Update invokeai_version.py

There are unresolved platform-specific issues with this component, and its utility is debatable.

Should be easy to just revert this commit to add it back in the future if desired.

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 / FAQ
-
-Please check out our **[FAQ](https://invoke-ai.github.io/InvokeAI/help/FAQ/)** 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.
-

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.

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/installation/010_INSTALL_AUTOMATED.md

@@ -1,8 +1,10 @@
-# Automatic Install
+# Automatic Install & Updates
 
-The installer is used for both new installs and updates.
+**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.
 
-Both release and pre-release versions can be installed using it. It also supports install a wheel if needed.
+Both release and pre-release versions can be installed using the installer. It also supports install through a wheel if needed.
 
 Be sure to review the [installation requirements] and ensure your system has everything it needs to install Invoke.
 

docs/installation/INSTALLATION.md

@@ -1,4 +1,4 @@
-# Installation Overview
+# Installation and Updating Overview
 
 Before installing, review the [installation requirements] to ensure your system is set up properly.
 
@@ -6,14 +6,21 @@ See the [FAQ] for frequently-encountered installation issues.
 
 If you need more help, join our [discord] or [create an issue].
 
-<h2>Automatic Install</h2>
+<h2>Automatic Install & Updates </h2>
 
 ✅ The automatic install is the best way to run InvokeAI. Check out the [installation guide] to get started.
 
+⬆️ The same installer is also the best way to update InvokeAI - Simply rerun it for the same folder you installed to.
+
+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].
 
+Updates are managed by reinstalling the latest version through PyPi.
+
 <h2>Developer Install</h2>
 
 If you want to contribute to InvokeAI, consult the [developer install guide].

invokeai/app/api_app.py

@@ -28,7 +28,7 @@ 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.session_processor.session_processor_common import ProgressImage
-from invokeai.backend.util.devices import get_torch_device_name
+from invokeai.backend.util.devices import TorchDevice
 
 from ..backend.util.logging import InvokeAILogger
 from .api.dependencies import ApiDependencies
@@ -63,7 +63,7 @@ logger = InvokeAILogger.get_logger(config=app_config)
 mimetypes.add_type("application/javascript", ".js")
 mimetypes.add_type("text/css", ".css")
 
-torch_device_name = get_torch_device_name()
+torch_device_name = TorchDevice.get_torch_device_name()
 logger.info(f"Using torch device: {torch_device_name}")
 
 

invokeai/app/invocations/compel.py

@@ -24,7 +24,7 @@ from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     ConditioningFieldData,
     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
@@ -99,7 +99,7 @@ class CompelInvocation(BaseInvocation):
                 tokenizer=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,
             )
 
@@ -193,7 +193,7 @@ class SDXLPromptInvocationBase:
                 tokenizer=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,

invokeai/app/invocations/controlnet_image_processors.py

@@ -35,22 +35,16 @@ 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):
@@ -171,13 +165,13 @@ 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 +199,13 @@ 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 +228,13 @@ 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 +250,13 @@ 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 +273,15 @@ 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 +304,13 @@ 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 +321,13 @@ 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 +344,13 @@ 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 +371,13 @@ 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 +401,7 @@ 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 +417,15 @@ 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 +444,7 @@ 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 +452,8 @@ 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 +473,7 @@ 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 +513,13 @@ 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 +560,12 @@ 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 +592,7 @@ 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 +600,7 @@ 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 +615,7 @@ 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 +623,7 @@ 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 +635,27 @@ 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/ip_adapter.py

@@ -4,20 +4,8 @@ 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,
-    TensorField,
-    UIType,
-)
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from invokeai.app.invocations.fields import FieldDescriptions, Input, 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
@@ -36,6 +24,7 @@ class IPAdapterField(BaseModel):
     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 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)"
     )
@@ -69,7 +58,7 @@ class IPAdapterOutput(BaseInvocationOutput):
 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="1.3.0")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.4.0")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
@@ -90,6 +79,9 @@ class IPAdapterInvocation(BaseInvocation):
     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)"
     )
@@ -124,12 +116,32 @@ class IPAdapterInvocation(BaseInvocation):
 
         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,

invokeai/app/invocations/latent.py

@@ -3,7 +3,7 @@ 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
@@ -11,7 +11,6 @@ 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
@@ -21,9 +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
@@ -51,6 +53,7 @@ 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 (
@@ -72,15 +75,12 @@ from ...backend.stable_diffusion.diffusers_pipeline import (
     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 ...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),
         )
 
@@ -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,
@@ -478,9 +523,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
             )
 
         if is_sdxl:
-            return SDXLConditioningInfo(
-                embeds=text_embedding, pooled_embeds=pooled_embedding, add_time_ids=add_time_ids
-            ), regions
+            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(
@@ -520,6 +566,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
             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,
@@ -682,6 +733,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 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),
@@ -776,7 +828,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         denoising_start: float,
         denoising_end: float,
         seed: int,
-    ) -> Tuple[int, List[int], 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")
@@ -804,13 +856,15 @@ class DenoiseLatentsInvocation(BaseInvocation):
         timesteps = timesteps[t_start_idx : t_start_idx + t_end_idx]
         num_inference_steps = len(timesteps) // scheduler.order
 
-        scheduler_step_kwargs = {}
+        scheduler_step_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 = {"generator": torch.Generator(device=device).manual_seed(seed ^ 0xFFFFFFFF)}
+            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
 
@@ -959,9 +1013,7 @@ 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=None)
@@ -1028,9 +1080,7 @@ 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
@@ -1042,9 +1092,7 @@ 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)
 
@@ -1083,9 +1131,7 @@ 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),
@@ -1096,9 +1142,8 @@ 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)
@@ -1125,8 +1170,7 @@ 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(
@@ -1138,9 +1182,7 @@ 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)
@@ -1272,8 +1314,7 @@ 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?
@@ -1326,9 +1367,8 @@ 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)

invokeai/app/invocations/mask.py

@@ -1,7 +1,8 @@
+import numpy as np
 import torch
 
-from invokeai.app.invocations.baseinvocation import BaseInvocation, InvocationContext, invocation
-from invokeai.app.invocations.fields import InputField, TensorField, WithMetadata
+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
 
 
@@ -34,3 +35,86 @@ class RectangleMaskInvocation(BaseInvocation, WithMetadata):
             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

@@ -3,7 +3,6 @@ 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.fields import (
     FieldDescriptions,
     ImageField,
@@ -14,6 +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__
 
@@ -36,6 +36,7 @@ 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/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/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.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):

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/config/config_default.py

@@ -27,12 +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:
@@ -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`
@@ -370,6 +370,9 @@ 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":
@@ -392,6 +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.
 
@@ -418,17 +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

@@ -318,10 +318,8 @@ 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(".."):
@@ -419,6 +417,26 @@ 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/model_install/model_install_default.py

@@ -3,7 +3,6 @@
 import locale
 import os
 import re
-import signal
 import threading
 import time
 from hashlib import sha256
@@ -13,6 +12,7 @@ from shutil import copyfile, copytree, move, rmtree
 from tempfile import mkdtemp
 from typing import Any, Dict, List, Optional, Union
 
+import torch
 import yaml
 from huggingface_hub import HfFolder
 from pydantic.networks import AnyHttpUrl
@@ -42,7 +42,8 @@ from invokeai.backend.model_manager.metadata.metadata_base import HuggingFaceMet
 from invokeai.backend.model_manager.probe import ModelProbe
 from invokeai.backend.model_manager.search import ModelSearch
 from invokeai.backend.util import InvokeAILogger
-from invokeai.backend.util.devices import choose_precision, choose_torch_device
+from invokeai.backend.util.catch_sigint import catch_sigint
+from invokeai.backend.util.devices import TorchDevice
 
 from .model_install_base import (
     MODEL_SOURCE_TO_TYPE_MAP,
@@ -111,17 +112,6 @@ 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")
@@ -131,7 +121,8 @@ class ModelInstallService(ModelInstallServiceBase):
             # 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:
-                self._register_orphaned_models()
+                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
@@ -634,11 +625,10 @@ 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(
@@ -754,6 +744,8 @@ 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,
@@ -762,6 +754,7 @@ 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:

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.
@@ -82,7 +84,7 @@ class ModelManagerService(ModelManagerServiceBase):
             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/util/controlnet_utils.py

@@ -1,13 +1,21 @@
-from typing import Union
+from typing import Any, Literal, Union
 
 import cv2
 import numpy as np
 import torch
-from controlnet_aux.util import HWC3
-from diffusers.utils import PIL_INTERPOLATION
 from einops import rearrange
 from PIL import Image
 
+from invokeai.backend.image_util.util import nms, normalize_image_channel_count
+
+CONTROLNET_RESIZE_VALUES = Literal[
+    "just_resize",
+    "crop_resize",
+    "fill_resize",
+    "just_resize_simple",
+]
+CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
+
 ###################################################################
 # Copy of scripts/lvminthin.py from Mikubill/sd-webui-controlnet
 ###################################################################
@@ -68,17 +76,6 @@ def lvmin_thin(x, prunings=True):
     return y
 
 
-def nake_nms(x):
-    f1 = np.array([[0, 0, 0], [1, 1, 1], [0, 0, 0]], dtype=np.uint8)
-    f2 = np.array([[0, 1, 0], [0, 1, 0], [0, 1, 0]], dtype=np.uint8)
-    f3 = np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]], dtype=np.uint8)
-    f4 = np.array([[0, 0, 1], [0, 1, 0], [1, 0, 0]], dtype=np.uint8)
-    y = np.zeros_like(x)
-    for f in [f1, f2, f3, f4]:
-        np.putmask(y, cv2.dilate(x, kernel=f) == x, x)
-    return y
-
-
 ################################################################################
 # copied from Mikubill/sd-webui-controlnet external_code.py and modified for InvokeAI
 ################################################################################
@@ -134,98 +131,122 @@ def pixel_perfect_resolution(
     return int(np.round(estimation))
 
 
+def clone_contiguous(x: np.ndarray[Any, Any]) -> np.ndarray[Any, Any]:
+    """Get a memory-contiguous clone of the given numpy array, as a safety measure and to improve computation efficiency."""
+    return np.ascontiguousarray(x).copy()
+
+
+def np_img_to_torch(np_img: np.ndarray[Any, Any], device: torch.device) -> torch.Tensor:
+    """Convert a numpy image to a PyTorch tensor. The image is normalized to 0-1, rearranged to BCHW format and sent to
+    the specified device."""
+
+    torch_img = torch.from_numpy(np_img)
+    normalized = torch_img.float() / 255.0
+    bchw = rearrange(normalized, "h w c -> 1 c h w")
+    on_device = bchw.to(device)
+    return on_device.clone()
+
+
+def heuristic_resize(np_img: np.ndarray[Any, Any], size: tuple[int, int]) -> np.ndarray[Any, Any]:
+    """Resizes an image using a heuristic to choose the best resizing strategy.
+
+    - If the image appears to be an edge map, special handling will be applied to ensure the edges are not distorted.
+    - Single-pixel edge maps use NMS and thinning to keep the edges as single-pixel lines.
+    - Low-color-count images are resized with nearest-neighbor to preserve color information (for e.g. segmentation maps).
+    - The alpha channel is handled separately to ensure it is resized correctly.
+
+    Args:
+        np_img (np.ndarray): The input image.
+        size (tuple[int, int]): The target size for the image.
+
+    Returns:
+        np.ndarray: The resized image.
+
+    Adapted from https://github.com/Mikubill/sd-webui-controlnet.
+    """
+
+    # Return early if the image is already at the requested size
+    if np_img.shape[0] == size[1] and np_img.shape[1] == size[0]:
+        return np_img
+
+    # If the image has an alpha channel, separate it for special handling later.
+    inpaint_mask = None
+    if np_img.ndim == 3 and np_img.shape[2] == 4:
+        inpaint_mask = np_img[:, :, 3]
+        np_img = np_img[:, :, 0:3]
+
+    new_size_is_smaller = (size[0] * size[1]) < (np_img.shape[0] * np_img.shape[1])
+    new_size_is_bigger = (size[0] * size[1]) > (np_img.shape[0] * np_img.shape[1])
+    unique_color_count = np.unique(np_img.reshape(-1, np_img.shape[2]), axis=0).shape[0]
+    is_one_pixel_edge = False
+    is_binary = False
+
+    if unique_color_count == 2:
+        # If the image has only two colors, it is likely binary. Check if the image has one-pixel edges.
+        is_binary = np.min(np_img) < 16 and np.max(np_img) > 240
+        if is_binary:
+            eroded = cv2.erode(np_img, np.ones(shape=(3, 3), dtype=np.uint8), iterations=1)
+            dilated = cv2.dilate(eroded, np.ones(shape=(3, 3), dtype=np.uint8), iterations=1)
+            one_pixel_edge_count = np.where(dilated < np_img)[0].shape[0]
+            all_edge_count = np.where(np_img > 127)[0].shape[0]
+            is_one_pixel_edge = one_pixel_edge_count * 2 > all_edge_count
+
+    if 2 < unique_color_count < 200:
+        # With a low color count, we assume this is a map where exact colors are important. Near-neighbor preserves
+        # the colors as needed.
+        interpolation = cv2.INTER_NEAREST
+    elif new_size_is_smaller:
+        # This works best for downscaling
+        interpolation = cv2.INTER_AREA
+    else:
+        # Fall back for other cases
+        interpolation = cv2.INTER_CUBIC  # Must be CUBIC because we now use nms. NEVER CHANGE THIS
+
+    # This may be further transformed depending on the binary nature of the image.
+    resized = cv2.resize(np_img, size, interpolation=interpolation)
+
+    if inpaint_mask is not None:
+        # Resize the inpaint mask to match the resized image using the same interpolation method.
+        inpaint_mask = cv2.resize(inpaint_mask, size, interpolation=interpolation)
+
+    # If the image is binary, we will perform some additional processing to ensure the edges are preserved.
+    if is_binary:
+        resized = np.mean(resized.astype(np.float32), axis=2).clip(0, 255).astype(np.uint8)
+        if is_one_pixel_edge:
+            # Use NMS and thinning to keep the edges as single-pixel lines.
+            resized = nms(resized)
+            _, resized = cv2.threshold(resized, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+            resized = lvmin_thin(resized, prunings=new_size_is_bigger)
+        else:
+            _, resized = cv2.threshold(resized, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+        resized = np.stack([resized] * 3, axis=2)
+
+    # Restore the alpha channel if it was present.
+    if inpaint_mask is not None:
+        inpaint_mask = (inpaint_mask > 127).astype(np.float32) * 255.0
+        inpaint_mask = inpaint_mask[:, :, None].clip(0, 255).astype(np.uint8)
+        resized = np.concatenate([resized, inpaint_mask], axis=2)
+
+    return resized
+
+
 ###########################################################################
 # Copied from detectmap_proc method in scripts/detectmap_proc.py in Mikubill/sd-webui-controlnet
 #    modified for InvokeAI
 ###########################################################################
-# def detectmap_proc(detected_map, module, resize_mode, h, w):
-def np_img_resize(np_img: np.ndarray, resize_mode: str, h: int, w: int, device: torch.device = torch.device("cpu")):
-    # if 'inpaint' in module:
-    #     np_img = np_img.astype(np.float32)
-    # else:
-    #     np_img = HWC3(np_img)
-    np_img = HWC3(np_img)
+def np_img_resize(
+    np_img: np.ndarray,
+    resize_mode: CONTROLNET_RESIZE_VALUES,
+    h: int,
+    w: int,
+    device: torch.device = torch.device("cpu"),
+) -> tuple[torch.Tensor, np.ndarray[Any, Any]]:
+    np_img = normalize_image_channel_count(np_img)
 
-    def safe_numpy(x):
-        # A very safe method to make sure that Apple/Mac works
-        y = x
-
-        # below is very boring but do not change these. If you change these Apple or Mac may fail.
-        y = y.copy()
-        y = np.ascontiguousarray(y)
-        y = y.copy()
-        return y
-
-    def get_pytorch_control(x):
-        # A very safe method to make sure that Apple/Mac works
-        y = x
-
-        # below is very boring but do not change these. If you change these Apple or Mac may fail.
-        y = torch.from_numpy(y)
-        y = y.float() / 255.0
-        y = rearrange(y, "h w c -> 1 c h w")
-        y = y.clone()
-        # y = y.to(devices.get_device_for("controlnet"))
-        y = y.to(device)
-        y = y.clone()
-        return y
-
-    def high_quality_resize(x: np.ndarray, size):
-        # Written by lvmin
-        # Super high-quality control map up-scaling, considering binary, seg, and one-pixel edges
-        inpaint_mask = None
-        if x.ndim == 3 and x.shape[2] == 4:
-            inpaint_mask = x[:, :, 3]
-            x = x[:, :, 0:3]
-
-        new_size_is_smaller = (size[0] * size[1]) < (x.shape[0] * x.shape[1])
-        new_size_is_bigger = (size[0] * size[1]) > (x.shape[0] * x.shape[1])
-        unique_color_count = np.unique(x.reshape(-1, x.shape[2]), axis=0).shape[0]
-        is_one_pixel_edge = False
-        is_binary = False
-        if unique_color_count == 2:
-            is_binary = np.min(x) < 16 and np.max(x) > 240
-            if is_binary:
-                xc = x
-                xc = cv2.erode(xc, np.ones(shape=(3, 3), dtype=np.uint8), iterations=1)
-                xc = cv2.dilate(xc, np.ones(shape=(3, 3), dtype=np.uint8), iterations=1)
-                one_pixel_edge_count = np.where(xc < x)[0].shape[0]
-                all_edge_count = np.where(x > 127)[0].shape[0]
-                is_one_pixel_edge = one_pixel_edge_count * 2 > all_edge_count
-
-        if 2 < unique_color_count < 200:
-            interpolation = cv2.INTER_NEAREST
-        elif new_size_is_smaller:
-            interpolation = cv2.INTER_AREA
-        else:
-            interpolation = cv2.INTER_CUBIC  # Must be CUBIC because we now use nms. NEVER CHANGE THIS
-
-        y = cv2.resize(x, size, interpolation=interpolation)
-        if inpaint_mask is not None:
-            inpaint_mask = cv2.resize(inpaint_mask, size, interpolation=interpolation)
-
-        if is_binary:
-            y = np.mean(y.astype(np.float32), axis=2).clip(0, 255).astype(np.uint8)
-            if is_one_pixel_edge:
-                y = nake_nms(y)
-                _, y = cv2.threshold(y, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
-                y = lvmin_thin(y, prunings=new_size_is_bigger)
-            else:
-                _, y = cv2.threshold(y, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
-            y = np.stack([y] * 3, axis=2)
-
-        if inpaint_mask is not None:
-            inpaint_mask = (inpaint_mask > 127).astype(np.float32) * 255.0
-            inpaint_mask = inpaint_mask[:, :, None].clip(0, 255).astype(np.uint8)
-            y = np.concatenate([y, inpaint_mask], axis=2)
-
-        return y
-
-    # if resize_mode == external_code.ResizeMode.RESIZE:
     if resize_mode == "just_resize":  # RESIZE
-        np_img = high_quality_resize(np_img, (w, h))
-        np_img = safe_numpy(np_img)
-        return get_pytorch_control(np_img), np_img
+        np_img = heuristic_resize(np_img, (w, h))
+        np_img = clone_contiguous(np_img)
+        return np_img_to_torch(np_img, device), np_img
 
     old_h, old_w, _ = np_img.shape
     old_w = float(old_w)
@@ -236,7 +257,6 @@ def np_img_resize(np_img: np.ndarray, resize_mode: str, h: int, w: int, device:
     def safeint(x: Union[int, float]) -> int:
         return int(np.round(x))
 
-    # if resize_mode == external_code.ResizeMode.OUTER_FIT:
     if resize_mode == "fill_resize":  # OUTER_FIT
         k = min(k0, k1)
         borders = np.concatenate([np_img[0, :, :], np_img[-1, :, :], np_img[:, 0, :], np_img[:, -1, :]], axis=0)
@@ -245,23 +265,23 @@ def np_img_resize(np_img: np.ndarray, resize_mode: str, h: int, w: int, device:
             # Inpaint hijack
             high_quality_border_color[3] = 255
         high_quality_background = np.tile(high_quality_border_color[None, None], [h, w, 1])
-        np_img = high_quality_resize(np_img, (safeint(old_w * k), safeint(old_h * k)))
+        np_img = heuristic_resize(np_img, (safeint(old_w * k), safeint(old_h * k)))
         new_h, new_w, _ = np_img.shape
         pad_h = max(0, (h - new_h) // 2)
         pad_w = max(0, (w - new_w) // 2)
         high_quality_background[pad_h : pad_h + new_h, pad_w : pad_w + new_w] = np_img
         np_img = high_quality_background
-        np_img = safe_numpy(np_img)
-        return get_pytorch_control(np_img), np_img
+        np_img = clone_contiguous(np_img)
+        return np_img_to_torch(np_img, device), np_img
     else:  # resize_mode == "crop_resize"  (INNER_FIT)
         k = max(k0, k1)
-        np_img = high_quality_resize(np_img, (safeint(old_w * k), safeint(old_h * k)))
+        np_img = heuristic_resize(np_img, (safeint(old_w * k), safeint(old_h * k)))
         new_h, new_w, _ = np_img.shape
         pad_h = max(0, (new_h - h) // 2)
         pad_w = max(0, (new_w - w) // 2)
         np_img = np_img[pad_h : pad_h + h, pad_w : pad_w + w]
-        np_img = safe_numpy(np_img)
-        return get_pytorch_control(np_img), np_img
+        np_img = clone_contiguous(np_img)
+        return np_img_to_torch(np_img, device), np_img
 
 
 def prepare_control_image(
@@ -269,12 +289,12 @@ def prepare_control_image(
     width: int,
     height: int,
     num_channels: int = 3,
-    device="cuda",
-    dtype=torch.float16,
-    do_classifier_free_guidance=True,
-    control_mode="balanced",
-    resize_mode="just_resize_simple",
-):
+    device: str = "cuda",
+    dtype: torch.dtype = torch.float16,
+    control_mode: CONTROLNET_MODE_VALUES = "balanced",
+    resize_mode: CONTROLNET_RESIZE_VALUES = "just_resize_simple",
+    do_classifier_free_guidance: bool = True,
+) -> torch.Tensor:
     """Pre-process images for ControlNets or T2I-Adapters.
 
     Args:
@@ -292,26 +312,15 @@ def prepare_control_image(
         resize_mode (str, optional): Defaults to "just_resize_simple".
 
     Raises:
-        NotImplementedError: If resize_mode == "crop_resize_simple".
-        NotImplementedError: If resize_mode == "fill_resize_simple".
         ValueError: If `resize_mode` is not recognized.
         ValueError: If `num_channels` is out of range.
 
     Returns:
         torch.Tensor: The pre-processed input tensor.
     """
-    if (
-        resize_mode == "just_resize_simple"
-        or resize_mode == "crop_resize_simple"
-        or resize_mode == "fill_resize_simple"
-    ):
+    if resize_mode == "just_resize_simple":
         image = image.convert("RGB")
-        if resize_mode == "just_resize_simple":
-            image = image.resize((width, height), resample=PIL_INTERPOLATION["lanczos"])
-        elif resize_mode == "crop_resize_simple":
-            raise NotImplementedError(f"prepare_control_image is not implemented for resize_mode='{resize_mode}'.")
-        elif resize_mode == "fill_resize_simple":
-            raise NotImplementedError(f"prepare_control_image is not implemented for resize_mode='{resize_mode}'.")
+        image = image.resize((width, height), resample=Image.LANCZOS)
         nimage = np.array(image)
         nimage = nimage[None, :]
         nimage = np.concatenate([nimage], axis=0)
@@ -328,8 +337,7 @@ def prepare_control_image(
             resize_mode=resize_mode,
             h=height,
             w=width,
-            # device=torch.device('cpu')
-            device=device,
+            device=torch.device(device),
         )
     else:
         raise ValueError(f"Unsupported resize_mode: '{resize_mode}'.")

invokeai/backend/image_util/depth_anything/__init__.py

@@ -13,7 +13,7 @@ from invokeai.app.services.config.config_default import get_config
 from invokeai.app.util.download_with_progress import download_with_progress_bar
 from invokeai.backend.image_util.depth_anything.model.dpt import DPT_DINOv2
 from invokeai.backend.image_util.depth_anything.utilities.util import NormalizeImage, PrepareForNet, Resize
-from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.logging import InvokeAILogger
 
 config = get_config()
@@ -56,7 +56,7 @@ class DepthAnythingDetector:
     def __init__(self) -> None:
         self.model = None
         self.model_size: Union[Literal["large", "base", "small"], None] = None
-        self.device = choose_torch_device()
+        self.device = TorchDevice.choose_torch_device()
 
     def load_model(self, model_size: Literal["large", "base", "small"] = "small"):
         DEPTH_ANYTHING_MODEL_PATH = config.models_path / DEPTH_ANYTHING_MODELS[model_size]["local"]
@@ -81,7 +81,7 @@ class DepthAnythingDetector:
             self.model.load_state_dict(torch.load(DEPTH_ANYTHING_MODEL_PATH.as_posix(), map_location="cpu"))
             self.model.eval()
 
-        self.model.to(choose_torch_device())
+        self.model.to(self.device)
         return self.model
 
     def __call__(self, image: Image.Image, resolution: int = 512) -> Image.Image:
@@ -94,7 +94,7 @@ class DepthAnythingDetector:
 
         image_height, image_width = np_image.shape[:2]
         np_image = transform({"image": np_image})["image"]
-        tensor_image = torch.from_numpy(np_image).unsqueeze(0).to(choose_torch_device())
+        tensor_image = torch.from_numpy(np_image).unsqueeze(0).to(self.device)
 
         with torch.no_grad():
             depth = self.model(tensor_image)

invokeai/backend/image_util/dw_openpose/wholebody.py

@@ -7,7 +7,7 @@ import onnxruntime as ort
 
 from invokeai.app.services.config.config_default import get_config
 from invokeai.app.util.download_with_progress import download_with_progress_bar
-from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.devices import TorchDevice
 
 from .onnxdet import inference_detector
 from .onnxpose import inference_pose
@@ -28,9 +28,9 @@ config = get_config()
 
 class Wholebody:
     def __init__(self):
-        device = choose_torch_device()
+        device = TorchDevice.choose_torch_device()
 
-        providers = ["CUDAExecutionProvider"] if device == "cuda" else ["CPUExecutionProvider"]
+        providers = ["CUDAExecutionProvider"] if device.type == "cuda" else ["CPUExecutionProvider"]
 
         DET_MODEL_PATH = config.models_path / DWPOSE_MODELS["yolox_l.onnx"]["local"]
         download_with_progress_bar("yolox_l.onnx", DWPOSE_MODELS["yolox_l.onnx"]["url"], DET_MODEL_PATH)

invokeai/backend/image_util/hed.py

@@ -8,7 +8,7 @@ from huggingface_hub import hf_hub_download
 from PIL import Image
 
 from invokeai.backend.image_util.util import (
-    non_maximum_suppression,
+    nms,
     normalize_image_channel_count,
     np_to_pil,
     pil_to_np,
@@ -134,7 +134,7 @@ class HEDProcessor:
         detected_map = cv2.resize(detected_map, (width, height), interpolation=cv2.INTER_LINEAR)
 
         if scribble:
-            detected_map = non_maximum_suppression(detected_map, 127, 3.0)
+            detected_map = nms(detected_map, 127, 3.0)
             detected_map = cv2.GaussianBlur(detected_map, (0, 0), 3.0)
             detected_map[detected_map > 4] = 255
             detected_map[detected_map < 255] = 0

invokeai/backend/image_util/infill_methods/lama.py

@@ -8,7 +8,7 @@ from PIL import Image
 import invokeai.backend.util.logging as logger
 from invokeai.app.services.config.config_default import get_config
 from invokeai.app.util.download_with_progress import download_with_progress_bar
-from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.devices import TorchDevice
 
 
 def norm_img(np_img):
@@ -29,7 +29,7 @@ def load_jit_model(url_or_path, device):
 
 class LaMA:
     def __call__(self, input_image: Image.Image, *args: Any, **kwds: Any) -> Any:
-        device = choose_torch_device()
+        device = TorchDevice.choose_torch_device()
         model_location = get_config().models_path / "core/misc/lama/lama.pt"
 
         if not model_location.exists():

invokeai/backend/image_util/realesrgan/realesrgan.py

@@ -11,7 +11,7 @@ from cv2.typing import MatLike
 from tqdm import tqdm
 
 from invokeai.backend.image_util.basicsr.rrdbnet_arch import RRDBNet
-from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.devices import TorchDevice
 
 """
 Adapted from https://github.com/xinntao/Real-ESRGAN/blob/master/realesrgan/utils.py
@@ -65,7 +65,7 @@ class RealESRGAN:
         self.pre_pad = pre_pad
         self.mod_scale: Optional[int] = None
         self.half = half
-        self.device = choose_torch_device()
+        self.device = TorchDevice.choose_torch_device()
 
         loadnet = torch.load(model_path, map_location=torch.device("cpu"))
 

invokeai/backend/image_util/safety_checker.py

@@ -13,7 +13,7 @@ from transformers import AutoFeatureExtractor
 
 import invokeai.backend.util.logging as logger
 from invokeai.app.services.config.config_default import get_config
-from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.silence_warnings import SilenceWarnings
 
 CHECKER_PATH = "core/convert/stable-diffusion-safety-checker"
@@ -51,7 +51,7 @@ class SafetyChecker:
         cls._load_safety_checker()
         if cls.safety_checker is None or cls.feature_extractor is None:
             return False
-        device = choose_torch_device()
+        device = TorchDevice.choose_torch_device()
         features = cls.feature_extractor([image], return_tensors="pt")
         features.to(device)
         cls.safety_checker.to(device)

invokeai/backend/image_util/util.py

@@ -1,4 +1,5 @@
 from math import ceil, floor, sqrt
+from typing import Optional
 
 import cv2
 import numpy as np
@@ -143,20 +144,21 @@ def resize_image_to_resolution(input_image: np.ndarray, resolution: int) -> np.n
     h = float(input_image.shape[0])
     w = float(input_image.shape[1])
     scaling_factor = float(resolution) / min(h, w)
-    h *= scaling_factor
-    w *= scaling_factor
-    h = int(np.round(h / 64.0)) * 64
-    w = int(np.round(w / 64.0)) * 64
+    h = int(h * scaling_factor)
+    w = int(w * scaling_factor)
     if scaling_factor > 1:
         return cv2.resize(input_image, (w, h), interpolation=cv2.INTER_LANCZOS4)
     else:
         return cv2.resize(input_image, (w, h), interpolation=cv2.INTER_AREA)
 
 
-def non_maximum_suppression(image: np.ndarray, threshold: int, sigma: float):
+def nms(np_img: np.ndarray, threshold: Optional[int] = None, sigma: Optional[float] = None) -> np.ndarray:
     """
     Apply non-maximum suppression to an image.
 
+    If both threshold and sigma are provided, the image will blurred before the suppression and thresholded afterwards,
+    resulting in a binary output image.
+
     This function is adapted from https://github.com/lllyasviel/ControlNet.
 
     Args:
@@ -166,23 +168,36 @@ def non_maximum_suppression(image: np.ndarray, threshold: int, sigma: float):
 
     Returns:
         The image after non-maximum suppression.
+
+    Raises:
+        ValueError: If only one of threshold and sigma provided.
     """
 
-    image = cv2.GaussianBlur(image.astype(np.float32), (0, 0), sigma)
+    # Raise a value error if only one of threshold and sigma is provided
+    if (threshold is None) != (sigma is None):
+        raise ValueError("Both threshold and sigma must be provided if one is provided.")
+
+    if sigma is not None and threshold is not None:
+        # Blurring the image can help to thin out features
+        np_img = cv2.GaussianBlur(np_img.astype(np.float32), (0, 0), sigma)
 
     filter_1 = np.array([[0, 0, 0], [1, 1, 1], [0, 0, 0]], dtype=np.uint8)
     filter_2 = np.array([[0, 1, 0], [0, 1, 0], [0, 1, 0]], dtype=np.uint8)
     filter_3 = np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]], dtype=np.uint8)
     filter_4 = np.array([[0, 0, 1], [0, 1, 0], [1, 0, 0]], dtype=np.uint8)
 
-    y = np.zeros_like(image)
+    nms_img = np.zeros_like(np_img)
 
     for f in [filter_1, filter_2, filter_3, filter_4]:
-        np.putmask(y, cv2.dilate(image, kernel=f) == image, image)
+        np.putmask(nms_img, cv2.dilate(np_img, kernel=f) == np_img, np_img)
 
-    z = np.zeros_like(y, dtype=np.uint8)
-    z[y > threshold] = 255
-    return z
+    if sigma is not None and threshold is not None:
+        # We blurred - now threshold to get a binary image
+        thresholded = np.zeros_like(nms_img, dtype=np.uint8)
+        thresholded[nms_img > threshold] = 255
+        return thresholded
+
+    return nms_img
 
 
 def safe_step(x: np.ndarray, step: int = 2) -> np.ndarray:

invokeai/backend/model_manager/config.py

@@ -301,12 +301,12 @@ class MainConfigBase(ModelConfigBase):
     default_settings: Optional[MainModelDefaultSettings] = Field(
         description="Default settings for this model", default=None
     )
+    variant: ModelVariantType = ModelVariantType.Normal
 
 
 class MainCheckpointConfig(CheckpointConfigBase, MainConfigBase):
     """Model config for main checkpoint models."""
 
-    variant: ModelVariantType = ModelVariantType.Normal
     prediction_type: SchedulerPredictionType = SchedulerPredictionType.Epsilon
     upcast_attention: bool = False
 

invokeai/backend/model_manager/load/load_default.py

@@ -18,7 +18,7 @@ from invokeai.backend.model_manager.load.load_base import LoadedModel, ModelLoad
 from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase, ModelLockerBase
 from invokeai.backend.model_manager.load.model_util import calc_model_size_by_data, calc_model_size_by_fs
 from invokeai.backend.model_manager.load.optimizations import skip_torch_weight_init
-from invokeai.backend.util.devices import choose_torch_device, torch_dtype
+from invokeai.backend.util.devices import TorchDevice
 
 
 # TO DO: The loader is not thread safe!
@@ -37,7 +37,7 @@ class ModelLoader(ModelLoaderBase):
         self._logger = logger
         self._ram_cache = ram_cache
         self._convert_cache = convert_cache
-        self._torch_dtype = torch_dtype(choose_torch_device())
+        self._torch_dtype = TorchDevice.choose_torch_dtype()
 
     def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
         """

invokeai/backend/model_manager/load/model_cache/model_cache_default.py

@@ -30,15 +30,12 @@ import torch
 
 from invokeai.backend.model_manager import AnyModel, SubModelType
 from invokeai.backend.model_manager.load.memory_snapshot import MemorySnapshot, get_pretty_snapshot_diff
-from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.logging import InvokeAILogger
 
 from .model_cache_base import CacheRecord, CacheStats, ModelCacheBase, ModelLockerBase
 from .model_locker import ModelLocker
 
-if choose_torch_device() == torch.device("mps"):
-    from torch import mps
-
 # Maximum size of the cache, in gigs
 # Default is roughly enough to hold three fp16 diffusers models in RAM simultaneously
 DEFAULT_MAX_CACHE_SIZE = 6.0
@@ -244,9 +241,7 @@ class ModelCache(ModelCacheBase[AnyModel]):
                     f"Removing {cache_entry.key} from VRAM to free {(cache_entry.size/GIG):.2f}GB; vram free = {(torch.cuda.memory_allocated()/GIG):.2f}GB"
                 )
 
-        torch.cuda.empty_cache()
-        if choose_torch_device() == torch.device("mps"):
-            mps.empty_cache()
+        TorchDevice.empty_cache()
 
     def move_model_to_device(self, cache_entry: CacheRecord[AnyModel], target_device: torch.device) -> None:
         """Move model into the indicated device.
@@ -416,10 +411,7 @@ class ModelCache(ModelCacheBase[AnyModel]):
                 self.stats.cleared = models_cleared
             gc.collect()
 
-        torch.cuda.empty_cache()
-        if choose_torch_device() == torch.device("mps"):
-            mps.empty_cache()
-
+        TorchDevice.empty_cache()
         self.logger.debug(f"After making room: cached_models={len(self._cached_models)}")
 
     def _delete_cache_entry(self, cache_entry: CacheRecord[AnyModel]) -> None:

invokeai/backend/model_manager/merge.py

@@ -17,7 +17,7 @@ from diffusers.utils import logging as dlogging
 
 from invokeai.app.services.model_install import ModelInstallServiceBase
 from invokeai.app.services.model_records.model_records_base import ModelRecordChanges
-from invokeai.backend.util.devices import choose_torch_device, torch_dtype
+from invokeai.backend.util.devices import TorchDevice
 
 from . import (
     AnyModelConfig,
@@ -43,6 +43,7 @@ class ModelMerger(object):
         Initialize a ModelMerger object with the model installer.
         """
         self._installer = installer
+        self._dtype = TorchDevice.choose_torch_dtype()
 
     def merge_diffusion_models(
         self,
@@ -68,7 +69,7 @@ class ModelMerger(object):
             warnings.simplefilter("ignore")
             verbosity = dlogging.get_verbosity()
             dlogging.set_verbosity_error()
-            dtype = torch.float16 if variant == "fp16" else torch_dtype(choose_torch_device())
+            dtype = torch.float16 if variant == "fp16" else self._dtype
 
             # Note that checkpoint_merger will not work with downloaded HuggingFace fp16 models
             # until upstream https://github.com/huggingface/diffusers/pull/6670 is merged and released.
@@ -151,7 +152,7 @@ class ModelMerger(object):
         dump_path.mkdir(parents=True, exist_ok=True)
         dump_path = dump_path / merged_model_name
 
-        dtype = torch.float16 if variant == "fp16" else torch_dtype(choose_torch_device())
+        dtype = torch.float16 if variant == "fp16" else self._dtype
         merged_pipe.save_pretrained(dump_path.as_posix(), safe_serialization=True, torch_dtype=dtype, variant=variant)
 
         # register model and get its unique key

invokeai/backend/model_manager/probe.py

@@ -51,6 +51,7 @@ LEGACY_CONFIGS: Dict[BaseModelType, Dict[ModelVariantType, Union[str, Dict[Sched
     },
     BaseModelType.StableDiffusionXL: {
         ModelVariantType.Normal: "sd_xl_base.yaml",
+        ModelVariantType.Inpaint: "sd_xl_inpaint.yaml",
     },
     BaseModelType.StableDiffusionXLRefiner: {
         ModelVariantType.Normal: "sd_xl_refiner.yaml",

invokeai/backend/model_manager/starter_models.py

@@ -155,7 +155,7 @@ STARTER_MODELS: list[StarterModel] = [
     StarterModel(
         name="IP Adapter",
         base=BaseModelType.StableDiffusion1,
-        source="InvokeAI/ip_adapter_sd15",
+        source="https://huggingface.co/InvokeAI/ip_adapter_sd15/resolve/main/ip-adapter_sd15.safetensors",
         description="IP-Adapter for SD 1.5 models",
         type=ModelType.IPAdapter,
         dependencies=[ip_adapter_sd_image_encoder],
@@ -163,7 +163,7 @@ STARTER_MODELS: list[StarterModel] = [
     StarterModel(
         name="IP Adapter Plus",
         base=BaseModelType.StableDiffusion1,
-        source="InvokeAI/ip_adapter_plus_sd15",
+        source="https://huggingface.co/InvokeAI/ip_adapter_plus_sd15/resolve/main/ip-adapter-plus_sd15.safetensors",
         description="Refined IP-Adapter for SD 1.5 models",
         type=ModelType.IPAdapter,
         dependencies=[ip_adapter_sd_image_encoder],
@@ -171,7 +171,7 @@ STARTER_MODELS: list[StarterModel] = [
     StarterModel(
         name="IP Adapter Plus Face",
         base=BaseModelType.StableDiffusion1,
-        source="InvokeAI/ip_adapter_plus_face_sd15",
+        source="https://huggingface.co/InvokeAI/ip_adapter_plus_face_sd15/resolve/main/ip-adapter-plus-face_sd15.safetensors",
         description="Refined IP-Adapter for SD 1.5 models, adapted for faces",
         type=ModelType.IPAdapter,
         dependencies=[ip_adapter_sd_image_encoder],
@@ -179,7 +179,7 @@ STARTER_MODELS: list[StarterModel] = [
     StarterModel(
         name="IP Adapter SDXL",
         base=BaseModelType.StableDiffusionXL,
-        source="InvokeAI/ip_adapter_sdxl",
+        source="https://huggingface.co/InvokeAI/ip_adapter_sdxl_vit_h/resolve/main/ip-adapter_sdxl_vit-h.safetensors",
         description="IP-Adapter for SDXL models",
         type=ModelType.IPAdapter,
         dependencies=[ip_adapter_sdxl_image_encoder],

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -21,14 +21,11 @@ from pydantic import Field
 from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
 
 from invokeai.app.services.config.config_default import get_config
-from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
-    IPAdapterData,
-    TextConditioningData,
-)
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import IPAdapterData, TextConditioningData
 from invokeai.backend.stable_diffusion.diffusion.shared_invokeai_diffusion import InvokeAIDiffuserComponent
-from invokeai.backend.stable_diffusion.diffusion.unet_attention_patcher import UNetAttentionPatcher
+from invokeai.backend.stable_diffusion.diffusion.unet_attention_patcher import UNetAttentionPatcher, UNetIPAdapterData
 from invokeai.backend.util.attention import auto_detect_slice_size
-from invokeai.backend.util.devices import normalize_device
+from invokeai.backend.util.devices import TorchDevice
 
 
 @dataclass
@@ -258,7 +255,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         if self.unet.device.type == "cpu" or self.unet.device.type == "mps":
             mem_free = psutil.virtual_memory().free
         elif self.unet.device.type == "cuda":
-            mem_free, _ = torch.cuda.mem_get_info(normalize_device(self.unet.device))
+            mem_free, _ = torch.cuda.mem_get_info(TorchDevice.normalize(self.unet.device))
         else:
             raise ValueError(f"unrecognized device {self.unet.device}")
         # input tensor of [1, 4, h/8, w/8]
@@ -394,8 +391,13 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         unet_attention_patcher = None
         self.use_ip_adapter = use_ip_adapter
         attn_ctx = nullcontext()
+
         if use_ip_adapter or use_regional_prompting:
-            ip_adapters = [ipa.ip_adapter_model for ipa in ip_adapter_data] if use_ip_adapter else None
+            ip_adapters: Optional[List[UNetIPAdapterData]] = (
+                [{"ip_adapter": ipa.ip_adapter_model, "target_blocks": ipa.target_blocks} for ipa in ip_adapter_data]
+                if use_ip_adapter
+                else None
+            )
             unet_attention_patcher = UNetAttentionPatcher(ip_adapters)
             attn_ctx = unet_attention_patcher.apply_ip_adapter_attention(self.invokeai_diffuser.model)
 

invokeai/backend/stable_diffusion/diffusion/conditioning_data.py

@@ -53,6 +53,7 @@ class IPAdapterData:
     ip_adapter_model: IPAdapter
     ip_adapter_conditioning: IPAdapterConditioningInfo
     mask: torch.Tensor
+    target_blocks: List[str]
 
     # Either a single weight applied to all steps, or a list of weights for each step.
     weight: Union[float, List[float]] = 1.0

invokeai/backend/stable_diffusion/diffusion/custom_atttention.py

@@ -1,4 +1,5 @@
-from typing import Optional
+from dataclasses import dataclass
+from typing import List, Optional, cast
 
 import torch
 import torch.nn.functional as F
@@ -9,6 +10,12 @@ from invokeai.backend.stable_diffusion.diffusion.regional_ip_data import Regiona
 from invokeai.backend.stable_diffusion.diffusion.regional_prompt_data import RegionalPromptData
 
 
+@dataclass
+class IPAdapterAttentionWeights:
+    ip_adapter_weights: IPAttentionProcessorWeights
+    skip: bool
+
+
 class CustomAttnProcessor2_0(AttnProcessor2_0):
     """A custom implementation of AttnProcessor2_0 that supports additional Invoke features.
     This implementation is based on
@@ -20,7 +27,7 @@ class CustomAttnProcessor2_0(AttnProcessor2_0):
 
     def __init__(
         self,
-        ip_adapter_weights: Optional[list[IPAttentionProcessorWeights]] = None,
+        ip_adapter_attention_weights: Optional[List[IPAdapterAttentionWeights]] = None,
     ):
         """Initialize a CustomAttnProcessor2_0.
         Note: Arguments that are the same for all attention layers are passed to __call__(). Arguments that are
@@ -30,23 +37,22 @@ class CustomAttnProcessor2_0(AttnProcessor2_0):
                 for the i'th IP-Adapter.
         """
         super().__init__()
-        self._ip_adapter_weights = ip_adapter_weights
-
-    def _is_ip_adapter_enabled(self) -> bool:
-        return self._ip_adapter_weights is not None
+        self._ip_adapter_attention_weights = ip_adapter_attention_weights
 
     def __call__(
         self,
         attn: Attention,
-        hidden_states: torch.FloatTensor,
-        encoder_hidden_states: Optional[torch.FloatTensor] = None,
-        attention_mask: Optional[torch.FloatTensor] = None,
-        temb: Optional[torch.FloatTensor] = None,
-        # For regional prompting:
+        hidden_states: torch.Tensor,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        temb: Optional[torch.Tensor] = None,
+        # For Regional Prompting:
         regional_prompt_data: Optional[RegionalPromptData] = None,
-        percent_through: Optional[torch.FloatTensor] = None,
+        percent_through: Optional[torch.Tensor] = None,
         # For IP-Adapter:
         regional_ip_data: Optional[RegionalIPData] = None,
+        *args,
+        **kwargs,
     ) -> torch.FloatTensor:
         """Apply attention.
         Args:
@@ -130,17 +136,19 @@ class CustomAttnProcessor2_0(AttnProcessor2_0):
 
         # Apply IP-Adapter conditioning.
         if is_cross_attention:
-            if self._is_ip_adapter_enabled():
+            if self._ip_adapter_attention_weights:
                 assert regional_ip_data is not None
                 ip_masks = regional_ip_data.get_masks(query_seq_len=query_seq_len)
+
                 assert (
                     len(regional_ip_data.image_prompt_embeds)
-                    == len(self._ip_adapter_weights)
+                    == len(self._ip_adapter_attention_weights)
                     == len(regional_ip_data.scales)
                     == ip_masks.shape[1]
                 )
+
                 for ipa_index, ipa_embed in enumerate(regional_ip_data.image_prompt_embeds):
-                    ipa_weights = self._ip_adapter_weights[ipa_index]
+                    ipa_weights = self._ip_adapter_attention_weights[ipa_index].ip_adapter_weights
                     ipa_scale = regional_ip_data.scales[ipa_index]
                     ip_mask = ip_masks[0, ipa_index, ...]
 
@@ -153,29 +161,33 @@ class CustomAttnProcessor2_0(AttnProcessor2_0):
 
                     # Expected ip_hidden_state shape: (batch_size, num_ip_images, ip_seq_len, ip_image_embedding)
 
-                    ip_key = ipa_weights.to_k_ip(ip_hidden_states)
-                    ip_value = ipa_weights.to_v_ip(ip_hidden_states)
+                    if not self._ip_adapter_attention_weights[ipa_index].skip:
+                        ip_key = ipa_weights.to_k_ip(ip_hidden_states)
+                        ip_value = ipa_weights.to_v_ip(ip_hidden_states)
 
-                    # Expected ip_key and ip_value shape: (batch_size, num_ip_images, ip_seq_len, head_dim * num_heads)
+                        # Expected ip_key and ip_value shape:
+                        # (batch_size, num_ip_images, ip_seq_len, head_dim * num_heads)
 
-                    ip_key = ip_key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-                    ip_value = ip_value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+                        ip_key = ip_key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+                        ip_value = ip_value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
 
-                    # Expected ip_key and ip_value shape: (batch_size, num_heads, num_ip_images * ip_seq_len, head_dim)
+                        # Expected ip_key and ip_value shape:
+                        # (batch_size, num_heads, num_ip_images * ip_seq_len, head_dim)
 
-                    # TODO: add support for attn.scale when we move to Torch 2.1
-                    ip_hidden_states = F.scaled_dot_product_attention(
-                        query, ip_key, ip_value, attn_mask=None, dropout_p=0.0, is_causal=False
-                    )
+                        # TODO: add support for attn.scale when we move to Torch 2.1
+                        ip_hidden_states = F.scaled_dot_product_attention(
+                            query, ip_key, ip_value, attn_mask=None, dropout_p=0.0, is_causal=False
+                        )
 
-                    # Expected ip_hidden_states shape: (batch_size, num_heads, query_seq_len, head_dim)
+                        # Expected ip_hidden_states shape: (batch_size, num_heads, query_seq_len, head_dim)
+                        ip_hidden_states = ip_hidden_states.transpose(1, 2).reshape(
+                            batch_size, -1, attn.heads * head_dim
+                        )
 
-                    ip_hidden_states = ip_hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
-                    ip_hidden_states = ip_hidden_states.to(query.dtype)
+                        ip_hidden_states = ip_hidden_states.to(query.dtype)
 
-                    # Expected ip_hidden_states shape: (batch_size, query_seq_len, num_heads * head_dim)
-
-                    hidden_states = hidden_states + ipa_scale * ip_hidden_states * ip_mask
+                        # Expected ip_hidden_states shape: (batch_size, query_seq_len, num_heads * head_dim)
+                        hidden_states = hidden_states + ipa_scale * ip_hidden_states * ip_mask
             else:
                 # If IP-Adapter is not enabled, then regional_ip_data should not be passed in.
                 assert regional_ip_data is None
@@ -188,11 +200,15 @@ class CustomAttnProcessor2_0(AttnProcessor2_0):
         hidden_states = attn.to_out[1](hidden_states)
 
         if input_ndim == 4:
+            batch_size, channel, height, width = hidden_states.shape
             hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
 
         if attn.residual_connection:
             hidden_states = hidden_states + residual
 
         hidden_states = hidden_states / attn.rescale_output_factor
+        # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+        # End of unmodified block from AttnProcessor2_0
 
-        return hidden_states
+        # casting torch.Tensor to torch.FloatTensor to avoid type issues
+        return cast(torch.FloatTensor, hidden_states)

invokeai/backend/stable_diffusion/diffusion/unet_attention_patcher.py

@@ -1,17 +1,25 @@
 from contextlib import contextmanager
-from typing import Optional
+from typing import List, Optional, TypedDict
 
 from diffusers.models import UNet2DConditionModel
 
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
-from invokeai.backend.stable_diffusion.diffusion.custom_atttention import CustomAttnProcessor2_0
+from invokeai.backend.stable_diffusion.diffusion.custom_atttention import (
+    CustomAttnProcessor2_0,
+    IPAdapterAttentionWeights,
+)
+
+
+class UNetIPAdapterData(TypedDict):
+    ip_adapter: IPAdapter
+    target_blocks: List[str]
 
 
 class UNetAttentionPatcher:
     """A class for patching a UNet with CustomAttnProcessor2_0 attention layers."""
 
-    def __init__(self, ip_adapters: Optional[list[IPAdapter]]):
-        self._ip_adapters = ip_adapters
+    def __init__(self, ip_adapter_data: Optional[List[UNetIPAdapterData]]):
+        self._ip_adapters = ip_adapter_data
 
     def _prepare_attention_processors(self, unet: UNet2DConditionModel):
         """Prepare a dict of attention processors that can be injected into a unet, and load the IP-Adapter attention
@@ -26,9 +34,22 @@ class UNetAttentionPatcher:
                 attn_procs[name] = CustomAttnProcessor2_0()
             else:
                 # Collect the weights from each IP Adapter for the idx'th attention processor.
-                attn_procs[name] = CustomAttnProcessor2_0(
-                    [ip_adapter.attn_weights.get_attention_processor_weights(idx) for ip_adapter in self._ip_adapters],
-                )
+                ip_adapter_attention_weights_collection: list[IPAdapterAttentionWeights] = []
+
+                for ip_adapter in self._ip_adapters:
+                    ip_adapter_weights = ip_adapter["ip_adapter"].attn_weights.get_attention_processor_weights(idx)
+                    skip = True
+                    for block in ip_adapter["target_blocks"]:
+                        if block in name:
+                            skip = False
+                            break
+                    ip_adapter_attention_weights: IPAdapterAttentionWeights = IPAdapterAttentionWeights(
+                        ip_adapter_weights=ip_adapter_weights, skip=skip
+                    )
+                    ip_adapter_attention_weights_collection.append(ip_adapter_attention_weights)
+
+                attn_procs[name] = CustomAttnProcessor2_0(ip_adapter_attention_weights_collection)
+
         return attn_procs
 
     @contextmanager

invokeai/backend/stable_diffusion/schedulers/schedulers.py

@@ -13,6 +13,7 @@ from diffusers import (
     LCMScheduler,
     LMSDiscreteScheduler,
     PNDMScheduler,
+    TCDScheduler,
     UniPCMultistepScheduler,
 )
 
@@ -40,4 +41,5 @@ SCHEDULER_MAP = {
     "dpmpp_sde_k": (DPMSolverSDEScheduler, {"use_karras_sigmas": True, "noise_sampler_seed": 0}),
     "unipc": (UniPCMultistepScheduler, {"cpu_only": True}),
     "lcm": (LCMScheduler, {}),
+    "tcd": (TCDScheduler, {}),
 }

invokeai/backend/util/__init__.py

@@ -2,7 +2,6 @@
 Initialization file for invokeai.backend.util
 """
 
-from .devices import choose_precision, choose_torch_device
 from .logging import InvokeAILogger
 from .util import GIG, Chdir, directory_size
 
@@ -11,6 +10,4 @@ __all__ = [
     "directory_size",
     "Chdir",
     "InvokeAILogger",
-    "choose_precision",
-    "choose_torch_device",
 ]

invokeai/backend/util/catch_sigint.py

@@ -0,0 +1,29 @@
+"""
+This module defines a context manager `catch_sigint()` which temporarily replaces
+the sigINT handler defined by the ASGI in order to allow the user to ^C the application
+and shut it down immediately. This was implemented in order to allow the user to interrupt
+slow model hashing during startup.
+
+Use like this:
+
+  from invokeai.backend.util.catch_sigint import catch_sigint
+  with catch_sigint():
+      run_some_hard_to_interrupt_process()
+"""
+
+import signal
+from contextlib import contextmanager
+from typing import Generator
+
+
+def sigint_handler(signum, frame):  # type: ignore
+    signal.signal(signal.SIGINT, signal.SIG_DFL)
+    signal.raise_signal(signal.SIGINT)
+
+
+@contextmanager
+def catch_sigint() -> Generator[None, None, None]:
+    original_handler = signal.getsignal(signal.SIGINT)
+    signal.signal(signal.SIGINT, sigint_handler)
+    yield
+    signal.signal(signal.SIGINT, original_handler)

invokeai/backend/util/devices.py

@@ -1,89 +1,110 @@
-from __future__ import annotations
-
-from contextlib import nullcontext
-from typing import Literal, Optional, Union
+from typing import Dict, Literal, Optional, Union
 
 import torch
-from torch import autocast
+from deprecated import deprecated
 
-from invokeai.app.services.config.config_default import PRECISION, get_config
+from invokeai.app.services.config.config_default import get_config
 
+# legacy APIs
+TorchPrecisionNames = Literal["float32", "float16", "bfloat16"]
 CPU_DEVICE = torch.device("cpu")
 CUDA_DEVICE = torch.device("cuda")
 MPS_DEVICE = torch.device("mps")
 
 
+@deprecated("Use TorchDevice.choose_torch_dtype() instead.")  # type: ignore
+def choose_precision(device: torch.device) -> TorchPrecisionNames:
+    """Return the string representation of the recommended torch device."""
+    torch_dtype = TorchDevice.choose_torch_dtype(device)
+    return PRECISION_TO_NAME[torch_dtype]
+
+
+@deprecated("Use TorchDevice.choose_torch_device() instead.")  # type: ignore
 def choose_torch_device() -> torch.device:
-    """Convenience routine for guessing which GPU device to run model on"""
-    config = get_config()
-    if config.device == "auto":
-        if torch.cuda.is_available():
-            return torch.device("cuda")
-        if hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
-            return torch.device("mps")
+    """Return the torch.device to use for accelerated inference."""
+    return TorchDevice.choose_torch_device()
+
+
+@deprecated("Use TorchDevice.choose_torch_dtype() instead.")  # type: ignore
+def torch_dtype(device: torch.device) -> torch.dtype:
+    """Return the torch precision for the recommended torch device."""
+    return TorchDevice.choose_torch_dtype(device)
+
+
+NAME_TO_PRECISION: Dict[TorchPrecisionNames, torch.dtype] = {
+    "float32": torch.float32,
+    "float16": torch.float16,
+    "bfloat16": torch.bfloat16,
+}
+PRECISION_TO_NAME: Dict[torch.dtype, TorchPrecisionNames] = {v: k for k, v in NAME_TO_PRECISION.items()}
+
+
+class TorchDevice:
+    """Abstraction layer for torch devices."""
+
+    @classmethod
+    def choose_torch_device(cls) -> torch.device:
+        """Return the torch.device to use for accelerated inference."""
+        app_config = get_config()
+        if app_config.device != "auto":
+            device = torch.device(app_config.device)
+        elif torch.cuda.is_available():
+            device = CUDA_DEVICE
+        elif torch.backends.mps.is_available():
+            device = MPS_DEVICE
         else:
-            return CPU_DEVICE
-    else:
-        return torch.device(config.device)
+            device = CPU_DEVICE
+        return cls.normalize(device)
 
+    @classmethod
+    def choose_torch_dtype(cls, device: Optional[torch.device] = None) -> torch.dtype:
+        """Return the precision to use for accelerated inference."""
+        device = device or cls.choose_torch_device()
+        config = get_config()
+        if device.type == "cuda" and torch.cuda.is_available():
+            device_name = torch.cuda.get_device_name(device)
+            if "GeForce GTX 1660" in device_name or "GeForce GTX 1650" in device_name:
+                # These GPUs have limited support for float16
+                return cls._to_dtype("float32")
+            elif config.precision == "auto":
+                # Default to float16 for CUDA devices
+                return cls._to_dtype("float16")
+            else:
+                # Use the user-defined precision
+                return cls._to_dtype(config.precision)
 
-def get_torch_device_name() -> str:
-    device = choose_torch_device()
-    return torch.cuda.get_device_name(device) if device.type == "cuda" else device.type.upper()
+        elif device.type == "mps" and torch.backends.mps.is_available():
+            if config.precision == "auto":
+                # Default to float16 for MPS devices
+                return cls._to_dtype("float16")
+            else:
+                # Use the user-defined precision
+                return cls._to_dtype(config.precision)
+        # CPU / safe fallback
+        return cls._to_dtype("float32")
 
+    @classmethod
+    def get_torch_device_name(cls) -> str:
+        """Return the device name for the current torch device."""
+        device = cls.choose_torch_device()
+        return torch.cuda.get_device_name(device) if device.type == "cuda" else device.type.upper()
 
-def choose_precision(device: torch.device) -> Literal["float32", "float16", "bfloat16"]:
-    """Return an appropriate precision for the given torch device."""
-    app_config = get_config()
-    if device.type == "cuda":
-        device_name = torch.cuda.get_device_name(device)
-        if "GeForce GTX 1660" in device_name or "GeForce GTX 1650" in device_name:
-            # These GPUs have limited support for float16
-            return "float32"
-        elif app_config.precision == "auto" or app_config.precision == "autocast":
-            # Default to float16 for CUDA devices
-            return "float16"
-        else:
-            # Use the user-defined precision
-            return app_config.precision
-    elif device.type == "mps":
-        if app_config.precision == "auto" or app_config.precision == "autocast":
-            # Default to float16 for MPS devices
-            return "float16"
-        else:
-            # Use the user-defined precision
-            return app_config.precision
-    # CPU / safe fallback
-    return "float32"
-
-
-def torch_dtype(device: Optional[torch.device] = None) -> torch.dtype:
-    device = device or choose_torch_device()
-    precision = choose_precision(device)
-    if precision == "float16":
-        return torch.float16
-    if precision == "bfloat16":
-        return torch.bfloat16
-    else:
-        # "auto", "autocast", "float32"
-        return torch.float32
-
-
-def choose_autocast(precision: PRECISION):
-    """Returns an autocast context or nullcontext for the given precision string"""
-    # float16 currently requires autocast to avoid errors like:
-    # 'expected scalar type Half but found Float'
-    if precision == "autocast" or precision == "float16":
-        return autocast
-    return nullcontext
-
-
-def normalize_device(device: Union[str, torch.device]) -> torch.device:
-    """Ensure device has a device index defined, if appropriate."""
-    device = torch.device(device)
-    if device.index is None:
-        # cuda might be the only torch backend that currently uses the device index?
-        # I don't see anything like `current_device` for cpu or mps.
-        if device.type == "cuda":
+    @classmethod
+    def normalize(cls, device: Union[str, torch.device]) -> torch.device:
+        """Add the device index to CUDA devices."""
+        device = torch.device(device)
+        if device.index is None and device.type == "cuda" and torch.cuda.is_available():
             device = torch.device(device.type, torch.cuda.current_device())
-    return device
+        return device
+
+    @classmethod
+    def empty_cache(cls) -> None:
+        """Clear the GPU device cache."""
+        if torch.backends.mps.is_available():
+            torch.mps.empty_cache()
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+
+    @classmethod
+    def _to_dtype(cls, precision_name: TorchPrecisionNames) -> torch.dtype:
+        return NAME_TO_PRECISION[precision_name]

invokeai/configs/stable-diffusion/sd_xl_inpaint.yaml

@@ -0,0 +1,98 @@
+model:
+  target: sgm.models.diffusion.DiffusionEngine
+  params:
+    scale_factor: 0.13025
+    disable_first_stage_autocast: True
+
+    denoiser_config:
+      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
+      params:
+        num_idx: 1000
+
+        weighting_config:
+          target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
+        scaling_config:
+          target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
+        discretization_config:
+          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
+
+    network_config:
+      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        adm_in_channels: 2816
+        num_classes: sequential
+        use_checkpoint: True
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [4, 2]
+        num_res_blocks: 2
+        channel_mult: [1, 2, 4]
+        num_head_channels: 64
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: [1, 2, 10]  # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
+        context_dim: 2048
+        spatial_transformer_attn_type: softmax-xformers
+        legacy: False
+
+    conditioner_config:
+      target: sgm.modules.GeneralConditioner
+      params:
+        emb_models:
+          # crossattn cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
+            params:
+              layer: hidden
+              layer_idx: 11
+          # crossattn and vector cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
+            params:
+              arch: ViT-bigG-14
+              version: laion2b_s39b_b160k
+              freeze: True
+              layer: penultimate
+              always_return_pooled: True
+              legacy: False
+          # vector cond
+          - is_trainable: False
+            input_key: original_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: crop_coords_top_left
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: target_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+
+    first_stage_config:
+      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          attn_type: vanilla-xformers
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult: [1, 2, 4, 4]
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity

invokeai/frontend/web/.storybook/preview.tsx

@@ -11,6 +11,7 @@ import { createStore } from '../src/app/store/store';
 // @ts-ignore
 import translationEN from '../public/locales/en.json';
 import { ReduxInit } from './ReduxInit';
+import { $store } from 'app/store/nanostores/store';
 
 i18n.use(initReactI18next).init({
   lng: 'en',
@@ -25,6 +26,7 @@ i18n.use(initReactI18next).init({
 });
 
 const store = createStore(undefined, false);
+$store.set(store);
 $baseUrl.set('http://localhost:9090');
 
 const preview: Preview = {

invokeai/frontend/web/package.json

@@ -52,58 +52,60 @@
   },
   "dependencies": {
     "@chakra-ui/react-use-size": "^2.1.0",
-    "@dagrejs/dagre": "^1.1.1",
-    "@dagrejs/graphlib": "^2.2.1",
+    "@dagrejs/dagre": "^1.1.2",
+    "@dagrejs/graphlib": "^2.2.2",
     "@dnd-kit/core": "^6.1.0",
     "@dnd-kit/sortable": "^8.0.0",
     "@dnd-kit/utilities": "^3.2.2",
-    "@fontsource-variable/inter": "^5.0.17",
-    "@invoke-ai/ui-library": "^0.0.21",
+    "@fontsource-variable/inter": "^5.0.18",
+    "@invoke-ai/ui-library": "^0.0.25",
     "@nanostores/react": "^0.7.2",
-    "@reduxjs/toolkit": "2.2.2",
+    "@reduxjs/toolkit": "2.2.3",
     "@roarr/browser-log-writer": "^1.3.0",
     "chakra-react-select": "^4.7.6",
     "compare-versions": "^6.1.0",
     "dateformat": "^5.0.3",
-    "framer-motion": "^11.0.22",
-    "i18next": "^23.10.1",
-    "i18next-http-backend": "^2.5.0",
+    "framer-motion": "^11.1.8",
+    "i18next": "^23.11.3",
+    "i18next-http-backend": "^2.5.1",
     "idb-keyval": "^6.2.1",
     "jsondiffpatch": "^0.6.0",
     "konva": "^9.3.6",
     "lodash-es": "^4.17.21",
-    "nanostores": "^0.10.0",
+    "nanostores": "^0.10.3",
     "new-github-issue-url": "^1.0.0",
-    "overlayscrollbars": "^2.6.1",
-    "overlayscrollbars-react": "^0.5.5",
+    "overlayscrollbars": "^2.7.3",
+    "overlayscrollbars-react": "^0.5.6",
     "query-string": "^9.0.0",
-    "react": "^18.2.0",
+    "react": "^18.3.1",
     "react-colorful": "^5.6.1",
-    "react-dom": "^18.2.0",
+    "react-dom": "^18.3.1",
     "react-dropzone": "^14.2.3",
     "react-error-boundary": "^4.0.13",
-    "react-hook-form": "^7.51.2",
+    "react-hook-form": "^7.51.4",
     "react-hotkeys-hook": "4.5.0",
-    "react-i18next": "^14.1.0",
-    "react-icons": "^5.0.1",
+    "react-i18next": "^14.1.1",
+    "react-icons": "^5.2.0",
     "react-konva": "^18.2.10",
-    "react-redux": "9.1.0",
-    "react-resizable-panels": "^2.0.16",
+    "react-redux": "9.1.2",
+    "react-resizable-panels": "^2.0.19",
     "react-select": "5.8.0",
     "react-use": "^17.5.0",
-    "react-virtuoso": "^4.7.5",
-    "reactflow": "^11.10.4",
+    "react-virtuoso": "^4.7.10",
+    "reactflow": "^11.11.3",
     "redux-dynamic-middlewares": "^2.2.0",
     "redux-remember": "^5.1.0",
+    "redux-undo": "^1.1.0",
     "rfdc": "^1.3.1",
     "roarr": "^7.21.1",
     "serialize-error": "^11.0.3",
     "socket.io-client": "^4.7.5",
     "use-debounce": "^10.0.0",
+    "use-device-pixel-ratio": "^1.1.2",
     "use-image": "^1.1.1",
     "uuid": "^9.0.1",
-    "zod": "^3.22.4",
-    "zod-validation-error": "^3.0.3"
+    "zod": "^3.23.6",
+    "zod-validation-error": "^3.2.0"
   },
   "peerDependencies": {
     "@chakra-ui/react": "^2.8.2",
@@ -114,19 +116,19 @@
   "devDependencies": {
     "@invoke-ai/eslint-config-react": "^0.0.14",
     "@invoke-ai/prettier-config-react": "^0.0.7",
-    "@storybook/addon-essentials": "^8.0.4",
-    "@storybook/addon-interactions": "^8.0.4",
-    "@storybook/addon-links": "^8.0.4",
-    "@storybook/addon-storysource": "^8.0.4",
-    "@storybook/manager-api": "^8.0.4",
-    "@storybook/react": "^8.0.4",
-    "@storybook/react-vite": "^8.0.4",
-    "@storybook/theming": "^8.0.4",
+    "@storybook/addon-essentials": "^8.0.10",
+    "@storybook/addon-interactions": "^8.0.10",
+    "@storybook/addon-links": "^8.0.10",
+    "@storybook/addon-storysource": "^8.0.10",
+    "@storybook/manager-api": "^8.0.10",
+    "@storybook/react": "^8.0.10",
+    "@storybook/react-vite": "^8.0.10",
+    "@storybook/theming": "^8.0.10",
     "@types/dateformat": "^5.0.2",
     "@types/lodash-es": "^4.17.12",
-    "@types/node": "^20.11.30",
-    "@types/react": "^18.2.73",
-    "@types/react-dom": "^18.2.22",
+    "@types/node": "^20.12.10",
+    "@types/react": "^18.3.1",
+    "@types/react-dom": "^18.3.0",
     "@types/uuid": "^9.0.8",
     "@vitejs/plugin-react-swc": "^3.6.0",
     "concurrently": "^8.2.2",
@@ -134,20 +136,20 @@
     "eslint": "^8.57.0",
     "eslint-plugin-i18next": "^6.0.3",
     "eslint-plugin-path": "^1.3.0",
-    "knip": "^5.6.1",
+    "knip": "^5.12.3",
     "openapi-types": "^12.1.3",
     "openapi-typescript": "^6.7.5",
     "prettier": "^3.2.5",
     "rollup-plugin-visualizer": "^5.12.0",
-    "storybook": "^8.0.4",
+    "storybook": "^8.0.10",
     "ts-toolbelt": "^9.6.0",
     "tsafe": "^1.6.6",
-    "typescript": "^5.4.3",
-    "vite": "^5.2.6",
-    "vite-plugin-css-injected-by-js": "^3.5.0",
-    "vite-plugin-dts": "^3.8.0",
+    "typescript": "^5.4.5",
+    "vite": "^5.2.11",
+    "vite-plugin-css-injected-by-js": "^3.5.1",
+    "vite-plugin-dts": "^3.9.1",
     "vite-plugin-eslint": "^1.8.1",
     "vite-tsconfig-paths": "^4.3.2",
-    "vitest": "^1.4.0"
+    "vitest": "^1.6.0"
   }
 }

invokeai/frontend/web/public/locales/de.json

@@ -85,7 +85,8 @@
         "loadMore": "Mehr laden",
         "noImagesInGallery": "Keine Bilder in der Galerie",
         "loading": "Lade",
-        "deleteImage": "Lösche Bild",
+        "deleteImage_one": "Lösche Bild",
+        "deleteImage_other": "",
         "copy": "Kopieren",
         "download": "Runterladen",
         "setCurrentImage": "Setze aktuelle Bild",

invokeai/frontend/web/public/locales/en.json

@@ -69,6 +69,7 @@
         "auto": "Auto",
         "back": "Back",
         "batch": "Batch Manager",
+        "beta": "Beta",
         "cancel": "Cancel",
         "copy": "Copy",
         "copyError": "$t(gallery.copy) Error",
@@ -83,13 +84,17 @@
         "direction": "Direction",
         "ipAdapter": "IP Adapter",
         "t2iAdapter": "T2I Adapter",
+        "positivePrompt": "Positive Prompt",
+        "negativePrompt": "Negative Prompt",
         "discordLabel": "Discord",
         "dontAskMeAgain": "Don't ask me again",
+        "editor": "Editor",
         "error": "Error",
         "file": "File",
         "folder": "Folder",
         "format": "format",
         "githubLabel": "Github",
+        "goTo": "Go to",
         "hotkeysLabel": "Hotkeys",
         "imageFailedToLoad": "Unable to Load Image",
         "img2img": "Image To Image",
@@ -135,7 +140,11 @@
         "red": "Red",
         "green": "Green",
         "blue": "Blue",
-        "alpha": "Alpha"
+        "alpha": "Alpha",
+        "selected": "Selected",
+        "viewer": "Viewer",
+        "tab": "Tab",
+        "close": "Close"
     },
     "controlnet": {
         "controlAdapter_one": "Control Adapter",
@@ -151,6 +160,7 @@
         "balanced": "Balanced",
         "base": "Base",
         "beginEndStepPercent": "Begin / End Step Percentage",
+        "beginEndStepPercentShort": "Begin/End %",
         "bgth": "bg_th",
         "canny": "Canny",
         "cannyDescription": "Canny edge detection",
@@ -213,12 +223,17 @@
         "resize": "Resize",
         "resizeSimple": "Resize (Simple)",
         "resizeMode": "Resize Mode",
+        "ipAdapterMethod": "Method",
+        "full": "Full",
+        "style": "Style Only",
+        "composition": "Composition Only",
         "safe": "Safe",
         "saveControlImage": "Save Control Image",
-        "scribble": "scribble",
+        "scribble": "Scribble",
         "selectModel": "Select a model",
         "selectCLIPVisionModel": "Select a CLIP Vision model",
-        "setControlImageDimensions": "Set Control Image Dimensions To W/H",
+        "setControlImageDimensions": "Copy size to W/H (optimize for model)",
+        "setControlImageDimensionsForce": "Copy size to W/H (ignore model)",
         "showAdvanced": "Show Advanced",
         "small": "Small",
         "toggleControlNet": "Toggle this ControlNet",
@@ -350,7 +365,10 @@
         "bulkDownloadRequestFailed": "Problem Preparing Download",
         "bulkDownloadFailed": "Download Failed",
         "problemDeletingImages": "Problem Deleting Images",
-        "problemDeletingImagesDesc": "One or more images could not be deleted"
+        "problemDeletingImagesDesc": "One or more images could not be deleted",
+        "switchTo": "Switch to {{ tab }} (Z)",
+        "openFloatingViewer": "Open Floating Viewer",
+        "closeFloatingViewer": "Close Floating Viewer"
     },
     "hotkeys": {
         "searchHotkeys": "Search Hotkeys",
@@ -573,6 +591,10 @@
         "upscale": {
             "desc": "Upscale the current image",
             "title": "Upscale"
+        },
+        "toggleViewer": {
+            "desc": "Switches between the Image Viewer and workspace for the current tab.",
+            "title": "Toggle Image Viewer"
         }
     },
     "metadata": {
@@ -770,6 +792,8 @@
         "float": "Float",
         "fullyContainNodes": "Fully Contain Nodes to Select",
         "fullyContainNodesHelp": "Nodes must be fully inside the selection box to be selected",
+        "showEdgeLabels": "Show Edge Labels",
+        "showEdgeLabelsHelp": "Show labels on edges, indicating the connected nodes",
         "hideLegendNodes": "Hide Field Type Legend",
         "hideMinimapnodes": "Hide MiniMap",
         "inputMayOnlyHaveOneConnection": "Input may only have one connection",
@@ -886,6 +910,7 @@
         "denoisingStrength": "Denoising Strength",
         "downloadImage": "Download Image",
         "general": "General",
+        "globalSettings": "Global Settings",
         "height": "Height",
         "imageFit": "Fit Initial Image To Output Size",
         "images": "Images",
@@ -903,6 +928,7 @@
             "missingInputForField": "{{nodeLabel}} -> {{fieldLabel}} missing input",
             "missingNodeTemplate": "Missing node template",
             "noControlImageForControlAdapter": "Control Adapter #{{number}} has no control image",
+            "imageNotProcessedForControlAdapter": "Control Adapter #{{number}}'s image is not processed",
             "noInitialImageSelected": "No initial image selected",
             "noModelForControlAdapter": "Control Adapter #{{number}} has no model selected.",
             "incompatibleBaseModelForControlAdapter": "Control Adapter #{{number}} model is incompatible with main model.",
@@ -1176,6 +1202,10 @@
             "heading": "Resize Mode",
             "paragraphs": ["Method to fit Control Adapter's input image size to the output generation size."]
         },
+        "ipAdapterMethod": {
+            "heading": "Method",
+            "paragraphs": ["Method by which to apply the current IP Adapter."]
+        },
         "controlNetWeight": {
             "heading": "Weight",
             "paragraphs": [
@@ -1494,5 +1524,55 @@
     },
     "app": {
         "storeNotInitialized": "Store is not initialized"
+    },
+    "controlLayers": {
+        "deleteAll": "Delete All",
+        "addLayer": "Add Layer",
+        "moveToFront": "Move to Front",
+        "moveToBack": "Move to Back",
+        "moveForward": "Move Forward",
+        "moveBackward": "Move Backward",
+        "brushSize": "Brush Size",
+        "controlLayers": "Control Layers",
+        "globalMaskOpacity": "Global Mask Opacity",
+        "autoNegative": "Auto Negative",
+        "toggleVisibility": "Toggle Layer Visibility",
+        "deletePrompt": "Delete Prompt",
+        "resetRegion": "Reset Region",
+        "debugLayers": "Debug Layers",
+        "rectangle": "Rectangle",
+        "maskPreviewColor": "Mask Preview Color",
+        "addPositivePrompt": "Add $t(common.positivePrompt)",
+        "addNegativePrompt": "Add $t(common.negativePrompt)",
+        "addIPAdapter": "Add $t(common.ipAdapter)",
+        "regionalGuidance": "Regional Guidance",
+        "regionalGuidanceLayer": "$t(controlLayers.regionalGuidance) $t(unifiedCanvas.layer)",
+        "controlNetLayer": "$t(common.controlNet) $t(unifiedCanvas.layer)",
+        "ipAdapterLayer": "$t(common.ipAdapter) $t(unifiedCanvas.layer)",
+        "opacity": "Opacity",
+        "globalControlAdapter": "Global $t(controlnet.controlAdapter_one)",
+        "globalControlAdapterLayer": "Global $t(controlnet.controlAdapter_one) $t(unifiedCanvas.layer)",
+        "globalIPAdapter": "Global $t(common.ipAdapter)",
+        "globalIPAdapterLayer": "Global $t(common.ipAdapter) $t(unifiedCanvas.layer)",
+        "globalInitialImage": "Global Initial Image",
+        "globalInitialImageLayer": "$t(controlLayers.globalInitialImage) $t(unifiedCanvas.layer)",
+        "opacityFilter": "Opacity Filter",
+        "clearProcessor": "Clear Processor",
+        "resetProcessor": "Reset Processor to Defaults",
+        "noLayersAdded": "No Layers Added"
+    },
+    "ui": {
+        "tabs": {
+            "generation": "Generation",
+            "generationTab": "$t(ui.tabs.generation) $t(common.tab)",
+            "canvas": "Canvas",
+            "canvasTab": "$t(ui.tabs.canvas) $t(common.tab)",
+            "workflows": "Workflows",
+            "workflowsTab": "$t(ui.tabs.workflows) $t(common.tab)",
+            "models": "Models",
+            "modelsTab": "$t(ui.tabs.models) $t(common.tab)",
+            "queue": "Queue",
+            "queueTab": "$t(ui.tabs.queue) $t(common.tab)"
+        }
     }
 }

invokeai/frontend/web/public/locales/es.json

@@ -33,7 +33,9 @@
         "autoSwitchNewImages": "Auto seleccionar Imágenes nuevas",
         "loadMore": "Cargar más",
         "noImagesInGallery": "No hay imágenes para mostrar",
-        "deleteImage": "Eliminar Imagen",
+        "deleteImage_one": "Eliminar Imagen",
+        "deleteImage_many": "",
+        "deleteImage_other": "",
         "deleteImageBin": "Las imágenes eliminadas se enviarán a la papelera de tu sistema operativo.",
         "deleteImagePermanent": "Las imágenes eliminadas no se pueden restaurar.",
         "assets": "Activos",

invokeai/frontend/web/public/locales/it.json

@@ -82,7 +82,9 @@
         "autoSwitchNewImages": "Passaggio automatico a nuove immagini",
         "loadMore": "Carica altro",
         "noImagesInGallery": "Nessuna immagine da visualizzare",
-        "deleteImage": "Elimina l'immagine",
+        "deleteImage_one": "Elimina l'immagine",
+        "deleteImage_many": "Elimina {{count}} immagini",
+        "deleteImage_other": "Elimina {{count}} immagini",
         "deleteImagePermanent": "Le immagini eliminate non possono essere ripristinate.",
         "deleteImageBin": "Le immagini eliminate verranno spostate nel cestino del tuo sistema operativo.",
         "assets": "Risorse",

invokeai/frontend/web/public/locales/ja.json

@@ -90,7 +90,7 @@
         "problemDeletingImages": "画像の削除中に問題が発生",
         "drop": "ドロップ",
         "dropOrUpload": "$t(gallery.drop) またはアップロード",
-        "deleteImage": "画像を削除",
+        "deleteImage_other": "画像を削除",
         "deleteImageBin": "削除された画像はOSのゴミ箱に送られます。",
         "deleteImagePermanent": "削除された画像は復元できません。",
         "download": "ダウンロード",

invokeai/frontend/web/public/locales/ko.json

@@ -82,7 +82,7 @@
         "drop": "드랍",
         "problemDeletingImages": "이미지 삭제 중 발생한 문제",
         "downloadSelection": "선택 항목 다운로드",
-        "deleteImage": "이미지 삭제",
+        "deleteImage_other": "이미지 삭제",
         "currentlyInUse": "이 이미지는 현재 다음 기능에서 사용되고 있습니다:",
         "dropOrUpload": "$t(gallery.drop) 또는 업로드",
         "copy": "복사",

invokeai/frontend/web/public/locales/nl.json

@@ -42,7 +42,8 @@
         "autoSwitchNewImages": "Wissel autom. naar nieuwe afbeeldingen",
         "loadMore": "Laad meer",
         "noImagesInGallery": "Geen afbeeldingen om te tonen",
-        "deleteImage": "Verwijder afbeelding",
+        "deleteImage_one": "Verwijder afbeelding",
+        "deleteImage_other": "",
         "deleteImageBin": "Verwijderde afbeeldingen worden naar de prullenbak van je besturingssysteem gestuurd.",
         "deleteImagePermanent": "Verwijderde afbeeldingen kunnen niet worden hersteld.",
         "assets": "Eigen onderdelen",

invokeai/frontend/web/public/locales/ru.json

@@ -86,7 +86,9 @@
         "noImagesInGallery": "Изображений нет",
         "deleteImagePermanent": "Удаленные изображения невозможно восстановить.",
         "deleteImageBin": "Удаленные изображения будут отправлены в корзину вашей операционной системы.",
-        "deleteImage": "Удалить изображение",
+        "deleteImage_one": "Удалить изображение",
+        "deleteImage_few": "",
+        "deleteImage_many": "",
         "assets": "Ресурсы",
         "autoAssignBoardOnClick": "Авто-назначение доски по клику",
         "deleteSelection": "Удалить выделенное",

invokeai/frontend/web/public/locales/tr.json

@@ -298,7 +298,8 @@
         "noImagesInGallery": "Gösterilecek Görsel Yok",
         "autoSwitchNewImages": "Yeni Görseli Biter Bitmez Gör",
         "currentlyInUse": "Bu görsel şurada kullanımda:",
-        "deleteImage": "Görseli Sil",
+        "deleteImage_one": "Görseli Sil",
+        "deleteImage_other": "",
         "loadMore": "Daha Getir",
         "setCurrentImage": "Çalışma Görseli Yap",
         "unableToLoad": "Galeri Yüklenemedi",

invokeai/frontend/web/public/locales/zh_CN.json

@@ -78,7 +78,7 @@
         "autoSwitchNewImages": "自动切换到新图像",
         "loadMore": "加载更多",
         "noImagesInGallery": "无图像可用于显示",
-        "deleteImage": "删除图片",
+        "deleteImage_other": "删除图片",
         "deleteImageBin": "被删除的图片会发送到你操作系统的回收站。",
         "deleteImagePermanent": "删除的图片无法被恢复。",
         "assets": "素材",

invokeai/frontend/web/src/app/logging/logger.ts

@@ -20,14 +20,14 @@ export type LoggerNamespace =
   | 'models'
   | 'config'
   | 'canvas'
-  | 'txt2img'
-  | 'img2img'
+  | 'generation'
   | 'nodes'
   | 'system'
   | 'socketio'
   | 'session'
   | 'queue'
-  | 'dnd';
+  | 'dnd'
+  | 'controlLayers';
 
 export const logger = (namespace: LoggerNamespace) => $logger.get().child({ namespace });
 

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/index.ts

@@ -16,6 +16,7 @@ import { addCanvasMaskSavedToGalleryListener } from 'app/store/middleware/listen
 import { addCanvasMaskToControlNetListener } from 'app/store/middleware/listenerMiddleware/listeners/canvasMaskToControlNet';
 import { addCanvasMergedListener } from 'app/store/middleware/listenerMiddleware/listeners/canvasMerged';
 import { addCanvasSavedToGalleryListener } from 'app/store/middleware/listenerMiddleware/listeners/canvasSavedToGallery';
+import { addControlAdapterPreprocessor } from 'app/store/middleware/listenerMiddleware/listeners/controlAdapterPreprocessor';
 import { addControlNetAutoProcessListener } from 'app/store/middleware/listenerMiddleware/listeners/controlNetAutoProcess';
 import { addControlNetImageProcessedListener } from 'app/store/middleware/listenerMiddleware/listeners/controlNetImageProcessed';
 import { addEnqueueRequestedCanvasListener } from 'app/store/middleware/listenerMiddleware/listeners/enqueueRequestedCanvas';
@@ -31,7 +32,6 @@ import { addImagesStarredListener } from 'app/store/middleware/listenerMiddlewar
 import { addImagesUnstarredListener } from 'app/store/middleware/listenerMiddleware/listeners/imagesUnstarred';
 import { addImageToDeleteSelectedListener } from 'app/store/middleware/listenerMiddleware/listeners/imageToDeleteSelected';
 import { addImageUploadedFulfilledListener } from 'app/store/middleware/listenerMiddleware/listeners/imageUploaded';
-import { addInitialImageSelectedListener } from 'app/store/middleware/listenerMiddleware/listeners/initialImageSelected';
 import { addModelSelectedListener } from 'app/store/middleware/listenerMiddleware/listeners/modelSelected';
 import { addModelsLoadedListener } from 'app/store/middleware/listenerMiddleware/listeners/modelsLoaded';
 import { addDynamicPromptsListener } from 'app/store/middleware/listenerMiddleware/listeners/promptChanged';
@@ -72,9 +72,6 @@ const startAppListening = listenerMiddleware.startListening as AppStartListening
 // Image uploaded
 addImageUploadedFulfilledListener(startAppListening);
 
-// Image selected
-addInitialImageSelectedListener(startAppListening);
-
 // Image deleted
 addRequestedSingleImageDeletionListener(startAppListening);
 addDeleteBoardAndImagesFulfilledListener(startAppListening);
@@ -157,3 +154,4 @@ addUpscaleRequestedListener(startAppListening);
 addDynamicPromptsListener(startAppListening);
 
 addSetDefaultSettingsListener(startAppListening);
+addControlAdapterPreprocessor(startAppListening);

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/boardAndImagesDeleted.ts

@@ -1,9 +1,9 @@
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
 import { resetCanvas } from 'features/canvas/store/canvasSlice';
 import { controlAdaptersReset } from 'features/controlAdapters/store/controlAdaptersSlice';
+import { allLayersDeleted } from 'features/controlLayers/store/controlLayersSlice';
 import { getImageUsage } from 'features/deleteImageModal/store/selectors';
 import { nodeEditorReset } from 'features/nodes/store/nodesSlice';
-import { clearInitialImage } from 'features/parameters/store/generationSlice';
 import { imagesApi } from 'services/api/endpoints/images';
 
 export const addDeleteBoardAndImagesFulfilledListener = (startAppListening: AppStartListening) => {
@@ -14,19 +14,14 @@ export const addDeleteBoardAndImagesFulfilledListener = (startAppListening: AppS
 
       // Remove all deleted images from the UI
 
-      let wasInitialImageReset = false;
       let wasCanvasReset = false;
       let wasNodeEditorReset = false;
       let wereControlAdaptersReset = false;
+      let wereControlLayersReset = false;
 
-      const { generation, canvas, nodes, controlAdapters } = getState();
+      const { canvas, nodes, controlAdapters, controlLayers } = getState();
       deleted_images.forEach((image_name) => {
-        const imageUsage = getImageUsage(generation, canvas, nodes, controlAdapters, image_name);
-
-        if (imageUsage.isInitialImage && !wasInitialImageReset) {
-          dispatch(clearInitialImage());
-          wasInitialImageReset = true;
-        }
+        const imageUsage = getImageUsage(canvas, nodes, controlAdapters, controlLayers.present, image_name);
 
         if (imageUsage.isCanvasImage && !wasCanvasReset) {
           dispatch(resetCanvas());
@@ -42,6 +37,11 @@ export const addDeleteBoardAndImagesFulfilledListener = (startAppListening: AppS
           dispatch(controlAdaptersReset());
           wereControlAdaptersReset = true;
         }
+
+        if (imageUsage.isControlLayerImage && !wereControlLayersReset) {
+          dispatch(allLayersDeleted());
+          wereControlLayersReset = true;
+        }
       });
     },
   });

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/controlAdapterPreprocessor.ts

@@ -0,0 +1,156 @@
+import { isAnyOf } from '@reduxjs/toolkit';
+import { logger } from 'app/logging/logger';
+import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
+import { parseify } from 'common/util/serialize';
+import {
+  caLayerImageChanged,
+  caLayerIsProcessingImageChanged,
+  caLayerModelChanged,
+  caLayerProcessedImageChanged,
+  caLayerProcessorConfigChanged,
+  isControlAdapterLayer,
+} from 'features/controlLayers/store/controlLayersSlice';
+import { CA_PROCESSOR_DATA } from 'features/controlLayers/util/controlAdapters';
+import { isImageOutput } from 'features/nodes/types/common';
+import { addToast } from 'features/system/store/systemSlice';
+import { t } from 'i18next';
+import { isEqual } from 'lodash-es';
+import { imagesApi } from 'services/api/endpoints/images';
+import { queueApi } from 'services/api/endpoints/queue';
+import type { BatchConfig, ImageDTO } from 'services/api/types';
+import { socketInvocationComplete } from 'services/events/actions';
+
+const matcher = isAnyOf(caLayerImageChanged, caLayerProcessorConfigChanged, caLayerModelChanged);
+
+const DEBOUNCE_MS = 300;
+const log = logger('session');
+
+export const addControlAdapterPreprocessor = (startAppListening: AppStartListening) => {
+  startAppListening({
+    matcher,
+    effect: async (action, { dispatch, getState, getOriginalState, cancelActiveListeners, delay, take }) => {
+      const { layerId } = action.payload;
+      const precheckLayerOriginal = getOriginalState()
+        .controlLayers.present.layers.filter(isControlAdapterLayer)
+        .find((l) => l.id === layerId);
+      const precheckLayer = getState()
+        .controlLayers.present.layers.filter(isControlAdapterLayer)
+        .find((l) => l.id === layerId);
+
+      // Conditions to bail
+      const layerDoesNotExist = !precheckLayer;
+      const layerHasNoImage = !precheckLayer?.controlAdapter.image;
+      const layerHasNoProcessorConfig = !precheckLayer?.controlAdapter.processorConfig;
+      const layerIsAlreadyProcessingImage = precheckLayer?.controlAdapter.isProcessingImage;
+      const areImageAndProcessorUnchanged =
+        isEqual(precheckLayer?.controlAdapter.image, precheckLayerOriginal?.controlAdapter.image) &&
+        isEqual(precheckLayer?.controlAdapter.processorConfig, precheckLayerOriginal?.controlAdapter.processorConfig);
+
+      if (
+        layerDoesNotExist ||
+        layerHasNoImage ||
+        layerHasNoProcessorConfig ||
+        areImageAndProcessorUnchanged ||
+        layerIsAlreadyProcessingImage
+      ) {
+        return;
+      }
+
+      // Cancel any in-progress instances of this listener
+      cancelActiveListeners();
+      log.trace('Control Layer CA auto-process triggered');
+
+      // Delay before starting actual work
+      await delay(DEBOUNCE_MS);
+      dispatch(caLayerIsProcessingImageChanged({ layerId, isProcessingImage: true }));
+
+      // Double-check that we are still eligible for processing
+      const state = getState();
+      const layer = state.controlLayers.present.layers.filter(isControlAdapterLayer).find((l) => l.id === layerId);
+      const image = layer?.controlAdapter.image;
+      const config = layer?.controlAdapter.processorConfig;
+
+      // If we have no image or there is no processor config, bail
+      if (!layer || !image || !config) {
+        return;
+      }
+
+      // @ts-expect-error: TS isn't able to narrow the typing of buildNode and `config` will error...
+      const processorNode = CA_PROCESSOR_DATA[config.type].buildNode(image, config);
+      const enqueueBatchArg: BatchConfig = {
+        prepend: true,
+        batch: {
+          graph: {
+            nodes: {
+              [processorNode.id]: { ...processorNode, is_intermediate: true },
+            },
+            edges: [],
+          },
+          runs: 1,
+        },
+      };
+
+      try {
+        const req = dispatch(
+          queueApi.endpoints.enqueueBatch.initiate(enqueueBatchArg, {
+            fixedCacheKey: 'enqueueBatch',
+          })
+        );
+        const enqueueResult = await req.unwrap();
+        req.reset();
+        log.debug({ enqueueResult: parseify(enqueueResult) }, t('queue.graphQueued'));
+
+        const [invocationCompleteAction] = await take(
+          (action): action is ReturnType<typeof socketInvocationComplete> =>
+            socketInvocationComplete.match(action) &&
+            action.payload.data.queue_batch_id === enqueueResult.batch.batch_id &&
+            action.payload.data.source_node_id === processorNode.id
+        );
+
+        // We still have to check the output type
+        if (isImageOutput(invocationCompleteAction.payload.data.result)) {
+          const { image_name } = invocationCompleteAction.payload.data.result.image;
+
+          // Wait for the ImageDTO to be received
+          const [{ payload }] = await take(
+            (action) =>
+              imagesApi.endpoints.getImageDTO.matchFulfilled(action) && action.payload.image_name === image_name
+          );
+
+          const imageDTO = payload as ImageDTO;
+
+          log.debug({ layerId, imageDTO }, 'ControlNet image processed');
+
+          // Update the processed image in the store
+          dispatch(
+            caLayerProcessedImageChanged({
+              layerId,
+              imageDTO,
+            })
+          );
+          dispatch(caLayerIsProcessingImageChanged({ layerId, isProcessingImage: false }));
+        }
+      } catch (error) {
+        console.log(error);
+        log.error({ enqueueBatchArg: parseify(enqueueBatchArg) }, t('queue.graphFailedToQueue'));
+        dispatch(caLayerIsProcessingImageChanged({ layerId, isProcessingImage: false }));
+
+        if (error instanceof Object) {
+          if ('data' in error && 'status' in error) {
+            if (error.status === 403) {
+              dispatch(caLayerImageChanged({ layerId, imageDTO: null }));
+              return;
+            }
+          }
+        }
+
+        dispatch(
+          addToast({
+            title: t('queue.graphFailedToQueue'),
+            status: 'error',
+          })
+        );
+      }
+    },
+  });
+};

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/enqueueRequestedCanvas.ts

@@ -30,7 +30,7 @@ import type { ImageDTO } from 'services/api/types';
 export const addEnqueueRequestedCanvasListener = (startAppListening: AppStartListening) => {
   startAppListening({
     predicate: (action): action is ReturnType<typeof enqueueRequested> =>
-      enqueueRequested.match(action) && action.payload.tabName === 'unifiedCanvas',
+      enqueueRequested.match(action) && action.payload.tabName === 'canvas',
     effect: async (action, { getState, dispatch }) => {
       const log = logger('queue');
       const { prepend } = action.payload;

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/enqueueRequestedLinear.ts

@@ -1,16 +1,14 @@
 import { enqueueRequested } from 'app/store/actions';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
+import { buildGenerationTabGraph } from 'features/nodes/util/graph/buildGenerationTabGraph';
+import { buildGenerationTabSDXLGraph } from 'features/nodes/util/graph/buildGenerationTabSDXLGraph';
 import { prepareLinearUIBatch } from 'features/nodes/util/graph/buildLinearBatchConfig';
-import { buildLinearImageToImageGraph } from 'features/nodes/util/graph/buildLinearImageToImageGraph';
-import { buildLinearSDXLImageToImageGraph } from 'features/nodes/util/graph/buildLinearSDXLImageToImageGraph';
-import { buildLinearSDXLTextToImageGraph } from 'features/nodes/util/graph/buildLinearSDXLTextToImageGraph';
-import { buildLinearTextToImageGraph } from 'features/nodes/util/graph/buildLinearTextToImageGraph';
 import { queueApi } from 'services/api/endpoints/queue';
 
 export const addEnqueueRequestedLinear = (startAppListening: AppStartListening) => {
   startAppListening({
     predicate: (action): action is ReturnType<typeof enqueueRequested> =>
-      enqueueRequested.match(action) && (action.payload.tabName === 'txt2img' || action.payload.tabName === 'img2img'),
+      enqueueRequested.match(action) && action.payload.tabName === 'generation',
     effect: async (action, { getState, dispatch }) => {
       const state = getState();
       const model = state.generation.model;
@@ -19,17 +17,9 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
       let graph;
 
       if (model && model.base === 'sdxl') {
-        if (action.payload.tabName === 'txt2img') {
-          graph = await buildLinearSDXLTextToImageGraph(state);
-        } else {
-          graph = await buildLinearSDXLImageToImageGraph(state);
-        }
+        graph = await buildGenerationTabSDXLGraph(state);
       } else {
-        if (action.payload.tabName === 'txt2img') {
-          graph = await buildLinearTextToImageGraph(state);
-        } else {
-          graph = await buildLinearImageToImageGraph(state);
-        }
+        graph = await buildGenerationTabGraph(state);
       }
 
       const batchConfig = prepareLinearUIBatch(state, graph, prepend);

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/enqueueRequestedNodes.ts

@@ -8,7 +8,7 @@ import type { BatchConfig } from 'services/api/types';
 export const addEnqueueRequestedNodes = (startAppListening: AppStartListening) => {
   startAppListening({
     predicate: (action): action is ReturnType<typeof enqueueRequested> =>
-      enqueueRequested.match(action) && action.payload.tabName === 'nodes',
+      enqueueRequested.match(action) && action.payload.tabName === 'workflows',
     effect: async (action, { getState, dispatch }) => {
       const state = getState();
       const { nodes, edges } = state.nodes;

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/galleryImageClicked.ts

@@ -1,7 +1,7 @@
 import { createAction } from '@reduxjs/toolkit';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
 import { selectListImagesQueryArgs } from 'features/gallery/store/gallerySelectors';
-import { selectionChanged } from 'features/gallery/store/gallerySlice';
+import { isImageViewerOpenChanged, selectionChanged } from 'features/gallery/store/gallerySlice';
 import { imagesApi } from 'services/api/endpoints/images';
 import type { ImageDTO } from 'services/api/types';
 import { imagesSelectors } from 'services/api/util';
@@ -62,6 +62,7 @@ export const addGalleryImageClickedListener = (startAppListening: AppStartListen
       } else {
         dispatch(selectionChanged([imageDTO]));
       }
+      dispatch(isImageViewerOpenChanged(true));
     },
   });
 };

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/imageDeleted.ts

@@ -1,5 +1,6 @@
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
+import type { AppDispatch, RootState } from 'app/store/store';
 import { resetCanvas } from 'features/canvas/store/canvasSlice';
 import {
   controlAdapterImageChanged,
@@ -7,6 +8,13 @@ import {
   selectControlAdapterAll,
 } from 'features/controlAdapters/store/controlAdaptersSlice';
 import { isControlNetOrT2IAdapter } from 'features/controlAdapters/store/types';
+import {
+  isControlAdapterLayer,
+  isInitialImageLayer,
+  isIPAdapterLayer,
+  isRegionalGuidanceLayer,
+  layerDeleted,
+} from 'features/controlLayers/store/controlLayersSlice';
 import { imageDeletionConfirmed } from 'features/deleteImageModal/store/actions';
 import { isModalOpenChanged } from 'features/deleteImageModal/store/slice';
 import { selectListImagesQueryArgs } from 'features/gallery/store/gallerySelectors';
@@ -14,12 +22,82 @@ import { imageSelected } from 'features/gallery/store/gallerySlice';
 import { fieldImageValueChanged } from 'features/nodes/store/nodesSlice';
 import { isImageFieldInputInstance } from 'features/nodes/types/field';
 import { isInvocationNode } from 'features/nodes/types/invocation';
-import { clearInitialImage } from 'features/parameters/store/generationSlice';
 import { clamp, forEach } from 'lodash-es';
 import { api } from 'services/api';
 import { imagesApi } from 'services/api/endpoints/images';
+import type { ImageDTO } from 'services/api/types';
 import { imagesSelectors } from 'services/api/util';
 
+const deleteNodesImages = (state: RootState, dispatch: AppDispatch, imageDTO: ImageDTO) => {
+  state.nodes.nodes.forEach((node) => {
+    if (!isInvocationNode(node)) {
+      return;
+    }
+
+    forEach(node.data.inputs, (input) => {
+      if (isImageFieldInputInstance(input) && input.value?.image_name === imageDTO.image_name) {
+        dispatch(
+          fieldImageValueChanged({
+            nodeId: node.data.id,
+            fieldName: input.name,
+            value: undefined,
+          })
+        );
+      }
+    });
+  });
+};
+
+const deleteControlAdapterImages = (state: RootState, dispatch: AppDispatch, imageDTO: ImageDTO) => {
+  forEach(selectControlAdapterAll(state.controlAdapters), (ca) => {
+    if (
+      ca.controlImage === imageDTO.image_name ||
+      (isControlNetOrT2IAdapter(ca) && ca.processedControlImage === imageDTO.image_name)
+    ) {
+      dispatch(
+        controlAdapterImageChanged({
+          id: ca.id,
+          controlImage: null,
+        })
+      );
+      dispatch(
+        controlAdapterProcessedImageChanged({
+          id: ca.id,
+          processedControlImage: null,
+        })
+      );
+    }
+  });
+};
+
+const deleteControlLayerImages = (state: RootState, dispatch: AppDispatch, imageDTO: ImageDTO) => {
+  state.controlLayers.present.layers.forEach((l) => {
+    if (isRegionalGuidanceLayer(l)) {
+      if (l.ipAdapters.some((ipa) => ipa.image?.imageName === imageDTO.image_name)) {
+        dispatch(layerDeleted(l.id));
+      }
+    }
+    if (isControlAdapterLayer(l)) {
+      if (
+        l.controlAdapter.image?.imageName === imageDTO.image_name ||
+        l.controlAdapter.processedImage?.imageName === imageDTO.image_name
+      ) {
+        dispatch(layerDeleted(l.id));
+      }
+    }
+    if (isIPAdapterLayer(l)) {
+      if (l.ipAdapter.image?.imageName === imageDTO.image_name) {
+        dispatch(layerDeleted(l.id));
+      }
+    }
+    if (isInitialImageLayer(l)) {
+      if (l.image?.imageName === imageDTO.image_name) {
+        dispatch(layerDeleted(l.id));
+      }
+    }
+  });
+};
+
 export const addRequestedSingleImageDeletionListener = (startAppListening: AppStartListening) => {
   startAppListening({
     actionCreator: imageDeletionConfirmed,
@@ -73,50 +151,9 @@ export const addRequestedSingleImageDeletionListener = (startAppListening: AppSt
       }
 
       imageDTOs.forEach((imageDTO) => {
-        // reset init image if we deleted it
-        if (getState().generation.initialImage?.imageName === imageDTO.image_name) {
-          dispatch(clearInitialImage());
-        }
-
-        // reset control adapters that use the deleted images
-        forEach(selectControlAdapterAll(getState().controlAdapters), (ca) => {
-          if (
-            ca.controlImage === imageDTO.image_name ||
-            (isControlNetOrT2IAdapter(ca) && ca.processedControlImage === imageDTO.image_name)
-          ) {
-            dispatch(
-              controlAdapterImageChanged({
-                id: ca.id,
-                controlImage: null,
-              })
-            );
-            dispatch(
-              controlAdapterProcessedImageChanged({
-                id: ca.id,
-                processedControlImage: null,
-              })
-            );
-          }
-        });
-
-        // reset nodes that use the deleted images
-        getState().nodes.nodes.forEach((node) => {
-          if (!isInvocationNode(node)) {
-            return;
-          }
-
-          forEach(node.data.inputs, (input) => {
-            if (isImageFieldInputInstance(input) && input.value?.image_name === imageDTO.image_name) {
-              dispatch(
-                fieldImageValueChanged({
-                  nodeId: node.data.id,
-                  fieldName: input.name,
-                  value: undefined,
-                })
-              );
-            }
-          });
-        });
+        deleteControlAdapterImages(state, dispatch, imageDTO);
+        deleteNodesImages(state, dispatch, imageDTO);
+        deleteControlLayerImages(state, dispatch, imageDTO);
       });
 
       // Delete from server
@@ -168,50 +205,9 @@ export const addRequestedSingleImageDeletionListener = (startAppListening: AppSt
         }
 
         imageDTOs.forEach((imageDTO) => {
-          // reset init image if we deleted it
-          if (getState().generation.initialImage?.imageName === imageDTO.image_name) {
-            dispatch(clearInitialImage());
-          }
-
-          // reset control adapters that use the deleted images
-          forEach(selectControlAdapterAll(getState().controlAdapters), (ca) => {
-            if (
-              ca.controlImage === imageDTO.image_name ||
-              (isControlNetOrT2IAdapter(ca) && ca.processedControlImage === imageDTO.image_name)
-            ) {
-              dispatch(
-                controlAdapterImageChanged({
-                  id: ca.id,
-                  controlImage: null,
-                })
-              );
-              dispatch(
-                controlAdapterProcessedImageChanged({
-                  id: ca.id,
-                  processedControlImage: null,
-                })
-              );
-            }
-          });
-
-          // reset nodes that use the deleted images
-          getState().nodes.nodes.forEach((node) => {
-            if (!isInvocationNode(node)) {
-              return;
-            }
-
-            forEach(node.data.inputs, (input) => {
-              if (isImageFieldInputInstance(input) && input.value?.image_name === imageDTO.image_name) {
-                dispatch(
-                  fieldImageValueChanged({
-                    nodeId: node.data.id,
-                    fieldName: input.name,
-                    value: undefined,
-                  })
-                );
-              }
-            });
-          });
+          deleteControlAdapterImages(state, dispatch, imageDTO);
+          deleteNodesImages(state, dispatch, imageDTO);
+          deleteControlLayerImages(state, dispatch, imageDTO);
         });
       } catch {
         // no-op

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/imageDropped.ts

@@ -7,10 +7,16 @@ import {
   controlAdapterImageChanged,
   controlAdapterIsEnabledChanged,
 } from 'features/controlAdapters/store/controlAdaptersSlice';
+import {
+  caLayerImageChanged,
+  iiLayerImageChanged,
+  ipaLayerImageChanged,
+  rgLayerIPAdapterImageChanged,
+} from 'features/controlLayers/store/controlLayersSlice';
 import type { TypesafeDraggableData, TypesafeDroppableData } from 'features/dnd/types';
 import { imageSelected } from 'features/gallery/store/gallerySlice';
 import { fieldImageValueChanged } from 'features/nodes/store/nodesSlice';
-import { initialImageChanged, selectOptimalDimension } from 'features/parameters/store/generationSlice';
+import { selectOptimalDimension } from 'features/parameters/store/generationSlice';
 import { imagesApi } from 'services/api/endpoints/images';
 
 export const dndDropped = createAction<{
@@ -47,18 +53,6 @@ export const addImageDroppedListener = (startAppListening: AppStartListening) =>
         return;
       }
 
-      /**
-       * Image dropped on initial image
-       */
-      if (
-        overData.actionType === 'SET_INITIAL_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        dispatch(initialImageChanged(activeData.payload.imageDTO));
-        return;
-      }
-
       /**
        * Image dropped on ControlNet
        */
@@ -83,6 +77,79 @@ export const addImageDroppedListener = (startAppListening: AppStartListening) =>
         return;
       }
 
+      /**
+       * Image dropped on Control Adapter Layer
+       */
+      if (
+        overData.actionType === 'SET_CA_LAYER_IMAGE' &&
+        activeData.payloadType === 'IMAGE_DTO' &&
+        activeData.payload.imageDTO
+      ) {
+        const { layerId } = overData.context;
+        dispatch(
+          caLayerImageChanged({
+            layerId,
+            imageDTO: activeData.payload.imageDTO,
+          })
+        );
+        return;
+      }
+
+      /**
+       * Image dropped on IP Adapter Layer
+       */
+      if (
+        overData.actionType === 'SET_IPA_LAYER_IMAGE' &&
+        activeData.payloadType === 'IMAGE_DTO' &&
+        activeData.payload.imageDTO
+      ) {
+        const { layerId } = overData.context;
+        dispatch(
+          ipaLayerImageChanged({
+            layerId,
+            imageDTO: activeData.payload.imageDTO,
+          })
+        );
+        return;
+      }
+
+      /**
+       * Image dropped on RG Layer IP Adapter
+       */
+      if (
+        overData.actionType === 'SET_RG_LAYER_IP_ADAPTER_IMAGE' &&
+        activeData.payloadType === 'IMAGE_DTO' &&
+        activeData.payload.imageDTO
+      ) {
+        const { layerId, ipAdapterId } = overData.context;
+        dispatch(
+          rgLayerIPAdapterImageChanged({
+            layerId,
+            ipAdapterId,
+            imageDTO: activeData.payload.imageDTO,
+          })
+        );
+        return;
+      }
+
+      /**
+       * Image dropped on II Layer Image
+       */
+      if (
+        overData.actionType === 'SET_II_LAYER_IMAGE' &&
+        activeData.payloadType === 'IMAGE_DTO' &&
+        activeData.payload.imageDTO
+      ) {
+        const { layerId } = overData.context;
+        dispatch(
+          iiLayerImageChanged({
+            layerId,
+            imageDTO: activeData.payload.imageDTO,
+          })
+        );
+        return;
+      }
+
       /**
        * Image dropped on Canvas
        */

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/imageToDeleteSelected.ts

@@ -14,7 +14,6 @@ export const addImageToDeleteSelectedListener = (startAppListening: AppStartList
 
       const isImageInUse =
         imagesUsage.some((i) => i.isCanvasImage) ||
-        imagesUsage.some((i) => i.isInitialImage) ||
         imagesUsage.some((i) => i.isControlImage) ||
         imagesUsage.some((i) => i.isNodesImage);
 

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/imageUploaded.ts

@@ -6,8 +6,14 @@ import {
   controlAdapterImageChanged,
   controlAdapterIsEnabledChanged,
 } from 'features/controlAdapters/store/controlAdaptersSlice';
+import {
+  caLayerImageChanged,
+  iiLayerImageChanged,
+  ipaLayerImageChanged,
+  rgLayerIPAdapterImageChanged,
+} from 'features/controlLayers/store/controlLayersSlice';
 import { fieldImageValueChanged } from 'features/nodes/store/nodesSlice';
-import { initialImageChanged, selectOptimalDimension } from 'features/parameters/store/generationSlice';
+import { selectOptimalDimension } from 'features/parameters/store/generationSlice';
 import { addToast } from 'features/system/store/systemSlice';
 import { t } from 'i18next';
 import { omit } from 'lodash-es';
@@ -108,15 +114,48 @@ export const addImageUploadedFulfilledListener = (startAppListening: AppStartLis
         return;
       }
 
-      if (postUploadAction?.type === 'SET_INITIAL_IMAGE') {
-        dispatch(initialImageChanged(imageDTO));
+      if (postUploadAction?.type === 'SET_CA_LAYER_IMAGE') {
+        const { layerId } = postUploadAction;
+        dispatch(caLayerImageChanged({ layerId, imageDTO }));
         dispatch(
           addToast({
             ...DEFAULT_UPLOADED_TOAST,
-            description: t('toast.setInitialImage'),
+            description: t('toast.setControlImage'),
+          })
+        );
+      }
+
+      if (postUploadAction?.type === 'SET_IPA_LAYER_IMAGE') {
+        const { layerId } = postUploadAction;
+        dispatch(ipaLayerImageChanged({ layerId, imageDTO }));
+        dispatch(
+          addToast({
+            ...DEFAULT_UPLOADED_TOAST,
+            description: t('toast.setControlImage'),
+          })
+        );
+      }
+
+      if (postUploadAction?.type === 'SET_RG_LAYER_IP_ADAPTER_IMAGE') {
+        const { layerId, ipAdapterId } = postUploadAction;
+        dispatch(rgLayerIPAdapterImageChanged({ layerId, ipAdapterId, imageDTO }));
+        dispatch(
+          addToast({
+            ...DEFAULT_UPLOADED_TOAST,
+            description: t('toast.setControlImage'),
+          })
+        );
+      }
+
+      if (postUploadAction?.type === 'SET_II_LAYER_IMAGE') {
+        const { layerId } = postUploadAction;
+        dispatch(iiLayerImageChanged({ layerId, imageDTO }));
+        dispatch(
+          addToast({
+            ...DEFAULT_UPLOADED_TOAST,
+            description: t('toast.setControlImage'),
           })
         );
-        return;
       }
 
       if (postUploadAction?.type === 'SET_NODES_IMAGE') {

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/initialImageSelected.ts

@@ -1,21 +0,0 @@
-import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import { initialImageSelected } from 'features/parameters/store/actions';
-import { initialImageChanged } from 'features/parameters/store/generationSlice';
-import { addToast } from 'features/system/store/systemSlice';
-import { makeToast } from 'features/system/util/makeToast';
-import { t } from 'i18next';
-
-export const addInitialImageSelectedListener = (startAppListening: AppStartListening) => {
-  startAppListening({
-    actionCreator: initialImageSelected,
-    effect: (action, { dispatch }) => {
-      if (!action.payload) {
-        dispatch(addToast(makeToast({ title: t('toast.imageNotLoadedDesc'), status: 'error' })));
-        return;
-      }
-
-      dispatch(initialImageChanged(action.payload));
-      dispatch(addToast(makeToast(t('toast.sentToImageToImage'))));
-    },
-  });
-};

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/modelsLoaded.ts

@@ -6,9 +6,10 @@ import {
   controlAdapterModelCleared,
   selectControlAdapterAll,
 } from 'features/controlAdapters/store/controlAdaptersSlice';
+import { heightChanged, widthChanged } from 'features/controlLayers/store/controlLayersSlice';
 import { loraRemoved } from 'features/lora/store/loraSlice';
 import { calculateNewSize } from 'features/parameters/components/ImageSize/calculateNewSize';
-import { heightChanged, modelChanged, vaeSelected, widthChanged } from 'features/parameters/store/generationSlice';
+import { modelChanged, vaeSelected } from 'features/parameters/store/generationSlice';
 import { zParameterModel, zParameterVAEModel } from 'features/parameters/types/parameterSchemas';
 import { getIsSizeOptimal, getOptimalDimension } from 'features/parameters/util/optimalDimension';
 import { refinerModelChanged } from 'features/sdxl/store/sdxlSlice';
@@ -69,16 +70,22 @@ const handleMainModels: ModelHandler = (models, state, dispatch, log) => {
       dispatch(modelChanged(defaultModelInList, currentModel));
 
       const optimalDimension = getOptimalDimension(defaultModelInList);
-      if (getIsSizeOptimal(state.generation.width, state.generation.height, optimalDimension)) {
+      if (
+        getIsSizeOptimal(
+          state.controlLayers.present.size.width,
+          state.controlLayers.present.size.height,
+          optimalDimension
+        )
+      ) {
         return;
       }
       const { width, height } = calculateNewSize(
-        state.generation.aspectRatio.value,
+        state.controlLayers.present.size.aspectRatio.value,
         optimalDimension * optimalDimension
       );
 
-      dispatch(widthChanged(width));
-      dispatch(heightChanged(height));
+      dispatch(widthChanged({ width }));
+      dispatch(heightChanged({ height }));
       return;
     }
   }

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/promptChanged.ts

@@ -1,5 +1,6 @@
 import { isAnyOf } from '@reduxjs/toolkit';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
+import { positivePromptChanged } from 'features/controlLayers/store/controlLayersSlice';
 import {
   combinatorialToggled,
   isErrorChanged,
@@ -10,11 +11,16 @@ import {
   promptsChanged,
 } from 'features/dynamicPrompts/store/dynamicPromptsSlice';
 import { getShouldProcessPrompt } from 'features/dynamicPrompts/util/getShouldProcessPrompt';
-import { setPositivePrompt } from 'features/parameters/store/generationSlice';
 import { utilitiesApi } from 'services/api/endpoints/utilities';
 import { socketConnected } from 'services/events/actions';
 
-const matcher = isAnyOf(setPositivePrompt, combinatorialToggled, maxPromptsChanged, maxPromptsReset, socketConnected);
+const matcher = isAnyOf(
+  positivePromptChanged,
+  combinatorialToggled,
+  maxPromptsChanged,
+  maxPromptsReset,
+  socketConnected
+);
 
 export const addDynamicPromptsListener = (startAppListening: AppStartListening) => {
   startAppListening({
@@ -22,7 +28,7 @@ export const addDynamicPromptsListener = (startAppListening: AppStartListening)
     effect: async (action, { dispatch, getState, cancelActiveListeners, delay }) => {
       cancelActiveListeners();
       const state = getState();
-      const { positivePrompt } = state.generation;
+      const { positivePrompt } = state.controlLayers.present;
       const { maxPrompts } = state.dynamicPrompts;
 
       if (state.config.disabledFeatures.includes('dynamicPrompting')) {
@@ -32,7 +38,7 @@ export const addDynamicPromptsListener = (startAppListening: AppStartListening)
       const cachedPrompts = utilitiesApi.endpoints.dynamicPrompts.select({
         prompt: positivePrompt,
         max_prompts: maxPrompts,
-      })(getState()).data;
+      })(state).data;
 
       if (cachedPrompts) {
         dispatch(promptsChanged(cachedPrompts.prompts));
@@ -40,8 +46,8 @@ export const addDynamicPromptsListener = (startAppListening: AppStartListening)
         return;
       }
 
-      if (!getShouldProcessPrompt(state.generation.positivePrompt)) {
-        dispatch(promptsChanged([state.generation.positivePrompt]));
+      if (!getShouldProcessPrompt(positivePrompt)) {
+        dispatch(promptsChanged([positivePrompt]));
         dispatch(parsingErrorChanged(undefined));
         dispatch(isErrorChanged(false));
         return;

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/setDefaultSettings.ts

@@ -1,14 +1,13 @@
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
+import { heightChanged, widthChanged } from 'features/controlLayers/store/controlLayersSlice';
 import { setDefaultSettings } from 'features/parameters/store/actions';
 import {
-  heightRecalled,
   setCfgRescaleMultiplier,
   setCfgScale,
   setScheduler,
   setSteps,
   vaePrecisionChanged,
   vaeSelected,
-  widthRecalled,
 } from 'features/parameters/store/generationSlice';
 import {
   isParameterCFGRescaleMultiplier,
@@ -97,16 +96,16 @@ export const addSetDefaultSettingsListener = (startAppListening: AppStartListeni
             dispatch(setScheduler(scheduler));
           }
         }
-
+        const setSizeOptions = { updateAspectRatio: true, clamp: true };
         if (width) {
           if (isParameterWidth(width)) {
-            dispatch(widthRecalled(width));
+            dispatch(widthChanged({ width, ...setSizeOptions }));
           }
         }
 
         if (height) {
           if (isParameterHeight(height)) {
-            dispatch(heightRecalled(height));
+            dispatch(heightChanged({ height, ...setSizeOptions }));
           }
         }
 

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/socketio/socketInvocationComplete.ts

@@ -2,7 +2,12 @@ import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
 import { parseify } from 'common/util/serialize';
 import { addImageToStagingArea } from 'features/canvas/store/canvasSlice';
-import { boardIdSelected, galleryViewChanged, imageSelected } from 'features/gallery/store/gallerySlice';
+import {
+  boardIdSelected,
+  galleryViewChanged,
+  imageSelected,
+  isImageViewerOpenChanged,
+} from 'features/gallery/store/gallerySlice';
 import { IMAGE_CATEGORIES } from 'features/gallery/store/types';
 import { isImageOutput } from 'features/nodes/types/common';
 import { CANVAS_OUTPUT } from 'features/nodes/util/graph/constants';
@@ -101,6 +106,7 @@ export const addInvocationCompleteEventListener = (startAppListening: AppStartLi
             }
 
             dispatch(imageSelected(imageDTO));
+            dispatch(isImageViewerOpenChanged(true));
           }
         }
       }

invokeai/frontend/web/src/app/store/store.ts

@@ -10,6 +10,11 @@ import {
   controlAdaptersPersistConfig,
   controlAdaptersSlice,
 } from 'features/controlAdapters/store/controlAdaptersSlice';
+import {
+  controlLayersPersistConfig,
+  controlLayersSlice,
+  controlLayersUndoableConfig,
+} from 'features/controlLayers/store/controlLayersSlice';
 import { deleteImageModalSlice } from 'features/deleteImageModal/store/slice';
 import { dynamicPromptsPersistConfig, dynamicPromptsSlice } from 'features/dynamicPrompts/store/dynamicPromptsSlice';
 import { galleryPersistConfig, gallerySlice } from 'features/gallery/store/gallerySlice';
@@ -30,6 +35,7 @@ import { defaultsDeep, keys, omit, pick } from 'lodash-es';
 import dynamicMiddlewares from 'redux-dynamic-middlewares';
 import type { SerializeFunction, UnserializeFunction } from 'redux-remember';
 import { rememberEnhancer, rememberReducer } from 'redux-remember';
+import undoable from 'redux-undo';
 import { serializeError } from 'serialize-error';
 import { api } from 'services/api';
 import { authToastMiddleware } from 'services/api/authToastMiddleware';
@@ -59,6 +65,7 @@ const allReducers = {
   [queueSlice.name]: queueSlice.reducer,
   [workflowSlice.name]: workflowSlice.reducer,
   [hrfSlice.name]: hrfSlice.reducer,
+  [controlLayersSlice.name]: undoable(controlLayersSlice.reducer, controlLayersUndoableConfig),
   [api.reducerPath]: api.reducer,
 };
 
@@ -103,6 +110,7 @@ const persistConfigs: { [key in keyof typeof allReducers]?: PersistConfig } = {
   [loraPersistConfig.name]: loraPersistConfig,
   [modelManagerV2PersistConfig.name]: modelManagerV2PersistConfig,
   [hrfPersistConfig.name]: hrfPersistConfig,
+  [controlLayersPersistConfig.name]: controlLayersPersistConfig,
 };
 
 const unserialize: UnserializeFunction = (data, key) => {
@@ -114,6 +122,7 @@ const unserialize: UnserializeFunction = (data, key) => {
   try {
     const { initialState, migrate } = persistConfig;
     const parsed = JSON.parse(data);
+
     // strip out old keys
     const stripped = pick(parsed, keys(initialState));
     // run (additive) migrations
@@ -141,7 +150,9 @@ const serialize: SerializeFunction = (data, key) => {
   if (!persistConfig) {
     throw new Error(`No persist config for slice "${key}"`);
   }
-  const result = omit(data, persistConfig.persistDenylist);
+  // Heuristic to determine if the slice is undoable - could just hardcode it in the persistConfig
+  const isUndoable = 'present' in data && 'past' in data && 'future' in data && '_latestUnfiltered' in data;
+  const result = omit(isUndoable ? data.present : data, persistConfig.persistDenylist);
   return JSON.stringify(result);
 };
 

invokeai/frontend/web/src/common/components/IAIColorPicker.tsx

@@ -26,7 +26,7 @@ const sx: ChakraProps['sx'] = {
 
 const colorPickerStyles: CSSProperties = { width: '100%' };
 
-const numberInputWidth: ChakraProps['w'] = '4.2rem';
+const numberInputWidth: ChakraProps['w'] = '3.5rem';
 
 const IAIColorPicker = (props: IAIColorPickerProps) => {
   const { color, onChange, withNumberInput, ...rest } = props;
@@ -41,7 +41,7 @@ const IAIColorPicker = (props: IAIColorPickerProps) => {
       {withNumberInput && (
         <Flex gap={5}>
           <FormControl gap={0}>
-            <FormLabel>{t('common.red')}</FormLabel>
+            <FormLabel>{t('common.red')[0]}</FormLabel>
             <CompositeNumberInput
               value={color.r}
               onChange={handleChangeR}
@@ -53,7 +53,7 @@ const IAIColorPicker = (props: IAIColorPickerProps) => {
             />
           </FormControl>
           <FormControl gap={0}>
-            <FormLabel>{t('common.green')}</FormLabel>
+            <FormLabel>{t('common.green')[0]}</FormLabel>
             <CompositeNumberInput
               value={color.g}
               onChange={handleChangeG}
@@ -65,7 +65,7 @@ const IAIColorPicker = (props: IAIColorPickerProps) => {
             />
           </FormControl>
           <FormControl gap={0}>
-            <FormLabel>{t('common.blue')}</FormLabel>
+            <FormLabel>{t('common.blue')[0]}</FormLabel>
             <CompositeNumberInput
               value={color.b}
               onChange={handleChangeB}
@@ -77,7 +77,7 @@ const IAIColorPicker = (props: IAIColorPickerProps) => {
             />
           </FormControl>
           <FormControl gap={0}>
-            <FormLabel>{t('common.alpha')}</FormLabel>
+            <FormLabel>{t('common.alpha')[0]}</FormLabel>
             <CompositeNumberInput
               value={color.a}
               onChange={handleChangeA}

invokeai/frontend/web/src/common/components/InformationalPopover/constants.ts

@@ -24,6 +24,7 @@ export type Feature =
   | 'dynamicPromptsSeedBehaviour'
   | 'imageFit'
   | 'infillMethod'
+  | 'ipAdapterMethod'
   | 'lora'
   | 'loraWeight'
   | 'noiseUseCPU'

invokeai/frontend/web/src/common/components/RgbColorPicker.tsx

@@ -0,0 +1,84 @@
+import type { ChakraProps } from '@invoke-ai/ui-library';
+import { CompositeNumberInput, Flex, FormControl, FormLabel } from '@invoke-ai/ui-library';
+import type { CSSProperties } from 'react';
+import { memo, useCallback } from 'react';
+import { RgbColorPicker as ColorfulRgbColorPicker } from 'react-colorful';
+import type { ColorPickerBaseProps, RgbColor } from 'react-colorful/dist/types';
+import { useTranslation } from 'react-i18next';
+
+type RgbColorPickerProps = ColorPickerBaseProps<RgbColor> & {
+  withNumberInput?: boolean;
+};
+
+const colorPickerPointerStyles: NonNullable<ChakraProps['sx']> = {
+  width: 6,
+  height: 6,
+  borderColor: 'base.100',
+};
+
+const sx: ChakraProps['sx'] = {
+  '.react-colorful__hue-pointer': colorPickerPointerStyles,
+  '.react-colorful__saturation-pointer': colorPickerPointerStyles,
+  '.react-colorful__alpha-pointer': colorPickerPointerStyles,
+  gap: 5,
+  flexDir: 'column',
+};
+
+const colorPickerStyles: CSSProperties = { width: '100%' };
+
+const numberInputWidth: ChakraProps['w'] = '3.5rem';
+
+const RgbColorPicker = (props: RgbColorPickerProps) => {
+  const { color, onChange, withNumberInput, ...rest } = props;
+  const { t } = useTranslation();
+  const handleChangeR = useCallback((r: number) => onChange({ ...color, r }), [color, onChange]);
+  const handleChangeG = useCallback((g: number) => onChange({ ...color, g }), [color, onChange]);
+  const handleChangeB = useCallback((b: number) => onChange({ ...color, b }), [color, onChange]);
+  return (
+    <Flex sx={sx}>
+      <ColorfulRgbColorPicker color={color} onChange={onChange} style={colorPickerStyles} {...rest} />
+      {withNumberInput && (
+        <Flex gap={5}>
+          <FormControl gap={0}>
+            <FormLabel>{t('common.red')[0]}</FormLabel>
+            <CompositeNumberInput
+              value={color.r}
+              onChange={handleChangeR}
+              min={0}
+              max={255}
+              step={1}
+              w={numberInputWidth}
+              defaultValue={90}
+            />
+          </FormControl>
+          <FormControl gap={0}>
+            <FormLabel>{t('common.green')[0]}</FormLabel>
+            <CompositeNumberInput
+              value={color.g}
+              onChange={handleChangeG}
+              min={0}
+              max={255}
+              step={1}
+              w={numberInputWidth}
+              defaultValue={90}
+            />
+          </FormControl>
+          <FormControl gap={0}>
+            <FormLabel>{t('common.blue')[0]}</FormLabel>
+            <CompositeNumberInput
+              value={color.b}
+              onChange={handleChangeB}
+              min={0}
+              max={255}
+              step={1}
+              w={numberInputWidth}
+              defaultValue={255}
+            />
+          </FormControl>
+        </Flex>
+      )}
+    </Flex>
+  );
+};
+
+export default memo(RgbColorPicker);

invokeai/frontend/web/src/common/hooks/useFullscreenDropzone.ts

@@ -17,14 +17,10 @@ const accept: Accept = {
 const selectPostUploadAction = createMemoizedSelector(activeTabNameSelector, (activeTabName) => {
   let postUploadAction: PostUploadAction = { type: 'TOAST' };
 
-  if (activeTabName === 'unifiedCanvas') {
+  if (activeTabName === 'canvas') {
     postUploadAction = { type: 'SET_CANVAS_INITIAL_IMAGE' };
   }
 
-  if (activeTabName === 'img2img') {
-    postUploadAction = { type: 'SET_INITIAL_IMAGE' };
-  }
-
   return postUploadAction;
 });
 

invokeai/frontend/web/src/common/hooks/useGlobalHotkeys.ts

@@ -9,7 +9,7 @@ import { useHotkeys } from 'react-hotkeys-hook';
 
 export const useGlobalHotkeys = () => {
   const dispatch = useAppDispatch();
-  const isModelManagerEnabled = useFeatureStatus('modelManager').isFeatureEnabled;
+  const isModelManagerEnabled = useFeatureStatus('modelManager');
   const { queueBack, isDisabled: isDisabledQueueBack, isLoading: isLoadingQueueBack } = useQueueBack();
 
   useHotkeys(
@@ -67,7 +67,7 @@ export const useGlobalHotkeys = () => {
   useHotkeys(
     '1',
     () => {
-      dispatch(setActiveTab('txt2img'));
+      dispatch(setActiveTab('generation'));
     },
     [dispatch]
   );
@@ -75,7 +75,7 @@ export const useGlobalHotkeys = () => {
   useHotkeys(
     '2',
     () => {
-      dispatch(setActiveTab('img2img'));
+      dispatch(setActiveTab('canvas'));
     },
     [dispatch]
   );
@@ -83,31 +83,23 @@ export const useGlobalHotkeys = () => {
   useHotkeys(
     '3',
     () => {
-      dispatch(setActiveTab('unifiedCanvas'));
+      dispatch(setActiveTab('workflows'));
     },
     [dispatch]
   );
 
   useHotkeys(
     '4',
-    () => {
-      dispatch(setActiveTab('nodes'));
-    },
-    [dispatch]
-  );
-
-  useHotkeys(
-    '5',
     () => {
       if (isModelManagerEnabled) {
-        dispatch(setActiveTab('modelManager'));
+        dispatch(setActiveTab('models'));
       }
     },
     [dispatch, isModelManagerEnabled]
   );
 
   useHotkeys(
-    isModelManagerEnabled ? '6' : '5',
+    isModelManagerEnabled ? '5' : '4',
     () => {
       dispatch(setActiveTab('queue'));
     },

invokeai/frontend/web/src/common/hooks/useIsReadyToEnqueue.ts

@@ -5,6 +5,7 @@ import {
   selectControlAdaptersSlice,
 } from 'features/controlAdapters/store/controlAdaptersSlice';
 import { isControlNetOrT2IAdapter } from 'features/controlAdapters/store/types';
+import { selectControlLayersSlice } from 'features/controlLayers/store/controlLayersSlice';
 import { selectDynamicPromptsSlice } from 'features/dynamicPrompts/store/dynamicPromptsSlice';
 import { getShouldProcessPrompt } from 'features/dynamicPrompts/util/getShouldProcessPrompt';
 import { selectNodesSlice } from 'features/nodes/store/nodesSlice';
@@ -23,10 +24,12 @@ const selector = createMemoizedSelector(
     selectSystemSlice,
     selectNodesSlice,
     selectDynamicPromptsSlice,
+    selectControlLayersSlice,
     activeTabNameSelector,
   ],
-  (controlAdapters, generation, system, nodes, dynamicPrompts, activeTabName) => {
-    const { initialImage, model, positivePrompt } = generation;
+  (controlAdapters, generation, system, nodes, dynamicPrompts, controlLayers, activeTabName) => {
+    const { model } = generation;
+    const { positivePrompt } = controlLayers.present;
 
     const { isConnected } = system;
 
@@ -37,11 +40,7 @@ const selector = createMemoizedSelector(
       reasons.push(i18n.t('parameters.invoke.systemDisconnected'));
     }
 
-    if (activeTabName === 'img2img' && !initialImage) {
-      reasons.push(i18n.t('parameters.invoke.noInitialImageSelected'));
-    }
-
-    if (activeTabName === 'nodes') {
+    if (activeTabName === 'workflows') {
       if (nodes.shouldValidateGraph) {
         if (!nodes.nodes.length) {
           reasons.push(i18n.t('parameters.invoke.noNodesInGraph'));
@@ -94,37 +93,93 @@ const selector = createMemoizedSelector(
         reasons.push(i18n.t('parameters.invoke.noModelSelected'));
       }
 
-      selectControlAdapterAll(controlAdapters).forEach((ca, i) => {
-        if (!ca.isEnabled) {
-          return;
-        }
+      if (activeTabName === 'generation') {
+        // Handling for generation tab
+        controlLayers.present.layers
+          .filter((l) => l.isEnabled)
+          .flatMap((l) => {
+            if (l.type === 'control_adapter_layer') {
+              return l.controlAdapter;
+            } else if (l.type === 'ip_adapter_layer') {
+              return l.ipAdapter;
+            } else if (l.type === 'regional_guidance_layer') {
+              return l.ipAdapters;
+            }
+            return [];
+          })
+          .forEach((ca, i) => {
+            const hasNoModel = !ca.model;
+            const mismatchedModelBase = ca.model?.base !== model?.base;
+            const hasNoImage = !ca.image;
+            const imageNotProcessed =
+              (ca.type === 'controlnet' || ca.type === 't2i_adapter') && !ca.processedImage && ca.processorConfig;
 
-        if (!ca.model) {
-          reasons.push(
-            i18n.t('parameters.invoke.noModelForControlAdapter', {
-              number: i + 1,
-            })
-          );
-        } else if (ca.model.base !== model?.base) {
-          // This should never happen, just a sanity check
-          reasons.push(
-            i18n.t('parameters.invoke.incompatibleBaseModelForControlAdapter', {
-              number: i + 1,
-            })
-          );
-        }
+            if (hasNoModel) {
+              reasons.push(
+                i18n.t('parameters.invoke.noModelForControlAdapter', {
+                  number: i + 1,
+                })
+              );
+            }
+            if (mismatchedModelBase) {
+              // This should never happen, just a sanity check
+              reasons.push(
+                i18n.t('parameters.invoke.incompatibleBaseModelForControlAdapter', {
+                  number: i + 1,
+                })
+              );
+            }
+            if (hasNoImage) {
+              reasons.push(
+                i18n.t('parameters.invoke.noControlImageForControlAdapter', {
+                  number: i + 1,
+                })
+              );
+            }
+            if (imageNotProcessed) {
+              reasons.push(
+                i18n.t('parameters.invoke.imageNotProcessedForControlAdapter', {
+                  number: i + 1,
+                })
+              );
+            }
+          });
+      } else {
+        // Handling for all other tabs
+        selectControlAdapterAll(controlAdapters)
+          .filter((ca) => ca.isEnabled)
+          .forEach((ca, i) => {
+            if (!ca.isEnabled) {
+              return;
+            }
 
-        if (
-          !ca.controlImage ||
-          (isControlNetOrT2IAdapter(ca) && !ca.processedControlImage && ca.processorType !== 'none')
-        ) {
-          reasons.push(
-            i18n.t('parameters.invoke.noControlImageForControlAdapter', {
-              number: i + 1,
-            })
-          );
-        }
-      });
+            if (!ca.model) {
+              reasons.push(
+                i18n.t('parameters.invoke.noModelForControlAdapter', {
+                  number: i + 1,
+                })
+              );
+            } else if (ca.model.base !== model?.base) {
+              // This should never happen, just a sanity check
+              reasons.push(
+                i18n.t('parameters.invoke.incompatibleBaseModelForControlAdapter', {
+                  number: i + 1,
+                })
+              );
+            }
+
+            if (
+              !ca.controlImage ||
+              (isControlNetOrT2IAdapter(ca) && !ca.processedControlImage && ca.processorType !== 'none')
+            ) {
+              reasons.push(
+                i18n.t('parameters.invoke.noControlImageForControlAdapter', {
+                  number: i + 1,
+                })
+              );
+            }
+          });
+      }
     }
 
     return { isReady: !reasons.length, reasons };

invokeai/frontend/web/src/common/util/arrayUtils.test.ts

@@ -0,0 +1,85 @@
+import { moveBackward, moveForward, moveToBack, moveToFront } from 'common/util/arrayUtils';
+import { describe, expect, it } from 'vitest';
+
+describe('Array Manipulation Functions', () => {
+  const originalArray = ['a', 'b', 'c', 'd'];
+  describe('moveForwardOne', () => {
+    it('should move an item forward by one position', () => {
+      const array = [...originalArray];
+      const result = moveForward(array, (item) => item === 'b');
+      expect(result).toEqual(['a', 'c', 'b', 'd']);
+    });
+
+    it('should do nothing if the item is at the end', () => {
+      const array = [...originalArray];
+      const result = moveForward(array, (item) => item === 'd');
+      expect(result).toEqual(['a', 'b', 'c', 'd']);
+    });
+
+    it("should leave the array unchanged if the item isn't in the array", () => {
+      const array = [...originalArray];
+      const result = moveForward(array, (item) => item === 'z');
+      expect(result).toEqual(originalArray);
+    });
+  });
+
+  describe('moveToFront', () => {
+    it('should move an item to the front', () => {
+      const array = [...originalArray];
+      const result = moveToFront(array, (item) => item === 'c');
+      expect(result).toEqual(['c', 'a', 'b', 'd']);
+    });
+
+    it('should do nothing if the item is already at the front', () => {
+      const array = [...originalArray];
+      const result = moveToFront(array, (item) => item === 'a');
+      expect(result).toEqual(['a', 'b', 'c', 'd']);
+    });
+
+    it("should leave the array unchanged if the item isn't in the array", () => {
+      const array = [...originalArray];
+      const result = moveToFront(array, (item) => item === 'z');
+      expect(result).toEqual(originalArray);
+    });
+  });
+
+  describe('moveBackwardsOne', () => {
+    it('should move an item backward by one position', () => {
+      const array = [...originalArray];
+      const result = moveBackward(array, (item) => item === 'c');
+      expect(result).toEqual(['a', 'c', 'b', 'd']);
+    });
+
+    it('should do nothing if the item is at the beginning', () => {
+      const array = [...originalArray];
+      const result = moveBackward(array, (item) => item === 'a');
+      expect(result).toEqual(['a', 'b', 'c', 'd']);
+    });
+
+    it("should leave the array unchanged if the item isn't in the array", () => {
+      const array = [...originalArray];
+      const result = moveBackward(array, (item) => item === 'z');
+      expect(result).toEqual(originalArray);
+    });
+  });
+
+  describe('moveToBack', () => {
+    it('should move an item to the back', () => {
+      const array = [...originalArray];
+      const result = moveToBack(array, (item) => item === 'b');
+      expect(result).toEqual(['a', 'c', 'd', 'b']);
+    });
+
+    it('should do nothing if the item is already at the back', () => {
+      const array = [...originalArray];
+      const result = moveToBack(array, (item) => item === 'd');
+      expect(result).toEqual(['a', 'b', 'c', 'd']);
+    });
+
+    it("should leave the array unchanged if the item isn't in the array", () => {
+      const array = [...originalArray];
+      const result = moveToBack(array, (item) => item === 'z');
+      expect(result).toEqual(originalArray);
+    });
+  });
+});

invokeai/frontend/web/src/common/util/arrayUtils.ts

@@ -0,0 +1,37 @@
+export const moveForward = <T>(array: T[], callback: (item: T) => boolean): T[] => {
+  const index = array.findIndex(callback);
+  if (index >= 0 && index < array.length - 1) {
+    //@ts-expect-error - These indicies are safe per the previous check
+    [array[index], array[index + 1]] = [array[index + 1], array[index]];
+  }
+  return array;
+};
+
+export const moveToFront = <T>(array: T[], callback: (item: T) => boolean): T[] => {
+  const index = array.findIndex(callback);
+  if (index > 0) {
+    const [item] = array.splice(index, 1);
+    //@ts-expect-error - These indicies are safe per the previous check
+    array.unshift(item);
+  }
+  return array;
+};
+
+export const moveBackward = <T>(array: T[], callback: (item: T) => boolean): T[] => {
+  const index = array.findIndex(callback);
+  if (index > 0) {
+    //@ts-expect-error - These indicies are safe per the previous check
+    [array[index], array[index - 1]] = [array[index - 1], array[index]];
+  }
+  return array;
+};
+
+export const moveToBack = <T>(array: T[], callback: (item: T) => boolean): T[] => {
+  const index = array.findIndex(callback);
+  if (index >= 0 && index < array.length - 1) {
+    const [item] = array.splice(index, 1);
+    //@ts-expect-error - These indicies are safe per the previous check
+    array.push(item);
+  }
+  return array;
+};

invokeai/frontend/web/src/common/util/stopPropagation.ts

@@ -0,0 +1,3 @@
+export const stopPropagation = (e: React.MouseEvent) => {
+  e.stopPropagation();
+};

invokeai/frontend/web/src/features/canvas/components/IAICanvasToolbar/IAICanvasToolbar.tsx

@@ -22,6 +22,7 @@ import {
 } from 'features/canvas/store/canvasSlice';
 import type { CanvasLayer } from 'features/canvas/store/canvasTypes';
 import { LAYER_NAMES_DICT } from 'features/canvas/store/canvasTypes';
+import { ViewerButton } from 'features/gallery/components/ImageViewer/ViewerButton';
 import { memo, useCallback, useMemo } from 'react';
 import { useHotkeys } from 'react-hotkeys-hook';
 import { useTranslation } from 'react-i18next';
@@ -219,97 +220,107 @@ const IAICanvasToolbar = () => {
   const value = useMemo(() => LAYER_NAMES_DICT.filter((o) => o.value === layer)[0], [layer]);
 
   return (
-    <Flex alignItems="center" gap={2} flexWrap="wrap">
-      <Tooltip label={`${t('unifiedCanvas.layer')} (Q)`}>
-        <FormControl isDisabled={isStaging} w="5rem">
-          <Combobox value={value} options={LAYER_NAMES_DICT} onChange={handleChangeLayer} />
-        </FormControl>
-      </Tooltip>
+    <Flex w="full" gap={2} alignItems="center">
+      <Flex flex={1} justifyContent="center">
+        <Flex gap={2} marginInlineEnd="auto" />
+      </Flex>
+      <Flex flex={1} gap={2} justifyContent="center">
+        <Tooltip label={`${t('unifiedCanvas.layer')} (Q)`}>
+          <FormControl isDisabled={isStaging} w="5rem">
+            <Combobox value={value} options={LAYER_NAMES_DICT} onChange={handleChangeLayer} />
+          </FormControl>
+        </Tooltip>
 
-      <IAICanvasMaskOptions />
-      <IAICanvasToolChooserOptions />
+        <IAICanvasMaskOptions />
+        <IAICanvasToolChooserOptions />
 
-      <ButtonGroup>
-        <IconButton
-          aria-label={`${t('unifiedCanvas.move')} (V)`}
-          tooltip={`${t('unifiedCanvas.move')} (V)`}
-          icon={<PiHandGrabbingBold />}
-          isChecked={tool === 'move' || isStaging}
-          onClick={handleSelectMoveTool}
-        />
-        <IconButton
-          aria-label={`${shouldShowBoundingBox ? t('unifiedCanvas.hideBoundingBox') : t('unifiedCanvas.showBoundingBox')} (Shift + H)`}
-          tooltip={`${shouldShowBoundingBox ? t('unifiedCanvas.hideBoundingBox') : t('unifiedCanvas.showBoundingBox')} (Shift + H)`}
-          icon={shouldShowBoundingBox ? <PiEyeBold /> : <PiEyeSlashBold />}
-          onClick={handleSetShouldShowBoundingBox}
-          isDisabled={isStaging}
-        />
-        <IconButton
-          aria-label={`${t('unifiedCanvas.resetView')} (R)`}
-          tooltip={`${t('unifiedCanvas.resetView')} (R)`}
-          icon={<PiCrosshairSimpleBold />}
-          onClick={handleClickResetCanvasView}
-        />
-      </ButtonGroup>
-
-      <ButtonGroup>
-        <IconButton
-          aria-label={`${t('unifiedCanvas.mergeVisible')} (Shift+M)`}
-          tooltip={`${t('unifiedCanvas.mergeVisible')} (Shift+M)`}
-          icon={<PiStackBold />}
-          onClick={handleMergeVisible}
-          isDisabled={isStaging}
-        />
-        <IconButton
-          aria-label={`${t('unifiedCanvas.saveToGallery')} (Shift+S)`}
-          tooltip={`${t('unifiedCanvas.saveToGallery')} (Shift+S)`}
-          icon={<PiFloppyDiskBold />}
-          onClick={handleSaveToGallery}
-          isDisabled={isStaging}
-        />
-        {isClipboardAPIAvailable && (
+        <ButtonGroup>
           <IconButton
-            aria-label={`${t('unifiedCanvas.copyToClipboard')} (Cmd/Ctrl+C)`}
-            tooltip={`${t('unifiedCanvas.copyToClipboard')} (Cmd/Ctrl+C)`}
-            icon={<PiCopyBold />}
-            onClick={handleCopyImageToClipboard}
+            aria-label={`${t('unifiedCanvas.move')} (V)`}
+            tooltip={`${t('unifiedCanvas.move')} (V)`}
+            icon={<PiHandGrabbingBold />}
+            isChecked={tool === 'move' || isStaging}
+            onClick={handleSelectMoveTool}
+          />
+          <IconButton
+            aria-label={`${shouldShowBoundingBox ? t('unifiedCanvas.hideBoundingBox') : t('unifiedCanvas.showBoundingBox')} (Shift + H)`}
+            tooltip={`${shouldShowBoundingBox ? t('unifiedCanvas.hideBoundingBox') : t('unifiedCanvas.showBoundingBox')} (Shift + H)`}
+            icon={shouldShowBoundingBox ? <PiEyeBold /> : <PiEyeSlashBold />}
+            onClick={handleSetShouldShowBoundingBox}
             isDisabled={isStaging}
           />
-        )}
-        <IconButton
-          aria-label={`${t('unifiedCanvas.downloadAsImage')} (Shift+D)`}
-          tooltip={`${t('unifiedCanvas.downloadAsImage')} (Shift+D)`}
-          icon={<PiDownloadSimpleBold />}
-          onClick={handleDownloadAsImage}
-          isDisabled={isStaging}
-        />
-      </ButtonGroup>
-      <ButtonGroup>
-        <IAICanvasUndoButton />
-        <IAICanvasRedoButton />
-      </ButtonGroup>
+          <IconButton
+            aria-label={`${t('unifiedCanvas.resetView')} (R)`}
+            tooltip={`${t('unifiedCanvas.resetView')} (R)`}
+            icon={<PiCrosshairSimpleBold />}
+            onClick={handleClickResetCanvasView}
+          />
+        </ButtonGroup>
 
-      <ButtonGroup>
-        <IconButton
-          aria-label={`${t('common.upload')}`}
-          tooltip={`${t('common.upload')}`}
-          icon={<PiUploadSimpleBold />}
-          isDisabled={isStaging}
-          {...getUploadButtonProps()}
-        />
-        <input {...getUploadInputProps()} />
-        <IconButton
-          aria-label={`${t('unifiedCanvas.clearCanvas')}`}
-          tooltip={`${t('unifiedCanvas.clearCanvas')}`}
-          icon={<PiTrashSimpleBold />}
-          onClick={handleResetCanvas}
-          colorScheme="error"
-          isDisabled={isStaging}
-        />
-      </ButtonGroup>
-      <ButtonGroup>
-        <IAICanvasSettingsButtonPopover />
-      </ButtonGroup>
+        <ButtonGroup>
+          <IconButton
+            aria-label={`${t('unifiedCanvas.mergeVisible')} (Shift+M)`}
+            tooltip={`${t('unifiedCanvas.mergeVisible')} (Shift+M)`}
+            icon={<PiStackBold />}
+            onClick={handleMergeVisible}
+            isDisabled={isStaging}
+          />
+          <IconButton
+            aria-label={`${t('unifiedCanvas.saveToGallery')} (Shift+S)`}
+            tooltip={`${t('unifiedCanvas.saveToGallery')} (Shift+S)`}
+            icon={<PiFloppyDiskBold />}
+            onClick={handleSaveToGallery}
+            isDisabled={isStaging}
+          />
+          {isClipboardAPIAvailable && (
+            <IconButton
+              aria-label={`${t('unifiedCanvas.copyToClipboard')} (Cmd/Ctrl+C)`}
+              tooltip={`${t('unifiedCanvas.copyToClipboard')} (Cmd/Ctrl+C)`}
+              icon={<PiCopyBold />}
+              onClick={handleCopyImageToClipboard}
+              isDisabled={isStaging}
+            />
+          )}
+          <IconButton
+            aria-label={`${t('unifiedCanvas.downloadAsImage')} (Shift+D)`}
+            tooltip={`${t('unifiedCanvas.downloadAsImage')} (Shift+D)`}
+            icon={<PiDownloadSimpleBold />}
+            onClick={handleDownloadAsImage}
+            isDisabled={isStaging}
+          />
+        </ButtonGroup>
+        <ButtonGroup>
+          <IAICanvasUndoButton />
+          <IAICanvasRedoButton />
+        </ButtonGroup>
+
+        <ButtonGroup>
+          <IconButton
+            aria-label={`${t('common.upload')}`}
+            tooltip={`${t('common.upload')}`}
+            icon={<PiUploadSimpleBold />}
+            isDisabled={isStaging}
+            {...getUploadButtonProps()}
+          />
+          <input {...getUploadInputProps()} />
+          <IconButton
+            aria-label={`${t('unifiedCanvas.clearCanvas')}`}
+            tooltip={`${t('unifiedCanvas.clearCanvas')}`}
+            icon={<PiTrashSimpleBold />}
+            onClick={handleResetCanvas}
+            colorScheme="error"
+            isDisabled={isStaging}
+          />
+        </ButtonGroup>
+        <ButtonGroup>
+          <IAICanvasSettingsButtonPopover />
+        </ButtonGroup>
+      </Flex>
+      <Flex flex={1} justifyContent="center">
+        <Flex gap={2} marginInlineStart="auto">
+          <ViewerButton />
+        </Flex>
+      </Flex>
     </Flex>
   );
 };

invokeai/frontend/web/src/features/canvas/hooks/useCanvasHotkeys.ts

@@ -75,7 +75,7 @@ const useInpaintingCanvasHotkeys = () => {
 
   const onKeyDown = useCallback(
     (e: KeyboardEvent) => {
-      if (e.repeat || e.key !== ' ' || isInteractiveTarget(e.target) || activeTabName !== 'unifiedCanvas') {
+      if (e.repeat || e.key !== ' ' || isInteractiveTarget(e.target) || activeTabName !== 'canvas') {
         return;
       }
       if ($toolStash.get() || $tool.get() === 'move') {
@@ -90,7 +90,7 @@ const useInpaintingCanvasHotkeys = () => {
   );
   const onKeyUp = useCallback(
     (e: KeyboardEvent) => {
-      if (e.repeat || e.key !== ' ' || isInteractiveTarget(e.target) || activeTabName !== 'unifiedCanvas') {
+      if (e.repeat || e.key !== ' ' || isInteractiveTarget(e.target) || activeTabName !== 'canvas') {
         return;
       }
       if (!$toolStash.get() || $tool.get() !== 'move') {

invokeai/frontend/web/src/features/canvas/hooks/useCanvasZoom.ts

@@ -10,6 +10,18 @@ import { clamp } from 'lodash-es';
 import type { MutableRefObject } from 'react';
 import { useCallback } from 'react';
 
+export const calculateNewBrushSize = (brushSize: number, delta: number) => {
+  // This equation was derived by fitting a curve to the desired brush sizes and deltas
+  // see https://github.com/invoke-ai/InvokeAI/pull/5542#issuecomment-1915847565
+  const targetDelta = Math.sign(delta) * 0.7363 * Math.pow(1.0394, brushSize);
+  // This needs to be clamped to prevent the delta from getting too large
+  const finalDelta = clamp(targetDelta, -20, 20);
+  // The new brush size is also clamped to prevent it from getting too large or small
+  const newBrushSize = clamp(brushSize + finalDelta, 1, 500);
+
+  return newBrushSize;
+};
+
 const useCanvasWheel = (stageRef: MutableRefObject<Konva.Stage | null>) => {
   const dispatch = useAppDispatch();
   const stageScale = useAppSelector((s) => s.canvas.stageScale);
@@ -36,15 +48,7 @@ const useCanvasWheel = (stageRef: MutableRefObject<Konva.Stage | null>) => {
       }
 
       if ($ctrl.get() || $meta.get()) {
-        // This equation was derived by fitting a curve to the desired brush sizes and deltas
-        // see https://github.com/invoke-ai/InvokeAI/pull/5542#issuecomment-1915847565
-        const targetDelta = Math.sign(delta) * 0.7363 * Math.pow(1.0394, brushSize);
-        // This needs to be clamped to prevent the delta from getting too large
-        const finalDelta = clamp(targetDelta, -20, 20);
-        // The new brush size is also clamped to prevent it from getting too large or small
-        const newBrushSize = clamp(brushSize + finalDelta, 1, 500);
-
-        dispatch(setBrushSize(newBrushSize));
+        dispatch(setBrushSize(calculateNewBrushSize(brushSize, delta)));
       } else {
         const cursorPos = stageRef.current.getPointerPosition();
         let delta = e.evt.deltaY;

invokeai/frontend/web/src/features/canvas/store/canvasSlice.ts

@@ -8,6 +8,7 @@ import calculateScale from 'features/canvas/util/calculateScale';
 import { STAGE_PADDING_PERCENTAGE } from 'features/canvas/util/constants';
 import floorCoordinates from 'features/canvas/util/floorCoordinates';
 import getScaledBoundingBoxDimensions from 'features/canvas/util/getScaledBoundingBoxDimensions';
+import { calculateNewSize } from 'features/parameters/components/ImageSize/calculateNewSize';
 import { initialAspectRatioState } from 'features/parameters/components/ImageSize/constants';
 import type { AspectRatioState } from 'features/parameters/components/ImageSize/types';
 import { modelChanged } from 'features/parameters/store/generationSlice';
@@ -588,8 +589,9 @@ export const canvasSlice = createSlice({
   },
   extraReducers: (builder) => {
     builder.addCase(modelChanged, (state, action) => {
-      if (action.meta.previousModel?.base === action.payload?.base) {
-        // The base model hasn't changed, we don't need to optimize the size
+      const newModel = action.payload;
+      if (!newModel || action.meta.previousModel?.base === newModel.base) {
+        // Model was cleared or the base didn't change
         return;
       }
       const optimalDimension = getOptimalDimension(action.payload);
@@ -597,14 +599,8 @@ export const canvasSlice = createSlice({
       if (getIsSizeOptimal(width, height, optimalDimension)) {
         return;
       }
-      setBoundingBoxDimensionsReducer(
-        state,
-        {
-          width,
-          height,
-        },
-        optimalDimension
-      );
+      const newSize = calculateNewSize(state.aspectRatio.value, optimalDimension * optimalDimension);
+      setBoundingBoxDimensionsReducer(state, newSize, optimalDimension);
     });
 
     builder.addCase(socketQueueItemStatusChanged, (state, action) => {

invokeai/frontend/web/src/features/canvas/util/blobToDataURL.ts

@@ -7,3 +7,22 @@ export const blobToDataURL = (blob: Blob): Promise<string> => {
     reader.readAsDataURL(blob);
   });
 };
+
+export function imageDataToDataURL(imageData: ImageData): string {
+  const { width, height } = imageData;
+
+  // Create a canvas to transfer the ImageData to
+  const canvas = document.createElement('canvas');
+  canvas.width = width;
+  canvas.height = height;
+
+  // Draw the ImageData onto the canvas
+  const ctx = canvas.getContext('2d');
+  if (!ctx) {
+    throw new Error('Unable to get canvas context');
+  }
+  ctx.putImageData(imageData, 0, 0);
+
+  // Convert the canvas to a data URL (base64)
+  return canvas.toDataURL();
+}

invokeai/frontend/web/src/features/canvas/util/colorToString.ts

@@ -1,6 +1,11 @@
-import type { RgbaColor } from 'react-colorful';
+import type { RgbaColor, RgbColor } from 'react-colorful';
 
 export const rgbaColorToString = (color: RgbaColor): string => {
   const { r, g, b, a } = color;
   return `rgba(${r}, ${g}, ${b}, ${a})`;
 };
+
+export const rgbColorToString = (color: RgbColor): string => {
+  const { r, g, b } = color;
+  return `rgba(${r}, ${g}, ${b})`;
+};

invokeai/frontend/web/src/features/controlAdapters/components/ControlAdapterConfig.tsx

@@ -21,6 +21,7 @@ import ControlAdapterShouldAutoConfig from './ControlAdapterShouldAutoConfig';
 import ControlNetCanvasImageImports from './imports/ControlNetCanvasImageImports';
 import { ParamControlAdapterBeginEnd } from './parameters/ParamControlAdapterBeginEnd';
 import ParamControlAdapterControlMode from './parameters/ParamControlAdapterControlMode';
+import ParamControlAdapterIPMethod from './parameters/ParamControlAdapterIPMethod';
 import ParamControlAdapterProcessorSelect from './parameters/ParamControlAdapterProcessorSelect';
 import ParamControlAdapterResizeMode from './parameters/ParamControlAdapterResizeMode';
 import ParamControlAdapterWeight from './parameters/ParamControlAdapterWeight';
@@ -75,7 +76,7 @@ const ControlAdapterConfig = (props: { id: string; number: number }) => {
         <Box minW={0} w="full" transitionProperty="common" transitionDuration="0.1s">
           <ParamControlAdapterModel id={id} />
         </Box>
-        {activeTabName === 'unifiedCanvas' && <ControlNetCanvasImageImports id={id} />}
+        {activeTabName === 'canvas' && <ControlNetCanvasImageImports id={id} />}
         <IconButton
           size="sm"
           tooltip={t('controlnet.duplicate')}
@@ -111,7 +112,8 @@ const ControlAdapterConfig = (props: { id: string; number: number }) => {
 
       <Flex w="full" flexDir="column" gap={4}>
         <Flex gap={8} w="full" alignItems="center">
-          <Flex flexDir="column" gap={2} h={32} w="full">
+          <Flex flexDir="column" gap={4} h={controlAdapterType === 'ip_adapter' ? 40 : 32} w="full">
+            <ParamControlAdapterIPMethod id={id} />
             <ParamControlAdapterWeight id={id} />
             <ParamControlAdapterBeginEnd id={id} />
           </Flex>

invokeai/frontend/web/src/features/controlAdapters/components/ControlAdapterImagePreview.tsx

@@ -13,9 +13,10 @@ import {
   controlAdapterImageChanged,
   selectControlAdaptersSlice,
 } from 'features/controlAdapters/store/controlAdaptersSlice';
+import { heightChanged, widthChanged } from 'features/controlLayers/store/controlLayersSlice';
 import type { TypesafeDraggableData, TypesafeDroppableData } from 'features/dnd/types';
 import { calculateNewSize } from 'features/parameters/components/ImageSize/calculateNewSize';
-import { heightChanged, selectOptimalDimension, widthChanged } from 'features/parameters/store/generationSlice';
+import { selectOptimalDimension } from 'features/parameters/store/generationSlice';
 import { activeTabNameSelector } from 'features/ui/store/uiSelectors';
 import { memo, useCallback, useEffect, useMemo, useState } from 'react';
 import { useTranslation } from 'react-i18next';
@@ -92,15 +93,16 @@ const ControlAdapterImagePreview = ({ isSmall, id }: Props) => {
       return;
     }
 
-    if (activeTabName === 'unifiedCanvas') {
+    if (activeTabName === 'canvas') {
       dispatch(setBoundingBoxDimensions({ width: controlImage.width, height: controlImage.height }, optimalDimension));
     } else {
+      const options = { updateAspectRatio: true, clamp: true };
       const { width, height } = calculateNewSize(
         controlImage.width / controlImage.height,
         optimalDimension * optimalDimension
       );
-      dispatch(widthChanged(width));
-      dispatch(heightChanged(height));
+      dispatch(widthChanged({ width, ...options }));
+      dispatch(heightChanged({ height, ...options }));
     }
   }, [controlImage, activeTabName, dispatch, optimalDimension]);
 

invokeai/frontend/web/src/features/controlAdapters/components/parameters/ParamControlAdapterIPMethod.tsx

@@ -0,0 +1,63 @@
+import type { ComboboxOnChange } from '@invoke-ai/ui-library';
+import { Combobox, FormControl, FormLabel } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { InformationalPopover } from 'common/components/InformationalPopover/InformationalPopover';
+import { useControlAdapterIPMethod } from 'features/controlAdapters/hooks/useControlAdapterIPMethod';
+import { useControlAdapterIsEnabled } from 'features/controlAdapters/hooks/useControlAdapterIsEnabled';
+import { controlAdapterIPMethodChanged } from 'features/controlAdapters/store/controlAdaptersSlice';
+import type { IPMethod } from 'features/controlAdapters/store/types';
+import { isIPMethod } from 'features/controlAdapters/store/types';
+import { memo, useCallback, useMemo } from 'react';
+import { useTranslation } from 'react-i18next';
+
+type Props = {
+  id: string;
+};
+
+const ParamControlAdapterIPMethod = ({ id }: Props) => {
+  const isEnabled = useControlAdapterIsEnabled(id);
+  const method = useControlAdapterIPMethod(id);
+  const dispatch = useAppDispatch();
+  const { t } = useTranslation();
+
+  const options: { label: string; value: IPMethod }[] = useMemo(
+    () => [
+      { label: t('controlnet.full'), value: 'full' },
+      { label: `${t('controlnet.style')} (${t('common.beta')})`, value: 'style' },
+      { label: `${t('controlnet.composition')} (${t('common.beta')})`, value: 'composition' },
+    ],
+    [t]
+  );
+
+  const handleIPMethodChanged = useCallback<ComboboxOnChange>(
+    (v) => {
+      if (!isIPMethod(v?.value)) {
+        return;
+      }
+      dispatch(
+        controlAdapterIPMethodChanged({
+          id,
+          method: v.value,
+        })
+      );
+    },
+    [id, dispatch]
+  );
+
+  const value = useMemo(() => options.find((o) => o.value === method), [options, method]);
+
+  if (!method) {
+    return null;
+  }
+
+  return (
+    <FormControl>
+      <InformationalPopover feature="controlNetResizeMode">
+        <FormLabel>{t('controlnet.ipAdapterMethod')}</FormLabel>
+      </InformationalPopover>
+      <Combobox value={value} options={options} isDisabled={!isEnabled} onChange={handleIPMethodChanged} />
+    </FormControl>
+  );
+};
+
+export default memo(ParamControlAdapterIPMethod);

invokeai/frontend/web/src/features/controlAdapters/hooks/useControlAdapterIPMethod.ts

@@ -0,0 +1,24 @@
+import { createMemoizedSelector } from 'app/store/createMemoizedSelector';
+import { useAppSelector } from 'app/store/storeHooks';
+import {
+  selectControlAdapterById,
+  selectControlAdaptersSlice,
+} from 'features/controlAdapters/store/controlAdaptersSlice';
+import { useMemo } from 'react';
+
+export const useControlAdapterIPMethod = (id: string) => {
+  const selector = useMemo(
+    () =>
+      createMemoizedSelector(selectControlAdaptersSlice, (controlAdapters) => {
+        const cn = selectControlAdapterById(controlAdapters, id);
+        if (cn && cn?.type === 'ip_adapter') {
+          return cn.method;
+        }
+      }),
+    [id]
+  );
+
+  const method = useAppSelector(selector);
+
+  return method;
+};

invokeai/frontend/web/src/features/controlAdapters/store/controlAdaptersSlice.ts

@@ -1,5 +1,5 @@
 import type { PayloadAction, Update } from '@reduxjs/toolkit';
-import { createEntityAdapter, createSlice, isAnyOf } from '@reduxjs/toolkit';
+import { createEntityAdapter, createSlice } from '@reduxjs/toolkit';
 import { getSelectorsOptions } from 'app/store/createMemoizedSelector';
 import type { PersistConfig, RootState } from 'app/store/store';
 import { deepClone } from 'common/util/deepClone';
@@ -21,6 +21,7 @@ import type {
   ControlAdapterType,
   ControlMode,
   ControlNetConfig,
+  IPMethod,
   RequiredControlAdapterProcessorNode,
   ResizeMode,
   T2IAdapterConfig,
@@ -245,6 +246,10 @@ export const controlAdaptersSlice = createSlice({
       }
       caAdapter.updateOne(state, { id, changes: { controlMode } });
     },
+    controlAdapterIPMethodChanged: (state, action: PayloadAction<{ id: string; method: IPMethod }>) => {
+      const { id, method } = action.payload;
+      caAdapter.updateOne(state, { id, changes: { method } });
+    },
     controlAdapterCLIPVisionModelChanged: (
       state,
       action: PayloadAction<{ id: string; clipVisionModel: CLIPVisionModel }>
@@ -390,6 +395,7 @@ export const {
   controlAdapterIsEnabledChanged,
   controlAdapterModelChanged,
   controlAdapterCLIPVisionModelChanged,
+  controlAdapterIPMethodChanged,
   controlAdapterWeightChanged,
   controlAdapterBeginStepPctChanged,
   controlAdapterEndStepPctChanged,
@@ -406,8 +412,6 @@ export const {
   t2iAdaptersReset,
 } = controlAdaptersSlice.actions;
 
-export const isAnyControlAdapterAdded = isAnyOf(controlAdapterAdded, controlAdapterRecalled);
-
 export const selectControlAdaptersSlice = (state: RootState) => state.controlAdapters;
 
 /* eslint-disable-next-line @typescript-eslint/no-explicit-any */

invokeai/frontend/web/src/features/controlAdapters/store/types.ts

@@ -210,6 +210,10 @@ const zResizeMode = z.enum(['just_resize', 'crop_resize', 'fill_resize', 'just_r
 export type ResizeMode = z.infer<typeof zResizeMode>;
 export const isResizeMode = (v: unknown): v is ResizeMode => zResizeMode.safeParse(v).success;
 
+const zIPMethod = z.enum(['full', 'style', 'composition']);
+export type IPMethod = z.infer<typeof zIPMethod>;
+export const isIPMethod = (v: unknown): v is IPMethod => zIPMethod.safeParse(v).success;
+
 export type ControlNetConfig = {
   type: 'controlnet';
   id: string;
@@ -253,6 +257,7 @@ export type IPAdapterConfig = {
   model: ParameterIPAdapterModel | null;
   clipVisionModel: CLIPVisionModel;
   weight: number;
+  method: IPMethod;
   beginStepPct: number;
   endStepPct: number;
 };

invokeai/frontend/web/src/features/controlAdapters/util/buildControlAdapter.ts

@@ -46,6 +46,7 @@ export const initialIPAdapter: Omit<IPAdapterConfig, 'id'> = {
   isEnabled: true,
   controlImage: null,
   model: null,
+  method: 'full',
   clipVisionModel: 'ViT-H',
   weight: 1,
   beginStepPct: 0,

invokeai/frontend/web/src/features/controlLayers/components/AddLayerButton.tsx

@@ -0,0 +1,42 @@
+import { Button, Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { useAddCALayer, useAddIILayer, useAddIPALayer } from 'features/controlLayers/hooks/addLayerHooks';
+import { rgLayerAdded } from 'features/controlLayers/store/controlLayersSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiPlusBold } from 'react-icons/pi';
+
+export const AddLayerButton = memo(() => {
+  const { t } = useTranslation();
+  const dispatch = useAppDispatch();
+  const [addCALayer, isAddCALayerDisabled] = useAddCALayer();
+  const [addIPALayer, isAddIPALayerDisabled] = useAddIPALayer();
+  const [addIILayer, isAddIILayerDisabled] = useAddIILayer();
+  const addRGLayer = useCallback(() => {
+    dispatch(rgLayerAdded());
+  }, [dispatch]);
+
+  return (
+    <Menu>
+      <MenuButton as={Button} leftIcon={<PiPlusBold />} variant="ghost">
+        {t('controlLayers.addLayer')}
+      </MenuButton>
+      <MenuList>
+        <MenuItem icon={<PiPlusBold />} onClick={addRGLayer}>
+          {t('controlLayers.regionalGuidanceLayer')}
+        </MenuItem>
+        <MenuItem icon={<PiPlusBold />} onClick={addCALayer} isDisabled={isAddCALayerDisabled}>
+          {t('controlLayers.globalControlAdapterLayer')}
+        </MenuItem>
+        <MenuItem icon={<PiPlusBold />} onClick={addIPALayer} isDisabled={isAddIPALayerDisabled}>
+          {t('controlLayers.globalIPAdapterLayer')}
+        </MenuItem>
+        <MenuItem icon={<PiPlusBold />} onClick={addIILayer} isDisabled={isAddIILayerDisabled}>
+          {t('controlLayers.globalInitialImageLayer')}
+        </MenuItem>
+      </MenuList>
+    </Menu>
+  );
+});
+
+AddLayerButton.displayName = 'AddLayerButton';

invokeai/frontend/web/src/features/controlLayers/components/AddPromptButtons.tsx

@@ -0,0 +1,74 @@
+import { Button, Flex } from '@invoke-ai/ui-library';
+import { createMemoizedSelector } from 'app/store/createMemoizedSelector';
+import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import { useAddIPAdapterToIPALayer } from 'features/controlLayers/hooks/addLayerHooks';
+import {
+  isRegionalGuidanceLayer,
+  rgLayerNegativePromptChanged,
+  rgLayerPositivePromptChanged,
+  selectControlLayersSlice,
+} from 'features/controlLayers/store/controlLayersSlice';
+import { useCallback, useMemo } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiPlusBold } from 'react-icons/pi';
+import { assert } from 'tsafe';
+type AddPromptButtonProps = {
+  layerId: string;
+};
+
+export const AddPromptButtons = ({ layerId }: AddPromptButtonProps) => {
+  const { t } = useTranslation();
+  const dispatch = useAppDispatch();
+  const [addIPAdapter, isAddIPAdapterDisabled] = useAddIPAdapterToIPALayer(layerId);
+  const selectValidActions = useMemo(
+    () =>
+      createMemoizedSelector(selectControlLayersSlice, (controlLayers) => {
+        const layer = controlLayers.present.layers.find((l) => l.id === layerId);
+        assert(isRegionalGuidanceLayer(layer), `Layer ${layerId} not found or not an RP layer`);
+        return {
+          canAddPositivePrompt: layer.positivePrompt === null,
+          canAddNegativePrompt: layer.negativePrompt === null,
+        };
+      }),
+    [layerId]
+  );
+  const validActions = useAppSelector(selectValidActions);
+  const addPositivePrompt = useCallback(() => {
+    dispatch(rgLayerPositivePromptChanged({ layerId, prompt: '' }));
+  }, [dispatch, layerId]);
+  const addNegativePrompt = useCallback(() => {
+    dispatch(rgLayerNegativePromptChanged({ layerId, prompt: '' }));
+  }, [dispatch, layerId]);
+
+  return (
+    <Flex w="full" p={2} justifyContent="space-between">
+      <Button
+        size="sm"
+        variant="ghost"
+        leftIcon={<PiPlusBold />}
+        onClick={addPositivePrompt}
+        isDisabled={!validActions.canAddPositivePrompt}
+      >
+        {t('common.positivePrompt')}
+      </Button>
+      <Button
+        size="sm"
+        variant="ghost"
+        leftIcon={<PiPlusBold />}
+        onClick={addNegativePrompt}
+        isDisabled={!validActions.canAddNegativePrompt}
+      >
+        {t('common.negativePrompt')}
+      </Button>
+      <Button
+        size="sm"
+        variant="ghost"
+        leftIcon={<PiPlusBold />}
+        onClick={addIPAdapter}
+        isDisabled={isAddIPAdapterDisabled}
+      >
+        {t('common.ipAdapter')}
+      </Button>
+    </Flex>
+  );
+};

invokeai/frontend/web/src/features/controlLayers/components/BrushSize.tsx

@@ -0,0 +1,63 @@
+import {
+  CompositeNumberInput,
+  CompositeSlider,
+  FormControl,
+  FormLabel,
+  Popover,
+  PopoverArrow,
+  PopoverBody,
+  PopoverContent,
+  PopoverTrigger,
+} from '@invoke-ai/ui-library';
+import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import { brushSizeChanged, initialControlLayersState } from 'features/controlLayers/store/controlLayersSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+
+const marks = [0, 100, 200, 300];
+const formatPx = (v: number | string) => `${v} px`;
+
+export const BrushSize = memo(() => {
+  const dispatch = useAppDispatch();
+  const { t } = useTranslation();
+  const brushSize = useAppSelector((s) => s.controlLayers.present.brushSize);
+  const onChange = useCallback(
+    (v: number) => {
+      dispatch(brushSizeChanged(Math.round(v)));
+    },
+    [dispatch]
+  );
+  return (
+    <FormControl w="min-content">
+      <FormLabel m={0}>{t('controlLayers.brushSize')}</FormLabel>
+      <Popover isLazy>
+        <PopoverTrigger>
+          <CompositeNumberInput
+            min={1}
+            max={600}
+            defaultValue={initialControlLayersState.brushSize}
+            value={brushSize}
+            onChange={onChange}
+            w={24}
+            format={formatPx}
+          />
+        </PopoverTrigger>
+        <PopoverContent w={200} py={2} px={4}>
+          <PopoverArrow />
+          <PopoverBody>
+            <CompositeSlider
+              min={1}
+              max={300}
+              defaultValue={initialControlLayersState.brushSize}
+              value={brushSize}
+              onChange={onChange}
+              marks={marks}
+            />
+          </PopoverBody>
+        </PopoverContent>
+      </Popover>
+    </FormControl>
+  );
+});
+
+BrushSize.displayName = 'BrushSize';