] the [InvokeAI repo].
+1. Follow the [manual installation] docs to create a new virtual environment for the development install.
+   - Create a new folder outside the repo root for the installation and create the venv inside that folder.
+   - When installing the InvokeAI package, add `-e` to the command so you get an [editable install].
+1. Install the [frontend dev toolchain] and do a production build of the UI as described.
+1. You can now run the app as described in the [manual installation] docs.
+
+As described in the [frontend dev toolchain] docs, you can run the UI using a dev server. If you do this, you won't need to continually rebuild the frontend. Instead, you run the dev server and use the app with the server URL it provides.
+
+[Fork and clone]: https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/fork-a-repo
+[InvokeAI repo]: https://github.com/invoke-ai/InvokeAI
+[frontend dev toolchain]: ../contributing/frontend/OVERVIEW.md
+[manual installation]: ./020_INSTALL_MANUAL.md
+[editable install]: https://pip.pypa.io/en/latest/cli/pip_install/#cmdoption-e

docs/installation/INSTALL_REQUIREMENTS.md

@@ -0,0 +1,181 @@
+# Requirements
+
+## GPU
+
+!!! warning "Problematic Nvidia GPUs"
+
+    We do not recommend these GPUs. They cannot operate with half precision, but have insufficient VRAM to generate 512x512 images at full precision.
+
+    - NVIDIA 10xx series cards such as the 1080 TI
+    - GTX 1650 series cards
+    - GTX 1660 series cards
+
+Invoke runs best with a dedicated GPU, but will fall back to running on CPU, albeit much slower. You'll need a beefier GPU for SDXL.
+
+!!! example "Stable Diffusion 1.5"
+
+    === "Nvidia"
+
+        ```
+        Any GPU with at least 4GB VRAM.
+        ```
+
+    === "AMD"
+
+        ```
+        Any GPU with at least 4GB VRAM. Linux only.
+        ```
+
+    === "Mac"
+
+        ```
+        Any Apple Silicon Mac with at least 8GB memory.
+        ```
+
+!!! example "Stable Diffusion XL"
+
+    === "Nvidia"
+
+        ```
+        Any GPU with at least 8GB VRAM.
+        ```
+
+    === "AMD"
+
+        ```
+        Any GPU with at least 16GB VRAM. Linux only.
+        ```
+
+    === "Mac"
+
+        ```
+        Any Apple Silicon Mac with at least 16GB memory.
+        ```
+
+## RAM
+
+At least 12GB of RAM.
+
+## Disk
+
+SSDs will, of course, offer the best performance.
+
+The base application disk usage depends on the torch backend.
+
+!!! example "Disk"
+
+    === "Nvidia (CUDA)"
+
+        ```
+        ~6.5GB
+        ```
+
+    === "AMD (ROCm)"
+
+        ```
+        ~12GB
+        ```
+
+    === "Mac (MPS)"
+
+        ```
+        ~3.5GB
+        ```
+
+You'll need to set aside some space for images, depending on how much you generate. A couple GB is enough to get started.
+
+You'll need a good chunk of space for models. Even if you only install the most popular models and the usual support models (ControlNet, IP Adapter ,etc), you will quickly hit 50GB of models.
+
+!!! info "`tmpfs` on Linux"
+
+    If your temporary directory is mounted as a `tmpfs`, ensure it has sufficient space.
+
+## Python
+
+Invoke requires python 3.10 or 3.11. If you don't already have one of these versions installed, we suggest installing 3.11, as it will be supported for longer.
+
+Check that your system has an up-to-date Python installed by running `python --version` in the terminal (Linux, macOS) or cmd/powershell (Windows).
+
+<h3>Installing Python (Windows)</h3>
+
+- Install python 3.11 with [an official installer].
+- The installer includes an option to add python to your PATH. Be sure to enable this. If you missed it, re-run the installer, choose to modify an existing installation, and tick that checkbox.
+- You may need to install [Microsoft Visual C++ Redistributable].
+
+<h3>Installing Python (macOS)</h3>
+
+- Install python 3.11 with [an official installer].
+- If model installs fail with a certificate error, you may need to run this command (changing the python version to match what you have installed): `/Applications/Python\ 3.10/Install\ Certificates.command`
+- If you haven't already, you will need to install the XCode CLI Tools by running `xcode-select --install` in a terminal.
+
+<h3>Installing Python (Linux)</h3>
+
+- Follow the [linux install instructions], being sure to install python 3.11.
+- You'll need to install `libglib2.0-0` and `libgl1-mesa-glx` for OpenCV to work. For example, on a Debian system: `sudo apt update && sudo apt install -y libglib2.0-0 libgl1-mesa-glx`
+
+## Drivers
+
+If you have an Nvidia or AMD GPU, you may need to manually install drivers or other support packages for things to work well or at all.
+
+### Nvidia
+
+Run `nvidia-smi` on your system's command line to verify that drivers and CUDA are installed. If this command fails, or doesn't report versions, you will need to install drivers.
+
+Go to the [CUDA Toolkit Downloads] and carefully follow the instructions for your system to get everything installed.
+
+Confirm that `nvidia-smi` displays driver and CUDA versions after installation.
+
+#### Linux - via Nvidia Container Runtime
+
+An alternative to installing CUDA locally is to use the [Nvidia Container Runtime] to run the application in a container.
+
+#### Windows - Nvidia cuDNN DLLs
+
+An out-of-date cuDNN library can greatly hamper performance on 30-series and 40-series cards. Check with the community on discord to compare your `it/s` if you think you may need this fix.
+
+First, locate the destination for the DLL files and make a quick back up:
+
+1. Find your InvokeAI installation folder, e.g. `C:\Users\Username\InvokeAI\`.
+1. Open the `.venv` folder, e.g. `C:\Users\Username\InvokeAI\.venv` (you may need to show hidden files to see it).
+1. Navigate deeper to the `torch` package, e.g. `C:\Users\Username\InvokeAI\.venv\Lib\site-packages\torch`.
+1. Copy the `lib` folder inside `torch` and back it up somewhere.
+
+Next, download and copy the updated cuDNN DLLs:
+
+1. Go to <https://developer.nvidia.com/cudnn>.
+1. Create an account if needed and log in.
+1. Choose the newest version of cuDNN that works with your GPU architecture. Consult the [cuDNN support matrix] to determine the correct version for your GPU.
+1. Download the latest version and extract it.
+1. Find the `bin` folder, e.g. `cudnn-windows-x86_64-SOME_VERSION\bin`.
+1. Copy and paste the `.dll` files into the `lib` folder you located earlier. Replace files when prompted.
+
+If, after restarting the app, this doesn't improve your performance, either restore your back up or re-run the installer to reset `torch` back to its original state.
+
+### AMD
+
+!!! info "Linux Only"
+
+    AMD GPUs are supported on Linux only, due to ROCm (the AMD equivalent of CUDA) support being Linux only.
+
+!!! warning "Bumps Ahead"
+
+    While the application does run on AMD GPUs, there are occasional bumps related to spotty torch support.
+
+Run `rocm-smi` on your system's command line verify that drivers and ROCm are installed. If this command fails, or doesn't report versions, you will need to install them.
+
+Go to the [ROCm Documentation] and carefully follow the instructions for your system to get everything installed.
+
+Confirm that `rocm-smi` displays driver and CUDA versions after installation.
+
+#### Linux - via Docker Container
+
+An alternative to installing ROCm locally is to use a [ROCm docker container] to run the application in a container.
+
+[ROCm docker container]: https://github.com/ROCm/ROCm-docker
+[ROCm Documentation]: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html
+[cuDNN support matrix]: https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html
+[Nvidia Container Runtime]: https://developer.nvidia.com/container-runtime
+[linux install instructions]: https://docs.python-guide.org/starting/install3/linux/
+[Microsoft Visual C++ Redistributable]: https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170
+[an official installer]: https://www.python.org/downloads/release/python-3118/
+[CUDA Toolkit Downloads]: https://developer.nvidia.com/cuda-downloads

docs/installation/deprecated_documentation/INSTALL_BINARY.md

@@ -1,64 +0,0 @@
----
-title: InvokeAI Binary Installer
----
-
-The InvokeAI binary installer is a shell script that will install InvokeAI onto a stock
-computer running recent versions of Linux, MacOSX or Windows. It will leave you
-with a version that runs a stable version of InvokeAI. When a new version of
-InvokeAI is released, you will download and reinstall the new version.
-
-If you wish to tinker with unreleased versions of InvokeAI that introduce
-potentially unstable new features, you should consider using the
-[source installer](INSTALL_SOURCE.md) or one of the
-[manual install](../020_INSTALL_MANUAL.md) methods.
-
-**Important Caveats**
-  - This script does not support AMD GPUs. For Linux AMD support,
-    please use the manual or source code installer methods.
-
-  - This script has difficulty on some Macintosh machines
-    that have previously been used for Python development due to
-    conflicting development tools versions. Mac developers may wish
-    to try the source code installer or one of the manual methods instead.
-
-!!! todo
-
-    Before you begin, make sure that you meet
-    the[hardware requirements](/#hardware-requirements) and has the
-    appropriate GPU drivers installed. In particular, if you are a Linux user with
-    an AMD GPU installed, you may need to install the
-    [ROCm-driver](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).
-
-Installation requires roughly 18G of free disk space to load the libraries and
-recommended model weights files.
-
-## Steps to Install
-
-1. Download the
-   [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest) of
-   InvokeAI's installer for your platform. Look for a file named `InvokeAI-binary-<your platform>.zip`
-
-2. Place the downloaded package someplace where you have plenty of HDD space,
-   and have full permissions (i.e. `~/` on Lin/Mac; your home folder on Windows)
-
-3. Extract the 'InvokeAI' folder from the downloaded package
-
-4. Open the extracted 'InvokeAI' folder
-
-5. Double-click 'install.bat' (Windows), or 'install.sh' (Lin/Mac) (or run from
-   a terminal)
-
-6. Follow the prompts
-
-7. After installation, please run the 'invoke.bat' file (on Windows) or
-   'invoke.sh' file (on Linux/Mac) to start InvokeAI.
-
-## Troubleshooting
-
-If you run into problems during or after installation, the InvokeAI team is
-available to help you. Either create an
-[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub site, or
-make a request for help on the "bugs-and-support" channel of our
-[Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100% volunteer
-organization, but typically somebody will be available to help you within 24
-hours, and often much sooner.

docs/installation/deprecated_documentation/INSTALL_JUPYTER.md

@@ -1,32 +0,0 @@
----
-title: Running InvokeAI on Google Colab using a Jupyter Notebook
----
-
-## Introduction
-
-We have a [Jupyter
-notebook](https://github.com/invoke-ai/InvokeAI/blob/main/notebooks/Stable_Diffusion_AI_Notebook.ipynb)
-with cell-by-cell installation steps. It will download the code in
-this repo as one of the steps, so instead of cloning this repo, simply
-download the notebook from the link above and load it up in VSCode
-(with the appropriate extensions installed)/Jupyter/JupyterLab and
-start running the cells one-by-one.
-
-!!! Note "you will need NVIDIA drivers, Python 3.10, and Git installed beforehand"
-
-## Running Online On Google Colabotary
-[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/invoke-ai/InvokeAI/blob/main/notebooks/Stable_Diffusion_AI_Notebook.ipynb)
-
-## Running Locally (Cloning)
-
-1. Install the Jupyter Notebook python library (one-time):
-pip install jupyter
-
-2. Clone the InvokeAI repository:
-git clone https://github.com/invoke-ai/InvokeAI.git
-cd invoke-ai
-3. Create a virtual environment using conda:
-conda create -n invoke jupyter
-4. Activate the environment and start the Jupyter notebook:
-conda activate invoke
-jupyter notebook

docs/installation/deprecated_documentation/INSTALL_LINUX.md

@@ -1,135 +0,0 @@
----
-title: Manual Installation, Linux
----
-
-# :fontawesome-brands-linux: Linux
-
-## Installation
-
-1.  You will need to install the following prerequisites if they are not already
-    available. Use your operating system's preferred installer.
-
-    - Python (version 3.8.5 recommended; higher may work)
-    - git
-
-2.  Install the Python Anaconda environment manager.
-
-    ```bash
-    ~$  wget https://repo.anaconda.com/archive/Anaconda3-2022.05-Linux-x86_64.sh
-    ~$  chmod +x Anaconda3-2022.05-Linux-x86_64.sh
-    ~$  ./Anaconda3-2022.05-Linux-x86_64.sh
-    ```
-
-    After installing anaconda, you should log out of your system and log back
-    in. If the installation worked, your command prompt will be prefixed by the
-    name of the current anaconda environment - `(base)`.
-
-3.  Copy the InvokeAI source code from GitHub:
-
-    ```bash
-    (base) ~$ git clone https://github.com/invoke-ai/InvokeAI.git
-    ```
-
-    This will create InvokeAI folder where you will follow the rest of the
-    steps.
-
-4.  Enter the newly-created InvokeAI folder. From this step forward make sure
-    that you are working in the InvokeAI directory!
-
-    ```bash
-    (base) ~$ cd InvokeAI
-    (base) ~/InvokeAI$
-    ```
-
-5.  Use anaconda to copy necessary python packages, create a new python
-    environment named `invokeai` and then activate the environment.
-
-    !!! todo "For systems with a CUDA (Nvidia) card:"
-
-       ```bash
-       (base) rm -rf src      # (this is a precaution in case there is already a src directory)
-       (base) ~/InvokeAI$ conda env create -f environment-cuda.yml
-       (base) ~/InvokeAI$ conda activate invokeai
-       (invokeai) ~/InvokeAI$
-       ```
-
-    !!! todo "For systems with an AMD card (using ROCm driver):"
-
-       ```bash
-       (base) rm -rf src      # (this is a precaution in case there is already a src directory)
-       (base) ~/InvokeAI$ conda env create -f environment-AMD.yml
-       (base) ~/InvokeAI$ conda activate invokeai
-       (invokeai) ~/InvokeAI$
-       ```
-
-    After these steps, your command prompt will be prefixed by `(invokeai)` as
-    shown above.
-
-6.  Load the big stable diffusion weights files and a couple of smaller
-    machine-learning models:
-
-    ```bash
-    (invokeai) ~/InvokeAI$ python3 scripts/configure_invokeai.py
-    ```
-
-    !!! note
-
-        This script will lead you through the process of creating an account on Hugging Face,
-        accepting the terms and conditions of the Stable Diffusion model license,
-        and obtaining an access token for downloading. It will then download and
-        install the weights files for you.
-
-        Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing
-        the same thing.
-
-7.  Start generating images!
-
-    !!! todo "Run InvokeAI!"
-
-        !!! warning "IMPORTANT"
-
-            Make sure that the conda environment is activated, which should create
-            `(invokeai)` in front of your prompt!
-
-        === "CLI"
-
-            ```bash
-            python scripts/invoke.py
-            ```
-
-        === "local Webserver"
-
-            ```bash
-            python scripts/invoke.py --web
-            ```
-
-        === "Public Webserver"
-
-            ```bash
-            python scripts/invoke.py --web --host 0.0.0.0
-            ```
-
-        To use an alternative model you may invoke the `!switch` command in
-        the CLI, or pass `--model <model_name>` during `invoke.py` launch for
-        either the CLI or the Web UI. See [Command Line
-        Client](../../deprecated/CLI.md#model-selection-and-importation). The
-        model names are defined in `configs/models.yaml`.
-
-8. Subsequently, to relaunch the script, be sure to run "conda activate
-   invokeai" (step 5, second command), enter the `InvokeAI` directory, and then
-   launch the invoke script (step 8). If you forget to activate the 'invokeai'
-   environment, the script will fail with multiple `ModuleNotFound` errors.
-
-## Updating to newer versions of the script
-
-This distribution is changing rapidly. If you used the `git clone` method
-(step 5) to download the InvokeAI directory, then to update to the latest and
-greatest version, launch the Anaconda window, enter `InvokeAI` and type:
-
-```bash
-(invokeai) ~/InvokeAI$ git pull
-(invokeai) ~/InvokeAI$ rm -rf src   # prevents conda freezing errors
-(invokeai) ~/InvokeAI$ conda env update -f environment.yml
-```
-
-This will bring your local copy into sync with the remote one.

docs/installation/deprecated_documentation/INSTALL_MAC.md

@@ -1,525 +0,0 @@
----
-title: Manual Installation, macOS
----
-
-# :fontawesome-brands-apple: macOS
-
-Invoke AI runs quite well on M1 Macs and we have a number of M1 users in the
-community.
-
-While the repo does run on Intel Macs, we only have a couple reports. If you
-have an Intel Mac and run into issues, please create an issue on Github and we
-will do our best to help.
-
-## Requirements
-
-- macOS 12.3 Monterey or later
-- About 10GB of storage (and 10GB of data if your internet connection has data
-  caps)
-- Any M1 Macs or an Intel Macs with 4GB+ of VRAM (ideally more)
-
-## Installation
-
-!!! todo "Homebrew"
-
-    First you will install the "brew" package manager. Skip this if brew is already installed.
-
-    ```bash title="install brew (and Xcode command line tools)"
-    /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
-    ```
-
-!!! todo "Conda Installation"
-
-    Now there are two different ways to set up the Python (miniconda) environment:
-
-       1. Standalone
-       2. with pyenv
-
-    If you don't know what we are talking about, choose Standalone. If you are familiar with python environments, choose "with pyenv"
-
-    === "Standalone"
-
-        ```bash title="Install cmake, protobuf, and rust"
-        brew install cmake protobuf rust
-        ```
-
-        ```bash title="Clone the InvokeAI repository"
-        # Clone the Invoke AI repo
-        git clone https://github.com/invoke-ai/InvokeAI.git
-        cd InvokeAI
-        ```
-
-        Choose the appropriate architecture for your system and install miniconda:
-
-        === "M1 arm64"
-
-            ```bash title="Install miniconda for M1 arm64"
-            curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh \
-              -o Miniconda3-latest-MacOSX-arm64.sh
-            /bin/bash Miniconda3-latest-MacOSX-arm64.sh
-            ```
-
-        === "Intel x86_64"
-
-            ```bash title="Install miniconda for Intel"
-            curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh \
-              -o Miniconda3-latest-MacOSX-x86_64.sh
-            /bin/bash Miniconda3-latest-MacOSX-x86_64.sh
-            ```
-
-    === "with pyenv"
-
-        ```bash
-        brew install pyenv-virtualenv
-        pyenv install anaconda3-2022.05
-        pyenv virtualenv anaconda3-2022.05
-        eval "$(pyenv init -)"
-        pyenv activate anaconda3-2022.05
-        ```
-
-!!! todo "Clone the Invoke AI repo"
-
-    ```bash
-    git clone https://github.com/invoke-ai/InvokeAI.git
-    cd InvokeAI
-    ```
-
-!!! todo "Create the environment & install packages"
-
-    === "M1 Mac"
-
-        ```bash
-        PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-arm64 conda env create -f environment-mac.yml
-        ```
-
-    === "Intel x86_64 Mac"
-
-        ```bash
-        PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-64 conda env create -f environment-mac.yml
-        ```
-
-    ```bash
-    # Activate the environment (you need to do this every time you want to run SD)
-    conda activate invokeai
-    ```
-
-    !!! info
-
-        `export PIP_EXISTS_ACTION=w` is a precaution to fix `conda env
-        create -f environment-mac.yml` never finishing in some situations. So
-        it isn't required but won't hurt.
-
-!!! todo "Download the model weight files"
-
-    The `configure_invokeai.py` script downloads and installs the model weight
-    files for you. It will lead you through the process of getting a Hugging Face
-    account, accepting the Stable Diffusion model weight license agreement, and
-    creating a download token:
-
-    ```bash
-    # This will take some time, depending on the speed of your internet connection
-    # and will consume about 10GB of space
-    python scripts/configure_invokeai.py
-    ```
-
-!!! todo "Run InvokeAI!"
-
-    !!! warning "IMPORTANT"
-
-        Make sure that the conda environment is activated, which should create
-        `(invokeai)` in front of your prompt!
-
-    === "CLI"
-
-        ```bash
-        python scripts/invoke.py
-        ```
-
-    === "local Webserver"
-
-        ```bash
-        python scripts/invoke.py --web
-        ```
-
-    === "Public Webserver"
-
-        ```bash
-        python scripts/invoke.py --web --host 0.0.0.0
-        ```
-
-    To use an alternative model you may invoke the `!switch` command in
-    the CLI, or pass `--model <model_name>` during `invoke.py` launch for
-    either the CLI or the Web UI. See [Command Line
-    Client](../../deprecated/CLI.md#model-selection-and-importation). The
-    model names are defined in `configs/models.yaml`.
-
----
-
-## Common problems
-
-After you followed all the instructions and try to run invoke.py, you might get
-several errors. Here's the errors I've seen and found solutions for.
-
-### Is it slow?
-
-```bash title="Be sure to specify 1 sample and 1 iteration."
-python ./scripts/orig_scripts/txt2img.py \
-  --prompt "ocean" \
-  --ddim_steps 5 \
-  --n_samples 1 \
-  --n_iter 1
-```
-
----
-
-### Doesn't work anymore?
-
-PyTorch nightly includes support for MPS. Because of this, this setup is
-inherently unstable. One morning I woke up and it no longer worked no matter
-what I did until I switched to miniforge. However, I have another Mac that works
-just fine with Anaconda. If you can't get it to work, please search a little
-first because many of the errors will get posted and solved. If you can't find a
-solution please [create an issue](https://github.com/invoke-ai/InvokeAI/issues).
-
-One debugging step is to update to the latest version of PyTorch nightly.
-
-```bash
-conda install \
-  pytorch \
-  torchvision \
-  -c pytorch-nightly \
-  -n invokeai
-```
-
-If it takes forever to run `conda env create -f environment-mac.yml`, try this:
-
-```bash
-git clean -f
-conda clean \
-  --yes \
-  --all
-```
-
-Or you could try to completley reset Anaconda:
-
-```bash
-conda update \
-  --force-reinstall \
-  -y \
-  -n base \
-  -c defaults conda
-```
-
----
-
-### "No module named cv2", torch, 'invokeai', 'transformers', 'taming', etc
-
-There are several causes of these errors:
-
-1. Did you remember to `conda activate invokeai`? If your terminal prompt begins
-   with "(invokeai)" then you activated it. If it begins with "(base)" or
-   something else you haven't.
-
-2. You might've run `./scripts/configure_invokeai.py` or `./scripts/invoke.py`
-   instead of `python ./scripts/configure_invokeai.py` or
-   `python ./scripts/invoke.py`. The cause of this error is long so it's below.
-
-    <!-- I could not find out where the error is, otherwise would have marked it as a footnote -->
-
-3. if it says you're missing taming you need to rebuild your virtual
-   environment.
-
-   ```bash
-   conda deactivate
-   conda env remove -n invokeai
-   conda env create -f environment-mac.yml
-   ```
-
-4. If you have activated the invokeai virtual environment and tried rebuilding
-   it, maybe the problem could be that I have something installed that you don't
-   and you'll just need to manually install it. Make sure you activate the
-   virtual environment so it installs there instead of globally.
-
-   ```bash
-   conda activate invokeai
-   pip install <package name>
-   ```
-
-You might also need to install Rust (I mention this again below).
-
----
-
-### How many snakes are living in your computer?
-
-You might have multiple Python installations on your system, in which case it's
-important to be explicit and consistent about which one to use for a given
-project. This is because virtual environments are coupled to the Python that
-created it (and all the associated 'system-level' modules).
-
-When you run `python` or `python3`, your shell searches the colon-delimited
-locations in the `PATH` environment variable (`echo $PATH` to see that list) in
-that order - first match wins. You can ask for the location of the first
-`python3` found in your `PATH` with the `which` command like this:
-
-```bash
-% which python3
-/usr/bin/python3
-```
-
-Anything in `/usr/bin` is
-[part of the OS](https://developer.apple.com/library/archive/documentation/FileManagement/Conceptual/FileSystemProgrammingGuide/FileSystemOverview/FileSystemOverview.html#//apple_ref/doc/uid/TP40010672-CH2-SW6).
-However, `/usr/bin/python3` is not actually python3, but rather a stub that
-offers to install Xcode (which includes python 3). If you have Xcode installed
-already, `/usr/bin/python3` will execute
-`/Library/Developer/CommandLineTools/usr/bin/python3` or
-`/Applications/Xcode.app/Contents/Developer/usr/bin/python3` (depending on which
-Xcode you've selected with `xcode-select`).
-
-Note that `/usr/bin/python` is an entirely different python - specifically,
-python 2. Note: starting in macOS 12.3, `/usr/bin/python` no longer exists.
-
-```bash
-% which python3
-/opt/homebrew/bin/python3
-```
-
-If you installed python3 with Homebrew and you've modified your path to search
-for Homebrew binaries before system ones, you'll see the above path.
-
-```bash
-% which python
-/opt/anaconda3/bin/python
-```
-
-If you have Anaconda installed, you will see the above path. There is a
-`/opt/anaconda3/bin/python3` also.
-
-We expect that `/opt/anaconda3/bin/python` and `/opt/anaconda3/bin/python3`
-should actually be the _same python_, which you can verify by comparing the
-output of `python3 -V` and `python -V`.
-
-```bash
-(invokeai) % which python
-/Users/name/miniforge3/envs/invokeai/bin/python
-```
-
-The above is what you'll see if you have miniforge and correctly activated the
-invokeai environment, while usingd the standalone setup instructions above.
-
-If you otherwise installed via pyenv, you will get this result:
-
-```bash
-(anaconda3-2022.05) % which python
-/Users/name/.pyenv/shims/python
-```
-
-It's all a mess and you should know
-[how to modify the path environment variable](https://support.apple.com/guide/terminal/use-environment-variables-apd382cc5fa-4f58-4449-b20a-41c53c006f8f/mac)
-if you want to fix it. Here's a brief hint of the most common ways you can
-modify it (don't really have the time to explain it all here).
-
-- ~/.zshrc
-- ~/.bash_profile
-- ~/.bashrc
-- /etc/paths.d
-- /etc/path
-
-Which one you use will depend on what you have installed, except putting a file
-in /etc/paths.d - which also is the way I prefer to do.
-
-Finally, to answer the question posed by this section's title, it may help to
-list all of the `python` / `python3` things found in `$PATH` instead of just the
-first hit. To do so, add the `-a` switch to `which`:
-
-```bash
-% which -a python3
-...
-```
-
-This will show a list of all binaries which are actually available in your PATH.
-
----
-
-### Debugging?
-
-Tired of waiting for your renders to finish before you can see if it works?
-Reduce the steps! The image quality will be horrible but at least you'll get
-quick feedback.
-
-```bash
-python ./scripts/txt2img.py \
-  --prompt "ocean" \
-  --ddim_steps 5 \
-  --n_samples 1 \
-  --n_iter 1
-```
-
----
-
-### OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'
-
-```bash
-python scripts/configure_invokeai.py
-```
-
----
-
-### "The operator [name] is not current implemented for the MPS device." (sic)
-
-!!! example "example error"
-
-    ```bash
-    ... NotImplementedError: The operator 'aten::_index_put_impl_' is not current
-    implemented for the MPS device. If you want this op to be added in priority
-    during the prototype phase of this feature, please comment on
-    https://github.com/pytorch/pytorch/issues/77764.
-    As a temporary fix, you can set the environment variable
-    `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op.
-    WARNING: this will be slower than running natively on MPS.
-    ```
-
-The InvokeAI version includes this fix in
-[environment-mac.yml](https://github.com/invoke-ai/InvokeAI/blob/main/environment-mac.yml).
-
-### "Could not build wheels for tokenizers"
-
-I have not seen this error because I had Rust installed on my computer before I
-started playing with Stable Diffusion. The fix is to install Rust.
-
-```bash
-curl \
-  --proto '=https' \
-  --tlsv1.2 \
-  -sSf https://sh.rustup.rs | sh
-```
-
----
-
-### How come `--seed` doesn't work?
-
-!!! Information
-
-    Completely reproducible results are not guaranteed across PyTorch releases,
-    individual commits, or different platforms. Furthermore, results may not be
-    reproducible between CPU and GPU executions, even when using identical seeds.
-
-[PyTorch docs](https://pytorch.org/docs/stable/notes/randomness.html)
-
-Second, we might have a fix that at least gets a consistent seed sort of. We're
-still working on it.
-
-### libiomp5.dylib error?
-
-```bash
-OMP: Error #15: Initializing libiomp5.dylib, but found libomp.dylib already initialized.
-```
-
-You are likely using an Intel package by mistake. Be sure to run conda with the
-environment variable `CONDA_SUBDIR=osx-arm64`, like so:
-
-`CONDA_SUBDIR=osx-arm64 conda install ...`
-
-This error happens with Anaconda on Macs when the Intel-only `mkl` is pulled in
-by a dependency.
-[nomkl](https://stackoverflow.com/questions/66224879/what-is-the-nomkl-python-package-used-for)
-is a metapackage designed to prevent this, by making it impossible to install
-`mkl`, but if your environment is already broken it may not work.
-
-Do _not_ use `os.environ['KMP_DUPLICATE_LIB_OK']='True'` or equivalents as this
-masks the underlying issue of using Intel packages.
-
----
-
-### Not enough memory
-
-This seems to be a common problem and is probably the underlying problem for a
-lot of symptoms (listed below). The fix is to lower your image size or to add
-`model.half()` right after the model is loaded. I should probably test it out.
-I've read that the reason this fixes problems is because it converts the model
-from 32-bit to 16-bit and that leaves more RAM for other things. I have no idea
-how that would affect the quality of the images though.
-
-See [this issue](https://github.com/CompVis/stable-diffusion/issues/71).
-
----
-
-### "Error: product of dimension sizes > 2\*\*31'"
-
-This error happens with img2img, which I haven't played with too much yet. But I
-know it's because your image is too big or the resolution isn't a multiple of
-32x32. Because the stable-diffusion model was trained on images that were 512 x
-512, it's always best to use that output size (which is the default). However,
-if you're using that size and you get the above error, try 256 x 256 or 512 x
-256 or something as the source image.
-
-BTW, 2\*\*31-1 =
-[2,147,483,647](https://en.wikipedia.org/wiki/2,147,483,647#In_computing), which
-is also 32-bit signed [LONG_MAX](https://en.wikipedia.org/wiki/C_data_types) in
-C.
-
----
-
-### I just got Rickrolled! Do I have a virus?
-
-You don't have a virus. It's part of the project. Here's
-[Rick](https://github.com/invoke-ai/InvokeAI/blob/main/assets/rick.jpeg) and
-here's
-[the code](https://github.com/invoke-ai/InvokeAI/blob/69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc/scripts/txt2img.py#L79)
-that swaps him in. It's a NSFW filter, which IMO, doesn't work very good (and we
-call this "computer vision", sheesh).
-
----
-
-### My images come out black
-
-We might have this fixed, we are still testing.
-
-There's a [similar issue](https://github.com/CompVis/stable-diffusion/issues/69)
-on CUDA GPU's where the images come out green. Maybe it's the same issue?
-Someone in that issue says to use "--precision full", but this fork actually
-disables that flag. I don't know why, someone else provided that code and I
-don't know what it does. Maybe the `model.half()` suggestion above would fix
-this issue too. I should probably test it.
-
-### "view size is not compatible with input tensor's size and stride"
-
-```bash
-File "/opt/anaconda3/envs/invokeai/lib/python3.10/site-packages/torch/nn/functional.py", line 2511, in layer_norm
-return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
-RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
-```
-
-Update to the latest version of invoke-ai/InvokeAI. We were patching pytorch but
-we found a file in stable-diffusion that we could change instead. This is a
-32-bit vs 16-bit problem.
-
-### The processor must support the Intel bla bla bla
-
-What? Intel? On an Apple Silicon?
-
-```bash
-Intel MKL FATAL ERROR: This system does not meet the minimum requirements for use of the Intel(R) Math Kernel Library. The processor must support the Intel(R) Supplemental Streaming SIMD Extensions 3 (Intel(R) SSSE3) instructions. The processor must support the Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) instructions. The processor must support the Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
-```
-
-This is due to the Intel `mkl` package getting picked up when you try to install
-something that depends on it-- Rosetta can translate some Intel instructions but
-not the specialized ones here. To avoid this, make sure to use the environment
-variable `CONDA_SUBDIR=osx-arm64`, which restricts the Conda environment to only
-use ARM packages, and use `nomkl` as described above.
-
----
-
-### input types 'tensor<2x1280xf32>' and 'tensor<\*xf16>' are not broadcast compatible
-
-May appear when just starting to generate, e.g.:
-
-```bash
-invoke> clouds
-Generating:   0%|                                                              | 0/1 [00:00<?, ?it/s]/Users/[...]/dev/stable-diffusion/ldm/modules/embedding_manager.py:152: UserWarning: The operator 'aten::nonzero' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/_temp/anaconda/conda-bld/pytorch_1662016319283/work/aten/src/ATen/mps/MPSFallback.mm:11.)
-  placeholder_idx = torch.where(
-                                                                                                    loc("mps_add"("(mpsFileLoc): /AppleInternal/Library/BuildRoots/20d6c351-ee94-11ec-bcaf-7247572f23b4/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShadersGraph/mpsgraph/MetalPerformanceShadersGraph/Core/Files/MPSGraphUtilities.mm":219:0)): error: input types 'tensor<2x1280xf32>' and 'tensor<*xf16>' are not broadcast compatible
-LLVM ERROR: Failed to infer result type(s).
-Abort trap: 6
-/Users/[...]/opt/anaconda3/envs/invokeai/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
-  warnings.warn('resource_tracker: There appear to be %d '
-```

docs/installation/deprecated_documentation/INSTALL_PCP.md

@@ -1,17 +0,0 @@
----
-title: Installing InvokeAI with the Pre-Compiled PIP Installer
----
-
-# THIS NEEDS TO BE FLESHED OUT
-
-## Introduction
-
-## Walkthrough
-
-## Updating to newer versions
-
-### Updating the stable version
-
-### Updating to the development version
-
-## Troubleshooting

docs/installation/deprecated_documentation/INSTALL_SOURCE.md

@@ -1,225 +0,0 @@
----
-title: Source Installer
----
-
-# The InvokeAI Source Installer
-
-## Introduction
-
-The source installer is a shell script that attempts to automate every step
-needed to install and run InvokeAI on a stock computer running recent versions
-of Linux, MacOS or Windows. It will leave you with a version that runs a stable
-version of InvokeAI with the option to upgrade to experimental versions later.
-
-Before you begin, make sure that you meet the
-[hardware requirements](../../index.md#hardware-requirements) and has the appropriate
-GPU drivers installed. In particular, if you are a Linux user with an AMD GPU
-installed, you may need to install the
-[ROCm driver](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).
-
-Installation requires roughly 18G of free disk space to load the libraries and
-recommended model weights files.
-
-## Walk through
-
-Though there are multiple steps, there really is only one click involved to kick
-off the process.
-
-1.  The source installer is distributed in ZIP files. Go to the
-    [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest), and
-    look for a series of files named:
-
-    - [invokeAI-src-installer-2.2.3-mac.zip](https://github.com/invoke-ai/InvokeAI/releases/latest/download/invokeAI-src-installer-2.2.3-mac.zip)
-    - [invokeAI-src-installer-2.2.3-windows.zip](https://github.com/invoke-ai/InvokeAI/releases/latest/download/invokeAI-src-installer-2.2.3-windows.zip)
-    - [invokeAI-src-installer-2.2.3-linux.zip](https://github.com/invoke-ai/InvokeAI/releases/latest/download/invokeAI-src-installer-2.2.3-linux.zip)
-
-    Download the one that is appropriate for your operating system.
-
-2.  Unpack the zip file into a directory that has at least 18G of free space. Do
-    _not_ unpack into a directory that has an earlier version of InvokeAI.
-
-    This will create a new directory named "InvokeAI". This example shows how
-    this would look using the `unzip` command-line tool, but you may use any
-    graphical or command-line Zip extractor:
-
-    ```cmd
-    C:\Documents\Linco> unzip invokeAI-windows.zip
-    Archive:  C: \Linco\Downloads\invokeAI-linux.zip
-    creating: invokeAI\
-    inflating: invokeAI\install.bat
-    inflating: invokeAI\readme.txt
-    ```
-
-3. If you are a macOS user, you may need to install the Xcode command line tools.
-   These are a set of tools that are needed to run certain applications in a Terminal,
-   including InvokeAI. This package is provided directly by Apple.
-
-   To install, open a terminal window and run `xcode-select --install`. You will get
-   a macOS system popup guiding you through the install. If you already have them
-   installed, you will instead see some output in the Terminal advising you that the
-   tools are already installed.
-
-   More information can be found here:
-   https://www.freecodecamp.org/news/install-xcode-command-line-tools/
-
-4.  If you are using a desktop GUI, double-click the installer file. It will be
-    named `install.bat` on Windows systems and `install.sh` on Linux and
-    Macintosh systems.
-
-5.  Alternatively, from the command line, run the shell script or .bat file:
-
-    ```cmd
-    C:\Documents\Linco> cd invokeAI
-    C:\Documents\Linco\invokeAI> install.bat
-    ```
-
-6.  Sit back and let the install script work. It will install various binary
-    requirements including Conda, Git and Python, then download the current
-    InvokeAI code and install it along with its dependencies.
-
-    Be aware that some of the library download and install steps take a long time.
-    In particular, the `pytorch` package is quite large and often appears to get
-    "stuck" at 99.9%. Similarly, the `pip installing requirements` step may
-    appear to hang. Have patience and the installation step will eventually
-    resume. However, there are occasions when the library install does
-    legitimately get stuck. If you have been waiting for more than ten minutes
-    and nothing is happening, you can interrupt the script with ^C. You may restart
-    it and it will pick up where it left off.
-
-7.  After installation completes, the installer will launch a script called
-    `configure_invokeai.py`, which will guide you through the first-time process of
-    selecting one or more Stable Diffusion model weights files, downloading and
-    configuring them.
-
-    Note that the main Stable Diffusion weights file is protected by a license
-    agreement that you must agree to in order to use. The script will list the
-    steps you need to take to create an account on the official site that hosts
-    the weights files, accept the agreement, and provide an access token that
-    allows InvokeAI to legally download and install the weights files.
-
-    If you have already downloaded the weights file(s) for another Stable
-    Diffusion distribution, you may skip this step (by selecting "skip" when
-    prompted) and configure InvokeAI to use the previously-downloaded files. The
-    process for this is described in [Installing Models](../050_INSTALLING_MODELS.md).
-
-8.  The script will now exit and you'll be ready to generate some images. The
-    invokeAI directory will contain numerous files. Look for a shell script
-    named `invoke.sh` (Linux/Mac) or `invoke.bat` (Windows). Launch the script
-    by double-clicking it or typing its name at the command-line:
-
-    ```cmd
-    C:\Documents\Linco> cd invokeAI
-    C:\Documents\Linco\invokeAI> invoke.bat
-    ```
-
-The `invoke.bat` (`invoke.sh`) script will give you the choice of starting (1)
-the command-line interface, or (2) the web GUI. If you start the latter, you can
-load the user interface by pointing your browser at http://localhost:9090.
-
-The `invoke` script also offers you a third option labeled "open the developer
-console". If you choose this option, you will be dropped into a command-line
-interface in which you can run python commands directly, access developer tools,
-and launch InvokeAI with customized options. To do the latter, you would launch
-the script `scripts/invoke.py` as shown in this example:
-
-```cmd
-python scripts/invoke.py --web --max_load_models=3 \
-    --model=waifu-1.3 --steps=30 --outdir=C:/Documents/AIPhotos
-```
-
-These options are described in detail in the
-[Command-Line Interface](../../deprecated/CLI.md) documentation.
-
-## Troubleshooting
-
-_Package dependency conflicts_ If you have previously installed
-InvokeAI or another Stable Diffusion package, the installer may
-occasionally pick up outdated libraries and either the installer or
-`invoke` will fail with complaints out library conflicts. There are
-two steps you can take to clear this problem. Both of these are done
-from within the "developer's console", which you can get to by
-launching `invoke.sh` (or `invoke.bat`) and selecting launch option
-#3:
-
-1. Remove the previous `invokeai` environment completely. From within
-   the developer's console, give the command `conda env remove -n
-   invokeai`. This will delete previous files installed by `invoke`.
-
-   Then exit from the developer's console and launch the script
-   `update.sh` (or `update.bat`). This will download the most recent
-   InvokeAI (including bug fixes) and reinstall the environment.
-   You should then be able to run `invoke.sh`/`invoke.bat`.
-
-2. If this doesn't work, you can try cleaning your system's conda
-   cache. This is slightly more extreme, but won't interfere with
-   any other python-based programs installed on your computer.
-   From the developer's console, run the command `conda clean -a`
-   and answer "yes" to all prompts.
-
-   After this is done, run `update.sh` and try again as before.
-
-_"Corrupted configuration file."__ Everything seems to install ok, but
-`invoke` complains of a corrupted configuration file and goes calls
-`configure_invokeai.py` to fix, but this doesn't fix the problem.
-
-This issue is often caused by a misconfigured configuration directive
-in the `.invokeai` initialization file that contains startup settings.
-This can be corrected by fixing the offending line.
-
-First find `.invokeai`. It is a small text file located in your home
-directory, `~/.invokeai` on Mac and Linux systems, and `C:\Users\*your
-name*\.invokeai` on Windows systems. Open it with a text editor
-(e.g. Notepad on Windows, TextEdit on Macs, or `nano` on Linux)
-and look for the lines starting with `--root` and `--outdir`.
-
-An example is here:
-
-```cmd
---root="/home/lstein/invokeai"
---outdir="/home/lstein/invokeai/outputs"
-```
-
-There should not be whitespace before or after the directory paths,
-and the paths should not end with slashes:
-
-```cmd
---root="/home/lstein/invokeai "     # wrong! no whitespace here
---root="/home\lstein\invokeai\"     # wrong! shouldn't end in a slash
-```
-
-Fix the problem with your text editor and save as a **plain text**
-file. This should clear the issue.
-
-_If none of these maneuvers fixes the problem_ then please report the
-problem to the [InvokeAI
-Issues](https://github.com/invoke-ai/InvokeAI/issues) section, or
-visit our [Discord Server](https://discord.gg/ZmtBAhwWhy) for interactive assistance.
-
-## Updating to newer versions
-
-This section describes how to update InvokeAI to new versions of the software.
-
-### Updating the stable version
-
-This distribution is changing rapidly, and we add new features on a daily basis.
-To update to the latest released version (recommended), run the `update.sh`
-(Linux/Mac) or `update.bat` (Windows) scripts. This will fetch the latest
-release and re-run the `configure_invokeai` script to download any updated models
-files that may be needed. You can also use this to add additional models that
-you did not select at installation time.
-
-You can now close the developer console and run `invoke` as before. If you get
-complaints about missing models, then you may need to do the additional step of
-running `configure_invokeai.py`. This happens relatively infrequently. To do this,
-simply open up the developer's console again and type
-`python scripts/configure_invokeai.py`.
-
-## Troubleshooting
-
-If you run into problems during or after installation, the InvokeAI team is
-available to help you. Either create an
-[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub site, or
-make a request for help on the "bugs-and-support" channel of our
-[Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100% volunteer
-organization, but typically somebody will be available to help you within 24
-hours, and often much sooner.

docs/installation/deprecated_documentation/INSTALL_WINDOWS.md

@@ -1,137 +0,0 @@
----
-title: Manual Installation, Windows
----
-
-# :fontawesome-brands-windows: Windows
-
-## **Notebook install (semi-automated)**
-
-We have a
-[Jupyter notebook](https://github.com/invoke-ai/InvokeAI/blob/main/notebooks/Stable_Diffusion_AI_Notebook.ipynb)
-with cell-by-cell installation steps. It will download the code in this repo as
-one of the steps, so instead of cloning this repo, simply download the notebook
-from the link above and load it up in VSCode (with the appropriate extensions
-installed)/Jupyter/JupyterLab and start running the cells one-by-one.
-
-Note that you will need NVIDIA drivers, Python 3.10, and Git installed beforehand.
-
-## **Manual Install with Conda**
-
-1. Install Anaconda3 (miniconda3 version) from [here](https://docs.anaconda.com/anaconda/install/windows/)
-
-2. Install Git from [here](https://git-scm.com/download/win)
-
-3. Launch Anaconda from the Windows Start menu. This will bring up a command
-   window. Type all the remaining commands in this window.
-
-4. Run the command:
-
-    ```batch
-    git clone https://github.com/invoke-ai/InvokeAI.git
-    ```
-
-    This will create stable-diffusion folder where you will follow the rest of
-    the steps.
-
-5. Enter the newly-created InvokeAI folder. From this step forward make sure that you are working in the InvokeAI directory!
-
-    ```batch
-    cd InvokeAI
-    ```
-
-6. Run the following commands:
-
-    !!! todo "For systems with a CUDA (Nvidia) card:"
-
-       ```bash
-       rmdir src      # (this is a precaution in case there is already a src directory)
-       conda env create -f environment-cuda.yml
-       conda activate invokeai
-       (invokeai)>
-       ```
-
-    !!! todo "For systems with an AMD card (using ROCm driver):"
-
-       ```bash
-       rmdir src      # (this is a precaution in case there is already a src directory)
-       conda env create -f environment-AMD.yml
-       conda activate invokeai
-       (invokeai)>
-       ```
-
-    This will install all python requirements and activate the "invokeai" environment
-    which sets PATH and other environment variables properly.
-
-7. Load the big stable diffusion weights files and a couple of smaller machine-learning models:
-
-    ```bash
-    python scripts/configure_invokeai.py
-    ```
-
-    !!! note
-
-          This script will lead you through the process of creating an account on Hugging Face,
-          accepting the terms and conditions of the Stable Diffusion model license, and
-          obtaining an access token for downloading. It will then download and install the
-          weights files for you.
-
-          Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing the
-          same thing.
-
-8. Start generating images!
-
-    !!! example ""
-
-        !!! warning "IMPORTANT"
-
-            Make sure that the conda environment is activated, which should create
-            `(invokeai)` in front of your prompt!
-
-        === "CLI"
-
-            ```bash
-            python scripts/invoke.py
-            ```
-
-        === "local Webserver"
-
-            ```bash
-            python scripts/invoke.py --web
-            ```
-
-        === "Public Webserver"
-
-            ```bash
-            python scripts/invoke.py --web --host 0.0.0.0
-            ```
-
-        To use an alternative model you may invoke the `!switch` command in
-        the CLI, or pass `--model <model_name>` during `invoke.py` launch for
-        either the CLI or the Web UI. See [Command Line
-        Client](../../deprecated/CLI.md#model-selection-and-importation). The
-        model names are defined in `configs/models.yaml`.
-
-9. Subsequently, to relaunch the script, first activate the Anaconda
-command window (step 3),enter the InvokeAI directory (step 5, `cd
-\path\to\InvokeAI`), run `conda activate invokeai` (step 6b), and then
-launch the invoke script (step 9).
-
-!!! tip "Tildebyte has written an alternative"
-
-    ["Easy peasy Windows install"](https://github.com/invoke-ai/InvokeAI/wiki/Easy-peasy-Windows-install)
-    which uses the Windows Powershell and pew. If you are having trouble with
-    Anaconda on Windows, give this a try (or try it first!)
-
----
-
-This distribution is changing rapidly. If you used the `git clone` method
-(step 5) to download the stable-diffusion directory, then to update to the
-latest and greatest version, launch the Anaconda window, enter
-`stable-diffusion`, and type:
-
-```bash
-git pull
-conda env update
-```
-
-This will bring your local copy into sync with the remote one.

installer/install.bat.in

@@ -16,7 +16,7 @@ if "%1" == "use-cache" (
 @rem The version in the next line is replaced by an up to date release number
 @rem when create_installer.sh is run. Change the release number there.
 set INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
-set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
+set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/help/FAQ/
 set PYTHON_URL=https://www.python.org/downloads/windows/
 set MINIMUM_PYTHON_VERSION=3.10.0
 set PYTHON_URL=https://www.python.org/downloads/release/python-3109/

installer/lib/installer.py

@@ -3,8 +3,10 @@
 InvokeAI installer script
 """
 
+import locale
 import os
 import platform
+import re
 import shutil
 import subprocess
 import sys
@@ -16,12 +18,23 @@ from typing import Optional, Tuple
 SUPPORTED_PYTHON = ">=3.10.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
 BOOTSTRAP_VENV_PREFIX = "invokeai-installer-tmp"
+DOCS_URL = "https://invoke-ai.github.io/InvokeAI/"
+DISCORD_URL = "https://discord.gg/ZmtBAhwWhy"
 
 OS = platform.uname().system
 ARCH = platform.uname().machine
 VERSION = "latest"
 
 
+def get_version_from_wheel_filename(wheel_filename: str) -> str:
+    match = re.search(r"-(\d+\.\d+\.\d+)", wheel_filename)
+    if match:
+        version = match.group(1)
+        return version
+    else:
+        raise ValueError(f"Could not extract version from wheel filename: {wheel_filename}")
+
+
 class Installer:
     """
     Deploys an InvokeAI installation into a given path
@@ -36,7 +49,7 @@ class Installer:
         self.bootstrap()
         self.available_releases = get_github_releases()
 
-    def mktemp_venv(self) -> TemporaryDirectory:
+    def mktemp_venv(self) -> TemporaryDirectory[str]:
         """
         Creates a temporary virtual environment for the installer itself
 
@@ -58,7 +71,7 @@ class Installer:
 
         return venv_dir
 
-    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory | None:
+    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory[str] | None:
         """
         Bootstrap the installer venv with packages required at install time
         """
@@ -87,7 +100,7 @@ class Installer:
         except subprocess.CalledProcessError as e:
             print(e)
 
-    def app_venv(self, venv_parent) -> Path:
+    def app_venv(self, venv_parent: Path) -> Path:
         """
         Create a virtualenv for the InvokeAI installation
         """
@@ -106,26 +119,29 @@ class Installer:
         return venv_dir
 
     def install(
-        self, version=None, root: str = "~/invokeai", yes_to_all=False, find_links: Optional[Path] = None
+        self,
+        root: str = "~/invokeai",
+        yes_to_all: bool = False,
+        find_links: Optional[str] = None,
+        wheel: Optional[Path] = None,
     ) -> None:
-        """
-        Install the InvokeAI application into the given runtime path
+        """Install the InvokeAI application into the given runtime path
 
-        :param root: Destination path for the installation
-        :type root: str
-        :param version: InvokeAI version to install
-        :type version: str
-        :param yes: Accept defaults to all questions
-        :type yes: bool
-        :param find_links: A local directory to search for requirement wheels before going to remote indexes
-        :type find_links: Path
+        Args:
+            root: Destination path for the installation
+            yes_to_all: Accept defaults to all questions
+            find_links: A local directory to search for requirement wheels before going to remote indexes
+            wheel: A wheel file to install
         """
 
         import messages
 
-        messages.welcome(self.available_releases)
-
-        version = messages.choose_version(self.available_releases)
+        if wheel:
+            messages.installing_from_wheel(wheel.name)
+            version = get_version_from_wheel_filename(wheel.name)
+        else:
+            messages.welcome(self.available_releases)
+            version = messages.choose_version(self.available_releases)
 
         auto_dest = Path(os.environ.get("INVOKEAI_ROOT", root)).expanduser().resolve()
         destination = auto_dest if yes_to_all else messages.dest_path(root)
@@ -140,15 +156,25 @@ class Installer:
 
         # install dependencies and the InvokeAI application
         (extra_index_url, optional_modules) = get_torch_source() if not yes_to_all else (None, None)
-        self.instance.install(
-            extra_index_url,
-            optional_modules,
-            find_links,
-        )
+        self.instance.install(extra_index_url, optional_modules, find_links, wheel)
 
         # install the launch/update scripts into the runtime directory
         self.instance.install_user_scripts()
 
+        message = f"""
+*** Installation Successful ***
+
+To start the application, run:
+    {destination}/invoke.{"bat" if sys.platform == "win32" else "sh"}
+
+For more information, troubleshooting and support, visit our docs at:
+    {DOCS_URL}
+
+Join the community on Discord:
+    {DISCORD_URL}
+"""
+        print(message)
+
 
 class InvokeAiInstance:
     """
@@ -178,18 +204,20 @@ class InvokeAiInstance:
 
         return (self.runtime, self.venv)
 
-    def install(self, extra_index_url=None, optional_modules=None, find_links=None):
-        """
-        Install the package from PyPi.
+    def install(
+        self,
+        extra_index_url: Optional[str] = None,
+        optional_modules: Optional[str] = None,
+        find_links: Optional[str] = None,
+        wheel: Optional[Path] = None,
+    ):
+        """Install the package from PyPi or a wheel, if provided.
 
-        :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
-        :type extra_index_url: str
-
-        :param optional_modules: optional modules to install using "[module1,module2]" format.
-        :type optional_modules: str
-
-        :param find_links: path to a directory containing wheels to be searched prior to going to the internet
-        :type find_links: Path
+        Args:
+            extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
+            optional_modules: optional modules to install using "[module1,module2]" format.
+            find_links: path to a directory containing wheels to be searched prior to going to the internet
+            wheel: a wheel file to install
         """
 
         import messages
@@ -213,7 +241,7 @@ class InvokeAiInstance:
 
         messages.simple_banner("Installing the InvokeAI Application :art:")
 
-        from plumbum import FG, ProcessExecutionError, local  # type: ignore
+        from plumbum import FG, ProcessExecutionError, local
 
         pip = local[self.pip]
 
@@ -222,12 +250,12 @@ class InvokeAiInstance:
             "--require-virtualenv",
             "--force-reinstall",
             "--use-pep517",
-            str(src),
+            str(src) if not wheel else str(wheel),
             "--find-links" if find_links is not None else None,
             find_links,
             "--extra-index-url" if extra_index_url is not None else None,
             extra_index_url,
-            pre_flag,
+            pre_flag if not wheel else None,  # Ignore the flag if we are installing a wheel
         ]
 
         try:
@@ -289,7 +317,9 @@ def upgrade_pip(venv_path: Path) -> str | None:
     python = str(venv_path.expanduser().resolve() / python)
 
     try:
-        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode()
+        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode(
+            encoding=locale.getpreferredencoding()
+        )
     except subprocess.CalledProcessError as e:
         print(e)
         result = None
@@ -320,7 +350,7 @@ def set_sys_path(venv_path: Path) -> None:
     sys.path.append(str(Path(venv_path, lib, "site-packages").expanduser().resolve()))
 
 
-def get_github_releases() -> tuple[list, list] | None:
+def get_github_releases() -> tuple[list[str], list[str]] | None:
     """
     Query Github for published (pre-)release versions.
     Return a tuple where the first element is a list of stable releases and the second element is a list of pre-releases.
@@ -331,7 +361,8 @@ def get_github_releases() -> tuple[list, list] | None:
 
     ## get latest releases using github api
     url = "https://api.github.com/repos/invoke-ai/InvokeAI/releases"
-    releases, pre_releases = [], []
+    releases: list[str] = []
+    pre_releases: list[str] = []
     try:
         res = requests.get(url)
         res.raise_for_status()
@@ -376,22 +407,29 @@ def get_torch_source() -> Tuple[str | None, str | None]:
     # device can be one of: "cuda", "rocm", "cpu", "cuda_and_dml, autodetect"
     device = select_gpu()
 
+    # The correct extra index URLs for torch are inconsistent, see https://pytorch.org/get-started/locally/#start-locally
+
     url = None
-    optional_modules = "[onnx]"
+    optional_modules: str | None = None
     if OS == "Linux":
         if device.value == "rocm":
             url = "https://download.pytorch.org/whl/rocm5.6"
         elif device.value == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
-
+        elif device.value == "cuda":
+            # CUDA uses the default PyPi index
+            optional_modules = "[xformers,onnx-cuda]"
     elif OS == "Windows":
         if device.value == "cuda":
             url = "https://download.pytorch.org/whl/cu121"
             optional_modules = "[xformers,onnx-cuda]"
-        if device.value == "cuda_and_dml":
-            url = "https://download.pytorch.org/whl/cu121"
-            optional_modules = "[xformers,onnx-directml]"
+        elif device.value == "cpu":
+            # CPU  uses the default PyPi index, no optional modules
+            pass
+    elif OS == "Darwin":
+        # macOS uses the default PyPi index, no optional modules
+        pass
 
-    # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
+    # Fall back to defaults
 
     return (url, optional_modules)

installer/lib/main.py

@@ -30,16 +30,17 @@ if __name__ == "__main__":
     )
 
     parser.add_argument(
-        "--version",
-        dest="version",
-        help="Version of InvokeAI to install. Default to the latest stable release. A special 'pre' value will install the latest published pre-release version.",
+        "--find-links",
+        dest="find_links",
+        help="Specifies a directory of local wheel files to be searched prior to searching the online repositories.",
+        type=Path,
         default=None,
     )
 
     parser.add_argument(
-        "--find-links",
-        dest="find_links",
-        help="Specifies a directory of local wheel files to be searched prior to searching the online repositories.",
+        "--wheel",
+        dest="wheel",
+        help="Specifies a wheel for the InvokeAI package. Used for troubleshooting or testing prereleases.",
         type=Path,
         default=None,
     )

installer/lib/messages.py

@@ -7,6 +7,7 @@ import os
 import platform
 from enum import Enum
 from pathlib import Path
+from typing import Optional
 
 from prompt_toolkit import prompt
 from prompt_toolkit.completion import FuzzyWordCompleter, PathCompleter
@@ -19,13 +20,6 @@ from rich.style import Style
 from rich.syntax import Syntax
 from rich.text import Text
 
-"""
-INVOKE_AI_SRC=https://github.com/invoke-ai/InvokeAI/archive/refs/tags/${INVOKEAI_VERSION}.zip
-INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
-TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
-"""
-
-
 OS = platform.uname().system
 ARCH = platform.uname().machine
 
@@ -36,7 +30,7 @@ else:
     console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
 
-def welcome(available_releases: tuple | None = None) -> None:
+def welcome(available_releases: tuple[list[str], list[str]] | None = None) -> None:
     @group()
     def text():
         if (platform_specific := _platform_specific_help()) is not None:
@@ -72,7 +66,34 @@ def welcome(available_releases: tuple | None = None) -> None:
     console.line()
 
 
-def choose_version(available_releases: tuple | None = None) -> str:
+def installing_from_wheel(wheel_filename: str) -> None:
+    """Display a message about installing from a wheel"""
+
+    @group()
+    def text():
+        yield Text.from_markup(f"You are installing from a wheel file: [bold]{wheel_filename}\n")
+        yield Text.from_markup(
+            "[bold orange3]If you are not sure why you are doing this, you should cancel and install InvokeAI normally."
+        )
+
+    console.print(
+        Panel(
+            title="Installing from Wheel",
+            renderable=text(),
+            box=box.DOUBLE,
+            expand=True,
+            padding=(1, 2),
+        )
+    )
+
+    should_proceed = Confirm.ask("Do you want to proceed?")
+
+    if not should_proceed:
+        console.print("Installation cancelled.")
+        exit()
+
+
+def choose_version(available_releases: tuple[list[str], list[str]] | None = None) -> str:
     """
     Prompt the user to choose an Invoke version to install
     """
@@ -114,7 +135,7 @@ def confirm_install(dest: Path) -> bool:
     return dest_confirmed
 
 
-def dest_path(dest=None) -> Path | None:
+def dest_path(dest: Optional[str | Path] = None) -> Path | None:
     """
     Prompt the user for the destination path and create the path
 
@@ -186,10 +207,8 @@ def dest_path(dest=None) -> Path | None:
 
 class GpuType(Enum):
     CUDA = "cuda"
-    CUDA_AND_DML = "cuda_and_dml"
     ROCM = "rocm"
     CPU = "cpu"
-    AUTODETECT = "autodetect"
 
 
 def select_gpu() -> GpuType:
@@ -205,10 +224,6 @@ def select_gpu() -> GpuType:
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
         GpuType.CUDA,
     )
-    nvidia_with_dml = (
-        "an [gold1 b]NVIDIA[/] GPU (using CUDA™, and DirectML™ for ONNX) -- ALPHA",
-        GpuType.CUDA_AND_DML,
-    )
     amd = (
         "an [gold1 b]AMD[/] GPU (using ROCm™)",
         GpuType.ROCM,
@@ -217,27 +232,19 @@ def select_gpu() -> GpuType:
         "Do not install any GPU support, use CPU for generation (slow)",
         GpuType.CPU,
     )
-    autodetect = (
-        "I'm not sure what to choose",
-        GpuType.AUTODETECT,
-    )
 
     options = []
     if OS == "Windows":
-        options = [nvidia, nvidia_with_dml, cpu]
+        options = [nvidia, cpu]
     if OS == "Linux":
         options = [nvidia, amd, cpu]
     elif OS == "Darwin":
         options = [cpu]
-        # future CoreML?
 
     if len(options) == 1:
         print(f'Your platform [gold1]{OS}-{ARCH}[/] only supports the "{options[0][1]}" driver. Proceeding with that.')
         return options[0][1]
 
-    # "I don't know" is always added the last option
-    options.append(autodetect)  # type: ignore
-
     options = {str(i): opt for i, opt in enumerate(options, 1)}
 
     console.rule(":space_invader: GPU (Graphics Card) selection :space_invader:")
@@ -271,11 +278,6 @@ def select_gpu() -> GpuType:
         ),
     )
 
-    if options[choice][1] is GpuType.AUTODETECT:
-        console.print(
-            "No problem. We will install CUDA support first :crossed_fingers: If Invoke does not detect a GPU, please re-run the installer and select one of the other GPU types."
-        )
-
     return options[choice][1]
 
 

installer/templates/invoke.bat.in

@@ -10,11 +10,12 @@ set INVOKEAI_ROOT=.
 echo Desired action:
 echo 1. Generate images with the browser-based interface
 echo 2. Open the developer console
-echo 3. Update InvokeAI (DEPRECATED - please use the installer)
-echo 4. Run the InvokeAI image database maintenance script
-echo 5. Command-line help
+echo 3. Command-line help
 echo Q - Quit
-set /P choice="Please enter 1-10, Q: [1] "
+echo.
+echo To update, download and run the installer from https://github.com/invoke-ai/InvokeAI/releases/latest.
+echo.
+set /P choice="Please enter 1-4, Q: [1] "
 if not defined choice set choice=1
 IF /I "%choice%" == "1" (
     echo Starting the InvokeAI browser-based UI..
@@ -32,14 +33,6 @@ IF /I "%choice%" == "1" (
     echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
     call cmd /k
 ) ELSE IF /I "%choice%" == "3" (
-    echo UPDATING FROM WITHIN THE APP IS BEING DEPRECATED.
-    echo Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.
-    timeout 4
-    python -m invokeai.frontend.install.invokeai_update
-) ELSE IF /I "%choice%" == "4" (
-   echo Running the db maintenance script...
-   python .venv\Scripts\invokeai-db-maintenance.exe
-) ELSE IF /I "%choice%" == "5" (
     echo Displaying command line help...
     python .venv\Scripts\invokeai-web.exe --help %*
     pause

installer/templates/invoke.sh.in

@@ -23,32 +23,15 @@ cd "$scriptdir"
 . .venv/bin/activate
 
 export INVOKEAI_ROOT="$scriptdir"
+
+# Stash the CLI args - when we prompt for user input, `$@` is overwritten
 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 "$PARAMS" | sed 's/--no-tui//')
-            break
-        fi
-    done
-else
-    tui=false
-fi
-
-# Set required env var for torch on mac MPS
+# This setting allows torch to fall back to CPU for operations that are not supported by MPS on macOS.
 if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
-# Avoid glibc memory fragmentation. See invokeai/backend/model_management/README.md for details.
-export MALLOC_MMAP_THRESHOLD_=1048576
-
 # Primary function for the case statement to determine user input
 do_choice() {
     case $1 in
@@ -64,18 +47,6 @@ do_choice() {
         bash --init-file "$file_name"
         ;;
     3)
-        clear
-        printf "UPDATING FROM WITHIN THE APP IS BEING DEPRECATED\n"
-        printf "Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.\n"
-        sleep 4
-        python -m invokeai.frontend.install.invokeai_update
-        ;;
-    4)
-        clear
-        printf "Running the db maintenance script\n"
-        invokeai-db-maintenance --root ${INVOKEAI_ROOT}
-        ;;
-    5)
         clear
         printf "Command-line help\n"
         invokeai-web --help
@@ -89,59 +60,25 @@ do_choice() {
     clear
 }
 
-# Dialog-based TUI for launcing Invoke functions
-do_dialog() {
-    options=(
-        1 "Generate images with a browser-based interface"
-        2 "Open the developer console"
-        3 "Update InvokeAI (DEPRECATED - please use the installer)"
-        4 "Run the InvokeAI image database maintenance script"
-        5 "Command-line help"
-    )
-
-    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 "$choice"
-    clear
-}
-
 # Command-line interface for launching Invoke functions
 do_line_input() {
     clear
-    printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
     printf "What would you like to do?\n"
     printf "1: Generate images using the browser-based interface\n"
     printf "2: Open the developer console\n"
-    printf "3: Update InvokeAI\n"
-    printf "4: Run the InvokeAI image database maintenance script\n"
-    printf "5: Command-line help\n"
+    printf "3: Command-line help\n"
     printf "Q: Quit\n\n"
-    read -p "Please enter 1-10, Q: [1] " yn
+    printf "To update, download and run the installer from https://github.com/invoke-ai/InvokeAI/releases/latest.\n\n"
+    read -p "Please enter 1-4, Q: [1] " yn
     choice=${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
+# Main IF statement for launching Invoke, 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
+        do_line_input
     done
 else # in developer console
     python --version

invokeai/app/api/dependencies.py

@@ -18,6 +18,7 @@ from ..services.boards.boards_default import BoardService
 from ..services.bulk_download.bulk_download_default import BulkDownloadService
 from ..services.config import InvokeAIAppConfig
 from ..services.download import DownloadQueueService
+from ..services.events.events_fastapievents import FastAPIEventService
 from ..services.image_files.image_files_disk import DiskImageFileStorage
 from ..services.image_records.image_records_sqlite import SqliteImageRecordStorage
 from ..services.images.images_default import ImageService
@@ -29,11 +30,10 @@ from ..services.model_images.model_images_default import ModelImageFileStorageDi
 from ..services.model_manager.model_manager_default import ModelManagerService
 from ..services.model_records import ModelRecordServiceSQL
 from ..services.names.names_default import SimpleNameService
-from ..services.session_processor.session_processor_default import DefaultSessionProcessor
+from ..services.session_processor.session_processor_default import DefaultSessionProcessor, DefaultSessionRunner
 from ..services.session_queue.session_queue_sqlite import SqliteSessionQueue
 from ..services.urls.urls_default import LocalUrlService
 from ..services.workflow_records.workflow_records_sqlite import SqliteWorkflowRecordsStorage
-from .events import FastAPIEventService
 
 
 # TODO: is there a better way to achieve this?
@@ -103,7 +103,7 @@ class ApiDependencies:
         )
         names = SimpleNameService()
         performance_statistics = InvocationStatsService()
-        session_processor = DefaultSessionProcessor()
+        session_processor = DefaultSessionProcessor(session_runner=DefaultSessionRunner())
         session_queue = SqliteSessionQueue(db=db)
         urls = LocalUrlService()
         workflow_records = SqliteWorkflowRecordsStorage(db=db)

invokeai/app/api/events.py

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

invokeai/app/api/routers/app_info.py

@@ -12,8 +12,7 @@ from pydantic import BaseModel, Field
 
 from invokeai.app.invocations.upscale import ESRGAN_MODELS
 from invokeai.app.services.invocation_cache.invocation_cache_common import InvocationCacheStatus
-from invokeai.backend.image_util.patchmatch import PatchMatch
-from invokeai.backend.image_util.safety_checker import SafetyChecker
+from invokeai.backend.image_util.infill_methods.patchmatch import PatchMatch
 from invokeai.backend.util.logging import logging
 from invokeai.version import __version__
 
@@ -100,7 +99,7 @@ async def get_app_deps() -> AppDependencyVersions:
 
 @app_router.get("/config", operation_id="get_config", status_code=200, response_model=AppConfig)
 async def get_config() -> AppConfig:
-    infill_methods = ["tile", "lama", "cv2"]
+    infill_methods = ["tile", "lama", "cv2", "color"]  # TODO: add mosaic back
     if PatchMatch.patchmatch_available():
         infill_methods.append("patchmatch")
 
@@ -109,9 +108,7 @@ async def get_config() -> AppConfig:
         upscaling_models.append(str(Path(model).stem))
     upscaler = Upscaler(upscaling_method="esrgan", upscaling_models=upscaling_models)
 
-    nsfw_methods = []
-    if SafetyChecker.safety_checker_available():
-        nsfw_methods.append("nsfw_checker")
+    nsfw_methods = ["nsfw_checker"]
 
     watermarking_methods = ["invisible_watermark"]
 

invokeai/app/api/routers/images.py

@@ -6,13 +6,12 @@ from fastapi import BackgroundTasks, Body, HTTPException, Path, Query, Request,
 from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
 from PIL import Image
-from pydantic import BaseModel, Field, ValidationError
+from pydantic import BaseModel, Field, JsonValue
 
-from invokeai.app.invocations.fields import MetadataField, MetadataFieldValidator
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ImageRecordChanges, ResourceOrigin
 from invokeai.app.services.images.images_common import ImageDTO, ImageUrlsDTO
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID, WorkflowWithoutIDValidator
 
 from ..dependencies import ApiDependencies
 
@@ -42,13 +41,17 @@ async def upload_image(
     board_id: Optional[str] = Query(default=None, description="The board to add this image to, if any"),
     session_id: Optional[str] = Query(default=None, description="The session ID associated with this upload, if any"),
     crop_visible: Optional[bool] = Query(default=False, description="Whether to crop the image"),
+    metadata: Optional[JsonValue] = Body(
+        default=None, description="The metadata to associate with the image", embed=True
+    ),
 ) -> ImageDTO:
     """Uploads an image"""
     if not file.content_type or not file.content_type.startswith("image"):
         raise HTTPException(status_code=415, detail="Not an image")
 
-    metadata = None
-    workflow = None
+    _metadata = None
+    _workflow = None
+    _graph = None
 
     contents = await file.read()
     try:
@@ -62,22 +65,28 @@ async def upload_image(
 
     # TODO: retain non-invokeai metadata on upload?
     # attempt to parse metadata from image
-    metadata_raw = pil_image.info.get("invokeai_metadata", None)
-    if metadata_raw:
-        try:
-            metadata = MetadataFieldValidator.validate_json(metadata_raw)
-        except ValidationError:
-            ApiDependencies.invoker.services.logger.warn("Failed to parse metadata for uploaded image")
-            pass
+    metadata_raw = metadata if isinstance(metadata, str) else pil_image.info.get("invokeai_metadata", None)
+    if isinstance(metadata_raw, str):
+        _metadata = metadata_raw
+    else:
+        ApiDependencies.invoker.services.logger.debug("Failed to parse metadata for uploaded image")
+        pass
 
     # attempt to parse workflow from image
     workflow_raw = pil_image.info.get("invokeai_workflow", None)
-    if workflow_raw is not None:
-        try:
-            workflow = WorkflowWithoutIDValidator.validate_json(workflow_raw)
-        except ValidationError:
-            ApiDependencies.invoker.services.logger.warn("Failed to parse metadata for uploaded image")
-            pass
+    if isinstance(workflow_raw, str):
+        _workflow = workflow_raw
+    else:
+        ApiDependencies.invoker.services.logger.debug("Failed to parse workflow for uploaded image")
+        pass
+
+    # attempt to extract graph from image
+    graph_raw = pil_image.info.get("invokeai_graph", None)
+    if isinstance(graph_raw, str):
+        _graph = graph_raw
+    else:
+        ApiDependencies.invoker.services.logger.debug("Failed to parse graph for uploaded image")
+        pass
 
     try:
         image_dto = ApiDependencies.invoker.services.images.create(
@@ -86,8 +95,9 @@ async def upload_image(
             image_category=image_category,
             session_id=session_id,
             board_id=board_id,
-            metadata=metadata,
-            workflow=workflow,
+            metadata=_metadata,
+            workflow=_workflow,
+            graph=_graph,
             is_intermediate=is_intermediate,
         )
 
@@ -185,14 +195,21 @@ async def get_image_metadata(
         raise HTTPException(status_code=404)
 
 
+class WorkflowAndGraphResponse(BaseModel):
+    workflow: Optional[str] = Field(description="The workflow used to generate the image, as stringified JSON")
+    graph: Optional[str] = Field(description="The graph used to generate the image, as stringified JSON")
+
+
 @images_router.get(
-    "/i/{image_name}/workflow", operation_id="get_image_workflow", response_model=Optional[WorkflowWithoutID]
+    "/i/{image_name}/workflow", operation_id="get_image_workflow", response_model=WorkflowAndGraphResponse
 )
 async def get_image_workflow(
     image_name: str = Path(description="The name of image whose workflow to get"),
-) -> Optional[WorkflowWithoutID]:
+) -> WorkflowAndGraphResponse:
     try:
-        return ApiDependencies.invoker.services.images.get_workflow(image_name)
+        workflow = ApiDependencies.invoker.services.images.get_workflow(image_name)
+        graph = ApiDependencies.invoker.services.images.get_graph(image_name)
+        return WorkflowAndGraphResponse(workflow=workflow, graph=graph)
     except Exception:
         raise HTTPException(status_code=404)
 

invokeai/app/api/routers/model_manager.py

@@ -1,16 +1,13 @@
 # Copyright (c) 2023 Lincoln D. Stein
 """FastAPI route for model configuration records."""
 
-import contextlib
 import io
 import pathlib
 import shutil
 import traceback
 from copy import deepcopy
-from enum import Enum
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Type
 
-import huggingface_hub
 from fastapi import Body, Path, Query, Response, UploadFile
 from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
@@ -19,14 +16,14 @@ from pydantic import AnyHttpUrl, BaseModel, ConfigDict, Field
 from starlette.exceptions import HTTPException
 from typing_extensions import Annotated
 
-from invokeai.app.services.model_install import ModelInstallJob
+from invokeai.app.services.model_images.model_images_common import ModelImageFileNotFoundException
+from invokeai.app.services.model_install.model_install_common import ModelInstallJob
 from invokeai.app.services.model_records import (
     DuplicateModelException,
     InvalidModelException,
     ModelRecordChanges,
     UnknownModelException,
 )
-from invokeai.app.util.suppress_output import SuppressOutput
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
@@ -56,6 +53,13 @@ class ModelsList(BaseModel):
     model_config = ConfigDict(use_enum_values=True)
 
 
+def add_cover_image_to_model_config(config: AnyModelConfig, dependencies: Type[ApiDependencies]) -> AnyModelConfig:
+    """Add a cover image URL to a model configuration."""
+    cover_image = dependencies.invoker.services.model_images.get_url(config.key)
+    config.cover_image = cover_image
+    return config
+
+
 ##############################################################################
 # These are example inputs and outputs that are used in places where Swagger
 # is unable to generate a correct example.
@@ -122,8 +126,7 @@ async def list_model_records(
             record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
         )
     for model in found_models:
-        cover_image = ApiDependencies.invoker.services.model_images.get_url(model.key)
-        model.cover_image = cover_image
+        model = add_cover_image_to_model_config(model, ApiDependencies)
     return ModelsList(models=found_models)
 
 
@@ -164,12 +167,9 @@ async def get_model_record(
     key: str = Path(description="Key of the model record to fetch."),
 ) -> AnyModelConfig:
     """Get a model record"""
-    record_store = ApiDependencies.invoker.services.model_manager.store
     try:
-        config: AnyModelConfig = record_store.get_model(key)
-        cover_image = ApiDependencies.invoker.services.model_images.get_url(key)
-        config.cover_image = cover_image
-        return config
+        config = ApiDependencies.invoker.services.model_manager.store.get_model(key)
+        return add_cover_image_to_model_config(config, ApiDependencies)
     except UnknownModelException as e:
         raise HTTPException(status_code=404, detail=str(e))
 
@@ -223,28 +223,13 @@ async def scan_for_models(
         non_core_model_paths = [p for p in found_model_paths if not p.is_relative_to(core_models_path)]
 
         installed_models = ApiDependencies.invoker.services.model_manager.store.search_by_attr()
-        resolved_installed_model_paths: list[str] = []
-        installed_model_sources: list[str] = []
-
-        # This call lists all installed models.
-        for model in installed_models:
-            path = pathlib.Path(model.path)
-            # If the model has a source, we need to add it to the list of installed sources.
-            if model.source:
-                installed_model_sources.append(model.source)
-            # If the path is not absolute, that means it is in the app models directory, and we need to join it with
-            # the models path before resolving.
-            if not path.is_absolute():
-                resolved_installed_model_paths.append(str(pathlib.Path(models_path, path).resolve()))
-                continue
-            resolved_installed_model_paths.append(str(path.resolve()))
 
         scan_results: list[FoundModel] = []
 
-        # Check if the model is installed by comparing the resolved paths, appending to the scan result.
+        # Check if the model is installed by comparing paths, appending to the scan result.
         for p in non_core_model_paths:
             path = str(p)
-            is_installed = path in resolved_installed_model_paths or path in installed_model_sources
+            is_installed = any(str(models_path / m.path) == path for m in installed_models)
             found_model = FoundModel(path=path, is_installed=is_installed)
             scan_results.append(found_model)
     except Exception as e:
@@ -313,14 +298,15 @@ async def update_model_record(
     installer = ApiDependencies.invoker.services.model_manager.install
     try:
         record_store.update_model(key, changes=changes)
-        model_response: AnyModelConfig = installer.sync_model_path(key)
+        config = installer.sync_model_path(key)
+        config = add_cover_image_to_model_config(config, ApiDependencies)
         logger.info(f"Updated model: {key}")
     except UnknownModelException as e:
         raise HTTPException(status_code=404, detail=str(e))
     except ValueError as e:
         logger.error(str(e))
         raise HTTPException(status_code=409, detail=str(e))
-    return model_response
+    return config
 
 
 @model_manager_router.get(
@@ -445,41 +431,6 @@ async def delete_model_image(
         raise HTTPException(status_code=404, detail=str(e))
 
 
-# @model_manager_router.post(
-#     "/i/",
-#     operation_id="add_model_record",
-#     responses={
-#         201: {
-#             "description": "The model added successfully",
-#             "content": {"application/json": {"example": example_model_config}},
-#         },
-#         409: {"description": "There is already a model corresponding to this path or repo_id"},
-#         415: {"description": "Unrecognized file/folder format"},
-#     },
-#     status_code=201,
-# )
-# async def add_model_record(
-#     config: Annotated[
-#         AnyModelConfig, Body(description="Model config", discriminator="type", example=example_model_input)
-#     ],
-# ) -> AnyModelConfig:
-#     """Add a model using the configuration information appropriate for its type."""
-#     logger = ApiDependencies.invoker.services.logger
-#     record_store = ApiDependencies.invoker.services.model_manager.store
-#     try:
-#         record_store.add_model(config)
-#     except DuplicateModelException as e:
-#         logger.error(str(e))
-#         raise HTTPException(status_code=409, detail=str(e))
-#     except InvalidModelException as e:
-#         logger.error(str(e))
-#         raise HTTPException(status_code=415)
-
-#     # now fetch it out
-#     result: AnyModelConfig = record_store.get_model(config.key)
-#     return result
-
-
 @model_manager_router.post(
     "/install",
     operation_id="install_model",
@@ -631,25 +582,6 @@ async def prune_model_install_jobs() -> Response:
     return Response(status_code=204)
 
 
-@model_manager_router.patch(
-    "/sync",
-    operation_id="sync_models_to_config",
-    responses={
-        204: {"description": "Model config record database resynced with files on disk"},
-        400: {"description": "Bad request"},
-    },
-)
-async def sync_models_to_config() -> Response:
-    """
-    Traverse the models and autoimport directories.
-
-    Model files without a corresponding
-    record in the database are added. Orphan records without a models file are deleted.
-    """
-    ApiDependencies.invoker.services.model_manager.install.sync_to_config()
-    return Response(status_code=204)
-
-
 @model_manager_router.put(
     "/convert/{key}",
     operation_id="convert_model",
@@ -672,8 +604,8 @@ async def convert_model(
     The return value is the model configuration for the converted model.
     """
     model_manager = ApiDependencies.invoker.services.model_manager
+    loader = model_manager.load
     logger = ApiDependencies.invoker.services.logger
-    loader = ApiDependencies.invoker.services.model_manager.load
     store = ApiDependencies.invoker.services.model_manager.store
     installer = ApiDependencies.invoker.services.model_manager.install
 
@@ -688,7 +620,13 @@ async def convert_model(
         raise HTTPException(400, f"The model with key {key} is not a main checkpoint model.")
 
     # loading the model will convert it into a cached diffusers file
-    model_manager.load.load_model(model_config, submodel_type=SubModelType.Scheduler)
+    try:
+        cc_size = loader.convert_cache.max_size
+        if cc_size == 0:  # temporary set the convert cache to a positive number so that cached model is written
+            loader._convert_cache.max_size = 1.0
+        loader.load_model(model_config, submodel_type=SubModelType.Scheduler)
+    finally:
+        loader._convert_cache.max_size = cc_size
 
     # Get the path of the converted model from the loader
     cache_path = loader.convert_cache.cache_path(key)
@@ -715,6 +653,14 @@ async def convert_model(
         logger.error(str(e))
         raise HTTPException(status_code=409, detail=str(e))
 
+    # Update the model image if the model had one
+    try:
+        model_image = ApiDependencies.invoker.services.model_images.get(key)
+        ApiDependencies.invoker.services.model_images.save(model_image, new_key)
+        ApiDependencies.invoker.services.model_images.delete(key)
+    except ModelImageFileNotFoundException:
+        pass
+
     # delete the original safetensors file
     installer.delete(key)
 
@@ -722,75 +668,11 @@ async def convert_model(
     shutil.rmtree(cache_path)
 
     # return the config record for the new diffusers directory
-    new_config: AnyModelConfig = store.get_model(new_key)
+    new_config = store.get_model(new_key)
+    new_config = add_cover_image_to_model_config(new_config, ApiDependencies)
     return new_config
 
 
-# @model_manager_router.put(
-#     "/merge",
-#     operation_id="merge",
-#     responses={
-#         200: {
-#             "description": "Model converted successfully",
-#             "content": {"application/json": {"example": example_model_config}},
-#         },
-#         400: {"description": "Bad request"},
-#         404: {"description": "Model not found"},
-#         409: {"description": "There is already a model registered at this location"},
-#     },
-# )
-# async def merge(
-#     keys: List[str] = Body(description="Keys for two to three models to merge", min_length=2, max_length=3),
-#     merged_model_name: Optional[str] = Body(description="Name of destination model", default=None),
-#     alpha: float = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
-#     force: bool = Body(
-#         description="Force merging of models created with different versions of diffusers",
-#         default=False,
-#     ),
-#     interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method", default=None),
-#     merge_dest_directory: Optional[str] = Body(
-#         description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
-#         default=None,
-#     ),
-# ) -> AnyModelConfig:
-#     """
-#     Merge diffusers models. The process is controlled by a set parameters provided in the body of the request.
-#     ```
-#     Argument                Description [default]
-#     --------               ----------------------
-#     keys                   List of 2-3 model keys to merge together. All models must use the same base type.
-#     merged_model_name      Name for the merged model [Concat model names]
-#     alpha                  Alpha value (0.0-1.0). Higher values give more weight to the second model [0.5]
-#     force                  If true, force the merge even if the models were generated by different versions of the diffusers library [False]
-#     interp                 Interpolation method. One of "weighted_sum", "sigmoid", "inv_sigmoid" or "add_difference" [weighted_sum]
-#     merge_dest_directory   Specify a directory to store the merged model in [models directory]
-#     ```
-#     """
-#     logger = ApiDependencies.invoker.services.logger
-#     try:
-#         logger.info(f"Merging models: {keys} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
-#         dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
-#         installer = ApiDependencies.invoker.services.model_manager.install
-#         merger = ModelMerger(installer)
-#         model_names = [installer.record_store.get_model(x).name for x in keys]
-#         response = merger.merge_diffusion_models_and_save(
-#             model_keys=keys,
-#             merged_model_name=merged_model_name or "+".join(model_names),
-#             alpha=alpha,
-#             interp=interp,
-#             force=force,
-#             merge_dest_directory=dest,
-#         )
-#     except UnknownModelException:
-#         raise HTTPException(
-#             status_code=404,
-#             detail=f"One or more of the models '{keys}' not found",
-#         )
-#     except ValueError as e:
-#         raise HTTPException(status_code=400, detail=str(e))
-#     return response
-
-
 @model_manager_router.get("/starter_models", operation_id="get_starter_models", response_model=list[StarterModel])
 async def get_starter_models() -> list[StarterModel]:
     installed_models = ApiDependencies.invoker.services.model_manager.store.search_by_attr()
@@ -807,51 +689,3 @@ async def get_starter_models() -> list[StarterModel]:
         model.dependencies = missing_deps
 
     return starter_models
-
-
-class HFTokenStatus(str, Enum):
-    VALID = "valid"
-    INVALID = "invalid"
-    UNKNOWN = "unknown"
-
-
-class HFTokenHelper:
-    @classmethod
-    def get_status(cls) -> HFTokenStatus:
-        try:
-            if huggingface_hub.get_token_permission(huggingface_hub.get_token()):
-                # Valid token!
-                return HFTokenStatus.VALID
-            # No token set
-            return HFTokenStatus.INVALID
-        except Exception:
-            return HFTokenStatus.UNKNOWN
-
-    @classmethod
-    def set_token(cls, token: str) -> HFTokenStatus:
-        with SuppressOutput(), contextlib.suppress(Exception):
-            huggingface_hub.login(token=token, add_to_git_credential=False)
-        return cls.get_status()
-
-
-@model_manager_router.get("/hf_login", operation_id="get_hf_login_status", response_model=HFTokenStatus)
-async def get_hf_login_status() -> HFTokenStatus:
-    token_status = HFTokenHelper.get_status()
-
-    if token_status is HFTokenStatus.UNKNOWN:
-        ApiDependencies.invoker.services.logger.warning("Unable to verify HF token")
-
-    return token_status
-
-
-@model_manager_router.post("/hf_login", operation_id="do_hf_login", response_model=HFTokenStatus)
-async def do_hf_login(
-    token: str = Body(description="Hugging Face token to use for login", embed=True),
-) -> HFTokenStatus:
-    HFTokenHelper.set_token(token)
-    token_status = HFTokenHelper.get_status()
-
-    if token_status is HFTokenStatus.UNKNOWN:
-        ApiDependencies.invoker.services.logger.warning("Unable to verify HF token")
-
-    return token_status

invokeai/app/api/routers/session_queue.py

@@ -203,6 +203,7 @@ async def get_batch_status(
     responses={
         200: {"model": SessionQueueItem},
     },
+    response_model_exclude_none=True,
 )
 async def get_queue_item(
     queue_id: str = Path(description="The queue id to perform this operation on"),

invokeai/app/api/sockets.py

@@ -1,66 +1,125 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+from typing import Any
+
 from fastapi import FastAPI
-from fastapi_events.handlers.local import local_handler
-from fastapi_events.typing import Event
+from pydantic import BaseModel
 from socketio import ASGIApp, AsyncServer
 
-from ..services.events.events_base import EventServiceBase
+from invokeai.app.services.events.events_common import (
+    BatchEnqueuedEvent,
+    BulkDownloadCompleteEvent,
+    BulkDownloadErrorEvent,
+    BulkDownloadEventBase,
+    BulkDownloadStartedEvent,
+    DownloadCancelledEvent,
+    DownloadCompleteEvent,
+    DownloadErrorEvent,
+    DownloadEventBase,
+    DownloadProgressEvent,
+    DownloadStartedEvent,
+    FastAPIEvent,
+    InvocationCompleteEvent,
+    InvocationDenoiseProgressEvent,
+    InvocationErrorEvent,
+    InvocationStartedEvent,
+    ModelEventBase,
+    ModelInstallCancelledEvent,
+    ModelInstallCompleteEvent,
+    ModelInstallDownloadProgressEvent,
+    ModelInstallDownloadsCompleteEvent,
+    ModelInstallErrorEvent,
+    ModelInstallStartedEvent,
+    ModelLoadCompleteEvent,
+    ModelLoadStartedEvent,
+    QueueClearedEvent,
+    QueueEventBase,
+    QueueItemStatusChangedEvent,
+    register_events,
+)
+
+
+class QueueSubscriptionEvent(BaseModel):
+    """Event data for subscribing to the socket.io queue room.
+    This is a pydantic model to ensure the data is in the correct format."""
+
+    queue_id: str
+
+
+class BulkDownloadSubscriptionEvent(BaseModel):
+    """Event data for subscribing to the socket.io bulk downloads room.
+    This is a pydantic model to ensure the data is in the correct format."""
+
+    bulk_download_id: str
+
+
+QUEUE_EVENTS = {
+    InvocationStartedEvent,
+    InvocationDenoiseProgressEvent,
+    InvocationCompleteEvent,
+    InvocationErrorEvent,
+    QueueItemStatusChangedEvent,
+    BatchEnqueuedEvent,
+    QueueClearedEvent,
+}
+
+MODEL_EVENTS = {
+    DownloadCancelledEvent,
+    DownloadCompleteEvent,
+    DownloadErrorEvent,
+    DownloadProgressEvent,
+    DownloadStartedEvent,
+    ModelLoadStartedEvent,
+    ModelLoadCompleteEvent,
+    ModelInstallDownloadProgressEvent,
+    ModelInstallDownloadsCompleteEvent,
+    ModelInstallStartedEvent,
+    ModelInstallCompleteEvent,
+    ModelInstallCancelledEvent,
+    ModelInstallErrorEvent,
+}
+
+BULK_DOWNLOAD_EVENTS = {BulkDownloadStartedEvent, BulkDownloadCompleteEvent, BulkDownloadErrorEvent}
 
 
 class SocketIO:
-    __sio: AsyncServer
-    __app: ASGIApp
+    _sub_queue = "subscribe_queue"
+    _unsub_queue = "unsubscribe_queue"
 
-    __sub_queue: str = "subscribe_queue"
-    __unsub_queue: str = "unsubscribe_queue"
-
-    __sub_bulk_download: str = "subscribe_bulk_download"
-    __unsub_bulk_download: str = "unsubscribe_bulk_download"
+    _sub_bulk_download = "subscribe_bulk_download"
+    _unsub_bulk_download = "unsubscribe_bulk_download"
 
     def __init__(self, app: FastAPI):
-        self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
-        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="/ws/socket.io")
-        app.mount("/ws", self.__app)
+        self._sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
+        self._app = ASGIApp(socketio_server=self._sio, socketio_path="/ws/socket.io")
+        app.mount("/ws", self._app)
 
-        self.__sio.on(self.__sub_queue, handler=self._handle_sub_queue)
-        self.__sio.on(self.__unsub_queue, handler=self._handle_unsub_queue)
-        local_handler.register(event_name=EventServiceBase.queue_event, _func=self._handle_queue_event)
-        local_handler.register(event_name=EventServiceBase.model_event, _func=self._handle_model_event)
+        self._sio.on(self._sub_queue, handler=self._handle_sub_queue)
+        self._sio.on(self._unsub_queue, handler=self._handle_unsub_queue)
+        self._sio.on(self._sub_bulk_download, handler=self._handle_sub_bulk_download)
+        self._sio.on(self._unsub_bulk_download, handler=self._handle_unsub_bulk_download)
 
-        self.__sio.on(self.__sub_bulk_download, handler=self._handle_sub_bulk_download)
-        self.__sio.on(self.__unsub_bulk_download, handler=self._handle_unsub_bulk_download)
-        local_handler.register(event_name=EventServiceBase.bulk_download_event, _func=self._handle_bulk_download_event)
+        register_events(QUEUE_EVENTS, self._handle_queue_event)
+        register_events(MODEL_EVENTS, self._handle_model_event)
+        register_events(BULK_DOWNLOAD_EVENTS, self._handle_bulk_image_download_event)
 
-    async def _handle_queue_event(self, event: Event):
-        await self.__sio.emit(
-            event=event[1]["event"],
-            data=event[1]["data"],
-            room=event[1]["data"]["queue_id"],
-        )
+    async def _handle_sub_queue(self, sid: str, data: Any) -> None:
+        await self._sio.enter_room(sid, QueueSubscriptionEvent(**data).queue_id)
 
-    async def _handle_sub_queue(self, sid, data, *args, **kwargs) -> None:
-        if "queue_id" in data:
-            await self.__sio.enter_room(sid, data["queue_id"])
+    async def _handle_unsub_queue(self, sid: str, data: Any) -> None:
+        await self._sio.leave_room(sid, QueueSubscriptionEvent(**data).queue_id)
 
-    async def _handle_unsub_queue(self, sid, data, *args, **kwargs) -> None:
-        if "queue_id" in data:
-            await self.__sio.leave_room(sid, data["queue_id"])
+    async def _handle_sub_bulk_download(self, sid: str, data: Any) -> None:
+        await self._sio.enter_room(sid, BulkDownloadSubscriptionEvent(**data).bulk_download_id)
 
-    async def _handle_model_event(self, event: Event) -> None:
-        await self.__sio.emit(event=event[1]["event"], data=event[1]["data"])
+    async def _handle_unsub_bulk_download(self, sid: str, data: Any) -> None:
+        await self._sio.leave_room(sid, BulkDownloadSubscriptionEvent(**data).bulk_download_id)
 
-    async def _handle_bulk_download_event(self, event: Event):
-        await self.__sio.emit(
-            event=event[1]["event"],
-            data=event[1]["data"],
-            room=event[1]["data"]["bulk_download_id"],
-        )
+    async def _handle_queue_event(self, event: FastAPIEvent[QueueEventBase]):
+        await self._sio.emit(event=event[0], data=event[1].model_dump(mode="json"), room=event[1].queue_id)
 
-    async def _handle_sub_bulk_download(self, sid, data, *args, **kwargs):
-        if "bulk_download_id" in data:
-            await self.__sio.enter_room(sid, data["bulk_download_id"])
+    async def _handle_model_event(self, event: FastAPIEvent[ModelEventBase | DownloadEventBase]) -> None:
+        await self._sio.emit(event=event[0], data=event[1].model_dump(mode="json"))
 
-    async def _handle_unsub_bulk_download(self, sid, data, *args, **kwargs):
-        if "bulk_download_id" in data:
-            await self.__sio.leave_room(sid, data["bulk_download_id"])
+    async def _handle_bulk_image_download_event(self, event: FastAPIEvent[BulkDownloadEventBase]) -> None:
+        await self._sio.emit(event=event[0], data=event[1].model_dump(mode="json"), room=event[1].bulk_download_id)

invokeai/app/api_app.py

@@ -1,4 +1,5 @@
 import asyncio
+import logging
 import mimetypes
 import socket
 from contextlib import asynccontextmanager
@@ -6,6 +7,7 @@ from inspect import signature
 from pathlib import Path
 from typing import Any
 
+import torch
 import uvicorn
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
@@ -25,7 +27,9 @@ import invokeai.frontend.web as web_dir
 from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.services.config.config_default import get_config
+from invokeai.app.services.events.events_common import EventBase
 from invokeai.app.services.session_processor.session_processor_common import ProgressImage
+from invokeai.backend.util.devices import TorchDevice
 
 from ..backend.util.logging import InvokeAILogger
 from .api.dependencies import ApiDependencies
@@ -60,6 +64,9 @@ logger = InvokeAILogger.get_logger(config=app_config)
 mimetypes.add_type("application/javascript", ".js")
 mimetypes.add_type("text/css", ".css")
 
+torch_device_name = TorchDevice.get_torch_device_name()
+logger.info(f"Using torch device: {torch_device_name}")
+
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
@@ -158,6 +165,12 @@ def custom_openapi() -> dict[str, Any]:
     for schema_key, schema_json in additional_schemas[1]["$defs"].items():
         openapi_schema["components"]["schemas"][schema_key] = schema_json
 
+    openapi_schema["components"]["schemas"]["InvocationOutputMap"] = {
+        "type": "object",
+        "properties": {},
+        "required": [],
+    }
+
     # Add a reference to the output type to additionalProperties of the invoker schema
     for invoker in all_invocations:
         invoker_name = invoker.__name__  # type: ignore [attr-defined] # this is a valid attribute
@@ -166,25 +179,18 @@ def custom_openapi() -> dict[str, Any]:
         invoker_schema = openapi_schema["components"]["schemas"][f"{invoker_name}"]
         outputs_ref = {"$ref": f"#/components/schemas/{output_type_title}"}
         invoker_schema["output"] = outputs_ref
+        openapi_schema["components"]["schemas"]["InvocationOutputMap"]["properties"][invoker.get_type()] = outputs_ref
+        openapi_schema["components"]["schemas"]["InvocationOutputMap"]["required"].append(invoker.get_type())
         invoker_schema["class"] = "invocation"
 
-    # This code no longer seems to be necessary?
-    # Leave it here just in case
-    #
-    # from invokeai.backend.model_manager import get_model_config_formats
-    # formats = get_model_config_formats()
-    # for model_config_name, enum_set in formats.items():
-
-    #     if model_config_name in openapi_schema["components"]["schemas"]:
-    #         # print(f"Config with name {name} already defined")
-    #         continue
-
-    #     openapi_schema["components"]["schemas"][model_config_name] = {
-    #         "title": model_config_name,
-    #         "description": "An enumeration.",
-    #         "type": "string",
-    #         "enum": [v.value for v in enum_set],
-    #     }
+    # Add all event schemas
+    for event in sorted(EventBase.get_events(), key=lambda e: e.__name__):
+        json_schema = event.model_json_schema(mode="serialization", ref_template="#/components/schemas/{model}")
+        if "$defs" in json_schema:
+            for schema_key, schema in json_schema["$defs"].items():
+                openapi_schema["components"]["schemas"][schema_key] = schema
+            del json_schema["$defs"]
+        openapi_schema["components"]["schemas"][event.__name__] = json_schema
 
     app.openapi_schema = openapi_schema
     return app.openapi_schema
@@ -222,6 +228,22 @@ app.mount(
 )  # docs favicon is in here
 
 
+def check_cudnn(logger: logging.Logger) -> None:
+    """Check for cuDNN issues that could be causing degraded performance."""
+    if torch.backends.cudnn.is_available():
+        try:
+            # Note: At the time of writing (torch 2.2.1), torch.backends.cudnn.version() only raises an error the first
+            # time it is called. Subsequent calls will return the version number without complaining about a mismatch.
+            cudnn_version = torch.backends.cudnn.version()
+            logger.info(f"cuDNN version: {cudnn_version}")
+        except RuntimeError as e:
+            logger.warning(
+                "Encountered a cuDNN version issue. This may result in degraded performance. This issue is usually "
+                "caused by an incompatible cuDNN version installed in your python environment, or on the host "
+                f"system. Full error message:\n{e}"
+            )
+
+
 def invoke_api() -> None:
     def find_port(port: int) -> int:
         """Find a port not in use starting at given port"""
@@ -248,6 +270,8 @@ def invoke_api() -> None:
     if port != app_config.port:
         logger.warn(f"Port {app_config.port} in use, using port {port}")
 
+    check_cudnn(logger)
+
     # Start our own event loop for eventing usage
     loop = asyncio.new_event_loop()
     config = uvicorn.Config(

invokeai/app/invocations/compel.py

@@ -5,7 +5,15 @@ from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
 from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
 
-from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIComponent
+from invokeai.app.invocations.fields import (
+    ConditioningField,
+    FieldDescriptions,
+    Input,
+    InputField,
+    OutputField,
+    TensorField,
+    UIComponent,
+)
 from invokeai.app.invocations.primitives import ConditioningOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.ti_utils import generate_ti_list
@@ -14,10 +22,9 @@ from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
     ConditioningFieldData,
-    ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
-from invokeai.backend.util.devices import torch_dtype
+from invokeai.backend.util.devices import TorchDevice
 
 from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from .model import CLIPField
@@ -36,7 +43,7 @@ from .model import CLIPField
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.1.1",
+    version="1.2.0",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -51,15 +58,14 @@ class CompelInvocation(BaseInvocation):
         description=FieldDescriptions.clip,
         input=Input.Connection,
     )
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this conditioning prompt applies to."
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         tokenizer_info = context.models.load(self.clip.tokenizer)
-        tokenizer_model = tokenizer_info.model
-        assert isinstance(tokenizer_model, CLIPTokenizer)
         text_encoder_info = context.models.load(self.clip.text_encoder)
-        text_encoder_model = text_encoder_info.model
-        assert isinstance(text_encoder_model, CLIPTextModel)
 
         def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in self.clip.loras:
@@ -74,51 +80,45 @@ class CompelInvocation(BaseInvocation):
         ti_list = generate_ti_list(self.prompt, text_encoder_info.config.base, context)
 
         with (
-            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
-                tokenizer,
-                ti_manager,
-            ),
+            # apply all patches while the model is on the target device
             text_encoder_info as text_encoder,
-            # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
+            tokenizer_info as tokenizer,
             ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_model, self.clip.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder, self.clip.skipped_layers),
+            ModelPatcher.apply_ti(tokenizer, text_encoder, ti_list) as (
+                patched_tokenizer,
+                ti_manager,
+            ),
         ):
             assert isinstance(text_encoder, CLIPTextModel)
+            assert isinstance(tokenizer, CLIPTokenizer)
             compel = Compel(
-                tokenizer=tokenizer,
+                tokenizer=patched_tokenizer,
                 text_encoder=text_encoder,
                 textual_inversion_manager=ti_manager,
-                dtype_for_device_getter=torch_dtype,
+                dtype_for_device_getter=TorchDevice.choose_torch_dtype,
                 truncate_long_prompts=False,
             )
 
             conjunction = Compel.parse_prompt_string(self.prompt)
 
             if context.config.get().log_tokenization:
-                log_tokenization_for_conjunction(conjunction, tokenizer)
+                log_tokenization_for_conjunction(conjunction, patched_tokenizer)
 
-            c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
-
-            ec = ExtraConditioningInfo(
-                tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
-                cross_attention_control_args=options.get("cross_attention_control", None),
-            )
+            c, _options = compel.build_conditioning_tensor_for_conjunction(conjunction)
 
         c = c.detach().to("cpu")
 
-        conditioning_data = ConditioningFieldData(
-            conditionings=[
-                BasicConditioningInfo(
-                    embeds=c,
-                    extra_conditioning=ec,
-                )
-            ]
-        )
+        conditioning_data = ConditioningFieldData(conditionings=[BasicConditioningInfo(embeds=c)])
 
         conditioning_name = context.conditioning.save(conditioning_data)
-
-        return ConditioningOutput.build(conditioning_name)
+        return ConditioningOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+                mask=self.mask,
+            )
+        )
 
 
 class SDXLPromptInvocationBase:
@@ -132,13 +132,9 @@ class SDXLPromptInvocationBase:
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[ExtraConditioningInfo]]:
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
         tokenizer_info = context.models.load(clip_field.tokenizer)
-        tokenizer_model = tokenizer_info.model
-        assert isinstance(tokenizer_model, CLIPTokenizer)
         text_encoder_info = context.models.load(clip_field.text_encoder)
-        text_encoder_model = text_encoder_info.model
-        assert isinstance(text_encoder_model, (CLIPTextModel, CLIPTextModelWithProjection))
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
@@ -159,7 +155,7 @@ class SDXLPromptInvocationBase:
                 )
             else:
                 c_pooled = None
-            return c, c_pooled, None
+            return c, c_pooled
 
         def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in clip_field.loras:
@@ -175,23 +171,26 @@ class SDXLPromptInvocationBase:
         ti_list = generate_ti_list(prompt, text_encoder_info.config.base, context)
 
         with (
-            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
-                tokenizer,
-                ti_manager,
-            ),
+            # apply all patches while the model is on the target device
             text_encoder_info as text_encoder,
-            # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
+            tokenizer_info as tokenizer,
             ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_model, clip_field.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder, clip_field.skipped_layers),
+            ModelPatcher.apply_ti(tokenizer, text_encoder, ti_list) as (
+                patched_tokenizer,
+                ti_manager,
+            ),
         ):
             assert isinstance(text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
+            assert isinstance(tokenizer, CLIPTokenizer)
+
             text_encoder = cast(CLIPTextModel, text_encoder)
             compel = Compel(
-                tokenizer=tokenizer,
+                tokenizer=patched_tokenizer,
                 text_encoder=text_encoder,
                 textual_inversion_manager=ti_manager,
-                dtype_for_device_getter=torch_dtype,
+                dtype_for_device_getter=TorchDevice.choose_torch_dtype,
                 truncate_long_prompts=False,  # TODO:
                 returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED,  # TODO: clip skip
                 requires_pooled=get_pooled,
@@ -201,20 +200,15 @@ class SDXLPromptInvocationBase:
 
             if context.config.get().log_tokenization:
                 # TODO: better logging for and syntax
-                log_tokenization_for_conjunction(conjunction, tokenizer)
+                log_tokenization_for_conjunction(conjunction, patched_tokenizer)
 
             # TODO: ask for optimizations? to not run text_encoder twice
-            c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
+            c, _options = compel.build_conditioning_tensor_for_conjunction(conjunction)
             if get_pooled:
                 c_pooled = compel.conditioning_provider.get_pooled_embeddings([prompt])
             else:
                 c_pooled = None
 
-            ec = ExtraConditioningInfo(
-                tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
-                cross_attention_control_args=options.get("cross_attention_control", None),
-            )
-
         del tokenizer
         del text_encoder
         del tokenizer_info
@@ -224,7 +218,7 @@ class SDXLPromptInvocationBase:
         if c_pooled is not None:
             c_pooled = c_pooled.detach().to("cpu")
 
-        return c, c_pooled, ec
+        return c, c_pooled
 
 
 @invocation(
@@ -232,7 +226,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.1.1",
+    version="1.2.0",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -255,20 +249,19 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     target_height: int = InputField(default=1024, description="")
     clip: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
     clip2: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this conditioning prompt applies to."
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        c1, c1_pooled, ec1 = self.run_clip_compel(
-            context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True
-        )
+        c1, c1_pooled = self.run_clip_compel(context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True)
         if self.style.strip() == "":
-            c2, c2_pooled, ec2 = self.run_clip_compel(
+            c2, c2_pooled = self.run_clip_compel(
                 context, self.clip2, self.prompt, True, "lora_te2_", zero_on_empty=True
             )
         else:
-            c2, c2_pooled, ec2 = self.run_clip_compel(
-                context, self.clip2, self.style, True, "lora_te2_", zero_on_empty=True
-            )
+            c2, c2_pooled = self.run_clip_compel(context, self.clip2, self.style, True, "lora_te2_", zero_on_empty=True)
 
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
@@ -307,17 +300,19 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
-                    embeds=torch.cat([c1, c2], dim=-1),
-                    pooled_embeds=c2_pooled,
-                    add_time_ids=add_time_ids,
-                    extra_conditioning=ec1,
+                    embeds=torch.cat([c1, c2], dim=-1), pooled_embeds=c2_pooled, add_time_ids=add_time_ids
                 )
             ]
         )
 
         conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput.build(conditioning_name)
+        return ConditioningOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+                mask=self.mask,
+            )
+        )
 
 
 @invocation(
@@ -345,7 +340,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         # TODO: if there will appear lora for refiner - write proper prefix
-        c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.style, True, "<NONE>", zero_on_empty=False)
+        c2, c2_pooled = self.run_clip_compel(context, self.clip2, self.style, True, "<NONE>", zero_on_empty=False)
 
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
@@ -354,14 +349,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
-            conditionings=[
-                SDXLConditioningInfo(
-                    embeds=c2,
-                    pooled_embeds=c2_pooled,
-                    add_time_ids=add_time_ids,
-                    extra_conditioning=ec2,  # or None
-                )
-            ]
+            conditionings=[SDXLConditioningInfo(embeds=c2, pooled_embeds=c2_pooled, add_time_ids=add_time_ids)]
         )
 
         conditioning_name = context.conditioning.save(conditioning_data)

invokeai/app/invocations/controlnet_image_processors.py

@@ -24,7 +24,6 @@ from pydantic import BaseModel, Field, field_validator, model_validator
 from invokeai.app.invocations.fields import (
     FieldDescriptions,
     ImageField,
-    Input,
     InputField,
     OutputField,
     UIType,
@@ -35,22 +34,16 @@ from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageOutput
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.controlnet_utils import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES, heuristic_resize
 from invokeai.backend.image_util.canny import get_canny_edges
 from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
 from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
 from invokeai.backend.image_util.hed import HEDProcessor
 from invokeai.backend.image_util.lineart import LineartProcessor
 from invokeai.backend.image_util.lineart_anime import LineartAnimeProcessor
+from invokeai.backend.image_util.util import np_to_pil, pil_to_np
 
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
-
-CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
-CONTROLNET_RESIZE_VALUES = Literal[
-    "just_resize",
-    "crop_resize",
-    "fill_resize",
-    "just_resize_simple",
-]
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, Classification, invocation, invocation_output
 
 
 class ControlField(BaseModel):
@@ -86,13 +79,13 @@ class ControlOutput(BaseInvocationOutput):
     control: ControlField = OutputField(description=FieldDescriptions.control)
 
 
-@invocation("controlnet", title="ControlNet", tags=["controlnet"], category="controlnet", version="1.1.1")
+@invocation("controlnet", title="ControlNet", tags=["controlnet"], category="controlnet", version="1.1.2")
 class ControlNetInvocation(BaseInvocation):
     """Collects ControlNet info to pass to other nodes"""
 
     image: ImageField = InputField(description="The control image")
     control_model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.controlnet_model, input=Input.Direct, ui_type=UIType.ControlNetModel
+        description=FieldDescriptions.controlnet_model, ui_type=UIType.ControlNetModel
     )
     control_weight: Union[float, List[float]] = InputField(
         default=1.0, ge=-1, le=2, description="The weight given to the ControlNet"
@@ -171,13 +164,13 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
     title="Canny Processor",
     tags=["controlnet", "canny"],
     category="controlnet",
-    version="1.3.2",
+    version="1.3.3",
 )
 class CannyImageProcessorInvocation(ImageProcessorInvocation):
     """Canny edge detection for ControlNet"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
     low_threshold: int = InputField(
         default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)"
     )
@@ -205,13 +198,13 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
     title="HED (softedge) Processor",
     tags=["controlnet", "hed", "softedge"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class HedImageProcessorInvocation(ImageProcessorInvocation):
     """Applies HED edge detection to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
     # safe not supported in controlnet_aux v0.0.3
     # safe: bool = InputField(default=False, description=FieldDescriptions.safe_mode)
     scribble: bool = InputField(default=False, description=FieldDescriptions.scribble_mode)
@@ -234,13 +227,13 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Processor",
     tags=["controlnet", "lineart"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class LineartImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
     coarse: bool = InputField(default=False, description="Whether to use coarse mode")
 
     def run_processor(self, image: Image.Image) -> Image.Image:
@@ -256,13 +249,13 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Anime Processor",
     tags=["controlnet", "lineart", "anime"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art anime processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image: Image.Image) -> Image.Image:
         processor = LineartAnimeProcessor()
@@ -279,15 +272,15 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     title="Midas Depth Processor",
     tags=["controlnet", "midas"],
     category="controlnet",
-    version="1.2.3",
+    version="1.2.4",
 )
 class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Midas depth processing to image"""
 
     a_mult: float = InputField(default=2.0, ge=0, description="Midas parameter `a_mult` (a = a_mult * PI)")
     bg_th: float = InputField(default=0.1, ge=0, description="Midas parameter `bg_th`")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
     # depth_and_normal not supported in controlnet_aux v0.0.3
     # depth_and_normal: bool = InputField(default=False, description="whether to use depth and normal mode")
 
@@ -310,13 +303,13 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Normal BAE Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies NormalBae processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image):
         normalbae_processor = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
@@ -327,13 +320,13 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.2"
+    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.3"
 )
 class MlsdImageProcessorInvocation(ImageProcessorInvocation):
     """Applies MLSD processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
     thr_v: float = InputField(default=0.1, ge=0, description="MLSD parameter `thr_v`")
     thr_d: float = InputField(default=0.1, ge=0, description="MLSD parameter `thr_d`")
 
@@ -350,13 +343,13 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.2"
+    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.3"
 )
 class PidiImageProcessorInvocation(ImageProcessorInvocation):
     """Applies PIDI processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
     safe: bool = InputField(default=False, description=FieldDescriptions.safe_mode)
     scribble: bool = InputField(default=False, description=FieldDescriptions.scribble_mode)
 
@@ -377,13 +370,13 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
     title="Content Shuffle Processor",
     tags=["controlnet", "contentshuffle"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     """Applies content shuffle processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
     h: int = InputField(default=512, ge=0, description="Content shuffle `h` parameter")
     w: int = InputField(default=512, ge=0, description="Content shuffle `w` parameter")
     f: int = InputField(default=256, ge=0, description="Content shuffle `f` parameter")
@@ -407,7 +400,7 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     title="Zoe (Depth) Processor",
     tags=["controlnet", "zoe", "depth"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Zoe depth processing to image"""
@@ -423,15 +416,15 @@ class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Mediapipe Face Processor",
     tags=["controlnet", "mediapipe", "face"],
     category="controlnet",
-    version="1.2.3",
+    version="1.2.4",
 )
 class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     """Applies mediapipe face processing to image"""
 
     max_faces: int = InputField(default=1, ge=1, description="Maximum number of faces to detect")
     min_confidence: float = InputField(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image):
         mediapipe_face_processor = MediapipeFaceDetector()
@@ -450,7 +443,7 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     title="Leres (Depth) Processor",
     tags=["controlnet", "leres", "depth"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class LeresImageProcessorInvocation(ImageProcessorInvocation):
     """Applies leres processing to image"""
@@ -458,8 +451,8 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
     thr_a: float = InputField(default=0, description="Leres parameter `thr_a`")
     thr_b: float = InputField(default=0, description="Leres parameter `thr_b`")
     boost: bool = InputField(default=False, description="Whether to use boost mode")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image):
         leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
@@ -479,7 +472,7 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
     title="Tile Resample Processor",
     tags=["controlnet", "tile"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     """Tile resampler processor"""
@@ -519,13 +512,13 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     title="Segment Anything Processor",
     tags=["controlnet", "segmentanything"],
     category="controlnet",
-    version="1.2.3",
+    version="1.2.4",
 )
 class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     """Applies segment anything processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image):
         # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
@@ -566,12 +559,12 @@ class SamDetectorReproducibleColors(SamDetector):
     title="Color Map Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.2",
+    version="1.2.3",
 )
 class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a color map from the provided image"""
 
-    color_map_tile_size: int = InputField(default=64, ge=0, description=FieldDescriptions.tile_size)
+    color_map_tile_size: int = InputField(default=64, ge=1, description=FieldDescriptions.tile_size)
 
     def run_processor(self, image: Image.Image):
         np_image = np.array(image, dtype=np.uint8)
@@ -598,7 +591,7 @@ DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
     title="Depth Anything Processor",
     tags=["controlnet", "depth", "depth anything"],
     category="controlnet",
-    version="1.1.1",
+    version="1.1.2",
 )
 class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a depth map based on the Depth Anything algorithm"""
@@ -606,7 +599,7 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     model_size: DEPTH_ANYTHING_MODEL_SIZES = InputField(
         default="small", description="The size of the depth model to use"
     )
-    resolution: int = InputField(default=512, ge=64, multiple_of=64, description=FieldDescriptions.image_res)
+    resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image: Image.Image):
         depth_anything_detector = DepthAnythingDetector()
@@ -621,7 +614,7 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     title="DW Openpose Image Processor",
     tags=["controlnet", "dwpose", "openpose"],
     category="controlnet",
-    version="1.1.0",
+    version="1.1.1",
 )
 class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
     """Generates an openpose pose from an image using DWPose"""
@@ -629,7 +622,7 @@ class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
     draw_body: bool = InputField(default=True)
     draw_face: bool = InputField(default=False)
     draw_hands: bool = InputField(default=False)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image: Image.Image):
         dw_openpose = DWOpenposeDetector()
@@ -641,3 +634,27 @@ class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
             resolution=self.image_resolution,
         )
         return processed_image
+
+
+@invocation(
+    "heuristic_resize",
+    title="Heuristic Resize",
+    tags=["image, controlnet"],
+    category="image",
+    version="1.0.1",
+    classification=Classification.Prototype,
+)
+class HeuristicResizeInvocation(BaseInvocation):
+    """Resize an image using a heuristic method. Preserves edge maps."""
+
+    image: ImageField = InputField(description="The image to resize")
+    width: int = InputField(default=512, ge=1, description="The width to resize to (px)")
+    height: int = InputField(default=512, ge=1, description="The height to resize to (px)")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.images.get_pil(self.image.image_name, "RGB")
+        np_img = pil_to_np(image)
+        np_resized = heuristic_resize(np_img, (self.width, self.height))
+        resized = np_to_pil(np_resized)
+        image_dto = context.images.save(image=resized)
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/custom_nodes/init.py

@@ -3,6 +3,7 @@ Invoke-managed custom node loader. See README.md for more information.
 """
 
 import sys
+import traceback
 from importlib.util import module_from_spec, spec_from_file_location
 from pathlib import Path
 
@@ -41,11 +42,15 @@ for d in Path(__file__).parent.iterdir():
 
     logger.info(f"Loading node pack {module_name}")
 
-    module = module_from_spec(spec)
-    sys.modules[spec.name] = module
-    spec.loader.exec_module(module)
+    try:
+        module = module_from_spec(spec)
+        sys.modules[spec.name] = module
+        spec.loader.exec_module(module)
 
-    loaded_count += 1
+        loaded_count += 1
+    except Exception:
+        full_error = traceback.format_exc()
+        logger.error(f"Failed to load node pack {module_name}:\n{full_error}")
 
     del init, module_name
 

invokeai/app/invocations/fields.py

@@ -203,6 +203,12 @@ class DenoiseMaskField(BaseModel):
     gradient: bool = Field(default=False, description="Used for gradient inpainting")
 
 
+class TensorField(BaseModel):
+    """A tensor primitive field."""
+
+    tensor_name: str = Field(description="The name of a tensor.")
+
+
 class LatentsField(BaseModel):
     """A latents tensor primitive field"""
 
@@ -226,7 +232,11 @@ class ConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 
     conditioning_name: str = Field(description="The name of conditioning tensor")
-    # endregion
+    mask: Optional[TensorField] = Field(
+        default=None,
+        description="The mask associated with this conditioning tensor. Excluded regions should be set to False, "
+        "included regions should be set to True.",
+    )
 
 
 class MetadataField(RootModel[dict[str, Any]]):

invokeai/app/invocations/image.py

@@ -1,6 +1,5 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from pathlib import Path
 from typing import Literal, Optional
 
 import cv2
@@ -504,7 +503,7 @@ class ImageInverseLerpInvocation(BaseInvocation, WithMetadata, WithBoard):
     title="Blur NSFW Image",
     tags=["image", "nsfw"],
     category="image",
-    version="1.2.2",
+    version="1.2.3",
 )
 class ImageNSFWBlurInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Add blur to NSFW-flagged images"""
@@ -516,23 +515,12 @@ class ImageNSFWBlurInvocation(BaseInvocation, WithMetadata, WithBoard):
 
         logger = context.logger
         logger.debug("Running NSFW checker")
-        if SafetyChecker.has_nsfw_concept(image):
-            logger.info("A potentially NSFW image has been detected. Image will be blurred.")
-            blurry_image = image.filter(filter=ImageFilter.GaussianBlur(radius=32))
-            caution = self._get_caution_img()
-            blurry_image.paste(caution, (0, 0), caution)
-            image = blurry_image
+        image = SafetyChecker.blur_if_nsfw(image)
 
         image_dto = context.images.save(image=image)
 
         return ImageOutput.build(image_dto)
 
-    def _get_caution_img(self) -> Image.Image:
-        import invokeai.app.assets.images as image_assets
-
-        caution = Image.open(Path(image_assets.__path__[0]) / "caution.png")
-        return caution.resize((caution.width // 2, caution.height // 2))
-
 
 @invocation(
     "img_watermark",

invokeai/app/invocations/infill.py

@@ -1,154 +1,91 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+from abc import abstractmethod
+from typing import Literal, get_args
 
-import math
-from typing import Literal, Optional, get_args
-
-import numpy as np
-from PIL import Image, ImageOps
+from PIL import Image
 
 from invokeai.app.invocations.fields import ColorField, ImageField
 from invokeai.app.invocations.primitives import ImageOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.app.util.download_with_progress import download_with_progress_bar
 from invokeai.app.util.misc import SEED_MAX
-from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
-from invokeai.backend.image_util.lama import LaMA
-from invokeai.backend.image_util.patchmatch import PatchMatch
+from invokeai.backend.image_util.infill_methods.cv2_inpaint import cv2_inpaint
+from invokeai.backend.image_util.infill_methods.lama import LaMA
+from invokeai.backend.image_util.infill_methods.mosaic import infill_mosaic
+from invokeai.backend.image_util.infill_methods.patchmatch import PatchMatch, infill_patchmatch
+from invokeai.backend.image_util.infill_methods.tile import infill_tile
+from invokeai.backend.util.logging import InvokeAILogger
 
 from .baseinvocation import BaseInvocation, invocation
 from .fields import InputField, WithBoard, WithMetadata
 from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
 
+logger = InvokeAILogger.get_logger()
 
-def infill_methods() -> list[str]:
-    methods = ["tile", "solid", "lama", "cv2"]
+
+def get_infill_methods():
+    methods = Literal["tile", "color", "lama", "cv2"]  # TODO: add mosaic back
     if PatchMatch.patchmatch_available():
-        methods.insert(0, "patchmatch")
+        methods = Literal["patchmatch", "tile", "color", "lama", "cv2"]  # TODO: add mosaic back
     return methods
 
 
-INFILL_METHODS = Literal[tuple(infill_methods())]
+INFILL_METHODS = get_infill_methods()
 DEFAULT_INFILL_METHOD = "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
 
 
-def infill_lama(im: Image.Image) -> Image.Image:
-    lama = LaMA()
-    return lama(im)
+class InfillImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Base class for invocations that preprocess images for Infilling"""
 
+    image: ImageField = InputField(description="The image to process")
 
-def infill_patchmatch(im: Image.Image) -> Image.Image:
-    if im.mode != "RGBA":
-        return im
+    @abstractmethod
+    def infill(self, image: Image.Image) -> Image.Image:
+        """Infill the image with the specified method"""
+        pass
 
-    # Skip patchmatch if patchmatch isn't available
-    if not PatchMatch.patchmatch_available():
-        return im
+    def load_image(self, context: InvocationContext) -> tuple[Image.Image, bool]:
+        """Process the image to have an alpha channel before being infilled"""
+        image = context.images.get_pil(self.image.image_name)
+        has_alpha = True if image.mode == "RGBA" else False
+        return image, has_alpha
 
-    # 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 invoke(self, context: InvocationContext) -> ImageOutput:
+        # Retrieve and process image to be infilled
+        input_image, has_alpha = self.load_image(context)
 
+        # If the input image has no alpha channel, return it
+        if has_alpha is False:
+            return ImageOutput.build(context.images.get_dto(self.image.image_name))
 
-def infill_cv2(im: Image.Image) -> Image.Image:
-    return cv2_inpaint(im)
+        # Perform Infill action
+        infilled_image = self.infill(input_image)
 
+        # Create ImageDTO for Infilled Image
+        infilled_image_dto = context.images.save(image=infilled_image)
 
-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: Optional[int] = 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()  # noqa: E712
-    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
+        # Return Infilled Image
+        return ImageOutput.build(infilled_image_dto)
 
 
 @invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
-class InfillColorInvocation(BaseInvocation, WithMetadata, WithBoard):
+class InfillColorInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image with a solid color"""
 
-    image: ImageField = InputField(description="The image to infill")
     color: ColorField = InputField(
         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.images.get_pil(self.image.image_name)
-
+    def infill(self, image: Image.Image):
         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.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+        return infilled
 
 
 @invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.3")
-class InfillTileInvocation(BaseInvocation, WithMetadata, WithBoard):
+class InfillTileInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image with tiles of the image"""
 
-    image: ImageField = InputField(description="The image to infill")
     tile_size: int = InputField(default=32, ge=1, description="The tile size (px)")
     seed: int = InputField(
         default=0,
@@ -157,92 +94,74 @@ class InfillTileInvocation(BaseInvocation, WithMetadata, WithBoard):
         description="The seed to use for tile generation (omit for random)",
     )
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name)
-
-        infilled = tile_fill_missing(image.copy(), seed=self.seed, tile_size=self.tile_size)
-        infilled.paste(image, (0, 0), image.split()[-1])
-
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+    def infill(self, image: Image.Image):
+        output = infill_tile(image, seed=self.seed, tile_size=self.tile_size)
+        return output.infilled
 
 
 @invocation(
     "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2"
 )
-class InfillPatchMatchInvocation(BaseInvocation, WithMetadata, WithBoard):
+class InfillPatchMatchInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
-    image: ImageField = InputField(description="The image to infill")
     downscale: float = InputField(default=2.0, gt=0, description="Run patchmatch on downscaled image to speedup infill")
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name).convert("RGBA")
-
+    def infill(self, image: Image.Image):
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
-        infill_image = image.copy()
         width = int(image.width / self.downscale)
         height = int(image.height / self.downscale)
-        infill_image = infill_image.resize(
+
+        infilled = image.resize(
             (width, height),
             resample=resample_mode,
         )
-
-        if PatchMatch.patchmatch_available():
-            infilled = infill_patchmatch(infill_image)
-        else:
-            raise ValueError("PatchMatch is not available on this system")
-
+        infilled = infill_patchmatch(image)
         infilled = infilled.resize(
             (image.width, image.height),
             resample=resample_mode,
         )
-
         infilled.paste(image, (0, 0), mask=image.split()[-1])
-        # image.paste(infilled, (0, 0), mask=image.split()[-1])
 
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+        return infilled
 
 
 @invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
-class LaMaInfillInvocation(BaseInvocation, WithMetadata, WithBoard):
+class LaMaInfillInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using the LaMa model"""
 
-    image: ImageField = InputField(description="The image to infill")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name)
-
-        # Downloads the LaMa model if it doesn't already exist
-        download_with_progress_bar(
-            name="LaMa Inpainting Model",
-            url="https://github.com/Sanster/models/releases/download/add_big_lama/big-lama.pt",
-            dest_path=context.config.get().models_path / "core/misc/lama/lama.pt",
-        )
-
-        infilled = infill_lama(image.copy())
-
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+    def infill(self, image: Image.Image):
+        lama = LaMA()
+        return lama(image)
 
 
 @invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
-class CV2InfillInvocation(BaseInvocation, WithMetadata, WithBoard):
+class CV2InfillInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
+    def infill(self, image: Image.Image):
+        return cv2_inpaint(image)
+
+
+# @invocation(
+#     "infill_mosaic", title="Mosaic Infill", tags=["image", "inpaint", "outpaint"], category="inpaint", version="1.0.0"
+# )
+class MosaicInfillInvocation(InfillImageProcessorInvocation):
+    """Infills transparent areas of an image with a mosaic pattern drawing colors from the rest of the image"""
+
     image: ImageField = InputField(description="The image to infill")
+    tile_width: int = InputField(default=64, description="Width of the tile")
+    tile_height: int = InputField(default=64, description="Height of the tile")
+    min_color: ColorField = InputField(
+        default=ColorField(r=0, g=0, b=0, a=255),
+        description="The min threshold for color",
+    )
+    max_color: ColorField = InputField(
+        default=ColorField(r=255, g=255, b=255, a=255),
+        description="The max threshold for color",
+    )
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.images.get_pil(self.image.image_name)
-
-        infilled = infill_cv2(image.copy())
-
-        image_dto = context.images.save(image=infilled)
-
-        return ImageOutput.build(image_dto)
+    def infill(self, image: Image.Image):
+        return infill_mosaic(image, (self.tile_width, self.tile_height), self.min_color.tuple(), self.max_color.tuple())

invokeai/app/invocations/ip_adapter.py

@@ -1,34 +1,41 @@
 from builtins import float
-from typing import List, Union
+from typing import List, Literal, Optional, Union
 
 from pydantic import BaseModel, Field, field_validator, model_validator
 from typing_extensions import Self
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
-from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from invokeai.app.invocations.fields import FieldDescriptions, InputField, OutputField, TensorField, UIType
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, IPAdapterConfig, ModelType
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    IPAdapterCheckpointConfig,
+    IPAdapterInvokeAIConfig,
+    ModelType,
+)
 
 
 class IPAdapterField(BaseModel):
     image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
     ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model to use.")
     image_encoder_model: ModelIdentifierField = Field(description="The name of the CLIP image encoder model.")
-    weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
+    weight: Union[float, List[float]] = Field(default=1, description="The weight given to the IP-Adapter.")
+    target_blocks: List[str] = Field(default=[], description="The IP Adapter blocks to apply")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
     )
     end_step_percent: float = Field(
         default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
+    mask: Optional[TensorField] = Field(
+        default=None,
+        description="The bool mask associated with this IP-Adapter. Excluded regions should be set to False, included "
+        "regions should be set to True.",
+    )
 
     @field_validator("weight")
     @classmethod
@@ -48,29 +55,41 @@ class IPAdapterOutput(BaseInvocationOutput):
     ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.2.2")
+CLIP_VISION_MODEL_MAP = {"ViT-H": "ip_adapter_sd_image_encoder", "ViT-G": "ip_adapter_sdxl_image_encoder"}
+
+
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.4.1")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
     # Inputs
-    image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).")
+    image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).", ui_order=1)
     ip_adapter_model: ModelIdentifierField = InputField(
         description="The IP-Adapter model.",
         title="IP-Adapter Model",
-        input=Input.Direct,
         ui_order=-1,
         ui_type=UIType.IPAdapterModel,
     )
-
+    clip_vision_model: Literal["ViT-H", "ViT-G"] = InputField(
+        description="CLIP Vision model to use. Overrides model settings. Mandatory for checkpoint models.",
+        default="ViT-H",
+        ui_order=2,
+    )
     weight: Union[float, List[float]] = InputField(
         default=1, description="The weight given to the IP-Adapter", title="Weight"
     )
+    method: Literal["full", "style", "composition"] = InputField(
+        default="full", description="The method to apply the IP-Adapter"
+    )
     begin_step_percent: float = InputField(
         default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
     )
     end_step_percent: float = InputField(
         default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this IP-Adapter applies to."
+    )
 
     @field_validator("weight")
     @classmethod
@@ -86,35 +105,68 @@ class IPAdapterInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> IPAdapterOutput:
         # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
         ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
-        assert isinstance(ip_adapter_info, IPAdapterConfig)
-        image_encoder_model_id = ip_adapter_info.image_encoder_model_id
-        image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
+        assert isinstance(ip_adapter_info, (IPAdapterInvokeAIConfig, IPAdapterCheckpointConfig))
+
+        if isinstance(ip_adapter_info, IPAdapterInvokeAIConfig):
+            image_encoder_model_id = ip_adapter_info.image_encoder_model_id
+            image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
+        else:
+            image_encoder_model_name = CLIP_VISION_MODEL_MAP[self.clip_vision_model]
+
         image_encoder_model = self._get_image_encoder(context, image_encoder_model_name)
+
+        if self.method == "style":
+            if ip_adapter_info.base == "sd-1":
+                target_blocks = ["up_blocks.1"]
+            elif ip_adapter_info.base == "sdxl":
+                target_blocks = ["up_blocks.0.attentions.1"]
+            else:
+                raise ValueError(f"Unsupported IP-Adapter base type: '{ip_adapter_info.base}'.")
+        elif self.method == "composition":
+            if ip_adapter_info.base == "sd-1":
+                target_blocks = ["down_blocks.2", "mid_block"]
+            elif ip_adapter_info.base == "sdxl":
+                target_blocks = ["down_blocks.2.attentions.1"]
+            else:
+                raise ValueError(f"Unsupported IP-Adapter base type: '{ip_adapter_info.base}'.")
+        elif self.method == "full":
+            target_blocks = ["block"]
+        else:
+            raise ValueError(f"Unexpected IP-Adapter method: '{self.method}'.")
+
         return IPAdapterOutput(
             ip_adapter=IPAdapterField(
                 image=self.image,
                 ip_adapter_model=self.ip_adapter_model,
                 image_encoder_model=ModelIdentifierField.from_config(image_encoder_model),
                 weight=self.weight,
+                target_blocks=target_blocks,
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,
+                mask=self.mask,
             ),
         )
 
     def _get_image_encoder(self, context: InvocationContext, image_encoder_model_name: str) -> AnyModelConfig:
-        found = False
-        while not found:
+        image_encoder_models = context.models.search_by_attrs(
+            name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
+        )
+
+        if not len(image_encoder_models) > 0:
+            context.logger.warning(
+                f"The image encoder required by this IP Adapter ({image_encoder_model_name}) is not installed. \
+                    Downloading and installing now. This may take a while."
+            )
+
+            installer = context._services.model_manager.install
+            job = installer.heuristic_import(f"InvokeAI/{image_encoder_model_name}")
+            installer.wait_for_job(job, timeout=600)  # Wait for up to 10 minutes
             image_encoder_models = context.models.search_by_attrs(
                 name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
             )
-            found = len(image_encoder_models) > 0
-            if not found:
-                context.logger.warning(
-                    f"The image encoder required by this IP Adapter ({image_encoder_model_name}) is not installed."
-                )
-                context.logger.warning("Downloading and installing now. This may take a while.")
-                installer = context._services.model_manager.install
-                job = installer.heuristic_import(f"InvokeAI/{image_encoder_model_name}")
-                installer.wait_for_job(job, timeout=600)  # wait up to 10 minutes - then raise a TimeoutException
-        assert len(image_encoder_models) == 1
+
+            if len(image_encoder_models) == 0:
+                context.logger.error("Error while fetching CLIP Vision Image Encoder")
+                assert len(image_encoder_models) == 1
+
         return image_encoder_models[0]

invokeai/app/invocations/latent.py

@@ -1,16 +1,16 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
+import inspect
 import math
 from contextlib import ExitStack
 from functools import singledispatchmethod
-from typing import Any, Iterator, List, Literal, Optional, Tuple, Union
+from typing import Any, Dict, Iterator, List, Literal, Optional, Tuple, Union
 
 import einops
 import numpy as np
 import numpy.typing as npt
 import torch
+import torchvision
 import torchvision.transforms as T
-from diffusers import AutoencoderKL, AutoencoderTiny
 from diffusers.configuration_utils import ConfigMixin
 from diffusers.image_processor import VaeImageProcessor
 from diffusers.models.adapter import T2IAdapter
@@ -20,9 +20,12 @@ from diffusers.models.attention_processor import (
     LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
+from diffusers.models.autoencoders.autoencoder_kl import AutoencoderKL
+from diffusers.models.autoencoders.autoencoder_tiny import AutoencoderTiny
 from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
-from diffusers.schedulers import DPMSolverSDEScheduler
-from diffusers.schedulers import SchedulerMixin as Scheduler
+from diffusers.schedulers.scheduling_dpmsolver_sde import DPMSolverSDEScheduler
+from diffusers.schedulers.scheduling_tcd import TCDScheduler
+from diffusers.schedulers.scheduling_utils import SchedulerMixin as Scheduler
 from PIL import Image, ImageFilter
 from pydantic import field_validator
 from torchvision.transforms.functional import resize as tv_resize
@@ -43,44 +46,41 @@ from invokeai.app.invocations.fields import (
     WithMetadata,
 )
 from invokeai.app.invocations.ip_adapter import IPAdapterField
-from invokeai.app.invocations.primitives import (
-    DenoiseMaskOutput,
-    ImageOutput,
-    LatentsOutput,
-)
+from invokeai.app.invocations.primitives import DenoiseMaskOutput, ImageOutput, LatentsOutput
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
 from invokeai.backend.lora import LoRAModelRaw
 from invokeai.backend.model_manager import BaseModelType, LoadedModel
+from invokeai.backend.model_manager.config import MainConfigBase, ModelVariantType
 from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion import PipelineIntermediateState, set_seamless
-from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
+    BasicConditioningInfo,
+    IPAdapterConditioningInfo,
+    IPAdapterData,
+    Range,
+    SDXLConditioningInfo,
+    TextConditioningData,
+    TextConditioningRegions,
+)
+from invokeai.backend.util.mask import to_standard_float_mask
 from invokeai.backend.util.silence_warnings import SilenceWarnings
 
 from ...backend.stable_diffusion.diffusers_pipeline import (
     ControlNetData,
-    IPAdapterData,
     StableDiffusionGeneratorPipeline,
     T2IAdapterData,
     image_resized_to_grid_as_tensor,
 )
 from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
-from ...backend.util.devices import choose_precision, choose_torch_device
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
+from ...backend.util.devices import TorchDevice
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from .controlnet_image_processors import ControlField
 from .model import ModelIdentifierField, UNetField, VAEField
 
-if choose_torch_device() == torch.device("mps"):
-    from torch import mps
-
-DEFAULT_PRECISION = choose_precision(choose_torch_device())
+DEFAULT_PRECISION = TorchDevice.choose_torch_dtype()
 
 
 @invocation_output("scheduler_output")
@@ -188,7 +188,7 @@ class GradientMaskOutput(BaseInvocationOutput):
     title="Create Gradient Mask",
     tags=["mask", "denoise"],
     category="latents",
-    version="1.0.0",
+    version="1.1.0",
 )
 class CreateGradientMaskInvocation(BaseInvocation):
     """Creates mask for denoising model run."""
@@ -201,6 +201,32 @@ class CreateGradientMaskInvocation(BaseInvocation):
     minimum_denoise: float = InputField(
         default=0.0, ge=0, le=1, description="Minimum denoise level for the coherence region", ui_order=4
     )
+    image: Optional[ImageField] = InputField(
+        default=None,
+        description="OPTIONAL: Only connect for specialized Inpainting models, masked_latents will be generated from the image with the VAE",
+        title="[OPTIONAL] Image",
+        ui_order=6,
+    )
+    unet: Optional[UNetField] = InputField(
+        description="OPTIONAL: If the Unet is a specialized Inpainting model, masked_latents will be generated from the image with the VAE",
+        default=None,
+        input=Input.Connection,
+        title="[OPTIONAL] UNet",
+        ui_order=5,
+    )
+    vae: Optional[VAEField] = InputField(
+        default=None,
+        description="OPTIONAL: Only connect for specialized Inpainting models, masked_latents will be generated from the image with the VAE",
+        title="[OPTIONAL] VAE",
+        input=Input.Connection,
+        ui_order=7,
+    )
+    tiled: bool = InputField(default=False, description=FieldDescriptions.tiled, ui_order=8)
+    fp32: bool = InputField(
+        default=DEFAULT_PRECISION == "float32",
+        description=FieldDescriptions.fp32,
+        ui_order=9,
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> GradientMaskOutput:
@@ -236,8 +262,27 @@ class CreateGradientMaskInvocation(BaseInvocation):
         expanded_mask_image = Image.fromarray((expanded_mask.squeeze(0).numpy() * 255).astype(np.uint8), mode="L")
         expanded_image_dto = context.images.save(expanded_mask_image)
 
+        masked_latents_name = None
+        if self.unet is not None and self.vae is not None and self.image is not None:
+            # all three fields must be present at the same time
+            main_model_config = context.models.get_config(self.unet.unet.key)
+            assert isinstance(main_model_config, MainConfigBase)
+            if main_model_config.variant is ModelVariantType.Inpaint:
+                mask = blur_tensor
+                vae_info: LoadedModel = context.models.load(self.vae.vae)
+                image = context.images.get_pil(self.image.image_name)
+                image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+                if image_tensor.dim() == 3:
+                    image_tensor = image_tensor.unsqueeze(0)
+                img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
+                masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
+                masked_latents = ImageToLatentsInvocation.vae_encode(
+                    vae_info, self.fp32, self.tiled, masked_image.clone()
+                )
+                masked_latents_name = context.tensors.save(tensor=masked_latents)
+
         return GradientMaskOutput(
-            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=None, gradient=True),
+            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=masked_latents_name, gradient=True),
             expanded_mask_area=ImageField(image_name=expanded_image_dto.image_name),
         )
 
@@ -284,10 +329,10 @@ def get_scheduler(
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
 
-    positive_conditioning: ConditioningField = InputField(
+    positive_conditioning: Union[ConditioningField, list[ConditioningField]] = InputField(
         description=FieldDescriptions.positive_cond, input=Input.Connection, ui_order=0
     )
-    negative_conditioning: ConditioningField = InputField(
+    negative_conditioning: Union[ConditioningField, list[ConditioningField]] = InputField(
         description=FieldDescriptions.negative_cond, input=Input.Connection, ui_order=1
     )
     noise: Optional[LatentsField] = InputField(
@@ -298,7 +343,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     )
     steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
     cfg_scale: Union[float, List[float]] = InputField(
-        default=7.5, ge=1, description=FieldDescriptions.cfg_scale, title="CFG Scale"
+        default=7.5, description=FieldDescriptions.cfg_scale, title="CFG Scale"
     )
     denoising_start: float = InputField(
         default=0.0,
@@ -365,33 +410,174 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 raise ValueError("cfg_scale must be greater than 1")
         return v
 
+    def _get_text_embeddings_and_masks(
+        self,
+        cond_list: list[ConditioningField],
+        context: InvocationContext,
+        device: torch.device,
+        dtype: torch.dtype,
+    ) -> tuple[Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]], list[Optional[torch.Tensor]]]:
+        """Get the text embeddings and masks from the input conditioning fields."""
+        text_embeddings: Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]] = []
+        text_embeddings_masks: list[Optional[torch.Tensor]] = []
+        for cond in cond_list:
+            cond_data = context.conditioning.load(cond.conditioning_name)
+            text_embeddings.append(cond_data.conditionings[0].to(device=device, dtype=dtype))
+
+            mask = cond.mask
+            if mask is not None:
+                mask = context.tensors.load(mask.tensor_name)
+            text_embeddings_masks.append(mask)
+
+        return text_embeddings, text_embeddings_masks
+
+    def _preprocess_regional_prompt_mask(
+        self, mask: Optional[torch.Tensor], target_height: int, target_width: int, dtype: torch.dtype
+    ) -> torch.Tensor:
+        """Preprocess a regional prompt mask to match the target height and width.
+        If mask is None, returns a mask of all ones with the target height and width.
+        If mask is not None, resizes the mask to the target height and width using 'nearest' interpolation.
+
+        Returns:
+            torch.Tensor: The processed mask. shape: (1, 1, target_height, target_width).
+        """
+
+        if mask is None:
+            return torch.ones((1, 1, target_height, target_width), dtype=dtype)
+
+        mask = to_standard_float_mask(mask, out_dtype=dtype)
+
+        tf = torchvision.transforms.Resize(
+            (target_height, target_width), interpolation=torchvision.transforms.InterpolationMode.NEAREST
+        )
+
+        # Add a batch dimension to the mask, because torchvision expects shape (batch, channels, h, w).
+        mask = mask.unsqueeze(0)  # Shape: (1, h, w) -> (1, 1, h, w)
+        resized_mask = tf(mask)
+        return resized_mask
+
+    def _concat_regional_text_embeddings(
+        self,
+        text_conditionings: Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]],
+        masks: Optional[list[Optional[torch.Tensor]]],
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
+    ) -> tuple[Union[BasicConditioningInfo, SDXLConditioningInfo], Optional[TextConditioningRegions]]:
+        """Concatenate regional text embeddings into a single embedding and track the region masks accordingly."""
+        if masks is None:
+            masks = [None] * len(text_conditionings)
+        assert len(text_conditionings) == len(masks)
+
+        is_sdxl = type(text_conditionings[0]) is SDXLConditioningInfo
+
+        all_masks_are_none = all(mask is None for mask in masks)
+
+        text_embedding = []
+        pooled_embedding = None
+        add_time_ids = None
+        cur_text_embedding_len = 0
+        processed_masks = []
+        embedding_ranges = []
+
+        for prompt_idx, text_embedding_info in enumerate(text_conditionings):
+            mask = masks[prompt_idx]
+
+            if is_sdxl:
+                # We choose a random SDXLConditioningInfo's pooled_embeds and add_time_ids here, with a preference for
+                # prompts without a mask. We prefer prompts without a mask, because they are more likely to contain
+                # global prompt information.  In an ideal case, there should be exactly one global prompt without a
+                # mask, but we don't enforce this.
+
+                # HACK(ryand): The fact that we have to choose a single pooled_embedding and add_time_ids here is a
+                # fundamental interface issue. The SDXL Compel nodes are not designed to be used in the way that we use
+                # them for regional prompting. Ideally, the DenoiseLatents invocation should accept a single
+                # pooled_embeds tensor and a list of standard text embeds with region masks. This change would be a
+                # pretty major breaking change to a popular node, so for now we use this hack.
+                if pooled_embedding is None or mask is None:
+                    pooled_embedding = text_embedding_info.pooled_embeds
+                if add_time_ids is None or mask is None:
+                    add_time_ids = text_embedding_info.add_time_ids
+
+            text_embedding.append(text_embedding_info.embeds)
+            if not all_masks_are_none:
+                embedding_ranges.append(
+                    Range(
+                        start=cur_text_embedding_len, end=cur_text_embedding_len + text_embedding_info.embeds.shape[1]
+                    )
+                )
+                processed_masks.append(
+                    self._preprocess_regional_prompt_mask(mask, latent_height, latent_width, dtype=dtype)
+                )
+
+            cur_text_embedding_len += text_embedding_info.embeds.shape[1]
+
+        text_embedding = torch.cat(text_embedding, dim=1)
+        assert len(text_embedding.shape) == 3  # batch_size, seq_len, token_len
+
+        regions = None
+        if not all_masks_are_none:
+            regions = TextConditioningRegions(
+                masks=torch.cat(processed_masks, dim=1),
+                ranges=embedding_ranges,
+            )
+
+        if is_sdxl:
+            return (
+                SDXLConditioningInfo(embeds=text_embedding, pooled_embeds=pooled_embedding, add_time_ids=add_time_ids),
+                regions,
+            )
+        return BasicConditioningInfo(embeds=text_embedding), regions
+
     def get_conditioning_data(
         self,
         context: InvocationContext,
-        scheduler: Scheduler,
         unet: UNet2DConditionModel,
-        seed: int,
-    ) -> ConditioningData:
-        positive_cond_data = context.conditioning.load(self.positive_conditioning.conditioning_name)
-        c = positive_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
+        latent_height: int,
+        latent_width: int,
+    ) -> TextConditioningData:
+        # Normalize self.positive_conditioning and self.negative_conditioning to lists.
+        cond_list = self.positive_conditioning
+        if not isinstance(cond_list, list):
+            cond_list = [cond_list]
+        uncond_list = self.negative_conditioning
+        if not isinstance(uncond_list, list):
+            uncond_list = [uncond_list]
 
-        negative_cond_data = context.conditioning.load(self.negative_conditioning.conditioning_name)
-        uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
-
-        conditioning_data = ConditioningData(
-            unconditioned_embeddings=uc,
-            text_embeddings=c,
-            guidance_scale=self.cfg_scale,
-            guidance_rescale_multiplier=self.cfg_rescale_multiplier,
+        cond_text_embeddings, cond_text_embedding_masks = self._get_text_embeddings_and_masks(
+            cond_list, context, unet.device, unet.dtype
+        )
+        uncond_text_embeddings, uncond_text_embedding_masks = self._get_text_embeddings_and_masks(
+            uncond_list, context, unet.device, unet.dtype
         )
 
-        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(  # FIXME
-            scheduler,
-            # for ddim scheduler
-            eta=0.0,  # ddim_eta
-            # for ancestral and sde schedulers
-            # flip all bits to have noise different from initial
-            generator=torch.Generator(device=unet.device).manual_seed(seed ^ 0xFFFFFFFF),
+        cond_text_embedding, cond_regions = self._concat_regional_text_embeddings(
+            text_conditionings=cond_text_embeddings,
+            masks=cond_text_embedding_masks,
+            latent_height=latent_height,
+            latent_width=latent_width,
+            dtype=unet.dtype,
+        )
+        uncond_text_embedding, uncond_regions = self._concat_regional_text_embeddings(
+            text_conditionings=uncond_text_embeddings,
+            masks=uncond_text_embedding_masks,
+            latent_height=latent_height,
+            latent_width=latent_width,
+            dtype=unet.dtype,
+        )
+
+        if isinstance(self.cfg_scale, list):
+            assert (
+                len(self.cfg_scale) == self.steps
+            ), "cfg_scale (list) must have the same length as the number of steps"
+
+        conditioning_data = TextConditioningData(
+            uncond_text=uncond_text_embedding,
+            cond_text=cond_text_embedding,
+            uncond_regions=uncond_regions,
+            cond_regions=cond_regions,
+            guidance_scale=self.cfg_scale,
+            guidance_rescale_multiplier=self.cfg_rescale_multiplier,
         )
         return conditioning_data
 
@@ -400,13 +586,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
         unet: UNet2DConditionModel,
         scheduler: Scheduler,
     ) -> StableDiffusionGeneratorPipeline:
-        # TODO:
-        # configure_model_padding(
-        #    unet,
-        #    self.seamless,
-        #    self.seamless_axes,
-        # )
-
         class FakeVae:
             class FakeVaeConfig:
                 def __init__(self) -> None:
@@ -497,8 +676,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
         self,
         context: InvocationContext,
         ip_adapter: Optional[Union[IPAdapterField, list[IPAdapterField]]],
-        conditioning_data: ConditioningData,
         exit_stack: ExitStack,
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
     ) -> Optional[list[IPAdapterData]]:
         """If IP-Adapter is enabled, then this function loads the requisite models, and adds the image prompt embeddings
         to the `conditioning_data` (in-place).
@@ -514,7 +695,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
             return None
 
         ip_adapter_data_list = []
-        conditioning_data.ip_adapter_conditioning = []
         for single_ip_adapter in ip_adapter:
             ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
                 context.models.load(single_ip_adapter.ip_adapter_model)
@@ -537,16 +717,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     single_ipa_images, image_encoder_model
                 )
 
-                conditioning_data.ip_adapter_conditioning.append(
-                    IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds)
-                )
+            mask = single_ip_adapter.mask
+            if mask is not None:
+                mask = context.tensors.load(mask.tensor_name)
+            mask = self._preprocess_regional_prompt_mask(mask, latent_height, latent_width, dtype=dtype)
 
             ip_adapter_data_list.append(
                 IPAdapterData(
                     ip_adapter_model=ip_adapter_model,
                     weight=single_ip_adapter.weight,
+                    target_blocks=single_ip_adapter.target_blocks,
                     begin_step_percent=single_ip_adapter.begin_step_percent,
                     end_step_percent=single_ip_adapter.end_step_percent,
+                    ip_adapter_conditioning=IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds),
+                    mask=mask,
                 )
             )
 
@@ -636,7 +820,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
         steps: int,
         denoising_start: float,
         denoising_end: float,
-    ) -> Tuple[int, List[int], int]:
+        seed: int,
+    ) -> Tuple[int, List[int], int, Dict[str, Any]]:
         assert isinstance(scheduler, ConfigMixin)
         if scheduler.config.get("cpu_only", False):
             scheduler.set_timesteps(steps, device="cpu")
@@ -664,7 +849,17 @@ class DenoiseLatentsInvocation(BaseInvocation):
         timesteps = timesteps[t_start_idx : t_start_idx + t_end_idx]
         num_inference_steps = len(timesteps) // scheduler.order
 
-        return num_inference_steps, timesteps, init_timestep
+        scheduler_step_kwargs: Dict[str, Any] = {}
+        scheduler_step_signature = inspect.signature(scheduler.step)
+        if "generator" in scheduler_step_signature.parameters:
+            # At some point, someone decided that schedulers that accept a generator should use the original seed with
+            # all bits flipped. I don't know the original rationale for this, but now we must keep it like this for
+            # reproducibility.
+            scheduler_step_kwargs.update({"generator": torch.Generator(device=device).manual_seed(seed ^ 0xFFFFFFFF)})
+        if isinstance(scheduler, TCDScheduler):
+            scheduler_step_kwargs.update({"eta": 1.0})
+
+        return num_inference_steps, timesteps, init_timestep, scheduler_step_kwargs
 
     def prep_inpaint_mask(
         self, context: InvocationContext, latents: torch.Tensor
@@ -735,9 +930,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
             assert isinstance(unet_info.model, UNet2DConditionModel)
             with (
                 ExitStack() as exit_stack,
-                ModelPatcher.apply_freeu(unet_info.model, self.unet.freeu_config),
-                set_seamless(unet_info.model, self.unet.seamless_axes),  # FIXME
                 unet_info as unet,
+                ModelPatcher.apply_freeu(unet, self.unet.freeu_config),
+                set_seamless(unet, self.unet.seamless_axes),  # FIXME
                 # Apply the LoRA after unet has been moved to its target device for faster patching.
                 ModelPatcher.apply_lora_unet(unet, _lora_loader()),
             ):
@@ -758,7 +953,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 )
 
                 pipeline = self.create_pipeline(unet, scheduler)
-                conditioning_data = self.get_conditioning_data(context, scheduler, unet, seed)
+
+                _, _, latent_height, latent_width = latents.shape
+                conditioning_data = self.get_conditioning_data(
+                    context=context, unet=unet, latent_height=latent_height, latent_width=latent_width
+                )
 
                 controlnet_data = self.prep_control_data(
                     context=context,
@@ -772,16 +971,19 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 ip_adapter_data = self.prep_ip_adapter_data(
                     context=context,
                     ip_adapter=self.ip_adapter,
-                    conditioning_data=conditioning_data,
                     exit_stack=exit_stack,
+                    latent_height=latent_height,
+                    latent_width=latent_width,
+                    dtype=unet.dtype,
                 )
 
-                num_inference_steps, timesteps, init_timestep = self.init_scheduler(
+                num_inference_steps, timesteps, init_timestep, scheduler_step_kwargs = self.init_scheduler(
                     scheduler,
                     device=unet.device,
                     steps=self.steps,
                     denoising_start=self.denoising_start,
                     denoising_end=self.denoising_end,
+                    seed=seed,
                 )
 
                 result_latents = pipeline.latents_from_embeddings(
@@ -794,6 +996,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     masked_latents=masked_latents,
                     gradient_mask=gradient_mask,
                     num_inference_steps=num_inference_steps,
+                    scheduler_step_kwargs=scheduler_step_kwargs,
                     conditioning_data=conditioning_data,
                     control_data=controlnet_data,
                     ip_adapter_data=ip_adapter_data,
@@ -803,12 +1006,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
             # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
             result_latents = result_latents.to("cpu")
-            torch.cuda.empty_cache()
-            if choose_torch_device() == torch.device("mps"):
-                mps.empty_cache()
+            TorchDevice.empty_cache()
 
             name = context.tensors.save(tensor=result_latents)
-        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=seed)
+        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=None)
 
 
 @invocation(
@@ -872,9 +1073,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
                 vae.disable_tiling()
 
             # clear memory as vae decode can request a lot
-            torch.cuda.empty_cache()
-            if choose_torch_device() == torch.device("mps"):
-                mps.empty_cache()
+            TorchDevice.empty_cache()
 
             with torch.inference_mode():
                 # copied from diffusers pipeline
@@ -886,9 +1085,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
 
                 image = VaeImageProcessor.numpy_to_pil(np_image)[0]
 
-        torch.cuda.empty_cache()
-        if choose_torch_device() == torch.device("mps"):
-            mps.empty_cache()
+        TorchDevice.empty_cache()
 
         image_dto = context.images.save(image=image)
 
@@ -927,9 +1124,7 @@ class ResizeLatentsInvocation(BaseInvocation):
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         latents = context.tensors.load(self.latents.latents_name)
-
-        # TODO:
-        device = choose_torch_device()
+        device = TorchDevice.choose_torch_device()
 
         resized_latents = torch.nn.functional.interpolate(
             latents.to(device),
@@ -940,9 +1135,8 @@ class ResizeLatentsInvocation(BaseInvocation):
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         resized_latents = resized_latents.to("cpu")
-        torch.cuda.empty_cache()
-        if device == torch.device("mps"):
-            mps.empty_cache()
+
+        TorchDevice.empty_cache()
 
         name = context.tensors.save(tensor=resized_latents)
         return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
@@ -969,8 +1163,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         latents = context.tensors.load(self.latents.latents_name)
 
-        # TODO:
-        device = choose_torch_device()
+        device = TorchDevice.choose_torch_device()
 
         # resizing
         resized_latents = torch.nn.functional.interpolate(
@@ -982,9 +1175,7 @@ class ScaleLatentsInvocation(BaseInvocation):
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         resized_latents = resized_latents.to("cpu")
-        torch.cuda.empty_cache()
-        if device == torch.device("mps"):
-            mps.empty_cache()
+        TorchDevice.empty_cache()
 
         name = context.tensors.save(tensor=resized_latents)
         return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
@@ -1116,8 +1307,7 @@ class BlendLatentsInvocation(BaseInvocation):
         if latents_a.shape != latents_b.shape:
             raise Exception("Latents to blend must be the same size.")
 
-        # TODO:
-        device = choose_torch_device()
+        device = TorchDevice.choose_torch_device()
 
         def slerp(
             t: Union[float, npt.NDArray[Any]],  # FIXME: maybe use np.float32 here?
@@ -1170,9 +1360,8 @@ class BlendLatentsInvocation(BaseInvocation):
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         blended_latents = blended_latents.to("cpu")
-        torch.cuda.empty_cache()
-        if device == torch.device("mps"):
-            mps.empty_cache()
+
+        TorchDevice.empty_cache()
 
         name = context.tensors.save(tensor=blended_latents)
         return LatentsOutput.build(latents_name=name, latents=blended_latents)
@@ -1263,7 +1452,7 @@ class IdealSizeInvocation(BaseInvocation):
         return tuple((x - x % multiple_of) for x in args)
 
     def invoke(self, context: InvocationContext) -> IdealSizeOutput:
-        unet_config = context.models.get_config(**self.unet.unet.model_dump())
+        unet_config = context.models.get_config(self.unet.unet.key)
         aspect = self.width / self.height
         dimension: float = 512
         if unet_config.base == BaseModelType.StableDiffusion2:

invokeai/app/invocations/mask.py

@@ -0,0 +1,120 @@
+import numpy as np
+import torch
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, InvocationContext, invocation
+from invokeai.app.invocations.fields import ImageField, InputField, TensorField, WithMetadata
+from invokeai.app.invocations.primitives import MaskOutput
+
+
+@invocation(
+    "rectangle_mask",
+    title="Create Rectangle Mask",
+    tags=["conditioning"],
+    category="conditioning",
+    version="1.0.1",
+)
+class RectangleMaskInvocation(BaseInvocation, WithMetadata):
+    """Create a rectangular mask."""
+
+    width: int = InputField(description="The width of the entire mask.")
+    height: int = InputField(description="The height of the entire mask.")
+    x_left: int = InputField(description="The left x-coordinate of the rectangular masked region (inclusive).")
+    y_top: int = InputField(description="The top y-coordinate of the rectangular masked region (inclusive).")
+    rectangle_width: int = InputField(description="The width of the rectangular masked region.")
+    rectangle_height: int = InputField(description="The height of the rectangular masked region.")
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        mask = torch.zeros((1, self.height, self.width), dtype=torch.bool)
+        mask[:, self.y_top : self.y_top + self.rectangle_height, self.x_left : self.x_left + self.rectangle_width] = (
+            True
+        )
+
+        mask_tensor_name = context.tensors.save(mask)
+        return MaskOutput(
+            mask=TensorField(tensor_name=mask_tensor_name),
+            width=self.width,
+            height=self.height,
+        )
+
+
+@invocation(
+    "alpha_mask_to_tensor",
+    title="Alpha Mask to Tensor",
+    tags=["conditioning"],
+    category="conditioning",
+    version="1.0.0",
+    classification=Classification.Beta,
+)
+class AlphaMaskToTensorInvocation(BaseInvocation):
+    """Convert a mask image to a tensor. Opaque regions are 1 and transparent regions are 0."""
+
+    image: ImageField = InputField(description="The mask image to convert.")
+    invert: bool = InputField(default=False, description="Whether to invert the mask.")
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        image = context.images.get_pil(self.image.image_name)
+        mask = torch.zeros((1, image.height, image.width), dtype=torch.bool)
+        if self.invert:
+            mask[0] = torch.tensor(np.array(image)[:, :, 3] == 0, dtype=torch.bool)
+        else:
+            mask[0] = torch.tensor(np.array(image)[:, :, 3] > 0, dtype=torch.bool)
+
+        return MaskOutput(
+            mask=TensorField(tensor_name=context.tensors.save(mask)),
+            height=mask.shape[1],
+            width=mask.shape[2],
+        )
+
+
+@invocation(
+    "invert_tensor_mask",
+    title="Invert Tensor Mask",
+    tags=["conditioning"],
+    category="conditioning",
+    version="1.0.0",
+    classification=Classification.Beta,
+)
+class InvertTensorMaskInvocation(BaseInvocation):
+    """Inverts a tensor mask."""
+
+    mask: TensorField = InputField(description="The tensor mask to convert.")
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        mask = context.tensors.load(self.mask.tensor_name)
+        inverted = ~mask
+
+        return MaskOutput(
+            mask=TensorField(tensor_name=context.tensors.save(inverted)),
+            height=inverted.shape[1],
+            width=inverted.shape[2],
+        )
+
+
+@invocation(
+    "image_mask_to_tensor",
+    title="Image Mask to Tensor",
+    tags=["conditioning"],
+    category="conditioning",
+    version="1.0.0",
+)
+class ImageMaskToTensorInvocation(BaseInvocation, WithMetadata):
+    """Convert a mask image to a tensor. Converts the image to grayscale and uses thresholding at the specified value."""
+
+    image: ImageField = InputField(description="The mask image to convert.")
+    cutoff: int = InputField(ge=0, le=255, description="Cutoff (<)", default=128)
+    invert: bool = InputField(default=False, description="Whether to invert the mask.")
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        image = context.images.get_pil(self.image.image_name, mode="L")
+
+        mask = torch.zeros((1, image.height, image.width), dtype=torch.bool)
+        if self.invert:
+            mask[0] = torch.tensor(np.array(image)[:, :] >= self.cutoff, dtype=torch.bool)
+        else:
+            mask[0] = torch.tensor(np.array(image)[:, :] < self.cutoff, dtype=torch.bool)
+
+        return MaskOutput(
+            mask=TensorField(tensor_name=context.tensors.save(mask)),
+            height=mask.shape[1],
+            width=mask.shape[2],
+        )

invokeai/app/invocations/metadata.py

@@ -2,16 +2,7 @@ from typing import Any, Literal, Optional, Union
 
 from pydantic import BaseModel, ConfigDict, Field
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
-from invokeai.app.invocations.controlnet_image_processors import (
-    CONTROLNET_MODE_VALUES,
-    CONTROLNET_RESIZE_VALUES,
-)
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from invokeai.app.invocations.fields import (
     FieldDescriptions,
     ImageField,
@@ -22,6 +13,7 @@ from invokeai.app.invocations.fields import (
 )
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.controlnet_utils import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES
 
 from ...version import __version__
 
@@ -43,6 +35,8 @@ class IPAdapterMetadataField(BaseModel):
 
     image: ImageField = Field(description="The IP-Adapter image prompt.")
     ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model.")
+    clip_vision_model: Literal["ViT-H", "ViT-G"] = Field(description="The CLIP Vision model")
+    method: Literal["full", "style", "composition"] = Field(description="Method to apply IP Weights with")
     weight: Union[float, list[float]] = Field(description="The weight given to the IP-Adapter")
     begin_step_percent: float = Field(description="When the IP-Adapter is first applied (% of total steps)")
     end_step_percent: float = Field(description="When the IP-Adapter is last applied (% of total steps)")

invokeai/app/invocations/model.py

@@ -11,6 +11,7 @@ from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType,
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
+    Classification,
     invocation,
     invocation_output,
 )
@@ -93,19 +94,46 @@ class ModelLoaderOutput(UNetOutput, CLIPOutput, VAEOutput):
     pass
 
 
+@invocation_output("model_identifier_output")
+class ModelIdentifierOutput(BaseInvocationOutput):
+    """Model identifier output"""
+
+    model: ModelIdentifierField = OutputField(description="Model identifier", title="Model")
+
+
+@invocation(
+    "model_identifier",
+    title="Model identifier",
+    tags=["model"],
+    category="model",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class ModelIdentifierInvocation(BaseInvocation):
+    """Selects any model, outputting it its identifier. Be careful with this one! The identifier will be accepted as
+    input for any model, even if the model types don't match. If you connect this to a mismatched input, you'll get an
+    error."""
+
+    model: ModelIdentifierField = InputField(description="The model to select", title="Model")
+
+    def invoke(self, context: InvocationContext) -> ModelIdentifierOutput:
+        if not context.models.exists(self.model.key):
+            raise Exception(f"Unknown model {self.model.key}")
+
+        return ModelIdentifierOutput(model=self.model)
+
+
 @invocation(
     "main_model_loader",
     title="Main Model",
     tags=["model"],
     category="model",
-    version="1.0.2",
+    version="1.0.3",
 )
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
 
-    model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.main_model, input=Input.Direct, ui_type=UIType.MainModel
-    )
+    model: ModelIdentifierField = InputField(description=FieldDescriptions.main_model, ui_type=UIType.MainModel)
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
@@ -134,12 +162,12 @@ class LoRALoaderOutput(BaseInvocationOutput):
     clip: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
-@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.2")
+@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.3")
 class LoRALoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
     lora: ModelIdentifierField = InputField(
-        description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA", ui_type=UIType.LoRAModel
+        description=FieldDescriptions.lora_model, title="LoRA", ui_type=UIType.LoRAModel
     )
     weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
     unet: Optional[UNetField] = InputField(
@@ -190,6 +218,75 @@ class LoRALoaderInvocation(BaseInvocation):
         return output
 
 
+@invocation_output("lora_selector_output")
+class LoRASelectorOutput(BaseInvocationOutput):
+    """Model loader output"""
+
+    lora: LoRAField = OutputField(description="LoRA model and weight", title="LoRA")
+
+
+@invocation("lora_selector", title="LoRA Selector", tags=["model"], category="model", version="1.0.1")
+class LoRASelectorInvocation(BaseInvocation):
+    """Selects a LoRA model and weight."""
+
+    lora: ModelIdentifierField = InputField(
+        description=FieldDescriptions.lora_model, title="LoRA", ui_type=UIType.LoRAModel
+    )
+    weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
+
+    def invoke(self, context: InvocationContext) -> LoRASelectorOutput:
+        return LoRASelectorOutput(lora=LoRAField(lora=self.lora, weight=self.weight))
+
+
+@invocation("lora_collection_loader", title="LoRA Collection Loader", tags=["model"], category="model", version="1.0.0")
+class LoRACollectionLoader(BaseInvocation):
+    """Applies a collection of LoRAs to the provided UNet and CLIP models."""
+
+    loras: LoRAField | list[LoRAField] = InputField(
+        description="LoRA models and weights. May be a single LoRA or collection.", title="LoRAs"
+    )
+    unet: Optional[UNetField] = InputField(
+        default=None,
+        description=FieldDescriptions.unet,
+        input=Input.Connection,
+        title="UNet",
+    )
+    clip: Optional[CLIPField] = InputField(
+        default=None,
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+        title="CLIP",
+    )
+
+    def invoke(self, context: InvocationContext) -> LoRALoaderOutput:
+        output = LoRALoaderOutput()
+        loras = self.loras if isinstance(self.loras, list) else [self.loras]
+        added_loras: list[str] = []
+
+        for lora in loras:
+            if lora.lora.key in added_loras:
+                continue
+
+            if not context.models.exists(lora.lora.key):
+                raise Exception(f"Unknown lora: {lora.lora.key}!")
+
+            assert lora.lora.base in (BaseModelType.StableDiffusion1, BaseModelType.StableDiffusion2)
+
+            added_loras.append(lora.lora.key)
+
+            if self.unet is not None:
+                if output.unet is None:
+                    output.unet = self.unet.model_copy(deep=True)
+                output.unet.loras.append(lora)
+
+            if self.clip is not None:
+                if output.clip is None:
+                    output.clip = self.clip.model_copy(deep=True)
+                output.clip.loras.append(lora)
+
+        return output
+
+
 @invocation_output("sdxl_lora_loader_output")
 class SDXLLoRALoaderOutput(BaseInvocationOutput):
     """SDXL LoRA Loader Output"""
@@ -204,13 +301,13 @@ class SDXLLoRALoaderOutput(BaseInvocationOutput):
     title="SDXL LoRA",
     tags=["lora", "model"],
     category="model",
-    version="1.0.2",
+    version="1.0.3",
 )
 class SDXLLoRALoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
     lora: ModelIdentifierField = InputField(
-        description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA", ui_type=UIType.LoRAModel
+        description=FieldDescriptions.lora_model, title="LoRA", ui_type=UIType.LoRAModel
     )
     weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
     unet: Optional[UNetField] = InputField(
@@ -279,12 +376,78 @@ class SDXLLoRALoaderInvocation(BaseInvocation):
         return output
 
 
-@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.2")
+@invocation(
+    "sdxl_lora_collection_loader",
+    title="SDXL LoRA Collection Loader",
+    tags=["model"],
+    category="model",
+    version="1.0.0",
+)
+class SDXLLoRACollectionLoader(BaseInvocation):
+    """Applies a collection of SDXL LoRAs to the provided UNet and CLIP models."""
+
+    loras: LoRAField | list[LoRAField] = InputField(
+        description="LoRA models and weights. May be a single LoRA or collection.", title="LoRAs"
+    )
+    unet: Optional[UNetField] = InputField(
+        default=None,
+        description=FieldDescriptions.unet,
+        input=Input.Connection,
+        title="UNet",
+    )
+    clip: Optional[CLIPField] = InputField(
+        default=None,
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+        title="CLIP",
+    )
+    clip2: Optional[CLIPField] = InputField(
+        default=None,
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+        title="CLIP 2",
+    )
+
+    def invoke(self, context: InvocationContext) -> SDXLLoRALoaderOutput:
+        output = SDXLLoRALoaderOutput()
+        loras = self.loras if isinstance(self.loras, list) else [self.loras]
+        added_loras: list[str] = []
+
+        for lora in loras:
+            if lora.lora.key in added_loras:
+                continue
+
+            if not context.models.exists(lora.lora.key):
+                raise Exception(f"Unknown lora: {lora.lora.key}!")
+
+            assert lora.lora.base is BaseModelType.StableDiffusionXL
+
+            added_loras.append(lora.lora.key)
+
+            if self.unet is not None:
+                if output.unet is None:
+                    output.unet = self.unet.model_copy(deep=True)
+                output.unet.loras.append(lora)
+
+            if self.clip is not None:
+                if output.clip is None:
+                    output.clip = self.clip.model_copy(deep=True)
+                output.clip.loras.append(lora)
+
+            if self.clip2 is not None:
+                if output.clip2 is None:
+                    output.clip2 = self.clip2.model_copy(deep=True)
+                output.clip2.loras.append(lora)
+
+        return output
+
+
+@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.3")
 class VAELoaderInvocation(BaseInvocation):
     """Loads a VAE model, outputting a VaeLoaderOutput"""
 
     vae_model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.vae_model, input=Input.Direct, title="VAE", ui_type=UIType.VAEModel
+        description=FieldDescriptions.vae_model, title="VAE", ui_type=UIType.VAEModel
     )
 
     def invoke(self, context: InvocationContext) -> VAEOutput:

invokeai/app/invocations/noise.py

@@ -9,7 +9,7 @@ from invokeai.app.invocations.fields import FieldDescriptions, InputField, Laten
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
-from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.util.devices import TorchDevice
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -46,7 +46,7 @@ def get_noise(
             height // downsampling_factor,
             width // downsampling_factor,
         ],
-        dtype=torch_dtype(device),
+        dtype=TorchDevice.choose_torch_dtype(device=device),
         device=noise_device_type,
         generator=generator,
     ).to("cpu")
@@ -111,14 +111,14 @@ class NoiseInvocation(BaseInvocation):
 
     @field_validator("seed", mode="before")
     def modulo_seed(cls, v):
-        """Returns the seed modulo (SEED_MAX + 1) to ensure it is within the valid range."""
+        """Return the seed modulo (SEED_MAX + 1) to ensure it is within the valid range."""
         return v % (SEED_MAX + 1)
 
     def invoke(self, context: InvocationContext) -> NoiseOutput:
         noise = get_noise(
             width=self.width,
             height=self.height,
-            device=choose_torch_device(),
+            device=TorchDevice.choose_torch_device(),
             seed=self.seed,
             use_cpu=self.use_cpu,
         )

invokeai/app/invocations/primitives.py

@@ -15,6 +15,7 @@ from invokeai.app.invocations.fields import (
     InputField,
     LatentsField,
     OutputField,
+    TensorField,
     UIComponent,
 )
 from invokeai.app.services.images.images_common import ImageDTO
@@ -405,9 +406,19 @@ class ColorInvocation(BaseInvocation):
 
 # endregion
 
+
 # region Conditioning
 
 
+@invocation_output("mask_output")
+class MaskOutput(BaseInvocationOutput):
+    """A torch mask tensor."""
+
+    mask: TensorField = OutputField(description="The mask.")
+    width: int = OutputField(description="The width of the mask in pixels.")
+    height: int = OutputField(description="The height of the mask in pixels.")
+
+
 @invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""

invokeai/app/invocations/sdxl.py

@@ -1,4 +1,4 @@
-from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
+from invokeai.app.invocations.fields import FieldDescriptions, InputField, OutputField, UIType
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.model_manager import SubModelType
 
@@ -30,12 +30,12 @@ class SDXLRefinerModelLoaderOutput(BaseInvocationOutput):
     vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
-@invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.2")
+@invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.3")
 class SDXLModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl base model, outputting its submodels."""
 
     model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.sdxl_main_model, input=Input.Direct, ui_type=UIType.SDXLMainModel
+        description=FieldDescriptions.sdxl_main_model, ui_type=UIType.SDXLMainModel
     )
     # TODO: precision?
 
@@ -67,13 +67,13 @@ class SDXLModelLoaderInvocation(BaseInvocation):
     title="SDXL Refiner Model",
     tags=["model", "sdxl", "refiner"],
     category="model",
-    version="1.0.2",
+    version="1.0.3",
 )
 class SDXLRefinerModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl refiner model, outputting its submodels."""
 
     model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.sdxl_refiner_model, input=Input.Direct, ui_type=UIType.SDXLRefinerModel
+        description=FieldDescriptions.sdxl_refiner_model, ui_type=UIType.SDXLRefinerModel
     )
     # TODO: precision?
 

invokeai/app/invocations/t2i_adapter.py

@@ -8,11 +8,11 @@ from invokeai.app.invocations.baseinvocation import (
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESIZE_VALUES
-from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField, OutputField, UIType
+from invokeai.app.invocations.fields import FieldDescriptions, ImageField, InputField, OutputField, UIType
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.controlnet_utils import CONTROLNET_RESIZE_VALUES
 
 
 class T2IAdapterField(BaseModel):
@@ -45,7 +45,7 @@ class T2IAdapterOutput(BaseInvocationOutput):
 
 
 @invocation(
-    "t2i_adapter", title="T2I-Adapter", tags=["t2i_adapter", "control"], category="t2i_adapter", version="1.0.2"
+    "t2i_adapter", title="T2I-Adapter", tags=["t2i_adapter", "control"], category="t2i_adapter", version="1.0.3"
 )
 class T2IAdapterInvocation(BaseInvocation):
     """Collects T2I-Adapter info to pass to other nodes."""
@@ -55,7 +55,6 @@ class T2IAdapterInvocation(BaseInvocation):
     t2i_adapter_model: ModelIdentifierField = InputField(
         description="The T2I-Adapter model.",
         title="T2I-Adapter Model",
-        input=Input.Direct,
         ui_order=-1,
         ui_type=UIType.T2IAdapterModel,
     )

invokeai/app/invocations/upscale.py

@@ -4,7 +4,6 @@ from typing import Literal
 
 import cv2
 import numpy as np
-import torch
 from PIL import Image
 from pydantic import ConfigDict
 
@@ -14,7 +13,7 @@ from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.download_with_progress import download_with_progress_bar
 from invokeai.backend.image_util.basicsr.rrdbnet_arch import RRDBNet
 from invokeai.backend.image_util.realesrgan.realesrgan import RealESRGAN
-from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.devices import TorchDevice
 
 from .baseinvocation import BaseInvocation, invocation
 from .fields import InputField, WithBoard, WithMetadata
@@ -35,9 +34,6 @@ ESRGAN_MODEL_URLS: dict[str, str] = {
     "RealESRGAN_x2plus.pth": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth",
 }
 
-if choose_torch_device() == torch.device("mps"):
-    from torch import mps
-
 
 @invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.3.2")
 class ESRGANInvocation(BaseInvocation, WithMetadata, WithBoard):
@@ -120,9 +116,7 @@ class ESRGANInvocation(BaseInvocation, WithMetadata, WithBoard):
         upscaled_image = upscaler.upscale(cv2_image)
         pil_image = Image.fromarray(cv2.cvtColor(upscaled_image, cv2.COLOR_BGR2RGB)).convert("RGBA")
 
-        torch.cuda.empty_cache()
-        if choose_torch_device() == torch.device("mps"):
-            mps.empty_cache()
+        TorchDevice.empty_cache()
 
         image_dto = context.images.save(image=pil_image)
 

invokeai/app/services/bulk_download/bulk_download_default.py

@@ -106,9 +106,7 @@ class BulkDownloadService(BulkDownloadBase):
         if self._invoker:
             assert bulk_download_id is not None
             self._invoker.services.events.emit_bulk_download_started(
-                bulk_download_id=bulk_download_id,
-                bulk_download_item_id=bulk_download_item_id,
-                bulk_download_item_name=bulk_download_item_name,
+                bulk_download_id, bulk_download_item_id, bulk_download_item_name
             )
 
     def _signal_job_completed(
@@ -118,10 +116,8 @@ class BulkDownloadService(BulkDownloadBase):
         if self._invoker:
             assert bulk_download_id is not None
             assert bulk_download_item_name is not None
-            self._invoker.services.events.emit_bulk_download_completed(
-                bulk_download_id=bulk_download_id,
-                bulk_download_item_id=bulk_download_item_id,
-                bulk_download_item_name=bulk_download_item_name,
+            self._invoker.services.events.emit_bulk_download_complete(
+                bulk_download_id, bulk_download_item_id, bulk_download_item_name
             )
 
     def _signal_job_failed(
@@ -131,11 +127,8 @@ class BulkDownloadService(BulkDownloadBase):
         if self._invoker:
             assert bulk_download_id is not None
             assert exception is not None
-            self._invoker.services.events.emit_bulk_download_failed(
-                bulk_download_id=bulk_download_id,
-                bulk_download_item_id=bulk_download_item_id,
-                bulk_download_item_name=bulk_download_item_name,
-                error=str(exception),
+            self._invoker.services.events.emit_bulk_download_error(
+                bulk_download_id, bulk_download_item_id, bulk_download_item_name, str(exception)
             )
 
     def stop(self, *args, **kwargs):

invokeai/app/services/config/config_default.py

@@ -3,6 +3,7 @@
 
 from __future__ import annotations
 
+import locale
 import os
 import re
 import shutil
@@ -26,12 +27,12 @@ DEFAULT_RAM_CACHE = 10.0
 DEFAULT_VRAM_CACHE = 0.25
 DEFAULT_CONVERT_CACHE = 20.0
 DEVICE = Literal["auto", "cpu", "cuda", "cuda:1", "mps"]
-PRECISION = Literal["auto", "float16", "bfloat16", "float32", "autocast"]
+PRECISION = Literal["auto", "float16", "bfloat16", "float32"]
 ATTENTION_TYPE = Literal["auto", "normal", "xformers", "sliced", "torch-sdp"]
 ATTENTION_SLICE_SIZE = Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8]
 LOG_FORMAT = Literal["plain", "color", "syslog", "legacy"]
 LOG_LEVEL = Literal["debug", "info", "warning", "error", "critical"]
-CONFIG_SCHEMA_VERSION = "4.0.0"
+CONFIG_SCHEMA_VERSION = "4.0.1"
 
 
 def get_default_ram_cache_size() -> float:
@@ -83,7 +84,6 @@ class InvokeAIAppConfig(BaseSettings):
         ssl_keyfile: SSL key file for HTTPS. See https://www.uvicorn.org/settings/#https.
         log_tokenization: Enable logging of parsed prompt tokens.
         patchmatch: Enable patchmatch inpaint code.
-        autoimport_dir: Path to a directory of models files to be imported on startup.
         models_dir: Path to the models directory.
         convert_cache_dir: Path to the converted models cache directory. When loading a non-diffusers model, it will be converted and store on disk at this location.
         legacy_conf_dir: Path to directory of legacy checkpoint config files.
@@ -105,7 +105,7 @@ class InvokeAIAppConfig(BaseSettings):
         lazy_offload: Keep models in VRAM until their space is needed.
         log_memory_usage: If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.
         device: Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.<br>Valid values: `auto`, `cpu`, `cuda`, `cuda:1`, `mps`
-        precision: Floating point precision. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system.<br>Valid values: `auto`, `float16`, `bfloat16`, `float32`, `autocast`
+        precision: Floating point precision. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system.<br>Valid values: `auto`, `float16`, `bfloat16`, `float32`
         sequential_guidance: Whether to calculate guidance in serial instead of in parallel, lowering memory requirements.
         attention_type: Attention type.<br>Valid values: `auto`, `normal`, `xformers`, `sliced`, `torch-sdp`
         attention_slice_size: Slice size, valid when attention_type=="sliced".<br>Valid values: `auto`, `balanced`, `max`, `1`, `2`, `3`, `4`, `5`, `6`, `7`, `8`
@@ -117,6 +117,7 @@ class InvokeAIAppConfig(BaseSettings):
         node_cache_size: How many cached nodes to keep in memory.
         hashing_algorithm: Model hashing algorthim for model installs. 'blake3_multi' is best for SSDs. 'blake3_single' is best for spinning disk HDDs. 'random' disables hashing, instead assigning a UUID to models. Useful when using a memory db to reduce model installation time, or if you don't care about storing stable hashes for models. Alternatively, any other hashlib algorithm is accepted, though these are not nearly as performant as blake3.<br>Valid values: `blake3_multi`, `blake3_single`, `random`, `md5`, `sha1`, `sha224`, `sha256`, `sha384`, `sha512`, `blake2b`, `blake2s`, `sha3_224`, `sha3_256`, `sha3_384`, `sha3_512`, `shake_128`, `shake_256`
         remote_api_tokens: List of regular expression and token pairs used when downloading models from URLs. The download URL is tested against the regex, and if it matches, the token is provided in as a Bearer token.
+        scan_models_on_startup: Scan the models directory on startup, registering orphaned models. This is typically only used in conjunction with `use_memory_db` for testing purposes.
     """
 
     _root: Optional[Path] = PrivateAttr(default=None)
@@ -144,7 +145,6 @@ class InvokeAIAppConfig(BaseSettings):
     patchmatch:                    bool = Field(default=True,               description="Enable patchmatch inpaint code.")
 
     # PATHS
-    autoimport_dir:                Path = Field(default=Path("autoimport"), description="Path to a directory of models files to be imported on startup.")
     models_dir:                    Path = Field(default=Path("models"),     description="Path to the models directory.")
     convert_cache_dir:             Path = Field(default=Path("models/.cache"), description="Path to the converted models cache directory. When loading a non-diffusers model, it will be converted and store on disk at this location.")
     legacy_conf_dir:               Path = Field(default=Path("configs"), description="Path to directory of legacy checkpoint config files.")
@@ -193,6 +193,7 @@ class InvokeAIAppConfig(BaseSettings):
     # MODEL INSTALL
     hashing_algorithm: HASHING_ALGORITHMS = Field(default="blake3_single",  description="Model hashing algorthim for model installs. 'blake3_multi' is best for SSDs. 'blake3_single' is best for spinning disk HDDs. 'random' disables hashing, instead assigning a UUID to models. Useful when using a memory db to reduce model installation time, or if you don't care about storing stable hashes for models. Alternatively, any other hashlib algorithm is accepted, though these are not nearly as performant as blake3.")
     remote_api_tokens: Optional[list[URLRegexTokenPair]] = Field(default=None, description="List of regular expression and token pairs used when downloading models from URLs. The download URL is tested against the regex, and if it matches, the token is provided in as a Bearer token.")
+    scan_models_on_startup:        bool = Field(default=False,              description="Scan the models directory on startup, registering orphaned models. This is typically only used in conjunction with `use_memory_db` for testing purposes.")
 
     # fmt: on
 
@@ -275,11 +276,6 @@ class InvokeAIAppConfig(BaseSettings):
         assert resolved_path is not None
         return resolved_path
 
-    @property
-    def autoimport_path(self) -> Path:
-        """Path to the autoimports directory, resolved to an absolute path.."""
-        return self._resolve(self.autoimport_dir)
-
     @property
     def outputs_path(self) -> Optional[Path]:
         """Path to the outputs directory, resolved to an absolute path.."""
@@ -322,11 +318,10 @@ class InvokeAIAppConfig(BaseSettings):
     @staticmethod
     def find_root() -> Path:
         """Choose the runtime root directory when not specified on command line or init file."""
-        venv = Path(os.environ.get("VIRTUAL_ENV") or ".")
         if os.environ.get("INVOKEAI_ROOT"):
             root = Path(os.environ["INVOKEAI_ROOT"])
-        elif any((venv.parent / x).exists() for x in [INIT_FILE, LEGACY_INIT_FILE]):
-            root = (venv.parent).resolve()
+        elif venv := os.environ.get("VIRTUAL_ENV", None):
+            root = Path(venv).parent.resolve()
         else:
             root = Path("~/invokeai").expanduser().resolve()
         return root
@@ -375,16 +370,22 @@ def migrate_v3_config_dict(config_dict: dict[str, Any]) -> InvokeAIAppConfig:
             # `max_vram_cache_size` was renamed to `vram` some time in v3, but both names were used
             if k == "max_vram_cache_size" and "vram" not in category_dict:
                 parsed_config_dict["vram"] = v
+            # autocast was removed in v4.0.1
+            if k == "precision" and v == "autocast":
+                parsed_config_dict["precision"] = "auto"
             if k == "conf_path":
                 parsed_config_dict["legacy_models_yaml_path"] = v
             if k == "legacy_conf_dir":
-                # The old default for this was "configs/stable-diffusion". If if the incoming config has that as the value, we won't set it.
-                # Else if the path ends in "stable-diffusion", we assume the parent is the new correct path.
-                # Else we do not attempt to migrate this setting
-                if v != "configs/stable-diffusion":
-                    parsed_config_dict["legacy_conf_dir"] = v
+                # The old default for this was "configs/stable-diffusion" ("configs\stable-diffusion" on Windows).
+                if v == "configs/stable-diffusion" or v == "configs\\stable-diffusion":
+                    # If if the incoming config has the default value, skip
+                    continue
                 elif Path(v).name == "stable-diffusion":
+                    # Else if the path ends in "stable-diffusion", we assume the parent is the new correct path.
                     parsed_config_dict["legacy_conf_dir"] = str(Path(v).parent)
+                else:
+                    # Else we do not attempt to migrate this setting
+                    parsed_config_dict["legacy_conf_dir"] = v
             elif k in InvokeAIAppConfig.model_fields:
                 # skip unknown fields
                 parsed_config_dict[k] = v
@@ -394,6 +395,28 @@ def migrate_v3_config_dict(config_dict: dict[str, Any]) -> InvokeAIAppConfig:
     return config
 
 
+def migrate_v4_0_0_config_dict(config_dict: dict[str, Any]) -> InvokeAIAppConfig:
+    """Migrate v4.0.0 config dictionary to a current config object.
+
+    Args:
+        config_dict: A dictionary of settings from a v4.0.0 config file.
+
+    Returns:
+        An instance of `InvokeAIAppConfig` with the migrated settings.
+    """
+    parsed_config_dict: dict[str, Any] = {}
+    for k, v in config_dict.items():
+        # autocast was removed from precision in v4.0.1
+        if k == "precision" and v == "autocast":
+            parsed_config_dict["precision"] = "auto"
+        else:
+            parsed_config_dict[k] = v
+        if k == "schema_version":
+            parsed_config_dict[k] = CONFIG_SCHEMA_VERSION
+    config = DefaultInvokeAIAppConfig.model_validate(parsed_config_dict)
+    return config
+
+
 def load_and_migrate_config(config_path: Path) -> InvokeAIAppConfig:
     """Load and migrate a config file to the latest version.
 
@@ -404,7 +427,7 @@ def load_and_migrate_config(config_path: Path) -> InvokeAIAppConfig:
         An instance of `InvokeAIAppConfig` with the loaded and migrated settings.
     """
     assert config_path.suffix == ".yaml"
-    with open(config_path) as file:
+    with open(config_path, "rt", encoding=locale.getpreferredencoding()) as file:
         loaded_config_dict = yaml.safe_load(file)
 
     assert isinstance(loaded_config_dict, dict)
@@ -420,17 +443,21 @@ def load_and_migrate_config(config_path: Path) -> InvokeAIAppConfig:
             raise RuntimeError(f"Failed to load and migrate v3 config file {config_path}: {e}") from e
         migrated_config.write_file(config_path)
         return migrated_config
-    else:
-        # Attempt to load as a v4 config file
-        try:
-            # Meta is not included in the model fields, so we need to validate it separately
-            config = InvokeAIAppConfig.model_validate(loaded_config_dict)
-            assert (
-                config.schema_version == CONFIG_SCHEMA_VERSION
-            ), f"Invalid schema version, expected {CONFIG_SCHEMA_VERSION}: {config.schema_version}"
-            return config
-        except Exception as e:
-            raise RuntimeError(f"Failed to load config file {config_path}: {e}") from e
+
+    if loaded_config_dict["schema_version"] == "4.0.0":
+        loaded_config_dict = migrate_v4_0_0_config_dict(loaded_config_dict)
+        loaded_config_dict.write_file(config_path)
+
+    # Attempt to load as a v4 config file
+    try:
+        # Meta is not included in the model fields, so we need to validate it separately
+        config = InvokeAIAppConfig.model_validate(loaded_config_dict)
+        assert (
+            config.schema_version == CONFIG_SCHEMA_VERSION
+        ), f"Invalid schema version, expected {CONFIG_SCHEMA_VERSION}: {config.schema_version}"
+        return config
+    except Exception as e:
+        raise RuntimeError(f"Failed to load config file {config_path}: {e}") from e
 
 
 @lru_cache(maxsize=1)

invokeai/app/services/download/download_default.py

@@ -8,14 +8,13 @@ import time
 import traceback
 from pathlib import Path
 from queue import Empty, PriorityQueue
-from typing import Any, Dict, List, Optional, Set
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Set
 
 import requests
 from pydantic.networks import AnyHttpUrl
 from requests import HTTPError
 from tqdm import tqdm
 
-from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.util.misc import get_iso_timestamp
 from invokeai.backend.util.logging import InvokeAILogger
 
@@ -30,6 +29,9 @@ from .download_base import (
     UnknownJobIDException,
 )
 
+if TYPE_CHECKING:
+    from invokeai.app.services.events.events_base import EventServiceBase
+
 # Maximum number of bytes to download during each call to requests.iter_content()
 DOWNLOAD_CHUNK_SIZE = 100000
 
@@ -40,7 +42,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
     def __init__(
         self,
         max_parallel_dl: int = 5,
-        event_bus: Optional[EventServiceBase] = None,
+        event_bus: Optional["EventServiceBase"] = None,
         requests_session: Optional[requests.sessions.Session] = None,
     ):
         """
@@ -318,10 +320,8 @@ class DownloadQueueService(DownloadQueueServiceBase):
         in_progress_path.rename(job.download_path)
 
     def _validate_filename(self, directory: str, filename: str) -> bool:
-        pc_name_max = os.pathconf(directory, "PC_NAME_MAX") if hasattr(os, "pathconf") else 260  # hardcoded for windows
-        pc_path_max = (
-            os.pathconf(directory, "PC_PATH_MAX") if hasattr(os, "pathconf") else 32767
-        )  # hardcoded for windows with long names enabled
+        pc_name_max = get_pc_name_max(directory)
+        pc_path_max = get_pc_path_max(directory)
         if "/" in filename:
             return False
         if filename.startswith(".."):
@@ -345,8 +345,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
                     f"An error occurred while processing the on_start callback: {traceback.format_exception(e)}"
                 )
         if self._event_bus:
-            assert job.download_path
-            self._event_bus.emit_download_started(str(job.source), job.download_path.as_posix())
+            self._event_bus.emit_download_started(job)
 
     def _signal_job_progress(self, job: DownloadJob) -> None:
         if job.on_progress:
@@ -357,13 +356,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
                     f"An error occurred while processing the on_progress callback: {traceback.format_exception(e)}"
                 )
         if self._event_bus:
-            assert job.download_path
-            self._event_bus.emit_download_progress(
-                str(job.source),
-                download_path=job.download_path.as_posix(),
-                current_bytes=job.bytes,
-                total_bytes=job.total_bytes,
-            )
+            self._event_bus.emit_download_progress(job)
 
     def _signal_job_complete(self, job: DownloadJob) -> None:
         job.status = DownloadJobStatus.COMPLETED
@@ -375,10 +368,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
                     f"An error occurred while processing the on_complete callback: {traceback.format_exception(e)}"
                 )
         if self._event_bus:
-            assert job.download_path
-            self._event_bus.emit_download_complete(
-                str(job.source), download_path=job.download_path.as_posix(), total_bytes=job.total_bytes
-            )
+            self._event_bus.emit_download_complete(job)
 
     def _signal_job_cancelled(self, job: DownloadJob) -> None:
         if job.status not in [DownloadJobStatus.RUNNING, DownloadJobStatus.WAITING]:
@@ -392,7 +382,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
                     f"An error occurred while processing the on_cancelled callback: {traceback.format_exception(e)}"
                 )
         if self._event_bus:
-            self._event_bus.emit_download_cancelled(str(job.source))
+            self._event_bus.emit_download_cancelled(job)
 
     def _signal_job_error(self, job: DownloadJob, excp: Optional[Exception] = None) -> None:
         job.status = DownloadJobStatus.ERROR
@@ -405,9 +395,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
                     f"An error occurred while processing the on_error callback: {traceback.format_exception(e)}"
                 )
         if self._event_bus:
-            assert job.error_type
-            assert job.error
-            self._event_bus.emit_download_error(str(job.source), error_type=job.error_type, error=job.error)
+            self._event_bus.emit_download_error(job)
 
     def _cleanup_cancelled_job(self, job: DownloadJob) -> None:
         self._logger.debug(f"Cleaning up leftover files from cancelled download job {job.download_path}")
@@ -419,6 +407,26 @@ class DownloadQueueService(DownloadQueueServiceBase):
             self._logger.warning(excp)
 
 
+def get_pc_name_max(directory: str) -> int:
+    if hasattr(os, "pathconf"):
+        try:
+            return os.pathconf(directory, "PC_NAME_MAX")
+        except OSError:
+            # macOS w/ external drives raise OSError
+            pass
+    return 260  # hardcoded for windows
+
+
+def get_pc_path_max(directory: str) -> int:
+    if hasattr(os, "pathconf"):
+        try:
+            return os.pathconf(directory, "PC_PATH_MAX")
+        except OSError:
+            # some platforms may not have this value
+            pass
+    return 32767  # hardcoded for windows with long names enabled
+
+
 # Example on_progress event handler to display a TQDM status bar
 # Activate with:
 #   download_service.download(DownloadJob('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().update))

invokeai/app/services/events/events_base.py

@@ -1,486 +1,195 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 
-from typing import Any, Dict, List, Optional, Union
+from typing import TYPE_CHECKING, Optional
 
-from invokeai.app.services.session_processor.session_processor_common import ProgressImage
-from invokeai.app.services.session_queue.session_queue_common import (
-    BatchStatus,
-    EnqueueBatchResult,
-    SessionQueueItem,
-    SessionQueueStatus,
+from invokeai.app.services.events.events_common import (
+    BatchEnqueuedEvent,
+    BulkDownloadCompleteEvent,
+    BulkDownloadErrorEvent,
+    BulkDownloadStartedEvent,
+    DownloadCancelledEvent,
+    DownloadCompleteEvent,
+    DownloadErrorEvent,
+    DownloadProgressEvent,
+    DownloadStartedEvent,
+    EventBase,
+    InvocationCompleteEvent,
+    InvocationDenoiseProgressEvent,
+    InvocationErrorEvent,
+    InvocationStartedEvent,
+    ModelInstallCancelledEvent,
+    ModelInstallCompleteEvent,
+    ModelInstallDownloadProgressEvent,
+    ModelInstallDownloadsCompleteEvent,
+    ModelInstallErrorEvent,
+    ModelInstallStartedEvent,
+    ModelLoadCompleteEvent,
+    ModelLoadStartedEvent,
+    QueueClearedEvent,
+    QueueItemStatusChangedEvent,
 )
-from invokeai.app.util.misc import get_timestamp
-from invokeai.backend.model_manager import AnyModelConfig
-from invokeai.backend.model_manager.config import SubModelType
+from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineIntermediateState
+
+if TYPE_CHECKING:
+    from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput
+    from invokeai.app.services.download.download_base import DownloadJob
+    from invokeai.app.services.events.events_common import EventBase
+    from invokeai.app.services.model_install.model_install_common import ModelInstallJob
+    from invokeai.app.services.session_processor.session_processor_common import ProgressImage
+    from invokeai.app.services.session_queue.session_queue_common import (
+        BatchStatus,
+        EnqueueBatchResult,
+        SessionQueueItem,
+        SessionQueueStatus,
+    )
+    from invokeai.backend.model_manager.config import AnyModelConfig, SubModelType
 
 
 class EventServiceBase:
-    queue_event: str = "queue_event"
-    bulk_download_event: str = "bulk_download_event"
-    download_event: str = "download_event"
-    model_event: str = "model_event"
-
     """Basic event bus, to have an empty stand-in when not needed"""
 
-    def dispatch(self, event_name: str, payload: Any) -> None:
+    def dispatch(self, event: "EventBase") -> None:
         pass
 
-    def _emit_bulk_download_event(self, event_name: str, payload: dict) -> None:
-        """Bulk download events are emitted to a room with queue_id as the room name"""
-        payload["timestamp"] = get_timestamp()
-        self.dispatch(
-            event_name=EventServiceBase.bulk_download_event,
-            payload={"event": event_name, "data": payload},
-        )
+    # region: Invocation
 
-    def __emit_queue_event(self, event_name: str, payload: dict) -> None:
-        """Queue events are emitted to a room with queue_id as the room name"""
-        payload["timestamp"] = get_timestamp()
-        self.dispatch(
-            event_name=EventServiceBase.queue_event,
-            payload={"event": event_name, "data": payload},
-        )
+    def emit_invocation_started(self, queue_item: "SessionQueueItem", invocation: "BaseInvocation") -> None:
+        """Emitted when an invocation is started"""
+        self.dispatch(InvocationStartedEvent.build(queue_item, invocation))
 
-    def __emit_download_event(self, event_name: str, payload: dict) -> None:
-        payload["timestamp"] = get_timestamp()
-        self.dispatch(
-            event_name=EventServiceBase.download_event,
-            payload={"event": event_name, "data": payload},
-        )
-
-    def __emit_model_event(self, event_name: str, payload: dict) -> None:
-        payload["timestamp"] = get_timestamp()
-        self.dispatch(
-            event_name=EventServiceBase.model_event,
-            payload={"event": event_name, "data": payload},
-        )
-
-    # Define events here for every event in the system.
-    # This will make them easier to integrate until we find a schema generator.
-    def emit_generator_progress(
+    def emit_invocation_denoise_progress(
         self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        node_id: str,
-        source_node_id: str,
-        progress_image: Optional[ProgressImage],
-        step: int,
-        order: int,
-        total_steps: int,
+        queue_item: "SessionQueueItem",
+        invocation: "BaseInvocation",
+        intermediate_state: PipelineIntermediateState,
+        progress_image: "ProgressImage",
     ) -> None:
-        """Emitted when there is generation progress"""
-        self.__emit_queue_event(
-            event_name="generator_progress",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-                "node_id": node_id,
-                "source_node_id": source_node_id,
-                "progress_image": progress_image.model_dump(mode="json") if progress_image is not None else None,
-                "step": step,
-                "order": order,
-                "total_steps": total_steps,
-            },
-        )
+        """Emitted at each step during denoising of an invocation."""
+        self.dispatch(InvocationDenoiseProgressEvent.build(queue_item, invocation, intermediate_state, progress_image))
 
     def emit_invocation_complete(
-        self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        result: dict,
-        node: dict,
-        source_node_id: str,
+        self, queue_item: "SessionQueueItem", invocation: "BaseInvocation", output: "BaseInvocationOutput"
     ) -> None:
-        """Emitted when an invocation has completed"""
-        self.__emit_queue_event(
-            event_name="invocation_complete",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-                "node": node,
-                "source_node_id": source_node_id,
-                "result": result,
-            },
-        )
+        """Emitted when an invocation is complete"""
+        self.dispatch(InvocationCompleteEvent.build(queue_item, invocation, output))
 
     def emit_invocation_error(
         self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        node: dict,
-        source_node_id: str,
+        queue_item: "SessionQueueItem",
+        invocation: "BaseInvocation",
         error_type: str,
-        error: str,
+        error_message: str,
+        error_traceback: str,
     ) -> None:
-        """Emitted when an invocation has completed"""
-        self.__emit_queue_event(
-            event_name="invocation_error",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-                "node": node,
-                "source_node_id": source_node_id,
-                "error_type": error_type,
-                "error": error,
-            },
-        )
+        """Emitted when an invocation encounters an error"""
+        self.dispatch(InvocationErrorEvent.build(queue_item, invocation, error_type, error_message, error_traceback))
 
-    def emit_invocation_started(
-        self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        node: dict,
-        source_node_id: str,
-    ) -> None:
-        """Emitted when an invocation has started"""
-        self.__emit_queue_event(
-            event_name="invocation_started",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-                "node": node,
-                "source_node_id": source_node_id,
-            },
-        )
+    # endregion
 
-    def emit_graph_execution_complete(
-        self, queue_id: str, queue_item_id: int, queue_batch_id: str, graph_execution_state_id: str
-    ) -> None:
-        """Emitted when a session has completed all invocations"""
-        self.__emit_queue_event(
-            event_name="graph_execution_state_complete",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-            },
-        )
-
-    def emit_model_load_started(
-        self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-    ) -> None:
-        """Emitted when a model is requested"""
-        self.__emit_queue_event(
-            event_name="model_load_started",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-                "model_config": model_config.model_dump(mode="json"),
-                "submodel_type": submodel_type,
-            },
-        )
-
-    def emit_model_load_completed(
-        self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-    ) -> None:
-        """Emitted when a model is correctly loaded (returns model info)"""
-        self.__emit_queue_event(
-            event_name="model_load_completed",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-                "model_config": model_config.model_dump(mode="json"),
-                "submodel_type": submodel_type,
-            },
-        )
-
-    def emit_session_canceled(
-        self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-    ) -> None:
-        """Emitted when a session is canceled"""
-        self.__emit_queue_event(
-            event_name="session_canceled",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-            },
-        )
+    # region Queue
 
     def emit_queue_item_status_changed(
-        self,
-        session_queue_item: SessionQueueItem,
-        batch_status: BatchStatus,
-        queue_status: SessionQueueStatus,
+        self, queue_item: "SessionQueueItem", batch_status: "BatchStatus", queue_status: "SessionQueueStatus"
     ) -> None:
         """Emitted when a queue item's status changes"""
-        self.__emit_queue_event(
-            event_name="queue_item_status_changed",
-            payload={
-                "queue_id": queue_status.queue_id,
-                "queue_item": {
-                    "queue_id": session_queue_item.queue_id,
-                    "item_id": session_queue_item.item_id,
-                    "status": session_queue_item.status,
-                    "batch_id": session_queue_item.batch_id,
-                    "session_id": session_queue_item.session_id,
-                    "error": session_queue_item.error,
-                    "created_at": str(session_queue_item.created_at) if session_queue_item.created_at else None,
-                    "updated_at": str(session_queue_item.updated_at) if session_queue_item.updated_at else None,
-                    "started_at": str(session_queue_item.started_at) if session_queue_item.started_at else None,
-                    "completed_at": str(session_queue_item.completed_at) if session_queue_item.completed_at else None,
-                },
-                "batch_status": batch_status.model_dump(mode="json"),
-                "queue_status": queue_status.model_dump(mode="json"),
-            },
-        )
+        self.dispatch(QueueItemStatusChangedEvent.build(queue_item, batch_status, queue_status))
 
-    def emit_batch_enqueued(self, enqueue_result: EnqueueBatchResult) -> None:
+    def emit_batch_enqueued(self, enqueue_result: "EnqueueBatchResult") -> None:
         """Emitted when a batch is enqueued"""
-        self.__emit_queue_event(
-            event_name="batch_enqueued",
-            payload={
-                "queue_id": enqueue_result.queue_id,
-                "batch_id": enqueue_result.batch.batch_id,
-                "enqueued": enqueue_result.enqueued,
-            },
-        )
+        self.dispatch(BatchEnqueuedEvent.build(enqueue_result))
 
     def emit_queue_cleared(self, queue_id: str) -> None:
-        """Emitted when the queue is cleared"""
-        self.__emit_queue_event(
-            event_name="queue_cleared",
-            payload={"queue_id": queue_id},
-        )
+        """Emitted when a queue is cleared"""
+        self.dispatch(QueueClearedEvent.build(queue_id))
 
-    def emit_download_started(self, source: str, download_path: str) -> None:
-        """
-        Emit when a download job is started.
+    # endregion
 
-        :param url: The downloaded url
-        """
-        self.__emit_download_event(
-            event_name="download_started",
-            payload={"source": source, "download_path": download_path},
-        )
+    # region Download
 
-    def emit_download_progress(self, source: str, download_path: str, current_bytes: int, total_bytes: int) -> None:
-        """
-        Emit "download_progress" events at regular intervals during a download job.
+    def emit_download_started(self, job: "DownloadJob") -> None:
+        """Emitted when a download is started"""
+        self.dispatch(DownloadStartedEvent.build(job))
 
-        :param source: The downloaded source
-        :param download_path: The local downloaded file
-        :param current_bytes: Number of bytes downloaded so far
-        :param total_bytes: The size of the file being downloaded (if known)
-        """
-        self.__emit_download_event(
-            event_name="download_progress",
-            payload={
-                "source": source,
-                "download_path": download_path,
-                "current_bytes": current_bytes,
-                "total_bytes": total_bytes,
-            },
-        )
+    def emit_download_progress(self, job: "DownloadJob") -> None:
+        """Emitted at intervals during a download"""
+        self.dispatch(DownloadProgressEvent.build(job))
 
-    def emit_download_complete(self, source: str, download_path: str, total_bytes: int) -> None:
-        """
-        Emit a "download_complete" event at the end of a successful download.
+    def emit_download_complete(self, job: "DownloadJob") -> None:
+        """Emitted when a download is completed"""
+        self.dispatch(DownloadCompleteEvent.build(job))
 
-        :param source: Source URL
-        :param download_path: Path to the locally downloaded file
-        :param total_bytes: The size of the downloaded file
-        """
-        self.__emit_download_event(
-            event_name="download_complete",
-            payload={
-                "source": source,
-                "download_path": download_path,
-                "total_bytes": total_bytes,
-            },
-        )
+    def emit_download_cancelled(self, job: "DownloadJob") -> None:
+        """Emitted when a download is cancelled"""
+        self.dispatch(DownloadCancelledEvent.build(job))
 
-    def emit_download_cancelled(self, source: str) -> None:
-        """Emit a "download_cancelled" event in the event that the download was cancelled by user."""
-        self.__emit_download_event(
-            event_name="download_cancelled",
-            payload={
-                "source": source,
-            },
-        )
+    def emit_download_error(self, job: "DownloadJob") -> None:
+        """Emitted when a download encounters an error"""
+        self.dispatch(DownloadErrorEvent.build(job))
 
-    def emit_download_error(self, source: str, error_type: str, error: str) -> None:
-        """
-        Emit a "download_error" event when an download job encounters an exception.
+    # endregion
 
-        :param source: Source URL
-        :param error_type: The name of the exception that raised the error
-        :param error: The traceback from this error
-        """
-        self.__emit_download_event(
-            event_name="download_error",
-            payload={
-                "source": source,
-                "error_type": error_type,
-                "error": error,
-            },
-        )
+    # region Model loading
 
-    def emit_model_install_downloading(
-        self,
-        source: str,
-        local_path: str,
-        bytes: int,
-        total_bytes: int,
-        parts: List[Dict[str, Union[str, int]]],
-        id: int,
+    def emit_model_load_started(self, config: "AnyModelConfig", submodel_type: Optional["SubModelType"] = None) -> None:
+        """Emitted when a model load is started."""
+        self.dispatch(ModelLoadStartedEvent.build(config, submodel_type))
+
+    def emit_model_load_complete(
+        self, config: "AnyModelConfig", submodel_type: Optional["SubModelType"] = None
     ) -> None:
-        """
-        Emit at intervals while the install job is in progress (remote models only).
+        """Emitted when a model load is complete."""
+        self.dispatch(ModelLoadCompleteEvent.build(config, submodel_type))
 
-        :param source: Source of the model
-        :param local_path: Where model is downloading to
-        :param parts: Progress of downloading URLs that comprise the model, if any.
-        :param bytes: Number of bytes downloaded so far.
-        :param total_bytes: Total size of download, including all files.
-        This emits a Dict with keys "source", "local_path", "bytes" and "total_bytes".
-        """
-        self.__emit_model_event(
-            event_name="model_install_downloading",
-            payload={
-                "source": source,
-                "local_path": local_path,
-                "bytes": bytes,
-                "total_bytes": total_bytes,
-                "parts": parts,
-                "id": id,
-            },
-        )
+    # endregion
 
-    def emit_model_install_downloads_done(self, source: str) -> None:
-        """
-        Emit once when all parts are downloaded, but before the probing and registration start.
+    # region Model install
 
-        :param source: Source of the model; local path, repo_id or url
-        """
-        self.__emit_model_event(
-            event_name="model_install_downloads_done",
-            payload={"source": source},
-        )
+    def emit_model_install_download_progress(self, job: "ModelInstallJob") -> None:
+        """Emitted at intervals while the install job is in progress (remote models only)."""
+        self.dispatch(ModelInstallDownloadProgressEvent.build(job))
 
-    def emit_model_install_running(self, source: str) -> None:
-        """
-        Emit once when an install job becomes active.
+    def emit_model_install_downloads_complete(self, job: "ModelInstallJob") -> None:
+        self.dispatch(ModelInstallDownloadsCompleteEvent.build(job))
 
-        :param source: Source of the model; local path, repo_id or url
-        """
-        self.__emit_model_event(
-            event_name="model_install_running",
-            payload={"source": source},
-        )
+    def emit_model_install_started(self, job: "ModelInstallJob") -> None:
+        """Emitted once when an install job is started (after any download)."""
+        self.dispatch(ModelInstallStartedEvent.build(job))
 
-    def emit_model_install_completed(self, source: str, key: str, id: int, total_bytes: Optional[int] = None) -> None:
-        """
-        Emit when an install job is completed successfully.
+    def emit_model_install_complete(self, job: "ModelInstallJob") -> None:
+        """Emitted when an install job is completed successfully."""
+        self.dispatch(ModelInstallCompleteEvent.build(job))
 
-        :param source: Source of the model; local path, repo_id or url
-        :param key: Model config record key
-        :param total_bytes: Size of the model (may be None for installation of a local path)
-        """
-        self.__emit_model_event(
-            event_name="model_install_completed",
-            payload={"source": source, "total_bytes": total_bytes, "key": key, "id": id},
-        )
+    def emit_model_install_cancelled(self, job: "ModelInstallJob") -> None:
+        """Emitted when an install job is cancelled."""
+        self.dispatch(ModelInstallCancelledEvent.build(job))
 
-    def emit_model_install_cancelled(self, source: str, id: int) -> None:
-        """
-        Emit when an install job is cancelled.
+    def emit_model_install_error(self, job: "ModelInstallJob") -> None:
+        """Emitted when an install job encounters an exception."""
+        self.dispatch(ModelInstallErrorEvent.build(job))
 
-        :param source: Source of the model; local path, repo_id or url
-        """
-        self.__emit_model_event(
-            event_name="model_install_cancelled",
-            payload={"source": source, "id": id},
-        )
+    # endregion
 
-    def emit_model_install_error(self, source: str, error_type: str, error: str, id: int) -> None:
-        """
-        Emit when an install job encounters an exception.
-
-        :param source: Source of the model
-        :param error_type: The name of the exception
-        :param error: A text description of the exception
-        """
-        self.__emit_model_event(
-            event_name="model_install_error",
-            payload={"source": source, "error_type": error_type, "error": error, "id": id},
-        )
+    # region Bulk image download
 
     def emit_bulk_download_started(
         self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
     ) -> None:
-        """Emitted when a bulk download starts"""
-        self._emit_bulk_download_event(
-            event_name="bulk_download_started",
-            payload={
-                "bulk_download_id": bulk_download_id,
-                "bulk_download_item_id": bulk_download_item_id,
-                "bulk_download_item_name": bulk_download_item_name,
-            },
-        )
+        """Emitted when a bulk image download is started"""
+        self.dispatch(BulkDownloadStartedEvent.build(bulk_download_id, bulk_download_item_id, bulk_download_item_name))
 
-    def emit_bulk_download_completed(
+    def emit_bulk_download_complete(
         self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
     ) -> None:
-        """Emitted when a bulk download completes"""
-        self._emit_bulk_download_event(
-            event_name="bulk_download_completed",
-            payload={
-                "bulk_download_id": bulk_download_id,
-                "bulk_download_item_id": bulk_download_item_id,
-                "bulk_download_item_name": bulk_download_item_name,
-            },
-        )
+        """Emitted when a bulk image download is complete"""
+        self.dispatch(BulkDownloadCompleteEvent.build(bulk_download_id, bulk_download_item_id, bulk_download_item_name))
 
-    def emit_bulk_download_failed(
+    def emit_bulk_download_error(
         self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str, error: str
     ) -> None:
-        """Emitted when a bulk download fails"""
-        self._emit_bulk_download_event(
-            event_name="bulk_download_failed",
-            payload={
-                "bulk_download_id": bulk_download_id,
-                "bulk_download_item_id": bulk_download_item_id,
-                "bulk_download_item_name": bulk_download_item_name,
-                "error": error,
-            },
+        """Emitted when a bulk image download has an error"""
+        self.dispatch(
+            BulkDownloadErrorEvent.build(bulk_download_id, bulk_download_item_id, bulk_download_item_name, error)
         )
+
+    # endregion

invokeai/app/services/events/events_common.py

@@ -0,0 +1,608 @@
+from math import floor
+from typing import TYPE_CHECKING, Any, ClassVar, Coroutine, Generic, Optional, Protocol, TypeAlias, TypeVar
+
+from fastapi_events.handlers.local import local_handler
+from fastapi_events.registry.payload_schema import registry as payload_schema
+from pydantic import BaseModel, ConfigDict, Field, SerializeAsAny, field_validator
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput
+from invokeai.app.services.session_processor.session_processor_common import ProgressImage
+from invokeai.app.services.session_queue.session_queue_common import (
+    QUEUE_ITEM_STATUS,
+    BatchStatus,
+    EnqueueBatchResult,
+    SessionQueueItem,
+    SessionQueueStatus,
+)
+from invokeai.app.util.misc import get_timestamp
+from invokeai.backend.model_manager.config import AnyModelConfig, SubModelType
+from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineIntermediateState
+
+if TYPE_CHECKING:
+    from invokeai.app.services.download.download_base import DownloadJob
+    from invokeai.app.services.model_install.model_install_common import ModelInstallJob
+
+
+class EventBase(BaseModel):
+    """Base class for all events. All events must inherit from this class.
+
+    Events must define a class attribute `__event_name__` to identify the event.
+
+    All other attributes should be defined as normal for a pydantic model.
+
+    A timestamp is automatically added to the event when it is created.
+    """
+
+    __event_name__: ClassVar[str]
+    timestamp: int = Field(description="The timestamp of the event", default_factory=get_timestamp)
+
+    model_config = ConfigDict(json_schema_serialization_defaults_required=True)
+
+    @classmethod
+    def get_events(cls) -> set[type["EventBase"]]:
+        """Get a set of all event models."""
+
+        event_subclasses: set[type["EventBase"]] = set()
+        for subclass in cls.__subclasses__():
+            # We only want to include subclasses that are event models, not intermediary classes
+            if hasattr(subclass, "__event_name__"):
+                event_subclasses.add(subclass)
+            event_subclasses.update(subclass.get_events())
+
+        return event_subclasses
+
+
+TEvent = TypeVar("TEvent", bound=EventBase, contravariant=True)
+
+FastAPIEvent: TypeAlias = tuple[str, TEvent]
+"""
+A tuple representing a `fastapi-events` event, with the event name and payload.
+Provide a generic type to `TEvent` to specify the payload type.
+"""
+
+
+class FastAPIEventFunc(Protocol, Generic[TEvent]):
+    def __call__(self, event: FastAPIEvent[TEvent]) -> Optional[Coroutine[Any, Any, None]]: ...
+
+
+def register_events(events: set[type[TEvent]] | type[TEvent], func: FastAPIEventFunc[TEvent]) -> None:
+    """Register a function to handle specific events.
+
+    :param events: An event or set of events to handle
+    :param func: The function to handle the events
+    """
+    events = events if isinstance(events, set) else {events}
+    for event in events:
+        assert hasattr(event, "__event_name__")
+        local_handler.register(event_name=event.__event_name__, _func=func)  # pyright: ignore [reportUnknownMemberType, reportUnknownArgumentType, reportAttributeAccessIssue]
+
+
+class QueueEventBase(EventBase):
+    """Base class for queue events"""
+
+    queue_id: str = Field(description="The ID of the queue")
+
+
+class QueueItemEventBase(QueueEventBase):
+    """Base class for queue item events"""
+
+    item_id: int = Field(description="The ID of the queue item")
+    batch_id: str = Field(description="The ID of the queue batch")
+
+
+class InvocationEventBase(QueueItemEventBase):
+    """Base class for invocation events"""
+
+    session_id: str = Field(description="The ID of the session (aka graph execution state)")
+    queue_id: str = Field(description="The ID of the queue")
+    item_id: int = Field(description="The ID of the queue item")
+    batch_id: str = Field(description="The ID of the queue batch")
+    session_id: str = Field(description="The ID of the session (aka graph execution state)")
+    invocation: SerializeAsAny[BaseInvocation] = Field(description="The ID of the invocation")
+    invocation_source_id: str = Field(description="The ID of the prepared invocation's source node")
+
+    @field_validator("invocation", mode="plain")
+    @classmethod
+    def validate_invocation(cls, v: Any):
+        """Validates the invocation using the dynamic type adapter."""
+
+        invocation = BaseInvocation.get_typeadapter().validate_python(v)
+        return invocation
+
+
+@payload_schema.register
+class InvocationStartedEvent(InvocationEventBase):
+    """Event model for invocation_started"""
+
+    __event_name__ = "invocation_started"
+
+    @classmethod
+    def build(cls, queue_item: SessionQueueItem, invocation: BaseInvocation) -> "InvocationStartedEvent":
+        return cls(
+            queue_id=queue_item.queue_id,
+            item_id=queue_item.item_id,
+            batch_id=queue_item.batch_id,
+            session_id=queue_item.session_id,
+            invocation=invocation,
+            invocation_source_id=queue_item.session.prepared_source_mapping[invocation.id],
+        )
+
+
+@payload_schema.register
+class InvocationDenoiseProgressEvent(InvocationEventBase):
+    """Event model for invocation_denoise_progress"""
+
+    __event_name__ = "invocation_denoise_progress"
+
+    progress_image: ProgressImage = Field(description="The progress image sent at each step during processing")
+    step: int = Field(description="The current step of the invocation")
+    total_steps: int = Field(description="The total number of steps in the invocation")
+    order: int = Field(description="The order of the invocation in the session")
+    percentage: float = Field(description="The percentage of completion of the invocation")
+
+    @classmethod
+    def build(
+        cls,
+        queue_item: SessionQueueItem,
+        invocation: BaseInvocation,
+        intermediate_state: PipelineIntermediateState,
+        progress_image: ProgressImage,
+    ) -> "InvocationDenoiseProgressEvent":
+        step = intermediate_state.step
+        total_steps = intermediate_state.total_steps
+        order = intermediate_state.order
+        return cls(
+            queue_id=queue_item.queue_id,
+            item_id=queue_item.item_id,
+            batch_id=queue_item.batch_id,
+            session_id=queue_item.session_id,
+            invocation=invocation,
+            invocation_source_id=queue_item.session.prepared_source_mapping[invocation.id],
+            progress_image=progress_image,
+            step=step,
+            total_steps=total_steps,
+            order=order,
+            percentage=cls.calc_percentage(step, total_steps, order),
+        )
+
+    @staticmethod
+    def calc_percentage(step: int, total_steps: int, scheduler_order: float) -> float:
+        """Calculate the percentage of completion of denoising."""
+        if total_steps == 0:
+            return 0.0
+        if scheduler_order == 2:
+            return floor((step + 1 + 1) / 2) / floor((total_steps + 1) / 2)
+        # order == 1
+        return (step + 1 + 1) / (total_steps + 1)
+
+
+@payload_schema.register
+class InvocationCompleteEvent(InvocationEventBase):
+    """Event model for invocation_complete"""
+
+    __event_name__ = "invocation_complete"
+
+    result: SerializeAsAny[BaseInvocationOutput] = Field(description="The result of the invocation")
+
+    @field_validator("result", mode="plain")
+    @classmethod
+    def validate_results(cls, v: Any):
+        """Validates the invocation result using the dynamic type adapter."""
+
+        result = BaseInvocationOutput.get_typeadapter().validate_python(v)
+        return result
+
+    @classmethod
+    def build(
+        cls, queue_item: SessionQueueItem, invocation: BaseInvocation, result: BaseInvocationOutput
+    ) -> "InvocationCompleteEvent":
+        return cls(
+            queue_id=queue_item.queue_id,
+            item_id=queue_item.item_id,
+            batch_id=queue_item.batch_id,
+            session_id=queue_item.session_id,
+            invocation=invocation,
+            invocation_source_id=queue_item.session.prepared_source_mapping[invocation.id],
+            result=result,
+        )
+
+
+@payload_schema.register
+class InvocationErrorEvent(InvocationEventBase):
+    """Event model for invocation_error"""
+
+    __event_name__ = "invocation_error"
+
+    error_type: str = Field(description="The error type")
+    error_message: str = Field(description="The error message")
+    error_traceback: str = Field(description="The error traceback")
+    user_id: Optional[str] = Field(default=None, description="The ID of the user who created the invocation")
+    project_id: Optional[str] = Field(default=None, description="The ID of the user who created the invocation")
+
+    @classmethod
+    def build(
+        cls,
+        queue_item: SessionQueueItem,
+        invocation: BaseInvocation,
+        error_type: str,
+        error_message: str,
+        error_traceback: str,
+    ) -> "InvocationErrorEvent":
+        return cls(
+            queue_id=queue_item.queue_id,
+            item_id=queue_item.item_id,
+            batch_id=queue_item.batch_id,
+            session_id=queue_item.session_id,
+            invocation=invocation,
+            invocation_source_id=queue_item.session.prepared_source_mapping[invocation.id],
+            error_type=error_type,
+            error_message=error_message,
+            error_traceback=error_traceback,
+            user_id=getattr(queue_item, "user_id", None),
+            project_id=getattr(queue_item, "project_id", None),
+        )
+
+
+@payload_schema.register
+class QueueItemStatusChangedEvent(QueueItemEventBase):
+    """Event model for queue_item_status_changed"""
+
+    __event_name__ = "queue_item_status_changed"
+
+    status: QUEUE_ITEM_STATUS = Field(description="The new status of the queue item")
+    error_type: Optional[str] = Field(default=None, description="The error type, if any")
+    error_message: Optional[str] = Field(default=None, description="The error message, if any")
+    error_traceback: Optional[str] = Field(default=None, description="The error traceback, if any")
+    created_at: Optional[str] = Field(default=None, description="The timestamp when the queue item was created")
+    updated_at: Optional[str] = Field(default=None, description="The timestamp when the queue item was last updated")
+    started_at: Optional[str] = Field(default=None, description="The timestamp when the queue item was started")
+    completed_at: Optional[str] = Field(default=None, description="The timestamp when the queue item was completed")
+    batch_status: BatchStatus = Field(description="The status of the batch")
+    queue_status: SessionQueueStatus = Field(description="The status of the queue")
+    session_id: str = Field(description="The ID of the session (aka graph execution state)")
+
+    @classmethod
+    def build(
+        cls, queue_item: SessionQueueItem, batch_status: BatchStatus, queue_status: SessionQueueStatus
+    ) -> "QueueItemStatusChangedEvent":
+        return cls(
+            queue_id=queue_item.queue_id,
+            item_id=queue_item.item_id,
+            batch_id=queue_item.batch_id,
+            session_id=queue_item.session_id,
+            status=queue_item.status,
+            error_type=queue_item.error_type,
+            error_message=queue_item.error_message,
+            error_traceback=queue_item.error_traceback,
+            created_at=str(queue_item.created_at) if queue_item.created_at else None,
+            updated_at=str(queue_item.updated_at) if queue_item.updated_at else None,
+            started_at=str(queue_item.started_at) if queue_item.started_at else None,
+            completed_at=str(queue_item.completed_at) if queue_item.completed_at else None,
+            batch_status=batch_status,
+            queue_status=queue_status,
+        )
+
+
+@payload_schema.register
+class BatchEnqueuedEvent(QueueEventBase):
+    """Event model for batch_enqueued"""
+
+    __event_name__ = "batch_enqueued"
+
+    batch_id: str = Field(description="The ID of the batch")
+    enqueued: int = Field(description="The number of invocations enqueued")
+    requested: int = Field(
+        description="The number of invocations initially requested to be enqueued (may be less than enqueued if queue was full)"
+    )
+    priority: int = Field(description="The priority of the batch")
+
+    @classmethod
+    def build(cls, enqueue_result: EnqueueBatchResult) -> "BatchEnqueuedEvent":
+        return cls(
+            queue_id=enqueue_result.queue_id,
+            batch_id=enqueue_result.batch.batch_id,
+            enqueued=enqueue_result.enqueued,
+            requested=enqueue_result.requested,
+            priority=enqueue_result.priority,
+        )
+
+
+@payload_schema.register
+class QueueClearedEvent(QueueEventBase):
+    """Event model for queue_cleared"""
+
+    __event_name__ = "queue_cleared"
+
+    @classmethod
+    def build(cls, queue_id: str) -> "QueueClearedEvent":
+        return cls(queue_id=queue_id)
+
+
+class DownloadEventBase(EventBase):
+    """Base class for events associated with a download"""
+
+    source: str = Field(description="The source of the download")
+
+
+@payload_schema.register
+class DownloadStartedEvent(DownloadEventBase):
+    """Event model for download_started"""
+
+    __event_name__ = "download_started"
+
+    download_path: str = Field(description="The local path where the download is saved")
+
+    @classmethod
+    def build(cls, job: "DownloadJob") -> "DownloadStartedEvent":
+        assert job.download_path
+        return cls(source=str(job.source), download_path=job.download_path.as_posix())
+
+
+@payload_schema.register
+class DownloadProgressEvent(DownloadEventBase):
+    """Event model for download_progress"""
+
+    __event_name__ = "download_progress"
+
+    download_path: str = Field(description="The local path where the download is saved")
+    current_bytes: int = Field(description="The number of bytes downloaded so far")
+    total_bytes: int = Field(description="The total number of bytes to be downloaded")
+
+    @classmethod
+    def build(cls, job: "DownloadJob") -> "DownloadProgressEvent":
+        assert job.download_path
+        return cls(
+            source=str(job.source),
+            download_path=job.download_path.as_posix(),
+            current_bytes=job.bytes,
+            total_bytes=job.total_bytes,
+        )
+
+
+@payload_schema.register
+class DownloadCompleteEvent(DownloadEventBase):
+    """Event model for download_complete"""
+
+    __event_name__ = "download_complete"
+
+    download_path: str = Field(description="The local path where the download is saved")
+    total_bytes: int = Field(description="The total number of bytes downloaded")
+
+    @classmethod
+    def build(cls, job: "DownloadJob") -> "DownloadCompleteEvent":
+        assert job.download_path
+        return cls(source=str(job.source), download_path=job.download_path.as_posix(), total_bytes=job.total_bytes)
+
+
+@payload_schema.register
+class DownloadCancelledEvent(DownloadEventBase):
+    """Event model for download_cancelled"""
+
+    __event_name__ = "download_cancelled"
+
+    @classmethod
+    def build(cls, job: "DownloadJob") -> "DownloadCancelledEvent":
+        return cls(source=str(job.source))
+
+
+@payload_schema.register
+class DownloadErrorEvent(DownloadEventBase):
+    """Event model for download_error"""
+
+    __event_name__ = "download_error"
+
+    error_type: str = Field(description="The type of error")
+    error: str = Field(description="The error message")
+
+    @classmethod
+    def build(cls, job: "DownloadJob") -> "DownloadErrorEvent":
+        assert job.error_type
+        assert job.error
+        return cls(source=str(job.source), error_type=job.error_type, error=job.error)
+
+
+class ModelEventBase(EventBase):
+    """Base class for events associated with a model"""
+
+
+@payload_schema.register
+class ModelLoadStartedEvent(ModelEventBase):
+    """Event model for model_load_started"""
+
+    __event_name__ = "model_load_started"
+
+    config: AnyModelConfig = Field(description="The model's config")
+    submodel_type: Optional[SubModelType] = Field(default=None, description="The submodel type, if any")
+
+    @classmethod
+    def build(cls, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> "ModelLoadStartedEvent":
+        return cls(config=config, submodel_type=submodel_type)
+
+
+@payload_schema.register
+class ModelLoadCompleteEvent(ModelEventBase):
+    """Event model for model_load_complete"""
+
+    __event_name__ = "model_load_complete"
+
+    config: AnyModelConfig = Field(description="The model's config")
+    submodel_type: Optional[SubModelType] = Field(default=None, description="The submodel type, if any")
+
+    @classmethod
+    def build(cls, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> "ModelLoadCompleteEvent":
+        return cls(config=config, submodel_type=submodel_type)
+
+
+@payload_schema.register
+class ModelInstallDownloadProgressEvent(ModelEventBase):
+    """Event model for model_install_download_progress"""
+
+    __event_name__ = "model_install_download_progress"
+
+    id: int = Field(description="The ID of the install job")
+    source: str = Field(description="Source of the model; local path, repo_id or url")
+    local_path: str = Field(description="Where model is downloading to")
+    bytes: int = Field(description="Number of bytes downloaded so far")
+    total_bytes: int = Field(description="Total size of download, including all files")
+    parts: list[dict[str, int | str]] = Field(
+        description="Progress of downloading URLs that comprise the model, if any"
+    )
+
+    @classmethod
+    def build(cls, job: "ModelInstallJob") -> "ModelInstallDownloadProgressEvent":
+        parts: list[dict[str, str | int]] = [
+            {
+                "url": str(x.source),
+                "local_path": str(x.download_path),
+                "bytes": x.bytes,
+                "total_bytes": x.total_bytes,
+            }
+            for x in job.download_parts
+        ]
+        return cls(
+            id=job.id,
+            source=str(job.source),
+            local_path=job.local_path.as_posix(),
+            parts=parts,
+            bytes=job.bytes,
+            total_bytes=job.total_bytes,
+        )
+
+
+@payload_schema.register
+class ModelInstallDownloadsCompleteEvent(ModelEventBase):
+    """Emitted once when an install job becomes active."""
+
+    __event_name__ = "model_install_downloads_complete"
+
+    id: int = Field(description="The ID of the install job")
+    source: str = Field(description="Source of the model; local path, repo_id or url")
+
+    @classmethod
+    def build(cls, job: "ModelInstallJob") -> "ModelInstallDownloadsCompleteEvent":
+        return cls(id=job.id, source=str(job.source))
+
+
+@payload_schema.register
+class ModelInstallStartedEvent(ModelEventBase):
+    """Event model for model_install_started"""
+
+    __event_name__ = "model_install_started"
+
+    id: int = Field(description="The ID of the install job")
+    source: str = Field(description="Source of the model; local path, repo_id or url")
+
+    @classmethod
+    def build(cls, job: "ModelInstallJob") -> "ModelInstallStartedEvent":
+        return cls(id=job.id, source=str(job.source))
+
+
+@payload_schema.register
+class ModelInstallCompleteEvent(ModelEventBase):
+    """Event model for model_install_complete"""
+
+    __event_name__ = "model_install_complete"
+
+    id: int = Field(description="The ID of the install job")
+    source: str = Field(description="Source of the model; local path, repo_id or url")
+    key: str = Field(description="Model config record key")
+    total_bytes: Optional[int] = Field(description="Size of the model (may be None for installation of a local path)")
+
+    @classmethod
+    def build(cls, job: "ModelInstallJob") -> "ModelInstallCompleteEvent":
+        assert job.config_out is not None
+        return cls(id=job.id, source=str(job.source), key=(job.config_out.key), total_bytes=job.total_bytes)
+
+
+@payload_schema.register
+class ModelInstallCancelledEvent(ModelEventBase):
+    """Event model for model_install_cancelled"""
+
+    __event_name__ = "model_install_cancelled"
+
+    id: int = Field(description="The ID of the install job")
+    source: str = Field(description="Source of the model; local path, repo_id or url")
+
+    @classmethod
+    def build(cls, job: "ModelInstallJob") -> "ModelInstallCancelledEvent":
+        return cls(id=job.id, source=str(job.source))
+
+
+@payload_schema.register
+class ModelInstallErrorEvent(ModelEventBase):
+    """Event model for model_install_error"""
+
+    __event_name__ = "model_install_error"
+
+    id: int = Field(description="The ID of the install job")
+    source: str = Field(description="Source of the model; local path, repo_id or url")
+    error_type: str = Field(description="The name of the exception")
+    error: str = Field(description="A text description of the exception")
+
+    @classmethod
+    def build(cls, job: "ModelInstallJob") -> "ModelInstallErrorEvent":
+        assert job.error_type is not None
+        assert job.error is not None
+        return cls(id=job.id, source=str(job.source), error_type=job.error_type, error=job.error)
+
+
+class BulkDownloadEventBase(EventBase):
+    """Base class for events associated with a bulk image download"""
+
+    bulk_download_id: str = Field(description="The ID of the bulk image download")
+    bulk_download_item_id: str = Field(description="The ID of the bulk image download item")
+    bulk_download_item_name: str = Field(description="The name of the bulk image download item")
+
+
+@payload_schema.register
+class BulkDownloadStartedEvent(BulkDownloadEventBase):
+    """Event model for bulk_download_started"""
+
+    __event_name__ = "bulk_download_started"
+
+    @classmethod
+    def build(
+        cls, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
+    ) -> "BulkDownloadStartedEvent":
+        return cls(
+            bulk_download_id=bulk_download_id,
+            bulk_download_item_id=bulk_download_item_id,
+            bulk_download_item_name=bulk_download_item_name,
+        )
+
+
+@payload_schema.register
+class BulkDownloadCompleteEvent(BulkDownloadEventBase):
+    """Event model for bulk_download_complete"""
+
+    __event_name__ = "bulk_download_complete"
+
+    @classmethod
+    def build(
+        cls, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
+    ) -> "BulkDownloadCompleteEvent":
+        return cls(
+            bulk_download_id=bulk_download_id,
+            bulk_download_item_id=bulk_download_item_id,
+            bulk_download_item_name=bulk_download_item_name,
+        )
+
+
+@payload_schema.register
+class BulkDownloadErrorEvent(BulkDownloadEventBase):
+    """Event model for bulk_download_error"""
+
+    __event_name__ = "bulk_download_error"
+
+    error: str = Field(description="The error message")
+
+    @classmethod
+    def build(
+        cls, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str, error: str
+    ) -> "BulkDownloadErrorEvent":
+        return cls(
+            bulk_download_id=bulk_download_id,
+            bulk_download_item_id=bulk_download_item_id,
+            bulk_download_item_name=bulk_download_item_name,
+            error=error,
+        )

invokeai/app/services/events/events_fastapievents.py

@@ -0,0 +1,47 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import asyncio
+import threading
+from queue import Empty, Queue
+
+from fastapi_events.dispatcher import dispatch
+
+from invokeai.app.services.events.events_common import (
+    EventBase,
+)
+
+from .events_base import EventServiceBase
+
+
+class FastAPIEventService(EventServiceBase):
+    def __init__(self, event_handler_id: int) -> None:
+        self.event_handler_id = event_handler_id
+        self._queue = Queue[EventBase | None]()
+        self._stop_event = threading.Event()
+        asyncio.create_task(self._dispatch_from_queue(stop_event=self._stop_event))
+
+        super().__init__()
+
+    def stop(self, *args, **kwargs):
+        self._stop_event.set()
+        self._queue.put(None)
+
+    def dispatch(self, event: EventBase) -> None:
+        self._queue.put(event)
+
+    async def _dispatch_from_queue(self, stop_event: threading.Event):
+        """Get events on from the queue and dispatch them, from the correct thread"""
+        while not stop_event.is_set():
+            try:
+                event = self._queue.get(block=False)
+                if not event:  # Probably stopping
+                    continue
+                # Leave the payloads as live pydantic models
+                dispatch(event, middleware_id=self.event_handler_id, payload_schema_dump=False)
+
+            except Empty:
+                await asyncio.sleep(0.1)
+                pass
+
+            except asyncio.CancelledError as e:
+                raise e  # Raise a proper error

invokeai/app/services/image_files/image_files_base.py

@@ -4,9 +4,6 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.fields import MetadataField
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
-
 
 class ImageFileStorageBase(ABC):
     """Low-level service responsible for storing and retrieving image files."""
@@ -33,8 +30,9 @@ class ImageFileStorageBase(ABC):
         self,
         image: PILImageType,
         image_name: str,
-        metadata: Optional[MetadataField] = None,
-        workflow: Optional[WorkflowWithoutID] = None,
+        metadata: Optional[str] = None,
+        workflow: Optional[str] = None,
+        graph: Optional[str] = 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."""
@@ -46,6 +44,11 @@ class ImageFileStorageBase(ABC):
         pass
 
     @abstractmethod
-    def get_workflow(self, image_name: str) -> Optional[WorkflowWithoutID]:
+    def get_workflow(self, image_name: str) -> Optional[str]:
         """Gets the workflow of an image."""
         pass
+
+    @abstractmethod
+    def get_graph(self, image_name: str) -> Optional[str]:
+        """Gets the graph of an image."""
+        pass

invokeai/app/services/image_files/image_files_disk.py

@@ -7,9 +7,7 @@ from PIL import Image, PngImagePlugin
 from PIL.Image import Image as PILImageType
 from send2trash import send2trash
 
-from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
 
 from .image_files_base import ImageFileStorageBase
@@ -56,8 +54,9 @@ class DiskImageFileStorage(ImageFileStorageBase):
         self,
         image: PILImageType,
         image_name: str,
-        metadata: Optional[MetadataField] = None,
-        workflow: Optional[WorkflowWithoutID] = None,
+        metadata: Optional[str] = None,
+        workflow: Optional[str] = None,
+        graph: Optional[str] = None,
         thumbnail_size: int = 256,
     ) -> None:
         try:
@@ -68,13 +67,14 @@ class DiskImageFileStorage(ImageFileStorageBase):
             info_dict = {}
 
             if metadata is not None:
-                metadata_json = metadata.model_dump_json()
-                info_dict["invokeai_metadata"] = metadata_json
-                pnginfo.add_text("invokeai_metadata", metadata_json)
+                info_dict["invokeai_metadata"] = metadata
+                pnginfo.add_text("invokeai_metadata", metadata)
             if workflow is not None:
-                workflow_json = workflow.model_dump_json()
-                info_dict["invokeai_workflow"] = workflow_json
-                pnginfo.add_text("invokeai_workflow", workflow_json)
+                info_dict["invokeai_workflow"] = workflow
+                pnginfo.add_text("invokeai_workflow", workflow)
+            if graph is not None:
+                info_dict["invokeai_graph"] = graph
+                pnginfo.add_text("invokeai_graph", graph)
 
             # When saving the image, the image object's info field is not populated. We need to set it
             image.info = info_dict
@@ -129,11 +129,18 @@ class DiskImageFileStorage(ImageFileStorageBase):
         path = path if isinstance(path, Path) else Path(path)
         return path.exists()
 
-    def get_workflow(self, image_name: str) -> WorkflowWithoutID | None:
+    def get_workflow(self, image_name: str) -> str | None:
         image = self.get(image_name)
         workflow = image.info.get("invokeai_workflow", None)
-        if workflow is not None:
-            return WorkflowWithoutID.model_validate_json(workflow)
+        if isinstance(workflow, str):
+            return workflow
+        return None
+
+    def get_graph(self, image_name: str) -> str | None:
+        image = self.get(image_name)
+        graph = image.info.get("invokeai_graph", None)
+        if isinstance(graph, str):
+            return graph
         return None
 
     def __validate_storage_folders(self) -> None:

invokeai/app/services/image_records/image_records_base.py

@@ -80,7 +80,7 @@ class ImageRecordStorageBase(ABC):
         starred: Optional[bool] = False,
         session_id: Optional[str] = None,
         node_id: Optional[str] = None,
-        metadata: Optional[MetadataField] = None,
+        metadata: Optional[str] = None,
     ) -> datetime:
         """Saves an image record."""
         pass

invokeai/app/services/image_records/image_records_sqlite.py

@@ -328,10 +328,9 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
         starred: Optional[bool] = False,
         session_id: Optional[str] = None,
         node_id: Optional[str] = None,
-        metadata: Optional[MetadataField] = None,
+        metadata: Optional[str] = None,
     ) -> datetime:
         try:
-            metadata_json = metadata.model_dump_json() if metadata is not None else None
             self._lock.acquire()
             self._cursor.execute(
                 """--sql
@@ -358,7 +357,7 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
                     height,
                     node_id,
                     session_id,
-                    metadata_json,
+                    metadata,
                     is_intermediate,
                     starred,
                     has_workflow,

invokeai/app/services/images/images_base.py

@@ -12,7 +12,6 @@ from invokeai.app.services.image_records.image_records_common import (
 )
 from invokeai.app.services.images.images_common import ImageDTO
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 
 
 class ImageServiceABC(ABC):
@@ -51,8 +50,9 @@ class ImageServiceABC(ABC):
         session_id: Optional[str] = None,
         board_id: Optional[str] = None,
         is_intermediate: Optional[bool] = False,
-        metadata: Optional[MetadataField] = None,
-        workflow: Optional[WorkflowWithoutID] = None,
+        metadata: Optional[str] = None,
+        workflow: Optional[str] = None,
+        graph: Optional[str] = None,
     ) -> ImageDTO:
         """Creates an image, storing the file and its metadata."""
         pass
@@ -87,7 +87,12 @@ class ImageServiceABC(ABC):
         pass
 
     @abstractmethod
-    def get_workflow(self, image_name: str) -> Optional[WorkflowWithoutID]:
+    def get_workflow(self, image_name: str) -> Optional[str]:
+        """Gets an image's workflow."""
+        pass
+
+    @abstractmethod
+    def get_graph(self, image_name: str) -> Optional[str]:
         """Gets an image's workflow."""
         pass
 

invokeai/app/services/images/images_default.py

@@ -5,7 +5,6 @@ from PIL.Image import Image as PILImageType
 from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 
 from ..image_files.image_files_common import (
     ImageFileDeleteException,
@@ -42,8 +41,9 @@ class ImageService(ImageServiceABC):
         session_id: Optional[str] = None,
         board_id: Optional[str] = None,
         is_intermediate: Optional[bool] = False,
-        metadata: Optional[MetadataField] = None,
-        workflow: Optional[WorkflowWithoutID] = None,
+        metadata: Optional[str] = None,
+        workflow: Optional[str] = None,
+        graph: Optional[str] = None,
     ) -> ImageDTO:
         if image_origin not in ResourceOrigin:
             raise InvalidOriginException
@@ -64,7 +64,7 @@ class ImageService(ImageServiceABC):
                 image_category=image_category,
                 width=width,
                 height=height,
-                has_workflow=workflow is not None,
+                has_workflow=workflow is not None or graph is not None,
                 # Meta fields
                 is_intermediate=is_intermediate,
                 # Nullable fields
@@ -75,7 +75,7 @@ class ImageService(ImageServiceABC):
             if board_id is not None:
                 self.__invoker.services.board_image_records.add_image_to_board(board_id=board_id, image_name=image_name)
             self.__invoker.services.image_files.save(
-                image_name=image_name, image=image, metadata=metadata, workflow=workflow
+                image_name=image_name, image=image, metadata=metadata, workflow=workflow, graph=graph
             )
             image_dto = self.get_dto(image_name)
 
@@ -157,7 +157,7 @@ class ImageService(ImageServiceABC):
             self.__invoker.services.logger.error("Problem getting image metadata")
             raise e
 
-    def get_workflow(self, image_name: str) -> Optional[WorkflowWithoutID]:
+    def get_workflow(self, image_name: str) -> Optional[str]:
         try:
             return self.__invoker.services.image_files.get_workflow(image_name)
         except ImageFileNotFoundException:
@@ -167,6 +167,16 @@ class ImageService(ImageServiceABC):
             self.__invoker.services.logger.error("Problem getting image workflow")
             raise
 
+    def get_graph(self, image_name: str) -> Optional[str]:
+        try:
+            return self.__invoker.services.image_files.get_graph(image_name)
+        except ImageFileNotFoundException:
+            self.__invoker.services.logger.error("Image file not found")
+            raise
+        except Exception:
+            self.__invoker.services.logger.error("Problem getting image graph")
+            raise
+
     def get_path(self, image_name: str, thumbnail: bool = False) -> str:
         try:
             return str(self.__invoker.services.image_files.get_path(image_name, thumbnail))

invokeai/app/services/model_install/__init__.py

@@ -1,11 +1,13 @@
 """Initialization file for model install service package."""
 
 from .model_install_base import (
+    ModelInstallServiceBase,
+)
+from .model_install_common import (
     HFModelSource,
     InstallStatus,
     LocalModelSource,
     ModelInstallJob,
-    ModelInstallServiceBase,
     ModelSource,
     UnknownInstallJobException,
     URLModelSource,

invokeai/app/services/model_install/model_install_base.py

@@ -1,244 +1,19 @@
 # Copyright 2023 Lincoln D. Stein and the InvokeAI development team
 """Baseclass definitions for the model installer."""
 
-import re
-import traceback
 from abc import ABC, abstractmethod
-from enum import Enum
 from pathlib import Path
-from typing import Any, Dict, List, Literal, Optional, Set, Union
+from typing import Any, Dict, List, Optional, Union
 
-from pydantic import BaseModel, Field, PrivateAttr, field_validator
 from pydantic.networks import AnyHttpUrl
-from typing_extensions import Annotated
 
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase
+from invokeai.app.services.download import DownloadQueueServiceBase
 from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.model_install.model_install_common import ModelInstallJob, ModelSource
 from invokeai.app.services.model_records import ModelRecordServiceBase
-from invokeai.backend.model_manager import AnyModelConfig, ModelRepoVariant
-from invokeai.backend.model_manager.config import ModelSourceType
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-
-class InstallStatus(str, Enum):
-    """State of an install job running in the background."""
-
-    WAITING = "waiting"  # waiting to be dequeued
-    DOWNLOADING = "downloading"  # downloading of model files in process
-    DOWNLOADS_DONE = "downloads_done"  # downloading done, waiting to run
-    RUNNING = "running"  # being processed
-    COMPLETED = "completed"  # finished running
-    ERROR = "error"  # terminated with an error message
-    CANCELLED = "cancelled"  # terminated with an error message
-
-
-class ModelInstallPart(BaseModel):
-    url: AnyHttpUrl
-    path: Path
-    bytes: int = 0
-    total_bytes: int = 0
-
-
-class UnknownInstallJobException(Exception):
-    """Raised when the status of an unknown job is requested."""
-
-
-class StringLikeSource(BaseModel):
-    """
-    Base class for model sources, implements functions that lets the source be sorted and indexed.
-
-    These shenanigans let this stuff work:
-
-      source1 = LocalModelSource(path='C:/users/mort/foo.safetensors')
-      mydict = {source1: 'model 1'}
-      assert mydict['C:/users/mort/foo.safetensors'] == 'model 1'
-      assert mydict[LocalModelSource(path='C:/users/mort/foo.safetensors')] == 'model 1'
-
-      source2 = LocalModelSource(path=Path('C:/users/mort/foo.safetensors'))
-      assert source1 == source2
-      assert source1 == 'C:/users/mort/foo.safetensors'
-    """
-
-    def __hash__(self) -> int:
-        """Return hash of the path field, for indexing."""
-        return hash(str(self))
-
-    def __lt__(self, other: object) -> int:
-        """Return comparison of the stringified version, for sorting."""
-        return str(self) < str(other)
-
-    def __eq__(self, other: object) -> bool:
-        """Return equality on the stringified version."""
-        if isinstance(other, Path):
-            return str(self) == other.as_posix()
-        else:
-            return str(self) == str(other)
-
-
-class LocalModelSource(StringLikeSource):
-    """A local file or directory path."""
-
-    path: str | Path
-    inplace: Optional[bool] = False
-    type: Literal["local"] = "local"
-
-    # these methods allow the source to be used in a string-like way,
-    # for example as an index into a dict
-    def __str__(self) -> str:
-        """Return string version of path when string rep needed."""
-        return Path(self.path).as_posix()
-
-
-class HFModelSource(StringLikeSource):
-    """
-    A HuggingFace repo_id with optional variant, sub-folder and access token.
-    Note that the variant option, if not provided to the constructor, will default to fp16, which is
-    what people (almost) always want.
-    """
-
-    repo_id: str
-    variant: Optional[ModelRepoVariant] = ModelRepoVariant.FP16
-    subfolder: Optional[Path] = None
-    access_token: Optional[str] = None
-    type: Literal["hf"] = "hf"
-
-    @field_validator("repo_id")
-    @classmethod
-    def proper_repo_id(cls, v: str) -> str:  # noqa D102
-        if not re.match(r"^([.\w-]+/[.\w-]+)$", v):
-            raise ValueError(f"{v}: invalid repo_id format")
-        return v
-
-    def __str__(self) -> str:
-        """Return string version of repoid when string rep needed."""
-        base: str = self.repo_id
-        if self.variant:
-            base += f":{self.variant or ''}"
-        if self.subfolder:
-            base += f":{self.subfolder}"
-        return base
-
-
-class URLModelSource(StringLikeSource):
-    """A generic URL point to a checkpoint file."""
-
-    url: AnyHttpUrl
-    access_token: Optional[str] = None
-    type: Literal["url"] = "url"
-
-    def __str__(self) -> str:
-        """Return string version of the url when string rep needed."""
-        return str(self.url)
-
-
-ModelSource = Annotated[Union[LocalModelSource, HFModelSource, URLModelSource], Field(discriminator="type")]
-
-MODEL_SOURCE_TO_TYPE_MAP = {
-    URLModelSource: ModelSourceType.Url,
-    HFModelSource: ModelSourceType.HFRepoID,
-    LocalModelSource: ModelSourceType.Path,
-}
-
-
-class ModelInstallJob(BaseModel):
-    """Object that tracks the current status of an install request."""
-
-    id: int = Field(description="Unique ID for this job")
-    status: InstallStatus = Field(default=InstallStatus.WAITING, description="Current status of install process")
-    error_reason: Optional[str] = Field(default=None, description="Information about why the job failed")
-    config_in: Dict[str, Any] = Field(
-        default_factory=dict, description="Configuration information (e.g. 'description') to apply to model."
-    )
-    config_out: Optional[AnyModelConfig] = Field(
-        default=None, description="After successful installation, this will hold the configuration object."
-    )
-    inplace: bool = Field(
-        default=False, description="Leave model in its current location; otherwise install under models directory"
-    )
-    source: ModelSource = Field(description="Source (URL, repo_id, or local path) of model")
-    local_path: Path = Field(description="Path to locally-downloaded model; may be the same as the source")
-    bytes: int = Field(
-        default=0, description="For a remote model, the number of bytes downloaded so far (may not be available)"
-    )
-    total_bytes: int = Field(default=0, description="Total size of the model to be installed")
-    source_metadata: Optional[AnyModelRepoMetadata] = Field(
-        default=None, description="Metadata provided by the model source"
-    )
-    download_parts: Set[DownloadJob] = Field(
-        default_factory=set, description="Download jobs contributing to this install"
-    )
-    error: Optional[str] = Field(
-        default=None, description="On an error condition, this field will contain the text of the exception"
-    )
-    error_traceback: Optional[str] = Field(
-        default=None, description="On an error condition, this field will contain the exception traceback"
-    )
-    # internal flags and transitory settings
-    _install_tmpdir: Optional[Path] = PrivateAttr(default=None)
-    _exception: Optional[Exception] = PrivateAttr(default=None)
-
-    def set_error(self, e: Exception) -> None:
-        """Record the error and traceback from an exception."""
-        self._exception = e
-        self.error = str(e)
-        self.error_traceback = self._format_error(e)
-        self.status = InstallStatus.ERROR
-        self.error_reason = self._exception.__class__.__name__ if self._exception else None
-
-    def cancel(self) -> None:
-        """Call to cancel the job."""
-        self.status = InstallStatus.CANCELLED
-
-    @property
-    def error_type(self) -> Optional[str]:
-        """Class name of the exception that led to status==ERROR."""
-        return self._exception.__class__.__name__ if self._exception else None
-
-    def _format_error(self, exception: Exception) -> str:
-        """Error traceback."""
-        return "".join(traceback.format_exception(exception))
-
-    @property
-    def cancelled(self) -> bool:
-        """Set status to CANCELLED."""
-        return self.status == InstallStatus.CANCELLED
-
-    @property
-    def errored(self) -> bool:
-        """Return true if job has errored."""
-        return self.status == InstallStatus.ERROR
-
-    @property
-    def waiting(self) -> bool:
-        """Return true if job is waiting to run."""
-        return self.status == InstallStatus.WAITING
-
-    @property
-    def downloading(self) -> bool:
-        """Return true if job is downloading."""
-        return self.status == InstallStatus.DOWNLOADING
-
-    @property
-    def downloads_done(self) -> bool:
-        """Return true if job's downloads ae done."""
-        return self.status == InstallStatus.DOWNLOADS_DONE
-
-    @property
-    def running(self) -> bool:
-        """Return true if job is running."""
-        return self.status == InstallStatus.RUNNING
-
-    @property
-    def complete(self) -> bool:
-        """Return true if job completed without errors."""
-        return self.status == InstallStatus.COMPLETED
-
-    @property
-    def in_terminal_state(self) -> bool:
-        """Return true if job is in a terminal state."""
-        return self.status in [InstallStatus.COMPLETED, InstallStatus.ERROR, InstallStatus.CANCELLED]
+from invokeai.backend.model_manager.config import AnyModelConfig
 
 
 class ModelInstallServiceBase(ABC):
@@ -282,7 +57,7 @@ class ModelInstallServiceBase(ABC):
 
     @property
     @abstractmethod
-    def event_bus(self) -> Optional[EventServiceBase]:
+    def event_bus(self) -> Optional["EventServiceBase"]:
         """Return the event service base object associated with the installer."""
 
     @abstractmethod
@@ -454,20 +229,6 @@ class ModelInstallServiceBase(ABC):
         will block indefinitely until the installs complete.
         """
 
-    @abstractmethod
-    def scan_directory(self, scan_dir: Path, install: bool = False) -> List[str]:
-        """
-        Recursively scan directory for new models and register or install them.
-
-        :param scan_dir: Path to the directory to scan.
-        :param install: Install if True, otherwise register in place.
-        :returns list of IDs: Returns list of IDs of models registered/installed
-        """
-
-    @abstractmethod
-    def sync_to_config(self) -> None:
-        """Synchronize models on disk to those in the model record database."""
-
     @abstractmethod
     def sync_model_path(self, key: str) -> AnyModelConfig:
         """

invokeai/app/services/model_install/model_install_common.py

@@ -0,0 +1,233 @@
+import re
+import traceback
+from enum import Enum
+from pathlib import Path
+from typing import Any, Dict, Literal, Optional, Set, Union
+
+from pydantic import BaseModel, Field, PrivateAttr, field_validator
+from pydantic.networks import AnyHttpUrl
+from typing_extensions import Annotated
+
+from invokeai.app.services.download import DownloadJob
+from invokeai.backend.model_manager import AnyModelConfig, ModelRepoVariant
+from invokeai.backend.model_manager.config import ModelSourceType
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
+
+
+class InstallStatus(str, Enum):
+    """State of an install job running in the background."""
+
+    WAITING = "waiting"  # waiting to be dequeued
+    DOWNLOADING = "downloading"  # downloading of model files in process
+    DOWNLOADS_DONE = "downloads_done"  # downloading done, waiting to run
+    RUNNING = "running"  # being processed
+    COMPLETED = "completed"  # finished running
+    ERROR = "error"  # terminated with an error message
+    CANCELLED = "cancelled"  # terminated with an error message
+
+
+class ModelInstallPart(BaseModel):
+    url: AnyHttpUrl
+    path: Path
+    bytes: int = 0
+    total_bytes: int = 0
+
+
+class UnknownInstallJobException(Exception):
+    """Raised when the status of an unknown job is requested."""
+
+
+class StringLikeSource(BaseModel):
+    """
+    Base class for model sources, implements functions that lets the source be sorted and indexed.
+
+    These shenanigans let this stuff work:
+
+      source1 = LocalModelSource(path='C:/users/mort/foo.safetensors')
+      mydict = {source1: 'model 1'}
+      assert mydict['C:/users/mort/foo.safetensors'] == 'model 1'
+      assert mydict[LocalModelSource(path='C:/users/mort/foo.safetensors')] == 'model 1'
+
+      source2 = LocalModelSource(path=Path('C:/users/mort/foo.safetensors'))
+      assert source1 == source2
+      assert source1 == 'C:/users/mort/foo.safetensors'
+    """
+
+    def __hash__(self) -> int:
+        """Return hash of the path field, for indexing."""
+        return hash(str(self))
+
+    def __lt__(self, other: object) -> int:
+        """Return comparison of the stringified version, for sorting."""
+        return str(self) < str(other)
+
+    def __eq__(self, other: object) -> bool:
+        """Return equality on the stringified version."""
+        if isinstance(other, Path):
+            return str(self) == other.as_posix()
+        else:
+            return str(self) == str(other)
+
+
+class LocalModelSource(StringLikeSource):
+    """A local file or directory path."""
+
+    path: str | Path
+    inplace: Optional[bool] = False
+    type: Literal["local"] = "local"
+
+    # these methods allow the source to be used in a string-like way,
+    # for example as an index into a dict
+    def __str__(self) -> str:
+        """Return string version of path when string rep needed."""
+        return Path(self.path).as_posix()
+
+
+class HFModelSource(StringLikeSource):
+    """
+    A HuggingFace repo_id with optional variant, sub-folder and access token.
+    Note that the variant option, if not provided to the constructor, will default to fp16, which is
+    what people (almost) always want.
+    """
+
+    repo_id: str
+    variant: Optional[ModelRepoVariant] = ModelRepoVariant.FP16
+    subfolder: Optional[Path] = None
+    access_token: Optional[str] = None
+    type: Literal["hf"] = "hf"
+
+    @field_validator("repo_id")
+    @classmethod
+    def proper_repo_id(cls, v: str) -> str:  # noqa D102
+        if not re.match(r"^([.\w-]+/[.\w-]+)$", v):
+            raise ValueError(f"{v}: invalid repo_id format")
+        return v
+
+    def __str__(self) -> str:
+        """Return string version of repoid when string rep needed."""
+        base: str = self.repo_id
+        if self.variant:
+            base += f":{self.variant or ''}"
+        if self.subfolder:
+            base += f":{self.subfolder}"
+        return base
+
+
+class URLModelSource(StringLikeSource):
+    """A generic URL point to a checkpoint file."""
+
+    url: AnyHttpUrl
+    access_token: Optional[str] = None
+    type: Literal["url"] = "url"
+
+    def __str__(self) -> str:
+        """Return string version of the url when string rep needed."""
+        return str(self.url)
+
+
+ModelSource = Annotated[Union[LocalModelSource, HFModelSource, URLModelSource], Field(discriminator="type")]
+
+MODEL_SOURCE_TO_TYPE_MAP = {
+    URLModelSource: ModelSourceType.Url,
+    HFModelSource: ModelSourceType.HFRepoID,
+    LocalModelSource: ModelSourceType.Path,
+}
+
+
+class ModelInstallJob(BaseModel):
+    """Object that tracks the current status of an install request."""
+
+    id: int = Field(description="Unique ID for this job")
+    status: InstallStatus = Field(default=InstallStatus.WAITING, description="Current status of install process")
+    error_reason: Optional[str] = Field(default=None, description="Information about why the job failed")
+    config_in: Dict[str, Any] = Field(
+        default_factory=dict, description="Configuration information (e.g. 'description') to apply to model."
+    )
+    config_out: Optional[AnyModelConfig] = Field(
+        default=None, description="After successful installation, this will hold the configuration object."
+    )
+    inplace: bool = Field(
+        default=False, description="Leave model in its current location; otherwise install under models directory"
+    )
+    source: ModelSource = Field(description="Source (URL, repo_id, or local path) of model")
+    local_path: Path = Field(description="Path to locally-downloaded model; may be the same as the source")
+    bytes: int = Field(
+        default=0, description="For a remote model, the number of bytes downloaded so far (may not be available)"
+    )
+    total_bytes: int = Field(default=0, description="Total size of the model to be installed")
+    source_metadata: Optional[AnyModelRepoMetadata] = Field(
+        default=None, description="Metadata provided by the model source"
+    )
+    download_parts: Set[DownloadJob] = Field(
+        default_factory=set, description="Download jobs contributing to this install"
+    )
+    error: Optional[str] = Field(
+        default=None, description="On an error condition, this field will contain the text of the exception"
+    )
+    error_traceback: Optional[str] = Field(
+        default=None, description="On an error condition, this field will contain the exception traceback"
+    )
+    # internal flags and transitory settings
+    _install_tmpdir: Optional[Path] = PrivateAttr(default=None)
+    _exception: Optional[Exception] = PrivateAttr(default=None)
+
+    def set_error(self, e: Exception) -> None:
+        """Record the error and traceback from an exception."""
+        self._exception = e
+        self.error = str(e)
+        self.error_traceback = self._format_error(e)
+        self.status = InstallStatus.ERROR
+        self.error_reason = self._exception.__class__.__name__ if self._exception else None
+
+    def cancel(self) -> None:
+        """Call to cancel the job."""
+        self.status = InstallStatus.CANCELLED
+
+    @property
+    def error_type(self) -> Optional[str]:
+        """Class name of the exception that led to status==ERROR."""
+        return self._exception.__class__.__name__ if self._exception else None
+
+    def _format_error(self, exception: Exception) -> str:
+        """Error traceback."""
+        return "".join(traceback.format_exception(exception))
+
+    @property
+    def cancelled(self) -> bool:
+        """Set status to CANCELLED."""
+        return self.status == InstallStatus.CANCELLED
+
+    @property
+    def errored(self) -> bool:
+        """Return true if job has errored."""
+        return self.status == InstallStatus.ERROR
+
+    @property
+    def waiting(self) -> bool:
+        """Return true if job is waiting to run."""
+        return self.status == InstallStatus.WAITING
+
+    @property
+    def downloading(self) -> bool:
+        """Return true if job is downloading."""
+        return self.status == InstallStatus.DOWNLOADING
+
+    @property
+    def downloads_done(self) -> bool:
+        """Return true if job's downloads ae done."""
+        return self.status == InstallStatus.DOWNLOADS_DONE
+
+    @property
+    def running(self) -> bool:
+        """Return true if job is running."""
+        return self.status == InstallStatus.RUNNING
+
+    @property
+    def complete(self) -> bool:
+        """Return true if job completed without errors."""
+        return self.status == InstallStatus.COMPLETED
+
+    @property
+    def in_terminal_state(self) -> bool:
+        """Return true if job is in a terminal state."""
+        return self.status in [InstallStatus.COMPLETED, InstallStatus.ERROR, InstallStatus.CANCELLED]

invokeai/app/services/model_install/model_install_default.py

@@ -1,8 +1,8 @@
 """Model installation class."""
 
+import locale
 import os
 import re
-import signal
 import threading
 import time
 from hashlib import sha256
@@ -10,8 +10,9 @@ from pathlib import Path
 from queue import Empty, Queue
 from shutil import copyfile, copytree, move, rmtree
 from tempfile import mkdtemp
-from typing import Any, Dict, List, Optional, Set, Union
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union
 
+import torch
 import yaml
 from huggingface_hub import HfFolder
 from pydantic.networks import AnyHttpUrl
@@ -19,18 +20,16 @@ from requests import Session
 
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase, TqdmProgress
-from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.model_install.model_install_base import ModelInstallServiceBase
 from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase
 from invokeai.app.services.model_records.model_records_base import ModelRecordChanges
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
-    BaseModelType,
     CheckpointConfigBase,
     InvalidModelConfigException,
     ModelRepoVariant,
     ModelSourceType,
-    ModelType,
 )
 from invokeai.backend.model_manager.metadata import (
     AnyModelRepoMetadata,
@@ -42,16 +41,16 @@ from invokeai.backend.model_manager.metadata import (
 from invokeai.backend.model_manager.metadata.metadata_base import HuggingFaceMetadata
 from invokeai.backend.model_manager.probe import ModelProbe
 from invokeai.backend.model_manager.search import ModelSearch
-from invokeai.backend.util import Chdir, InvokeAILogger
-from invokeai.backend.util.devices import choose_precision, choose_torch_device
+from invokeai.backend.util import InvokeAILogger
+from invokeai.backend.util.catch_sigint import catch_sigint
+from invokeai.backend.util.devices import TorchDevice
 
-from .model_install_base import (
+from .model_install_common import (
     MODEL_SOURCE_TO_TYPE_MAP,
     HFModelSource,
     InstallStatus,
     LocalModelSource,
     ModelInstallJob,
-    ModelInstallServiceBase,
     ModelSource,
     StringLikeSource,
     URLModelSource,
@@ -59,6 +58,9 @@ from .model_install_base import (
 
 TMPDIR_PREFIX = "tmpinstall_"
 
+if TYPE_CHECKING:
+    from invokeai.app.services.events.events_base import EventServiceBase
+
 
 class ModelInstallService(ModelInstallServiceBase):
     """class for InvokeAI model installation."""
@@ -68,7 +70,7 @@ class ModelInstallService(ModelInstallServiceBase):
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
         download_queue: DownloadQueueServiceBase,
-        event_bus: Optional[EventServiceBase] = None,
+        event_bus: Optional["EventServiceBase"] = None,
         session: Optional[Session] = None,
     ):
         """
@@ -84,8 +86,6 @@ class ModelInstallService(ModelInstallServiceBase):
         self._logger = InvokeAILogger.get_logger(name=self.__class__.__name__)
         self._install_jobs: List[ModelInstallJob] = []
         self._install_queue: Queue[ModelInstallJob] = Queue()
-        self._cached_model_paths: Set[Path] = set()
-        self._models_installed: Set[str] = set()
         self._lock = threading.Lock()
         self._stop_event = threading.Event()
         self._downloads_changed_event = threading.Event()
@@ -106,7 +106,7 @@ class ModelInstallService(ModelInstallServiceBase):
         return self._record_store
 
     @property
-    def event_bus(self) -> Optional[EventServiceBase]:  # noqa D102
+    def event_bus(self) -> Optional["EventServiceBase"]:  # noqa D102
         return self._event_bus
 
     # make the invoker optional here because we don't need it and it
@@ -114,24 +114,23 @@ class ModelInstallService(ModelInstallServiceBase):
     def start(self, invoker: Optional[Invoker] = None) -> None:
         """Start the installer thread."""
 
-        # Yes, this is weird. When the installer thread is running, the
-        # thread masks the ^C signal. When we receive a
-        # sigINT, we stop the thread, reset sigINT, and send a new
-        # sigINT to the parent process.
-        def sigint_handler(signum, frame):
-            self.stop()
-            signal.signal(signal.SIGINT, signal.SIG_DFL)
-            signal.raise_signal(signal.SIGINT)
-
-        signal.signal(signal.SIGINT, sigint_handler)
-
         with self._lock:
             if self._running:
                 raise Exception("Attempt to start the installer service twice")
             self._start_installer_thread()
             self._remove_dangling_install_dirs()
             self._migrate_yaml()
-            self.sync_to_config()
+            # In normal use, we do not want to scan the models directory - it should never have orphaned models.
+            # We should only do the scan when the flag is set (which should only be set when testing).
+            if self.app_config.scan_models_on_startup:
+                with catch_sigint():
+                    self._register_orphaned_models()
+
+            # Check all models' paths and confirm they exist. A model could be missing if it was installed on a volume
+            # that isn't currently mounted. In this case, we don't want to delete the model from the database, but we do
+            # want to alert the user.
+            for model in self._scan_for_missing_models():
+                self._logger.warning(f"Missing model file: {model.name} at {model.path}")
 
     def stop(self, invoker: Optional[Invoker] = None) -> None:
         """Stop the installer thread; after this the object can be deleted and garbage collected."""
@@ -306,15 +305,6 @@ class ModelInstallService(ModelInstallServiceBase):
         unfinished_jobs = [x for x in self._install_jobs if not x.in_terminal_state]
         self._install_jobs = unfinished_jobs
 
-    def sync_to_config(self) -> None:
-        """Synchronize models on disk to those in the config record store database."""
-        self._scan_models_directory()
-        if self._app_config.autoimport_path:
-            self._logger.info("Scanning autoimport directory for new models")
-            installed = self.scan_directory(self._app_config.autoimport_path)
-            self._logger.info(f"{len(installed)} new models registered")
-        self._logger.info("Model installer (re)initialized")
-
     def _migrate_yaml(self) -> None:
         db_models = self.record_store.all_models()
 
@@ -327,7 +317,8 @@ class ModelInstallService(ModelInstallServiceBase):
             legacy_models_yaml_path = Path(self._app_config.root_path, legacy_models_yaml_path)
 
         if legacy_models_yaml_path.exists():
-            legacy_models_yaml = yaml.safe_load(legacy_models_yaml_path.read_text())
+            with open(legacy_models_yaml_path, "rt", encoding=locale.getpreferredencoding()) as file:
+                legacy_models_yaml = yaml.safe_load(file)
 
             yaml_metadata = legacy_models_yaml.pop("__metadata__")
             yaml_version = yaml_metadata.get("version")
@@ -352,8 +343,13 @@ class ModelInstallService(ModelInstallServiceBase):
                     config: dict[str, Any] = {}
                     config["name"] = model_name
                     config["description"] = stanza.get("description")
-                    config["config_path"] = stanza.get("config")
-
+                    legacy_config_path = stanza.get("config")
+                    if legacy_config_path:
+                        # In v3, these paths were relative to the root. Migrate them to be relative to the legacy_conf_dir.
+                        legacy_config_path: Path = self._app_config.root_path / legacy_config_path
+                        if legacy_config_path.is_relative_to(self._app_config.legacy_conf_path):
+                            legacy_config_path = legacy_config_path.relative_to(self._app_config.legacy_conf_path)
+                        config["config_path"] = str(legacy_config_path)
                     try:
                         id = self.register_path(model_path=model_path, config=config)
                         self._logger.info(f"Migrated {model_name} with id {id}")
@@ -366,34 +362,28 @@ class ModelInstallService(ModelInstallServiceBase):
         # Unset the path - we are done with it either way
         self._app_config.legacy_models_yaml_path = None
 
-    def scan_directory(self, scan_dir: Path, install: bool = False) -> List[str]:  # noqa D102
-        self._cached_model_paths = {Path(x.path).resolve() for x in self.record_store.all_models()}
-        callback = self._scan_install if install else self._scan_register
-        search = ModelSearch(on_model_found=callback)
-        self._models_installed.clear()
-        search.search(scan_dir)
-        return list(self._models_installed)
-
     def unregister(self, key: str) -> None:  # noqa D102
         self.record_store.del_model(key)
 
     def delete(self, key: str) -> None:  # noqa D102
         """Unregister the model. Delete its files only if they are within our models directory."""
         model = self.record_store.get_model(key)
-        models_dir = self.app_config.models_path
-        model_path = models_dir / Path(model.path)  # handle legacy relative model paths
-        if model_path.is_relative_to(models_dir):
+        model_path = self.app_config.models_path / model.path
+
+        if model_path.is_relative_to(self.app_config.models_path):
+            # If the models is in the Invoke-managed models dir, we delete it
             self.unconditionally_delete(key)
         else:
+            # Else we only unregister it, leaving the file in place
             self.unregister(key)
 
     def unconditionally_delete(self, key: str) -> None:  # noqa D102
         model = self.record_store.get_model(key)
         model_path = self.app_config.models_path / model.path
-        if model_path.is_dir():
-            rmtree(model_path)
-        else:
+        if model_path.is_file() or model_path.is_symlink():
             model_path.unlink()
+        elif model_path.is_dir():
+            rmtree(model_path)
         self.unregister(key)
 
     def download_and_cache(
@@ -457,11 +447,10 @@ class ModelInstallService(ModelInstallServiceBase):
                 elif job.waiting or job.downloads_done:
                     self._register_or_install(job)
 
-            except InvalidModelConfigException as excp:
-                self._set_error(job, excp)
-
-            except (OSError, DuplicateModelException) as excp:
-                self._set_error(job, excp)
+            except Exception as e:
+                # Expected errors include InvalidModelConfigException, DuplicateModelException, OSError, but we must
+                # gracefully handle _any_ error here.
+                self._set_error(job, e)
 
             finally:
                 # if this is an install of a remote file, then clean up the temporary directory
@@ -510,34 +499,46 @@ class ModelInstallService(ModelInstallServiceBase):
             self._logger.info(f"Removing dangling temporary directory {tmpdir}")
             rmtree(tmpdir)
 
-    def _scan_models_directory(self) -> None:
+    def _scan_for_missing_models(self) -> list[AnyModelConfig]:
+        """Scan the models directory for missing models and return a list of them."""
+        missing_models: list[AnyModelConfig] = []
+        for model_config in self.record_store.all_models():
+            if not (self.app_config.models_path / model_config.path).resolve().exists():
+                missing_models.append(model_config)
+        return missing_models
+
+    def _register_orphaned_models(self) -> None:
+        """Scan the invoke-managed models directory for orphaned models and registers them.
+
+        This is typically only used during testing with a new DB or when using the memory DB, because those are the
+        only situations in which we may have orphaned models in the models directory.
         """
-        Scan the models directory for new and missing models.
 
-        New models will be added to the storage backend. Missing models
-        will be deleted.
-        """
-        defunct_models = set()
-        installed = set()
+        installed_model_paths = {
+            (self._app_config.models_path / x.path).resolve() for x in self.record_store.all_models()
+        }
 
-        with Chdir(self._app_config.models_path):
-            self._logger.info("Checking for models that have been moved or deleted from disk")
-            for model_config in self.record_store.all_models():
-                path = Path(model_config.path)
-                if not path.exists():
-                    self._logger.info(f"{model_config.name}: path {path.as_posix()} no longer exists. Unregistering")
-                    defunct_models.add(model_config.key)
-            for key in defunct_models:
-                self.unregister(key)
+        # The bool returned by this callback determines if the model is added to the list of models found by the search
+        def on_model_found(model_path: Path) -> bool:
+            resolved_path = model_path.resolve()
+            # Already registered models should be in the list of found models, but not re-registered.
+            if resolved_path in installed_model_paths:
+                return True
+            # Skip core models entirely - these aren't registered with the model manager.
+            if str(resolved_path).startswith(str(self.app_config.models_path / "core")):
+                return False
+            try:
+                model_id = self.register_path(model_path)
+                self._logger.info(f"Registered {model_path.name} with id {model_id}")
+            except DuplicateModelException:
+                # In case a duplicate models sneaks by, we will ignore this error - we "found" the model
+                pass
+            return True
 
-            self._logger.info(f"Scanning {self._app_config.models_path} for new and orphaned models")
-            for cur_base_model in BaseModelType:
-                for cur_model_type in ModelType:
-                    models_dir = self._app_config.models_path / Path(cur_base_model.value, cur_model_type.value)
-                    if not models_dir.exists():
-                        continue
-                    installed.update(self.scan_directory(models_dir))
-            self._logger.info(f"{len(installed)} new models registered; {len(defunct_models)} unregistered")
+        self._logger.info(f"Scanning {self._app_config.models_path} for orphaned models")
+        search = ModelSearch(on_model_found=on_model_found)
+        found_models = search.search(self._app_config.models_path)
+        self._logger.info(f"{len(found_models)} new models registered")
 
     def sync_model_path(self, key: str) -> AnyModelConfig:
         """
@@ -551,46 +552,24 @@ class ModelInstallService(ModelInstallServiceBase):
         May raise an UnknownModelException.
         """
         model = self.record_store.get_model(key)
-        old_path = Path(model.path).resolve()
-        models_dir = self.app_config.models_path.resolve()
+        models_dir = self.app_config.models_path
+        old_path = self.app_config.models_path / model.path
 
         if not old_path.is_relative_to(models_dir):
+            # The model is not in the models directory - we don't need to move it.
             return model
 
-        new_path = (models_dir / model.base.value / model.type.value / model.name).with_suffix(old_path.suffix)
+        new_path = models_dir / model.base.value / model.type.value / old_path.name
 
         if old_path == new_path or new_path.exists() and old_path == new_path.resolve():
             return model
 
         self._logger.info(f"Moving {model.name} to {new_path}.")
         new_path = self._move_model(old_path, new_path)
-        model.path = new_path.as_posix()
+        model.path = new_path.relative_to(models_dir).as_posix()
         self.record_store.update_model(key, ModelRecordChanges(path=model.path))
         return model
 
-    def _scan_register(self, model: Path) -> bool:
-        if model.resolve() in self._cached_model_paths:
-            return True
-        try:
-            id = self.register_path(model)
-            self.sync_model_path(id)  # possibly move it to right place in `models`
-            self._logger.info(f"Registered {model.name} with id {id}")
-            self._models_installed.add(id)
-        except DuplicateModelException:
-            pass
-        return True
-
-    def _scan_install(self, model: Path) -> bool:
-        if model in self._cached_model_paths:
-            return True
-        try:
-            id = self.install_path(model)
-            self._logger.info(f"Installed {model} with id {id}")
-            self._models_installed.add(id)
-        except DuplicateModelException:
-            pass
-        return True
-
     def _copy_model(self, old_path: Path, new_path: Path) -> Path:
         if old_path == new_path:
             return old_path
@@ -626,12 +605,19 @@ class ModelInstallService(ModelInstallServiceBase):
 
         model_path = model_path.resolve()
 
+        # Models in the Invoke-managed models dir should use relative paths.
+        if model_path.is_relative_to(self.app_config.models_path):
+            model_path = model_path.relative_to(self.app_config.models_path)
+
         info.path = model_path.as_posix()
 
-        # Checkpoints have a config file needed for conversion - resolve this to an absolute path
         if isinstance(info, CheckpointConfigBase):
-            legacy_conf = (self.app_config.legacy_conf_path / info.config_path).resolve()
-            info.config_path = legacy_conf.as_posix()
+            # Checkpoints have a config file needed for conversion. Same handling as the model weights - if it's in the
+            # invoke-managed legacy config dir, we use a relative path.
+            legacy_config_path = self.app_config.legacy_conf_path / info.config_path
+            if legacy_config_path.is_relative_to(self.app_config.legacy_conf_path):
+                legacy_config_path = legacy_config_path.relative_to(self.app_config.legacy_conf_path)
+            info.config_path = legacy_config_path.as_posix()
         self.record_store.add_model(info)
         return info.key
 
@@ -641,11 +627,10 @@ class ModelInstallService(ModelInstallServiceBase):
             self._next_job_id += 1
         return id
 
-    @staticmethod
-    def _guess_variant() -> Optional[ModelRepoVariant]:
+    def _guess_variant(self) -> Optional[ModelRepoVariant]:
         """Guess the best HuggingFace variant type to download."""
-        precision = choose_precision(choose_torch_device())
-        return ModelRepoVariant.FP16 if precision == "float16" else None
+        precision = TorchDevice.choose_torch_dtype()
+        return ModelRepoVariant.FP16 if precision == torch.float16 else None
 
     def _import_local_model(self, source: LocalModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
         return ModelInstallJob(
@@ -761,6 +746,8 @@ class ModelInstallService(ModelInstallServiceBase):
             self._download_cache[download_job.source] = install_job  # matches a download job to an install job
             install_job.download_parts.add(download_job)
 
+        # only start the jobs once install_job.download_parts is fully populated
+        for download_job in install_job.download_parts:
             self._download_queue.submit_download_job(
                 download_job,
                 on_start=self._download_started_callback,
@@ -769,6 +756,7 @@ class ModelInstallService(ModelInstallServiceBase):
                 on_error=self._download_error_callback,
                 on_cancelled=self._download_cancelled_callback,
             )
+
         return install_job
 
     def _stat_size(self, path: Path) -> int:
@@ -869,35 +857,17 @@ class ModelInstallService(ModelInstallServiceBase):
         job.status = InstallStatus.RUNNING
         self._logger.info(f"Model install started: {job.source}")
         if self._event_bus:
-            self._event_bus.emit_model_install_running(str(job.source))
+            self._event_bus.emit_model_install_started(job)
 
     def _signal_job_downloading(self, job: ModelInstallJob) -> None:
         if self._event_bus:
-            parts: List[Dict[str, str | int]] = [
-                {
-                    "url": str(x.source),
-                    "local_path": str(x.download_path),
-                    "bytes": x.bytes,
-                    "total_bytes": x.total_bytes,
-                }
-                for x in job.download_parts
-            ]
-            assert job.bytes is not None
-            assert job.total_bytes is not None
-            self._event_bus.emit_model_install_downloading(
-                str(job.source),
-                local_path=job.local_path.as_posix(),
-                parts=parts,
-                bytes=job.bytes,
-                total_bytes=job.total_bytes,
-                id=job.id,
-            )
+            self._event_bus.emit_model_install_download_progress(job)
 
     def _signal_job_downloads_done(self, job: ModelInstallJob) -> None:
         job.status = InstallStatus.DOWNLOADS_DONE
         self._logger.info(f"Model download complete: {job.source}")
         if self._event_bus:
-            self._event_bus.emit_model_install_downloads_done(str(job.source))
+            self._event_bus.emit_model_install_downloads_complete(job)
 
     def _signal_job_completed(self, job: ModelInstallJob) -> None:
         job.status = InstallStatus.COMPLETED
@@ -905,24 +875,19 @@ class ModelInstallService(ModelInstallServiceBase):
         self._logger.info(f"Model install complete: {job.source}")
         self._logger.debug(f"{job.local_path} registered key {job.config_out.key}")
         if self._event_bus:
-            assert job.local_path is not None
-            assert job.config_out is not None
-            key = job.config_out.key
-            self._event_bus.emit_model_install_completed(str(job.source), key, id=job.id)
+            self._event_bus.emit_model_install_complete(job)
 
     def _signal_job_errored(self, job: ModelInstallJob) -> None:
-        self._logger.info(f"Model install error: {job.source}, {job.error_type}\n{job.error}")
+        self._logger.error(f"Model install error: {job.source}\n{job.error_type}: {job.error}")
         if self._event_bus:
-            error_type = job.error_type
-            error = job.error
-            assert error_type is not None
-            assert error is not None
-            self._event_bus.emit_model_install_error(str(job.source), error_type, error, id=job.id)
+            assert job.error_type is not None
+            assert job.error is not None
+            self._event_bus.emit_model_install_error(job)
 
     def _signal_job_cancelled(self, job: ModelInstallJob) -> None:
         self._logger.info(f"Model install canceled: {job.source}")
         if self._event_bus:
-            self._event_bus.emit_model_install_cancelled(str(job.source), id=job.id)
+            self._event_bus.emit_model_install_cancelled(job)
 
     @staticmethod
     def get_fetcher_from_url(url: str) -> ModelMetadataFetchBase:

invokeai/app/services/model_load/model_load_base.py

@@ -4,7 +4,6 @@
 from abc import ABC, abstractmethod
 from typing import Optional
 
-from invokeai.app.services.shared.invocation_context import InvocationContextData
 from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
 from invokeai.backend.model_manager.load import LoadedModel
 from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
@@ -15,18 +14,12 @@ class ModelLoadServiceBase(ABC):
     """Wrapper around AnyModelLoader."""
 
     @abstractmethod
-    def load_model(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
+    def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
         """
         Given a model's configuration, load it and return the LoadedModel object.
 
         :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
         :param submodel: For main (pipeline models), the submodel to fetch.
-        :param context_data: Invocation context data used for event reporting
         """
 
     @property

invokeai/app/services/model_load/model_load_default.py

@@ -5,7 +5,6 @@ from typing import Optional, Type
 
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.shared.invocation_context import InvocationContextData
 from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
 from invokeai.backend.model_manager.load import (
     LoadedModel,
@@ -51,25 +50,18 @@ class ModelLoadService(ModelLoadServiceBase):
         """Return the checkpoint convert cache used by this loader."""
         return self._convert_cache
 
-    def load_model(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModel:
+    def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
         """
         Given a model's configuration, load it and return the LoadedModel object.
 
         :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
         :param submodel: For main (pipeline models), the submodel to fetch.
-        :param context: Invocation context used for event reporting
         """
-        if context_data:
-            self._emit_load_event(
-                context_data=context_data,
-                model_config=model_config,
-                submodel_type=submodel_type,
-            )
+
+        # We don't have an invoker during testing
+        # TODO(psyche): Mock this method on the invoker in the tests
+        if hasattr(self, "_invoker"):
+            self._invoker.services.events.emit_model_load_started(model_config, submodel_type)
 
         implementation, model_config, submodel_type = self._registry.get_implementation(model_config, submodel_type)  # type: ignore
         loaded_model: LoadedModel = implementation(
@@ -79,40 +71,7 @@ class ModelLoadService(ModelLoadServiceBase):
             convert_cache=self._convert_cache,
         ).load_model(model_config, submodel_type)
 
-        if context_data:
-            self._emit_load_event(
-                context_data=context_data,
-                model_config=model_config,
-                submodel_type=submodel_type,
-                loaded=True,
-            )
+        if hasattr(self, "_invoker"):
+            self._invoker.services.events.emit_model_load_complete(model_config, submodel_type)
+
         return loaded_model
-
-    def _emit_load_event(
-        self,
-        context_data: InvocationContextData,
-        model_config: AnyModelConfig,
-        loaded: Optional[bool] = False,
-        submodel_type: Optional[SubModelType] = None,
-    ) -> None:
-        if not self._invoker:
-            return
-
-        if not loaded:
-            self._invoker.services.events.emit_model_load_started(
-                queue_id=context_data.queue_item.queue_id,
-                queue_item_id=context_data.queue_item.item_id,
-                queue_batch_id=context_data.queue_item.batch_id,
-                graph_execution_state_id=context_data.queue_item.session_id,
-                model_config=model_config,
-                submodel_type=submodel_type,
-            )
-        else:
-            self._invoker.services.events.emit_model_load_completed(
-                queue_id=context_data.queue_item.queue_id,
-                queue_item_id=context_data.queue_item.item_id,
-                queue_batch_id=context_data.queue_item.batch_id,
-                graph_execution_state_id=context_data.queue_item.session_id,
-                model_config=model_config,
-                submodel_type=submodel_type,
-            )

invokeai/app/services/model_manager/model_manager_default.py

@@ -1,12 +1,14 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
 """Implementation of ModelManagerServiceBase."""
 
+from typing import Optional
+
 import torch
 from typing_extensions import Self
 
 from invokeai.app.services.invoker import Invoker
 from invokeai.backend.model_manager.load import ModelCache, ModelConvertCache, ModelLoaderRegistry
-from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.logging import InvokeAILogger
 
 from ..config import InvokeAIAppConfig
@@ -67,7 +69,7 @@ class ModelManagerService(ModelManagerServiceBase):
         model_record_service: ModelRecordServiceBase,
         download_queue: DownloadQueueServiceBase,
         events: EventServiceBase,
-        execution_device: torch.device = choose_torch_device(),
+        execution_device: Optional[torch.device] = None,
     ) -> Self:
         """
         Construct the model manager service instance.
@@ -80,8 +82,9 @@ class ModelManagerService(ModelManagerServiceBase):
         ram_cache = ModelCache(
             max_cache_size=app_config.ram,
             max_vram_cache_size=app_config.vram,
+            lazy_offloading=app_config.lazy_offload,
             logger=logger,
-            execution_device=execution_device,
+            execution_device=execution_device or TorchDevice.choose_torch_device(),
         )
         convert_cache = ModelConvertCache(cache_path=app_config.convert_cache_path, max_size=app_config.convert_cache)
         loader = ModelLoadService(

invokeai/app/services/object_serializer/object_serializer_disk.py

@@ -1,6 +1,6 @@
+import shutil
 import tempfile
 import typing
-from dataclasses import dataclass
 from pathlib import Path
 from typing import TYPE_CHECKING, Optional, TypeVar
 
@@ -17,12 +17,6 @@ if TYPE_CHECKING:
 T = TypeVar("T")
 
 
-@dataclass
-class DeleteAllResult:
-    deleted_count: int
-    freed_space_bytes: float
-
-
 class ObjectSerializerDisk(ObjectSerializerBase[T]):
     """Disk-backed storage for arbitrary python objects. Serialization is handled by `torch.save` and `torch.load`.
 
@@ -35,6 +29,12 @@ class ObjectSerializerDisk(ObjectSerializerBase[T]):
         self._ephemeral = ephemeral
         self._base_output_dir = output_dir
         self._base_output_dir.mkdir(parents=True, exist_ok=True)
+
+        if self._ephemeral:
+            # Remove dangling tempdirs that might have been left over from an earlier unplanned shutdown.
+            for temp_dir in filter(Path.is_dir, self._base_output_dir.glob("tmp*")):
+                shutil.rmtree(temp_dir)
+
         # Must specify `ignore_cleanup_errors` to avoid fatal errors during cleanup on Windows
         self._tempdir = (
             tempfile.TemporaryDirectory(dir=self._base_output_dir, ignore_cleanup_errors=True) if ephemeral else None

invokeai/app/services/session_processor/session_processor_base.py

@@ -1,6 +1,49 @@
 from abc import ABC, abstractmethod
+from threading import Event
+from typing import Optional, Protocol
 
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput
+from invokeai.app.services.invocation_services import InvocationServices
 from invokeai.app.services.session_processor.session_processor_common import SessionProcessorStatus
+from invokeai.app.services.session_queue.session_queue_common import SessionQueueItem
+from invokeai.app.util.profiler import Profiler
+
+
+class SessionRunnerBase(ABC):
+    """
+    Base class for session runner.
+    """
+
+    @abstractmethod
+    def start(self, services: InvocationServices, cancel_event: Event, profiler: Optional[Profiler] = None) -> None:
+        """Starts the session runner.
+
+        Args:
+            services: The invocation services.
+            cancel_event: The cancel event.
+            profiler: The profiler to use for session profiling via cProfile. Omit to disable profiling. Basic session
+                stats will be still be recorded and logged when profiling is disabled.
+        """
+        pass
+
+    @abstractmethod
+    def run(self, queue_item: SessionQueueItem) -> None:
+        """Runs a session.
+
+        Args:
+            queue_item: The session to run.
+        """
+        pass
+
+    @abstractmethod
+    def run_node(self, invocation: BaseInvocation, queue_item: SessionQueueItem) -> None:
+        """Run a single node in the graph.
+
+        Args:
+            invocation: The invocation to run.
+            queue_item: The session queue item.
+        """
+        pass
 
 
 class SessionProcessorBase(ABC):
@@ -26,3 +69,85 @@ class SessionProcessorBase(ABC):
     def get_status(self) -> SessionProcessorStatus:
         """Gets the status of the session processor"""
         pass
+
+
+class OnBeforeRunNode(Protocol):
+    def __call__(self, invocation: BaseInvocation, queue_item: SessionQueueItem) -> None:
+        """Callback to run before executing a node.
+
+        Args:
+            invocation: The invocation that will be executed.
+            queue_item: The session queue item.
+        """
+        ...
+
+
+class OnAfterRunNode(Protocol):
+    def __call__(self, invocation: BaseInvocation, queue_item: SessionQueueItem, output: BaseInvocationOutput) -> None:
+        """Callback to run before executing a node.
+
+        Args:
+            invocation: The invocation that was executed.
+            queue_item: The session queue item.
+        """
+        ...
+
+
+class OnNodeError(Protocol):
+    def __call__(
+        self,
+        invocation: BaseInvocation,
+        queue_item: SessionQueueItem,
+        error_type: str,
+        error_message: str,
+        error_traceback: str,
+    ) -> None:
+        """Callback to run when a node has an error.
+
+        Args:
+            invocation: The invocation that errored.
+            queue_item: The session queue item.
+            error_type: The type of error, e.g. "ValueError".
+            error_message: The error message, e.g. "Invalid value".
+            error_traceback: The stringified error traceback.
+        """
+        ...
+
+
+class OnBeforeRunSession(Protocol):
+    def __call__(self, queue_item: SessionQueueItem) -> None:
+        """Callback to run before executing a session.
+
+        Args:
+            queue_item: The session queue item.
+        """
+        ...
+
+
+class OnAfterRunSession(Protocol):
+    def __call__(self, queue_item: SessionQueueItem) -> None:
+        """Callback to run after executing a session.
+
+        Args:
+            queue_item: The session queue item.
+        """
+        ...
+
+
+class OnNonFatalProcessorError(Protocol):
+    def __call__(
+        self,
+        queue_item: Optional[SessionQueueItem],
+        error_type: str,
+        error_message: str,
+        error_traceback: str,
+    ) -> None:
+        """Callback to run when a non-fatal error occurs in the processor.
+
+        Args:
+            queue_item: The session queue item, if one was being executed when the error occurred.
+            error_type: The type of error, e.g. "ValueError".
+            error_message: The error message, e.g. "Invalid value".
+            error_traceback: The stringified error traceback.
+        """
+        ...