Blackified

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

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


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

## Description

[fix(nodes): fix missing generation
modes](8615d53e65)

Lax typing on the metadata util functions allowed a typing issue to slip
through. Fixed the lax typing, updated core metadata node.

## Related Tickets & Documents

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

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

- Related Issue #
- Closes #4959 (thanks @coder543)

.github/workflows/pypi-release.yml

@@ -28,7 +28,7 @@ jobs:
         run: twine check dist/*
 
       - name: check PyPI versions
-        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/v2.3'
+        if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
         run: |
           pip install --upgrade requests
           python -c "\

.gitignore

@@ -1,8 +1,5 @@
 .idea/
 
-# ignore the Anaconda/Miniconda installer used while building Docker image
-anaconda.sh
-
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -136,12 +133,10 @@ celerybeat.pid
 
 # Environments
 .env
-.venv
+.venv*
 env/
 venv/
 ENV/
-env.bak/
-venv.bak/
 
 # Spyder project settings
 .spyderproject
@@ -186,11 +181,6 @@ cython_debug/
 .scratch/
 .vscode/
 
-# ignore environment.yml and requirements.txt
-# these are links to the real files in environments-and-requirements
-environment.yml
-requirements.txt
-
 # source installer files
 installer/*zip
 installer/install.bat

README.md

@@ -123,7 +123,7 @@ and go to http://localhost:9090.
 
 ### Command-Line Installation (for developers and users familiar with Terminals)
 
-You must have Python 3.9 through 3.11 installed on your machine. Earlier or
+You must have Python 3.10 through 3.11 installed on your machine. Earlier or
 later versions are not supported.
 Node.js also needs to be installed along with yarn (can be installed with
 the command `npm install -g yarn` if needed)

docker/.env.sample

@@ -1,13 +1,15 @@
 ## Make a copy of this file named `.env` and fill in the values below.
-## Any environment variables supported by InvokeAI can be specified here.
+## Any environment variables supported by InvokeAI can be specified here,
+## in addition to the examples below.
 
 # INVOKEAI_ROOT is the path to a path on the local filesystem where InvokeAI will store data.
 # Outputs will also be stored here by default.
 # This **must** be an absolute path.
 INVOKEAI_ROOT=
 
-HUGGINGFACE_TOKEN=
+# Get this value from your HuggingFace account settings page.
+# HUGGING_FACE_HUB_TOKEN=
 
-## optional variables specific to the docker setup
+## optional variables specific to the docker setup.
 # GPU_DRIVER=cuda
 # CONTAINER_UID=1000

docker/Dockerfile

@@ -2,7 +2,7 @@
 
 ## Builder stage
 
-FROM library/ubuntu:22.04 AS builder
+FROM library/ubuntu:23.04 AS builder
 
 ARG DEBIAN_FRONTEND=noninteractive
 RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
@@ -10,7 +10,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
     --mount=type=cache,target=/var/lib/apt,sharing=locked \
     apt update && apt-get install -y \
         git \
-        python3.10-venv \
+        python3-venv \
         python3-pip \
         build-essential
 
@@ -37,7 +37,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     elif [ "$GPU_DRIVER" = "rocm" ]; then \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm5.4.2"; \
     else \
-        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu118"; \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
     fi &&\
     pip install $extra_index_url_arg \
         torch==$TORCH_VERSION \
@@ -70,7 +70,7 @@ RUN --mount=type=cache,target=/usr/lib/node_modules \
 
 #### Runtime stage ---------------------------------------
 
-FROM library/ubuntu:22.04 AS runtime
+FROM library/ubuntu:23.04 AS runtime
 
 ARG DEBIAN_FRONTEND=noninteractive
 ENV PYTHONUNBUFFERED=1
@@ -85,6 +85,7 @@ RUN apt update && apt install -y --no-install-recommends \
         iotop \
         bzip2 \
         gosu \
+        magic-wormhole \
         libglib2.0-0 \
         libgl1-mesa-glx \
         python3-venv \
@@ -94,10 +95,6 @@ RUN apt update && apt install -y --no-install-recommends \
         libstdc++-10-dev &&\
     apt-get clean && apt-get autoclean
 
-# globally add magic-wormhole
-# for ease of transferring data to and from the container
-# when running in sandboxed cloud environments; e.g. Runpod etc.
-RUN pip install magic-wormhole
 
 ENV INVOKEAI_SRC=/opt/invokeai
 ENV VIRTUAL_ENV=/opt/venv/invokeai
@@ -120,9 +117,7 @@ WORKDIR ${INVOKEAI_SRC}
 RUN cd /usr/lib/$(uname -p)-linux-gnu/pkgconfig/ && ln -sf opencv4.pc opencv.pc
 RUN python3 -c "from patchmatch import patch_match"
 
-# Create unprivileged user and make the local dir
-RUN useradd --create-home --shell /bin/bash -u 1000 --comment "container local user" invoke
-RUN mkdir -p ${INVOKEAI_ROOT} && chown -R invoke:invoke ${INVOKEAI_ROOT}
+RUN mkdir -p ${INVOKEAI_ROOT} && chown -R 1000:1000 ${INVOKEAI_ROOT}
 
 COPY docker/docker-entrypoint.sh ./
 ENTRYPOINT ["/opt/invokeai/docker-entrypoint.sh"]

docker/README.md

@@ -5,7 +5,7 @@ All commands are to be run from the `docker` directory: `cd docker`
 #### Linux
 
 1. Ensure builkit is enabled in the Docker daemon settings (`/etc/docker/daemon.json`)
-2. Install the `docker compose` plugin using your package manager, or follow a [tutorial](https://www.digitalocean.com/community/tutorials/how-to-install-and-use-docker-compose-on-ubuntu-22-04).
+2. Install the `docker compose` plugin using your package manager, or follow a [tutorial](https://docs.docker.com/compose/install/linux/#install-using-the-repository).
     - The deprecated `docker-compose` (hyphenated) CLI continues to work for now.
 3. Ensure docker daemon is able to access the GPU.
     - You may need to install [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
@@ -20,7 +20,6 @@ This is done via Docker Desktop preferences
 
 ## Quickstart
 
-
 1. Make a copy of `env.sample` and name it `.env` (`cp env.sample .env` (Mac/Linux) or `copy example.env .env` (Windows)). Make changes as necessary. Set `INVOKEAI_ROOT` to an absolute path to:
     a. the desired location of the InvokeAI runtime directory, or
     b. an existing, v3.0.0 compatible runtime directory.
@@ -42,20 +41,22 @@ The Docker daemon on the system must be already set up to use the GPU. In case o
 
 Check the `.env.sample` file. It contains some environment variables for running in Docker. Copy it, name it `.env`, and fill it in with your own values. Next time you run `docker compose up`, your custom values will be used.
 
-You can also set these values in `docker compose.yml` directly, but `.env` will help avoid conflicts when code is updated.
+You can also set these values in `docker-compose.yml` directly, but `.env` will help avoid conflicts when code is updated.
 
-Example (most values are optional):
+Example (values are optional, but setting `INVOKEAI_ROOT` is highly recommended):
 
-```
+```bash
 INVOKEAI_ROOT=/Volumes/WorkDrive/invokeai
 HUGGINGFACE_TOKEN=the_actual_token
 CONTAINER_UID=1000
 GPU_DRIVER=cuda
 ```
 
+Any environment variables supported by InvokeAI can be set here - please see the [Configuration docs](https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/) for further detail.
+
 ## Even Moar Customizing!
 
-See the `docker compose.yaml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
+See the `docker-compose.yml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
 
 ### Reconfigure the runtime directory
 
@@ -63,7 +64,7 @@ Can be used to download additional models from the supported model list
 
 In conjunction with `INVOKEAI_ROOT` can be also used to initialize a runtime directory
 
-```
+```yaml
 command:
   - invokeai-configure
   - --yes
@@ -71,7 +72,7 @@ command:
 
 Or install models:
 
-```
+```yaml
 command:
   - invokeai-model-install
-```
+```

docker/build.sh

@@ -5,7 +5,7 @@ build_args=""
 
 [[ -f ".env" ]] && build_args=$(awk '$1 ~ /\=[^$]/ {print "--build-arg " $0 " "}' .env)
 
-echo "docker-compose build args:"
+echo "docker compose build args:"
 echo $build_args
 
-docker-compose build $build_args
+docker compose build $build_args

docker/docker-entrypoint.sh

@@ -19,7 +19,7 @@ set -e -o pipefail
 # Default UID: 1000 chosen due to popularity on Linux systems. Possibly 501 on MacOS.
 
 USER_ID=${CONTAINER_UID:-1000}
-USER=invoke
+USER=ubuntu
 usermod -u ${USER_ID} ${USER} 1>/dev/null
 
 configure() {

docker/run.sh

@@ -1,8 +1,11 @@
 #!/usr/bin/env bash
 set -e
 
+# This script is provided for backwards compatibility with the old docker setup.
+# it doesn't do much aside from wrapping the usual docker compose CLI.
+
 SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
 cd "$SCRIPTDIR" || exit 1
 
-docker-compose up --build -d
-docker-compose logs -f
+docker compose up --build -d
+docker compose logs -f

docs/CHANGELOG.md

@@ -488,7 +488,7 @@ sections describe what's new for InvokeAI.
 
 - A choice of installer scripts that automate installation and configuration.
   See
-  [Installation](installation/index.md).
+  [Installation](installation/INSTALLATION.md).
 - A streamlined manual installation process that works for both Conda and
   PIP-only installs. See
   [Manual Installation](installation/020_INSTALL_MANUAL.md).
@@ -657,7 +657,7 @@ sections describe what's new for InvokeAI.
 
 ## v1.13 <small>(3 September 2022)</small>
 
-- Support image variations (see [VARIATIONS](features/VARIATIONS.md)
+- Support image variations (see [VARIATIONS](deprecated/VARIATIONS.md)
   ([Kevin Gibbons](https://github.com/bakkot) and many contributors and
   reviewers)
 - Supports a Google Colab notebook for a standalone server running on Google

docs/contributing/LOCAL_DEVELOPMENT.md

@@ -47,34 +47,9 @@ pip install ".[dev,test]"
 These are optional groups of packages which are defined within the `pyproject.toml`
 and will be required for testing the changes you make to the code.
 
-### Running Tests
-
-We use [pytest](https://docs.pytest.org/en/7.2.x/) for our test suite. Tests can
-be found under the `./tests` folder and can be run with a single `pytest`
-command. Optionally, to review test coverage you can append `--cov`.
-
-```zsh
-pytest --cov
-```
-
-Test outcomes and coverage will be reported in the terminal. In addition a more
-detailed report is created in both XML and HTML format in the `./coverage`
-folder. The HTML one in particular can help identify missing statements
-requiring tests to ensure coverage. This can be run by opening
-`./coverage/html/index.html`.
-
-For example.
-
-```zsh
-pytest --cov; open ./coverage/html/index.html
-```
-
-??? info "HTML coverage report output"
-
-    ![html-overview](../assets/contributing/html-overview.png)
-
-    ![html-detail](../assets/contributing/html-detail.png)
+### Tests
 
+See the [tests documentation](./TESTS.md) for information about running and writing tests.
 ### Reloading Changes
 
 Experimenting with changes to the Python source code is a drag if you have to re-start the server —
@@ -167,6 +142,23 @@ and so you'll have access to the same python environment as the InvokeAI app.
 
 This is _super_ handy.
 
+#### Enabling Type-Checking with Pylance
+
+We use python's typing system in InvokeAI. PR reviews will include checking that types are present and correct. We don't enforce types with `mypy` at this time, but that is on the horizon.
+
+Using a code analysis tool to automatically type check your code (and types) is very important when writing with types. These tools provide immediate feedback in your editor when types are incorrect, and following their suggestions lead to fewer runtime bugs.
+
+Pylance, installed at the beginning of this guide, is the de-facto python LSP (language server protocol). It provides type checking in the editor (among many other features). Once installed, you do need to enable type checking manually:
+
+- Open a python file
+- Look along the status bar in VSCode for `{ } Python`
+- Click the `{ }`
+- Turn type checking on - basic is fine
+
+You'll now see red squiggly lines where type issues are detected. Hover your cursor over the indicated symbols to see what's wrong.
+
+In 99% of cases when the type checker says there is a problem, there really is a problem, and you should take some time to understand and resolve what it is pointing out.
+
 #### Debugging configs with `launch.json`
 
 Debugging configs are managed in a `launch.json` file. Like most VSCode configs,

docs/contributing/TESTS.md

@@ -0,0 +1,89 @@
+# InvokeAI Backend Tests
+
+We use `pytest` to run the backend python tests. (See [pyproject.toml](/pyproject.toml) for the default `pytest` options.)
+
+## Fast vs. Slow
+All tests are categorized as either 'fast' (no test annotation) or 'slow' (annotated with the `@pytest.mark.slow` decorator).
+
+'Fast' tests are run to validate every PR, and are fast enough that they can be run routinely during development.
+
+'Slow' tests are currently only run manually on an ad-hoc basis. In the future, they may be automated to run nightly. Most developers are only expected to run the 'slow' tests that directly relate to the feature(s) that they are working on.
+
+As a rule of thumb, tests should be marked as 'slow' if there is a chance that they take >1s (e.g. on a CPU-only machine with slow internet connection). Common examples of slow tests are tests that depend on downloading a model, or running model inference.
+
+## Running Tests
+
+Below are some common test commands:
+```bash
+# Run the fast tests. (This implicitly uses the configured default option: `-m "not slow"`.)
+pytest tests/
+
+# Equivalent command to run the fast tests.
+pytest tests/ -m "not slow"
+
+# Run the slow tests.
+pytest tests/ -m "slow"
+
+# Run the slow tests from a specific file.
+pytest tests/path/to/slow_test.py -m "slow"
+
+# Run all tests (fast and slow).
+pytest tests -m ""
+```
+
+## Test Organization
+
+All backend tests are in the [`tests/`](/tests/) directory. This directory mirrors the organization of the `invokeai/` directory. For example, tests for `invokeai/model_management/model_manager.py` would be found in `tests/model_management/test_model_manager.py`.
+
+TODO: The above statement is aspirational. A re-organization of legacy tests is required to make it true.
+
+## Tests that depend on models
+
+There are a few things to keep in mind when adding tests that depend on models.
+
+1. If a required model is not already present, it should automatically be downloaded as part of the test setup.
+2. If a model is already downloaded, it should not be re-downloaded unnecessarily.
+3. Take reasonable care to keep the total number of models required for the tests low. Whenever possible, re-use models that are already required for other tests. If you are adding a new model, consider including a comment to explain why it is required/unique.
+
+There are several utilities to help with model setup for tests. Here is a sample test that depends on a model:
+```python
+import pytest
+import torch
+
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType
+from invokeai.backend.util.test_utils import install_and_load_model
+
+@pytest.mark.slow
+def test_model(model_installer, torch_device):
+    model_info = install_and_load_model(
+        model_installer=model_installer,
+        model_path_id_or_url="HF/dummy_model_id",
+        model_name="dummy_model",
+        base_model=BaseModelType.StableDiffusion1,
+        model_type=ModelType.Dummy,
+    )
+
+    dummy_input = build_dummy_input(torch_device)
+
+    with torch.no_grad(), model_info as model:
+        model.to(torch_device, dtype=torch.float32)
+        output = model(dummy_input)
+
+    # Validate output...
+
+```
+
+## Test Coverage
+
+To review test coverage, append `--cov` to your pytest command:
+```bash
+pytest tests/ --cov
+```
+
+Test outcomes and coverage will be reported in the terminal. In addition, a more detailed report is created in both XML and HTML format in the `./coverage` folder. The HTML output is particularly helpful in identifying untested statements where coverage should be improved. The HTML report can be viewed by opening `./coverage/html/index.html`.
+
+??? info "HTML coverage report output"
+
+    ![html-overview](../assets/contributing/html-overview.png)
+
+    ![html-detail](../assets/contributing/html-detail.png)

docs/contributing/contribution_guides/development.md

@@ -12,7 +12,7 @@ To get started, take a look at our [new contributors checklist](newContributorCh
 Once you're setup, for more information, you can review the documentation specific to your area of interest:
 
 * #### [InvokeAI Architecure](../ARCHITECTURE.md)
-* #### [Frontend Documentation](development_guides/contributingToFrontend.md)
+* #### [Frontend Documentation](./contributingToFrontend.md)
 * #### [Node Documentation](../INVOCATIONS.md)
 * #### [Local Development](../LOCAL_DEVELOPMENT.md)
 
@@ -38,12 +38,12 @@ There are two paths to making a development contribution:
 
 If you need help, you can ask questions in the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord.
 
-For frontend related work, **@pyschedelicious** is the best person to reach out to. 
+For frontend related work, **@psychedelicious** is the best person to reach out to. 
 
-For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@pyschedelicious**.
+For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@psychedelicious**.
 
 
 ## **What does the Code of Conduct mean for me?**
 
-Our [Code of Conduct](CODE_OF_CONDUCT.md)  means that you are responsible for treating everyone on the project with respect and courtesy regardless of their identity. If you are the victim of any inappropriate behavior or comments as described in our Code of Conduct, we are here for you and will do the best to ensure that the abuser is reprimanded appropriately, per our code.
+Our [Code of Conduct](../../CODE_OF_CONDUCT.md)  means that you are responsible for treating everyone on the project with respect and courtesy regardless of their identity. If you are the victim of any inappropriate behavior or comments as described in our Code of Conduct, we are here for you and will do the best to ensure that the abuser is reprimanded appropriately, per our code.
 

docs/contributing/contribution_guides/documentation.md

@@ -10,4 +10,4 @@ When updating or creating documentation, please keep in mind InvokeAI is a tool
 
 ## Help & Questions
 
-Please ping @imic1 or @hipsterusername in the [Discord](https://discord.com/channels/1020123559063990373/1049495067846524939) if you have any questions.
+Please ping @imic or @hipsterusername in the [Discord](https://discord.com/channels/1020123559063990373/1049495067846524939) if you have any questions.

docs/deprecated/CLI.md

@@ -211,8 +211,8 @@ Here are the invoke> command that apply to txt2img:
 | `--facetool <name>`                       | `-ft <name>`                              | `-ft gfpgan`                             | Select face restoration algorithm to use: gfpgan, codeformer                                                                                                                                                                                     |
 | `--codeformer_fidelity`                   | `-cf <float>`                             | `0.75`                                   | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality                                                                                                     |
 | `--save_original`                         | `-save_orig`                              | `False`                                  | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced.                                                                                                                                             |
-| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](../features/VARIATIONS.md). |
-| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](../features/VARIATIONS.md) for now to use this.                                                                                                                                                           |
+| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](VARIATIONS.md). |
+| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](VARIATIONS.md) for now to use this.                                                                                                                                                           |
 | `--save_intermediates <n>`                |                                           | `None`                                   | Save the image from every nth step into an "intermediates" folder inside the output directory                                                                                                                                                    |
 | `--h_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
 | `--v_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |

docs/deprecated/VARIATIONS.md

@@ -126,6 +126,6 @@ amounts of image-to-image variation even when the seed is fixed and the
 `-v` argument is very low. Others are more deterministic. Feel free to
 experiment until you find the combination that you like.
 
-Also be aware of the [Perlin Noise](OTHER.md#thresholding-and-perlin-noise-initialization-options)
+Also be aware of the [Perlin Noise](../features/OTHER.md#thresholding-and-perlin-noise-initialization-options)
 feature, which provides another way of introducing variability into your
 image generation requests.

docs/features/CONCEPTS.md

@@ -28,8 +28,9 @@ by placing them in the designated directory for the compatible model type
 
 ### An Example
 
-Here are a few examples to illustrate how it works. All these images were
-generated using the command-line client and the Stable Diffusion 1.5 model:
+Here are a few examples to illustrate how it works. All these images
+were generated using the legacy command-line client and the Stable
+Diffusion 1.5 model:
 
 |         Japanese gardener          | Japanese gardener <ghibli-face> | Japanese gardener <hoi4-leaders> | Japanese gardener <cartoona-animals> |
 | :--------------------------------: | :-----------------------------------: | :------------------------------------: | :----------------------------------------: |

docs/features/CONFIGURATION.md

@@ -82,7 +82,7 @@ format of YAML files can be found
 [here](https://circleci.com/blog/what-is-yaml-a-beginner-s-guide/).
 
 You can fix a broken `invokeai.yaml` by deleting it and running the
-configuration script again -- option [7] in the launcher, "Re-run the
+configuration script again -- option [6] in the launcher, "Re-run the
 configure script".
 
 #### Reading Environment Variables

docs/features/CONTROLNET.md

@@ -1,13 +1,11 @@
 ---
-title: ControlNet
+title: Control Adapters
 ---
 
-# :material-loupe: ControlNet
+# :material-loupe: Control Adapters
 
 ## ControlNet
 
-ControlNet
-
 ControlNet is a powerful set of features developed by the open-source
 community (notably, Stanford researcher
 [**@ilyasviel**](https://github.com/lllyasviel)) that allows you to
@@ -19,9 +17,6 @@ image generation, providing you with a way to direct the network
 towards generating images that better fit your desired style or
 outcome.
 
-
-### How it works
-
 ControlNet works by analyzing an input image, pre-processing that
 image to identify relevant information that can be interpreted by each
 specific ControlNet model, and then inserting that control information
@@ -29,35 +24,21 @@ into the generation process. This can be used to adjust the style,
 composition, or other aspects of the image to better achieve a
 specific result.
 
-
-### Models
+#### Installation
 
 InvokeAI provides access to a series of ControlNet models that provide
-different effects or styles in your generated images.  Currently
-InvokeAI only supports "diffuser" style ControlNet models. These are
-folders that contain the files `config.json` and/or
-`diffusion_pytorch_model.safetensors` and
-`diffusion_pytorch_model.fp16.safetensors`. The name of the folder is
-the name of the model.
+different effects or styles in your generated images.
 
-***InvokeAI does not currently support checkpoint-format
-ControlNets. These come in the form of a single file with the
-extension `.safetensors`.***
+To install ControlNet Models:
 
-Diffuser-style ControlNet models are available at HuggingFace
-(http://huggingface.co) and accessed via their repo IDs (identifiers
-in the format "author/modelname"). The easiest way to install them is
+1. The easiest way to install them is
 to use the InvokeAI model installer application. Use the
-`invoke.sh`/`invoke.bat` launcher to select item [5] and then navigate
+`invoke.sh`/`invoke.bat` launcher to select item [4] and then navigate
 to the CONTROLNETS section. Select the models you wish to install and
 press "APPLY CHANGES". You may also enter additional HuggingFace
-repo_ids in the "Additional models" textbox:
+repo_ids in the "Additional models" textbox. 
+2. Using the "Add Model" function of the  model manager, enter the HuggingFace Repo ID of the ControlNet. The ID is in the format "author/repoName"
 
-![Model Installer -
-Controlnetl](../assets/installing-models/model-installer-controlnet.png){:width="640px"}
-
-Command-line users can launch the model installer using the command
-`invokeai-model-install`.
 
 _Be aware that some ControlNet models require additional code
 functionality in order to work properly, so just installing a
@@ -65,6 +46,17 @@ third-party ControlNet model may not have the desired effect._ Please
 read and follow the documentation for installing a third party model
 not currently included among InvokeAI's default list.
 
+Currently InvokeAI **only** supports 🤗 Diffusers-format ControlNet models. These are
+folders that contain the files `config.json` and/or
+`diffusion_pytorch_model.safetensors` and
+`diffusion_pytorch_model.fp16.safetensors`. The name of the folder is
+the name of the model.
+
+🤗 Diffusers-format ControlNet models are available at HuggingFace
+(http://huggingface.co) and accessed via their repo IDs (identifiers
+in the format "author/modelname").
+
+#### ControlNet Models
 The models currently supported include:
 
 **Canny**:
@@ -96,6 +88,8 @@ A model that generates normal maps from input images, allowing for more realisti
 **Image Segmentation**: 
 A model that divides input images into segments or regions, each of which corresponds to a different object or part of the image. (More details coming soon)
 
+**QR Code Monster**:
+A model that helps generate creative QR codes that still scan. Can also be used to create images with text, logos or shapes within them. 
 
 **Openpose**: 
 The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
@@ -120,7 +114,7 @@ With Pix2Pix, you can input an image into the controlnet, and then "instruct" th
 Each of these models can be adjusted and combined with other ControlNet models to achieve different results, giving you even more control over your image generation process.
 
 
-## Using ControlNet
+### Using ControlNet
 
 To use ControlNet, you can simply select the desired model and adjust both the ControlNet and Pre-processor settings to achieve the desired result. You can also use multiple ControlNet models at the same time, allowing you to achieve even more complex effects or styles in your generated images.
 
@@ -132,3 +126,55 @@ Weight - Strength of the Controlnet model applied to the generation for the sect
 Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
 
 Additionally, each ControlNet section can be expanded in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in when you Invoke.
+
+## T2I-Adapter
+[T2I-Adapter](https://github.com/TencentARC/T2I-Adapter) is a tool similar to ControlNet that allows for control over the generation process by providing control information during the generation process. T2I-Adapter models tend to be smaller and more efficient than ControlNets. 
+
+##### Installation
+To install T2I-Adapter Models:
+
+1. The easiest way to install models is
+to use the InvokeAI model installer application. Use the
+`invoke.sh`/`invoke.bat` launcher to select item [5] and then navigate
+to the T2I-Adapters section. Select the models you wish to install and
+press "APPLY CHANGES". You may also enter additional HuggingFace
+repo_ids in the "Additional models" textbox. 
+2. Using the "Add Model" function of the  model manager, enter the HuggingFace Repo ID of the T2I-Adapter. The ID is in the format "author/repoName"
+
+#### Usage
+Each T2I Adapter has two settings that are applied.
+
+Weight - Strength of the model applied to the generation for the section, defined by start/end.
+
+Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
+
+Additionally, each  section can be expanded with the "Show Advanced" button in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in during the generation process.
+
+**Note:** T2I-Adapter models and ControlNet models cannot currently be used together.
+
+## IP-Adapter
+
+[IP-Adapter](https://ip-adapter.github.io) is a tooling that allows for image prompt capabilities with text-to-image diffusion models. IP-Adapter works by analyzing the given image prompt to extract features, then passing those features to the UNet along with any other conditioning provided. 
+
+![IP-Adapter + T2I](https://github.com/tencent-ailab/IP-Adapter/raw/main/assets/demo/ip_adpter_plus_multi.jpg)
+
+![IP-Adapter + IMG2IMG](https://raw.githubusercontent.com/tencent-ailab/IP-Adapter/main/assets/demo/image-to-image.jpg)
+
+#### Installation
+There are several ways to install IP-Adapter models with an existing InvokeAI installation:
+
+1. Through the command line interface launched from the invoke.sh / invoke.bat scripts, option [4] to download models.
+2. Through the Model Manager UI with models from the *Tools* section of [www.models.invoke.ai](https://www.models.invoke.ai). To do this, copy the repo ID from the desired model page, and paste it in the Add Model field of the model manager. **Note** Both the IP-Adapter and the Image Encoder must be installed for IP-Adapter to work. For example, the [SD 1.5 IP-Adapter](https://models.invoke.ai/InvokeAI/ip_adapter_plus_sd15) and [SD1.5 Image Encoder](https://models.invoke.ai/InvokeAI/ip_adapter_sd_image_encoder) must be installed to use IP-Adapter with SD1.5 based models.  
+3. **Advanced -- Not recommended ** Manually downloading the IP-Adapter and Image Encoder files - Image Encoder folders shouid be placed in the `models\any\clip_vision` folders. IP Adapter Model folders should be placed in the relevant `ip-adapter` folder of relevant base model folder of Invoke root directory. For example, for the SDXL IP-Adapter, files should be added to the `model/sdxl/ip_adapter/` folder. 
+
+#### Using IP-Adapter
+
+IP-Adapter can be used by navigating to the *Control Adapters* options and enabling IP-Adapter. 
+
+IP-Adapter requires an image to be used as the Image Prompt. It can also be used in conjunction with text prompts, Image-to-Image, Inpainting, Outpainting, ControlNets and LoRAs.
+
+
+Each IP-Adapter has two settings that are applied to the IP-Adapter:
+
+* Weight - Strength of the IP-Adapter model applied to the generation for the section, defined by start/end
+* Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the IP-Adapter applied.

docs/features/MODEL_MERGING.md

@@ -16,9 +16,10 @@ Model Merging can be be done by navigating to the Model Manager and clicking the
   display all the diffusers-style models that InvokeAI knows about.
   If you do not see the model you are looking for, then it is probably
   a legacy checkpoint model and needs to be converted using the
-  `invoke` command-line client and its `!optimize` command. You
-  must select at least two models to merge. The third can be left at
-  "None" if you desire.
+  "Convert" option in the Web-based Model Manager tab.
+  
+  You must select at least two models to merge. The third can be left
+  at "None" if you desire.
 
 * Alpha: This is the ratio to use when combining models. It ranges
   from 0 to 1. The higher the value, the more weight is given to the

docs/features/UTILITIES.md

@@ -8,7 +8,7 @@ title: Command-line Utilities
 
 InvokeAI comes with several scripts that are accessible via the
 command line. To access these commands, start the "developer's
-console" from the launcher (`invoke.bat` menu item [8]). Users who are
+console" from the launcher (`invoke.bat` menu item [7]). Users who are
 familiar with Python can alternatively activate InvokeAI's virtual
 environment (typically, but not necessarily `invokeai/.venv`).
 
@@ -34,7 +34,7 @@ invokeai-web --ram 7
 
 ## **invokeai-merge**
 
-This is the model merge script, the same as launcher option [4]. Call
+This is the model merge script, the same as launcher option [3]. Call
 it with the `--gui` command-line argument to start the interactive
 console-based GUI. Alternatively, you can run it non-interactively
 using command-line arguments as illustrated in the example below which
@@ -48,7 +48,7 @@ invokeai-merge --force --base-model sd-1 --models stable-diffusion-1.5 inkdiffus
 ## **invokeai-ti**
 
 This is the textual inversion training script that is run by launcher
-option [3]. Call it with `--gui` to run the interactive console-based
+option [2]. Call it with `--gui` to run the interactive console-based
 front end. It can also be run non-interactively. It has about a
 zillion arguments, but a typical training session can be launched
 with:
@@ -68,7 +68,7 @@ in Windows).
 ## **invokeai-install**
 
 This is the console-based model install script that is run by launcher
-option [5]. If called without arguments, it will launch the
+option [4]. If called without arguments, it will launch the
 interactive console-based interface. It can also be used
 non-interactively to list, add and remove models as shown by these
 examples:
@@ -148,7 +148,7 @@ launch the web server against it with `invokeai-web --root InvokeAI-New`.
 ## **invokeai-update**
 
 This is the interactive console-based script that is run by launcher
-menu item [9] to update to a new version of InvokeAI. It takes no
+menu item [8] to update to a new version of InvokeAI. It takes no
 command-line arguments.
 
 ## **invokeai-metadata**

docs/features/index.md

@@ -28,7 +28,7 @@ Learn how to install and use ControlNet models for fine control over
 image output.
 
 ### * [Image-to-Image Guide](IMG2IMG.md)
-Use a seed image to build new creations in the CLI.
+Use a seed image to build new creations.
 
 ## Model Management
 

docs/help/gettingStartedWithAI.md

@@ -57,7 +57,9 @@ Prompts provide the models directions on what to generate. As a general rule of
 
 Models are the magic that power InvokeAI. These files represent the output of training a machine on understanding massive amounts of images - providing them with the capability to generate new images using just a text description of what you’d like to see. (Like Stable Diffusion!)
 
-Invoke offers a simple way to download several different models upon installation, but many more can be discovered online, including at ****. Each model can produce a unique style of output, based on the images it was trained on - Try out different models to see which best fits your creative vision!
+Invoke offers a simple way to download several different models upon installation, but many more can be discovered online, including at https://models.invoke.ai 
+
+Each model can produce a unique style of output, based on the images it was trained on - Try out different models to see which best fits your creative vision!
 
 - *Models that contain “inpainting” in the name are designed for use with the inpainting feature of the Unified Canvas*
 

docs/index.md

@@ -143,7 +143,6 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 <!-- seperator -->
 ### Prompt Engineering
 - [Prompt Syntax](features/PROMPTS.md)
-- [Generating Variations](features/VARIATIONS.md)
 
 ### InvokeAI Configuration
 - [Guide to InvokeAI Runtime Settings](features/CONFIGURATION.md)
@@ -166,10 +165,8 @@ still a work in progress, but coming soon.
 
 ### Command-Line Interface Retired
 
-The original "invokeai" command-line interface has been retired. The
-`invokeai` command will now launch a new command-line client that can
-be used by developers to create and test nodes. It is not intended to
-be used for routine image generation or manipulation.
+All "invokeai" command-line interfaces have been retired as of version
+3.4.
 
 To launch the Web GUI from the command-line, use the command
 `invokeai-web` rather than the traditional `invokeai --web`.

docs/installation/010_INSTALL_AUTOMATED.md

@@ -40,7 +40,7 @@ experimental versions later.
     this, open up a command-line window ("Terminal" on Linux and
     Macintosh, "Command" or "Powershell" on Windows) and type `python
     --version`. If Python is installed, it will print out the version
-    number. If it is version `3.9.*`, `3.10.*` or `3.11.*` you meet
+    number. If it is version `3.10.*` or `3.11.*` you meet
     requirements.
 
     !!! warning "What to do if you have an unsupported version"
@@ -48,7 +48,7 @@ experimental versions later.
         Go to [Python Downloads](https://www.python.org/downloads/)
         and download the appropriate installer package for your
         platform. We recommend [Version
-        3.10.9](https://www.python.org/downloads/release/python-3109/),
+        3.10.12](https://www.python.org/downloads/release/python-3109/),
         which has been extensively tested with InvokeAI.
 
     _Please select your platform in the section below for platform-specific

docs/installation/020_INSTALL_MANUAL.md

@@ -32,7 +32,7 @@ gaming):
 
 * **Python**
 
-    version 3.9 through 3.11
+    version 3.10 through 3.11
 
 * **CUDA Tools**
 
@@ -65,7 +65,7 @@ gaming):
 To install InvokeAI with virtual environments and the PIP package
 manager, please follow these steps:
 
-1.  Please make sure you are using Python 3.9 through 3.11. The rest of the install
+1.  Please make sure you are using Python 3.10 through 3.11. The rest of the install
     procedure depends on this and will not work with other versions:
 
     ```bash
@@ -256,6 +256,10 @@ manager, please follow these steps:
         *highly recommended** if your virtual environment is located outside of
         your runtime directory.
 
+    !!! tip
+
+        On linux, it is recommended to run invokeai with the following env var: `MALLOC_MMAP_THRESHOLD_=1048576`. For example: `MALLOC_MMAP_THRESHOLD_=1048576 invokeai --web`. This helps to prevent memory fragmentation that can lead to memory accumulation over time. This env var is set automatically when running via `invoke.sh`.
+
 10.  Render away!
 
     Browse the [features](../features/index.md) section to learn about all the
@@ -296,8 +300,18 @@ code for InvokeAI. For this to work, you will need to install the
 on your system, please see the [Git Installation
 Guide](https://github.com/git-guides/install-git)
 
+You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md).
+
+If you have a "normal" installation, you should create a totally separate virtual environment for the git-based installation, else the two may interfere.
+
+> **Why do I need the frontend toolchain**?
+>
+> The InvokeAI project uses trunk-based development. That means our `main` branch is the development branch, and releases are tags on that branch. Because development is very active, we don't keep an updated build of the UI in `main` - we only build it for production releases.
+>
+> That means that between releases, to have a functioning application when running directly from the repo, you will need to run the UI in dev mode or build it regularly (any time the UI code changes).
+
 1. Create a fork of the InvokeAI repository through the GitHub UI or [this link](https://github.com/invoke-ai/InvokeAI/fork) 
-1. From the command line, run this command:
+2. From the command line, run this command:
    ```bash
    git clone https://github.com/<your_github_username>/InvokeAI.git
    ```
@@ -305,10 +319,10 @@ Guide](https://github.com/git-guides/install-git)
     This will create a directory named `InvokeAI` and populate it with the
     full source code from your fork of the InvokeAI repository.
 
-2. Activate the InvokeAI virtual environment as per step (4) of the manual
+3. Activate the InvokeAI virtual environment as per step (4) of the manual
 installation protocol (important!)
 
-3. Enter the InvokeAI repository directory and run one of these
+4. Enter the InvokeAI repository directory and run one of these
    commands, based on your GPU:
 
     === "CUDA (NVidia)"
@@ -334,11 +348,15 @@ installation protocol (important!)
     Be sure to pass `-e` (for an editable install) and don't forget the
     dot ("."). It is part of the command.
 
-    You can now run `invokeai` and its related commands. The code will be
+5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md) and do a production build of the UI as described.
+
+6.  You can now run `invokeai` and its related commands. The code will be
     read from the repository, so that you can edit the .py source files
     and watch the code's behavior change.
 
-4.  If you wish to contribute to the InvokeAI project, you are
+    When you pull in new changes to the repo, be sure to re-build the UI.
+
+7.  If you wish to contribute to the InvokeAI project, you are
     encouraged to establish a GitHub account and "fork"
     https://github.com/invoke-ai/InvokeAI into your own copy of the
     repository. You can then use GitHub functions to create and submit

docs/installation/040_INSTALL_DOCKER.md

@@ -4,30 +4,31 @@ title: Installing with Docker
 
 # :fontawesome-brands-docker: Docker
 
-!!! warning "For most users"
+!!! warning "macOS and AMD GPU Users"
 
-    We highly recommend to Install InvokeAI locally using [these instructions](INSTALLATION.md)
+    We highly recommend to Install InvokeAI locally using [these instructions](INSTALLATION.md),
+    because Docker containers can not access the GPU on macOS.
 
-!!! tip "For developers"
+!!! warning "AMD GPU Users"
 
-    For container-related development tasks or for enabling easy
-    deployment to other environments (on-premises or cloud), follow these
-    instructions.
+    Container support for AMD GPUs has been reported to work by the community, but has not received
+    extensive testing. Please make sure to set the `GPU_DRIVER=rocm` environment variable (see below), and
+    use the `build.sh` script to build the image for this to take effect at build time.
 
-    For general use, install locally to leverage your machine's GPU.
+!!! tip "Linux and Windows Users"
+
+    For optimal performance, configure your Docker daemon to access your machine's GPU.
+    Docker Desktop on Windows [includes GPU support](https://www.docker.com/blog/wsl-2-gpu-support-for-docker-desktop-on-nvidia-gpus/).
+    Linux users should install and configure the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
 
 ## Why containers?
 
-They provide a flexible, reliable way to build and deploy InvokeAI. You'll also
-use a Docker volume to store the largest model files and image outputs as a
-first step in decoupling storage and compute. Future enhancements can do this
-for other assets. See [Processes](https://12factor.net/processes) under the
-Twelve-Factor App methodology for details on why running applications in such a
-stateless fashion is important.
+They provide a flexible, reliable way to build and deploy InvokeAI.
+See [Processes](https://12factor.net/processes) under the Twelve-Factor App
+methodology for details on why running applications in such a stateless fashion is important.
 
-You can specify the target platform when building the image and running the
-container. You'll also need to specify the InvokeAI requirements file that
-matches the container's OS and the architecture it will run on.
+The container is configured for CUDA by default, but can be built to support AMD GPUs
+by setting the `GPU_DRIVER=rocm` environment variable at Docker image build time.
 
 Developers on Apple silicon (M1/M2): You
 [can't access your GPU cores from Docker containers](https://github.com/pytorch/pytorch/issues/81224)
@@ -36,6 +37,16 @@ development purposes it's fine. Once you're done with development tasks on your
 laptop you can build for the target platform and architecture and deploy to
 another environment with NVIDIA GPUs on-premises or in the cloud.
 
+## TL;DR
+
+This assumes properly configured Docker on Linux or Windows/WSL2. Read on for detailed customization options.
+
+    ```bash
+    # docker compose commands should be run from the `docker` directory
+    cd docker
+    docker compose up
+    ```
+
 ## Installation in a Linux container (desktop)
 
 ### Prerequisites
@@ -58,222 +69,33 @@ a token and copy it, since you will need in for the next step.
 
 ### Setup
 
-Set the fork you want to use and other variables.
+Set up your environmnent variables. In the `docker` directory, make a copy of `env.sample` and name it `.env`. Make changes as necessary.
 
-!!! tip
+Any environment variables supported by InvokeAI can be set here - please see the [CONFIGURATION](../features/CONFIGURATION.md) for further detail.
 
-    I preffer to save my env vars
-    in the repository root in a `.env` (or `.envrc`) file to automatically re-apply
-    them when I come back.
-
-The build- and run- scripts contain default values for almost everything,
-besides the [Hugging Face Token](https://huggingface.co/settings/tokens) you
-created in the last step.
-
-Some Suggestions of variables you may want to change besides the Token:
+At a minimum, you might want to set the `INVOKEAI_ROOT` environment variable
+to point to the location where you wish to store your InvokeAI models, configuration, and outputs.
 
 <figure markdown>
 
 | Environment-Variable <img width="220" align="right"/> | Default value <img width="360" align="right"/> | Description                                                                                                                                                                                       |
 | ----------------------------------------------------- | ---------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `HUGGING_FACE_HUB_TOKEN`                              | No default, but **required**!                  | This is the only **required** variable, without it you can't download the huggingface models                                                                                                      |
-| `REPOSITORY_NAME`                                     | The Basename of the Repo folder                | This name will used as the container repository/image name                                                                                                                                        |
-| `VOLUMENAME`                                          | `${REPOSITORY_NAME,,}_data`                    | Name of the Docker Volume where model files will be stored                                                                                                                                        |
-| `ARCH`                                                | arch of the build machine                      | Can be changed if you want to build the image for another arch                                                                                                                                    |
-| `CONTAINER_REGISTRY`                                  | ghcr.io                                        | Name of the Container Registry to use for the full tag                                                                                                                                            |
-| `CONTAINER_REPOSITORY`                                | `$(whoami)/${REPOSITORY_NAME}`                 | Name of the Container Repository                                                                                                                                                                  |
-| `CONTAINER_FLAVOR`                                    | `cuda`                                         | The flavor of the image to built, available options are `cuda`, `rocm` and `cpu`. If you choose `rocm` or `cpu`, the extra-index-url will be selected automatically, unless you set one yourself. |
-| `CONTAINER_TAG`                                       | `${INVOKEAI_BRANCH##*/}-${CONTAINER_FLAVOR}`   | The Container Repository / Tag which will be used                                                                                                                                                 |
-| `INVOKE_DOCKERFILE`                                   | `Dockerfile`                                   | The Dockerfile which should be built, handy for development                                                                                                                                       |
-| `PIP_EXTRA_INDEX_URL`                                 |                                                | If you want to use a custom pip-extra-index-url                                                                                                                                                   |
+| `INVOKEAI_ROOT`                                       | `~/invokeai`                                   | **Required** - the location of your InvokeAI root directory. It will be created if it does not exist.
+| `HUGGING_FACE_HUB_TOKEN`                              |                                                | InvokeAI will work without it, but some of the integrations with HuggingFace (like downloading from models from private repositories) may not work|
+| `GPU_DRIVER`                                          | `cuda`                                         | Optionally change this to `rocm` to build the image for AMD GPUs. NOTE: Use the `build.sh` script to build the image for this to take effect.
 
 </figure>
 
 #### Build the Image
 
-I provided a build script, which is located next to the Dockerfile in
-`docker/build.sh`. It can be executed from repository root like this:
+Use the standard `docker compose build` command from within the `docker` directory.
 
-```bash
-./docker/build.sh
-```
-
-The build Script not only builds the container, but also creates the docker
-volume if not existing yet.
+If using an AMD GPU:
+    a: set the `GPU_DRIVER=rocm` environment variable in `docker-compose.yml` and continue using `docker compose build` as usual, or
+    b: set `GPU_DRIVER=rocm` in the `.env` file and use the `build.sh` script, provided for convenience
 
 #### Run the Container
 
-After the build process is done, you can run the container via the provided
-`docker/run.sh` script
+Use the standard `docker compose up` command, and generally the `docker compose` [CLI](https://docs.docker.com/compose/reference/) as usual.
 
-```bash
-./docker/run.sh
-```
-
-When used without arguments, the container will start the webserver and provide
-you the link to open it. But if you want to use some other parameters you can
-also do so.
-
-!!! example "run script example"
-
-    ```bash
-    ./docker/run.sh "banana sushi" -Ak_lms -S42 -s10
-    ```
-
-    This would generate the legendary "banana sushi" with Seed 42, k_lms Sampler and 10 steps.
-
-    Find out more about available CLI-Parameters at [features/CLI.md](../../features/CLI/#arguments)
-
----
-
-## Running the container on your GPU
-
-If you have an Nvidia GPU, you can enable InvokeAI to run on the GPU by running
-the container with an extra environment variable to enable GPU usage and have
-the process run much faster:
-
-```bash
-GPU_FLAGS=all ./docker/run.sh
-```
-
-This passes the `--gpus all` to docker and uses the GPU.
-
-If you don't have a GPU (or your host is not yet setup to use it) you will see a
-message like this:
-
-`docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]].`
-
-You can use the full set of GPU combinations documented here:
-
-https://docs.docker.com/config/containers/resource_constraints/#gpu
-
-For example, use `GPU_FLAGS=device=GPU-3a23c669-1f69-c64e-cf85-44e9b07e7a2a` to
-choose a specific device identified by a UUID.
-
----
-
-!!! warning "Deprecated"
-
-    From here on you will find the the previous Docker-Docs, which will still
-    provide some usefull informations.
-
-## Usage (time to have fun)
-
-### Startup
-
-If you're on a **Linux container** the `invoke` script is **automatically
-started** and the output dir set to the Docker volume you created earlier.
-
-If you're **directly on macOS follow these startup instructions**. With the
-Conda environment activated (`conda activate ldm`), run the interactive
-interface that combines the functionality of the original scripts `txt2img` and
-`img2img`: Use the more accurate but VRAM-intensive full precision math because
-half-precision requires autocast and won't work. By default the images are saved
-in `outputs/img-samples/`.
-
-```Shell
-python3 scripts/invoke.py --full_precision
-```
-
-You'll get the script's prompt. You can see available options or quit.
-
-```Shell
-invoke> -h
-invoke> q
-```
-
-### Text to Image
-
-For quick (but bad) image results test with 5 steps (default 50) and 1 sample
-image. This will let you know that everything is set up correctly. Then increase
-steps to 100 or more for good (but slower) results. The prompt can be in quotes
-or not.
-
-```Shell
-invoke> The hulk fighting with sheldon cooper -s5 -n1
-invoke> "woman closeup highly detailed"  -s 150
-# Reuse previous seed and apply face restoration
-invoke> "woman closeup highly detailed"  --steps 150 --seed -1 -G 0.75
-```
-
-You'll need to experiment to see if face restoration is making it better or
-worse for your specific prompt.
-
-If you're on a container the output is set to the Docker volume. You can copy it
-wherever you want. You can download it from the Docker Desktop app, Volumes,
-my-vol, data. Or you can copy it from your Mac terminal. Keep in mind
-`docker cp` can't expand `*.png` so you'll need to specify the image file name.
-
-On your host Mac (you can use the name of any container that mounted the
-volume):
-
-```Shell
-docker cp dummy:/data/000001.928403745.png /Users/<your-user>/Pictures
-```
-
-### Image to Image
-
-You can also do text-guided image-to-image translation. For example, turning a
-sketch into a detailed drawing.
-
-`strength` is a value between 0.0 and 1.0 that controls the amount of noise that
-is added to the input image. Values that approach 1.0 allow for lots of
-variations but will also produce images that are not semantically consistent
-with the input. 0.0 preserves image exactly, 1.0 replaces it completely.
-
-Make sure your input image size dimensions are multiples of 64 e.g. 512x512.
-Otherwise you'll get `Error: product of dimension sizes > 2**31'`. If you still
-get the error
-[try a different size](https://support.apple.com/guide/preview/resize-rotate-or-flip-an-image-prvw2015/mac#:~:text=image's%20file%20size-,In%20the%20Preview%20app%20on%20your%20Mac%2C%20open%20the%20file,is%20shown%20at%20the%20bottom.)
-like 512x256.
-
-If you're on a Docker container, copy your input image into the Docker volume
-
-```Shell
-docker cp /Users/<your-user>/Pictures/sketch-mountains-input.jpg dummy:/data/
-```
-
-Try it out generating an image (or more). The `invoke` script needs absolute
-paths to find the image so don't use `~`.
-
-If you're on your Mac
-
-```Shell
-invoke> "A fantasy landscape, trending on artstation" -I /Users/<your-user>/Pictures/sketch-mountains-input.jpg --strength 0.75  --steps 100 -n4
-```
-
-If you're on a Linux container on your Mac
-
-```Shell
-invoke> "A fantasy landscape, trending on artstation" -I /data/sketch-mountains-input.jpg --strength 0.75  --steps 50 -n1
-```
-
-### Web Interface
-
-You can use the `invoke` script with a graphical web interface. Start the web
-server with:
-
-```Shell
-python3 scripts/invoke.py --full_precision --web
-```
-
-If it's running on your Mac point your Mac web browser to
-<http://127.0.0.1:9090>
-
-Press Control-C at the command line to stop the web server.
-
-### Notes
-
-Some text you can add at the end of the prompt to make it very pretty:
-
-```Shell
-cinematic photo, highly detailed, cinematic lighting, ultra-detailed, ultrarealistic, photorealism, Octane Rendering, cyberpunk lights, Hyper Detail, 8K, HD, Unreal Engine, V-Ray, full hd, cyberpunk, abstract, 3d octane render + 4k UHD + immense detail + dramatic lighting + well lit + black, purple, blue, pink, cerulean, teal, metallic colours, + fine details, ultra photoreal, photographic, concept art, cinematic composition, rule of thirds, mysterious, eerie, photorealism, breathtaking detailed, painting art deco pattern, by hsiao, ron cheng, john james audubon, bizarre compositions, exquisite detail, extremely moody lighting, painted by greg rutkowski makoto shinkai takashi takeuchi studio ghibli, akihiko yoshida
-```
-
-The original scripts should work as well.
-
-```Shell
-python3 scripts/orig_scripts/txt2img.py --help
-python3 scripts/orig_scripts/txt2img.py --ddim_steps 100 --n_iter 1 --n_samples 1  --plms --prompt "new born baby kitten. Hyper Detail, Octane Rendering, Unreal Engine, V-Ray"
-python3 scripts/orig_scripts/txt2img.py --ddim_steps 5   --n_iter 1 --n_samples 1  --plms --prompt "ocean" # or --klms
-```
+Once the container starts up (and configures the InvokeAI root directory if this is a new installation), you can access InvokeAI at [http://localhost:9090](http://localhost:9090)

docs/installation/050_INSTALLING_MODELS.md

@@ -84,7 +84,7 @@ InvokeAI root directory's `autoimport` folder.
 
 ### Installation via `invokeai-model-install`
 
-From the `invoke` launcher, choose option [5] "Download and install
+From the `invoke` launcher, choose option [4] "Download and install
 models." This will launch the same script that prompted you to select
 models at install time. You can use this to add models that you
 skipped the first time around. It is all right to specify a model that
@@ -171,3 +171,16 @@ subfolders and organize them as you wish.
 
 The location of the autoimport directories are controlled by settings
 in `invokeai.yaml`. See [Configuration](../features/CONFIGURATION.md).
+
+### Installing models that live in HuggingFace subfolders
+
+On rare occasions you may need to install a diffusers-style model that
+lives in a subfolder of a HuggingFace repo id. In this event, simply
+add ":_subfolder-name_" to the end of the repo id. For example, if the
+repo id is "monster-labs/control_v1p_sd15_qrcode_monster" and the model
+you wish to fetch lives in a subfolder named "v2", then the repo id to
+pass to the various model installers should be 
+
+```
+monster-labs/control_v1p_sd15_qrcode_monster:v2
+```

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -59,8 +59,7 @@ Prior to installing PyPatchMatch, you need to take the following steps:
    `from patchmatch import patch_match`: It should look like the following:
 
     ```py
-    Python 3.9.5 (default, Nov 23 2021, 15:27:38)
-    [GCC 9.3.0] on linux
+    Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] on linux
     Type "help", "copyright", "credits" or "license" for more information.
     >>> from patchmatch import patch_match
     Compiling and loading c extensions from "/home/lstein/Projects/InvokeAI/.invokeai-env/src/pypatchmatch/patchmatch".

docs/installation/deprecated_documentation/INSTALL_LINUX.md

@@ -79,7 +79,7 @@ title: Manual Installation, Linux
         and obtaining an access token for downloading. It will then download and
         install the weights files for you.
 
-        Please look [here](../INSTALL_MANUAL.md) for a manual process for doing
+        Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing
         the same thing.
 
 7.  Start generating images!
@@ -112,7 +112,7 @@ title: Manual Installation, Linux
         To use an alternative model you may invoke the `!switch` command in
         the CLI, or pass `--model <model_name>` during `invoke.py` launch for
         either the CLI or the Web UI. See [Command Line
-        Client](../../features/CLI.md#model-selection-and-importation). The
+        Client](../../deprecated/CLI.md#model-selection-and-importation). The
         model names are defined in `configs/models.yaml`.
 
 8. Subsequently, to relaunch the script, be sure to run "conda activate

docs/installation/deprecated_documentation/INSTALL_MAC.md

@@ -150,7 +150,7 @@ will do our best to help.
     To use an alternative model you may invoke the `!switch` command in
     the CLI, or pass `--model <model_name>` during `invoke.py` launch for
     either the CLI or the Web UI. See [Command Line
-    Client](../../features/CLI.md#model-selection-and-importation). The
+    Client](../../deprecated/CLI.md#model-selection-and-importation). The
     model names are defined in `configs/models.yaml`.
 
 ---

docs/installation/deprecated_documentation/INSTALL_SOURCE.md

@@ -128,7 +128,7 @@ python scripts/invoke.py --web --max_load_models=3 \
 ```
 
 These options are described in detail in the
-[Command-Line Interface](../../features/CLI.md) documentation.
+[Command-Line Interface](../../deprecated/CLI.md) documentation.
 
 ## Troubleshooting
 

docs/installation/deprecated_documentation/INSTALL_WINDOWS.md

@@ -75,7 +75,7 @@ Note that you will need NVIDIA drivers, Python 3.10, and Git installed beforehan
           obtaining an access token for downloading. It will then download and install the
           weights files for you.
 
-          Please look [here](../INSTALL_MANUAL.md) for a manual process for doing the
+          Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing the
           same thing.
 
 8. Start generating images!
@@ -108,7 +108,7 @@ Note that you will need NVIDIA drivers, Python 3.10, and Git installed beforehan
         To use an alternative model you may invoke the `!switch` command in
         the CLI, or pass `--model <model_name>` during `invoke.py` launch for
         either the CLI or the Web UI. See [Command Line
-        Client](../../features/CLI.md#model-selection-and-importation). The
+        Client](../../deprecated/CLI.md#model-selection-and-importation). The
         model names are defined in `configs/models.yaml`.
 
 9. Subsequently, to relaunch the script, first activate the Anaconda

docs/nodes/NODES.md

@@ -4,12 +4,12 @@ The workflow editor is a blank canvas allowing for the use of individual functio
 
 If you're not familiar with Diffusion, take a look at our [Diffusion Overview.](../help/diffusion.md) Understanding how diffusion works will enable you to more easily use the Workflow Editor and build workflows to suit your needs.
 
-## UI Features
+## Features
 
 ### Linear View
 The Workflow Editor allows you to create a UI for your workflow, to make it easier to iterate on your generations. 
 
-To add an input to the Linear UI, right click on the input and select "Add to Linear View".
+To add an input to the Linear UI, right click on the input label and select "Add to Linear View".
 
 The Linear UI View will also be part of the saved workflow, allowing you share workflows and enable other to use them, regardless of complexity. 
 
@@ -25,6 +25,10 @@ Any node or input field can be renamed in the workflow editor. If the input fiel
 * Backspace/Delete to delete a node
 * Shift+Click to drag and select multiple nodes 
 
+### Node Caching 
+
+Nodes have a "Use Cache" option in their footer. This allows for performance improvements by using the previously cached values during the workflow processing. 
+
 
 ## Important Concepts 
 

docs/nodes/communityNodes.md

@@ -8,26 +8,42 @@ To download a node, simply download the `.py` node file from the link and add it
 
 To use a community workflow, download the the `.json` node graph file and load it into Invoke AI via the **Load Workflow** button in the Workflow Editor. 
 
-## Community Nodes
+- Community Nodes
+    + [Depth Map from Wavefront OBJ](#depth-map-from-wavefront-obj)
+    + [Film Grain](#film-grain)
+    + [Generative Grammar-Based Prompt Nodes](#generative-grammar-based-prompt-nodes)
+    + [GPT2RandomPromptMaker](#gpt2randompromptmaker)
+    + [Grid to Gif](#grid-to-gif)
+    + [Halftone](#halftone)
+    + [Ideal Size](#ideal-size)
+    + [Image and Mask Composition Pack](#image-and-mask-composition-pack)
+    + [Image to Character Art Image Nodes](#image-to-character-art-image-nodes)
+    + [Image Picker](#image-picker)
+    + [Load Video Frame](#load-video-frame)
+    + [Make 3D](#make-3d)
+    + [Oobabooga](#oobabooga)
+    + [Prompt Tools](#prompt-tools)
+    + [Retroize](#retroize)
+    + [Size Stepper Nodes](#size-stepper-nodes)
+    + [Text font to Image](#text-font-to-image)
+    + [Thresholding](#thresholding)
+    + [XY Image to Grid and Images to Grids nodes](#xy-image-to-grid-and-images-to-grids-nodes)
+- [Example Node Template](#example-node-template)
+- [Disclaimer](#disclaimer)
+- [Help](#help)
 
-### FaceTools
-
-**Description:** FaceTools is a collection of nodes created to manipulate faces as you would in Unified Canvas. It includes FaceMask, FaceOff, and FacePlace. FaceMask autodetects a face in the image using MediaPipe and creates a mask from it. FaceOff similarly detects a face, then takes the face off of the image by adding a square bounding box around it and cropping/scaling it. FacePlace puts the bounded face image from FaceOff back onto the original image. Using these nodes with other inpainting node(s), you can put new faces on existing things, put new things around existing faces, and work closer with a face as a bounded image. Additionally, you can supply X and Y offset values to scale/change the shape of the mask for finer control on FaceMask and FaceOff. See GitHub repository below for usage examples.
-
-**Node Link:** https://github.com/ymgenesis/FaceTools/
-
-**FaceMask Output Examples** 
-
-![5cc8abce-53b0-487a-b891-3bf94dcc8960](https://github.com/invoke-ai/InvokeAI/assets/25252829/43f36d24-1429-4ab1-bd06-a4bedfe0955e)
-![b920b710-1882-49a0-8d02-82dff2cca907](https://github.com/invoke-ai/InvokeAI/assets/25252829/7660c1ed-bf7d-4d0a-947f-1fc1679557ba)
-![71a91805-fda5-481c-b380-264665703133](https://github.com/invoke-ai/InvokeAI/assets/25252829/f8f6a2ee-2b68-4482-87da-b90221d5c3e2)
 
 --------------------------------
-### Ideal Size
+### Depth Map from Wavefront OBJ
 
-**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
+**Description:** Render depth maps from Wavefront .obj files (triangulated) using this simple 3D renderer utilizing numpy and matplotlib to compute and color the scene. There are simple parameters to change the FOV, camera position, and model orientation.
 
-**Node Link:** https://github.com/JPPhoto/ideal-size-node
+To be imported, an .obj must use triangulated meshes, so make sure to enable that option if exporting from a 3D modeling program. This renderer makes each triangle a solid color based on its average depth, so it will cause anomalies if your .obj has large triangles. In Blender, the Remesh modifier can be helpful to subdivide a mesh into small pieces that work well given these limitations.
+
+**Node Link:** https://github.com/dwringer/depth-from-obj-node
+
+**Example Usage:**
+</br><img src="https://raw.githubusercontent.com/dwringer/depth-from-obj-node/main/depth_from_obj_usage.jpg" width="500" />
 
 --------------------------------
 ### Film Grain
@@ -37,22 +53,19 @@ To use a community workflow, download the the `.json` node graph file and load i
 **Node Link:** https://github.com/JPPhoto/film-grain-node
 
 --------------------------------
-### Image Picker
+### Generative Grammar-Based Prompt Nodes
 
-**Description:** This InvokeAI node takes in a collection of images and randomly chooses one. This can be useful when you have a number of poses to choose from for a ControlNet node, or a number of input images for another purpose.
+**Description:** This set of 3 nodes generates prompts from simple user-defined grammar rules (loaded from custom files - examples provided below). The prompts are made by recursively expanding a special template string, replacing nonterminal "parts-of-speech" until no nonterminal terms remain in the string.
 
-**Node Link:** https://github.com/JPPhoto/image-picker-node
+This includes 3 Nodes:
+- *Lookup Table from File* - loads a YAML file "prompt" section (or of a whole folder of YAML's) into a JSON-ified dictionary (Lookups output)
+- *Lookups Entry from Prompt* - places a single entry in a new Lookups output under the specified heading
+- *Prompt from Lookup Table* - uses a Collection of Lookups as grammar rules from which to randomly generate prompts.
 
---------------------------------
-### Retroize
+**Node Link:** https://github.com/dwringer/generative-grammar-prompt-nodes
 
-**Description:** Retroize is a collection of nodes for InvokeAI to "Retroize" images. Any image can be given a fresh coat of retro paint with these nodes, either from your gallery or from within the graph itself. It includes nodes to pixelize, quantize, palettize, and ditherize images; as well as to retrieve palettes from existing images.
-
-**Node Link:** https://github.com/Ar7ific1al/invokeai-retroizeinode/
-
-**Retroize Output Examples**
-
-![image](https://github.com/Ar7ific1al/InvokeAI_nodes_retroize/assets/2306586/de8b4fa6-324c-4c2d-b36c-297600c73974)
+**Example Usage:**
+</br><img src="https://raw.githubusercontent.com/dwringer/generative-grammar-prompt-nodes/main/lookuptables_usage.jpg" width="500" />
 
 --------------------------------
 ### GPT2RandomPromptMaker
@@ -65,31 +78,133 @@ To use a community workflow, download the the `.json` node graph file and load i
 
 Generated Prompt: An enchanted weapon will be usable by any character regardless of their alignment.
 
-![9acf5aef-7254-40dd-95b3-8eac431dfab0 (1)](https://github.com/mickr777/InvokeAI/assets/115216705/8496ba09-bcdd-4ff7-8076-ff213b6a1e4c)
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/8496ba09-bcdd-4ff7-8076-ff213b6a1e4c" width="200" />
+
+--------------------------------
+### Grid to Gif
+
+**Description:** One node that turns a grid image into an image collection, one node that turns an image collection into a gif.
+
+**Node Link:** https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/GridToGif.py
+
+**Example Node Graph:**  https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/Grid%20to%20Gif%20Example%20Workflow.json
+
+**Output Examples** 
+
+<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/input.png" width="300" />
+<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/output.gif" width="300" />
+
+--------------------------------
+### Halftone
+
+**Description**: Halftone converts the source image to grayscale and then performs halftoning. CMYK Halftone converts the image to CMYK and applies a per-channel halftoning to make the source image look like a magazine or newspaper. For both nodes, you can specify angles and halftone dot spacing.
+
+**Node Link:** https://github.com/JPPhoto/halftone-node
+
+**Example**
+
+Input:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/fd5efb9f-4355-4409-a1c2-c1ca99e0cab4" width="300" />
+
+Halftone Output:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/7e606f29-e68f-4d46-b3d5-97f799a4ec2f" width="300" />
+
+CMYK Halftone Output:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c59c578f-db8e-4d66-8c66-2851752d75ea" width="300" />
+
+--------------------------------
+### Ideal Size
+
+**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
+
+**Node Link:** https://github.com/JPPhoto/ideal-size-node
+
+--------------------------------
+### Image and Mask Composition Pack
+
+**Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
+
+This includes 15 Nodes:
+
+- *Adjust Image Hue Plus* - Rotate the hue of an image in one of several different color spaces.
+- *Blend Latents/Noise (Masked)* - Use a mask to blend part of one latents tensor [including Noise outputs] into another. Can be used to "renoise" sections during a multi-stage [masked] denoising process.
+- *Enhance Image* - Boost or reduce color saturation, contrast, brightness, sharpness, or invert colors of any image at any stage with this simple wrapper for pillow [PIL]'s ImageEnhance module.
+- *Equivalent Achromatic Lightness* - Calculates image lightness accounting for Helmholtz-Kohlrausch effect based on a method described by High, Green, and Nussbaum (2023).
+- *Text to Mask (Clipseg)* - Input a prompt and an image to generate a mask representing areas of the image matched by the prompt.
+- *Text to Mask Advanced (Clipseg)* - Output up to four prompt masks combined with logical "and", logical "or", or as separate channels of an RGBA image.
+- *Image Layer Blend* - Perform a layered blend of two images using alpha compositing. Opacity of top layer is selectable, with optional mask and several different blend modes/color spaces.
+- *Image Compositor* - Take a subject from an image with a flat backdrop and layer it on another image using a chroma key or flood select background removal.
+- *Image Dilate or Erode* - Dilate or expand a mask (or any image!). This is equivalent to an expand/contract operation.
+- *Image Value Thresholds* - Clip an image to pure black/white beyond specified thresholds.
+- *Offset Latents* - Offset a latents tensor in the vertical and/or horizontal dimensions, wrapping it around.
+- *Offset Image* - Offset an image in the vertical and/or horizontal dimensions, wrapping it around.
+- *Rotate/Flip Image* - Rotate an image in degrees clockwise/counterclockwise about its center, optionally resizing the image boundaries to fit, or flipping it about the vertical and/or horizontal axes.
+- *Shadows/Highlights/Midtones* - Extract three masks (with adjustable hard or soft thresholds) representing shadows, midtones, and highlights regions of an image.
+- *Text Mask (simple 2D)* - create and position a white on black (or black on white) line of text using any font locally available to Invoke.
+
+**Node Link:** https://github.com/dwringer/composition-nodes
+  
+</br><img src="https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_pack_overview.jpg" width="500" />
+
+--------------------------------
+### Image to Character Art Image Nodes
+
+**Description:** Group of nodes to convert an input image into ascii/unicode art Image
+
+**Node Link:** https://github.com/mickr777/imagetoasciiimage
+
+**Output Examples**
+
+<img src="https://user-images.githubusercontent.com/115216705/271817646-8e061fcc-9a2c-4fa9-bcc7-c0f7b01e9056.png" width="300" /><img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/3c4990eb-2f42-46b9-90f9-0088b939dc6a" width="300" /></br>
+<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/fee7f800-a4a8-41e2-a66b-c66e4343307e" width="300" />
+<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/1d9c1003-a45f-45c2-aac7-46470bb89330" width="300" />
+
+--------------------------------
+
+### Image Picker
+
+**Description:** This InvokeAI node takes in a collection of images and randomly chooses one. This can be useful when you have a number of poses to choose from for a ControlNet node, or a number of input images for another purpose.
+
+**Node Link:** https://github.com/JPPhoto/image-picker-node
 
 --------------------------------
 ### Load Video Frame
 
-**Description:** This is a video frame image provider + indexer/video creation nodes for hooking up to iterators and ranges and ControlNets and such for invokeAI node experimentation. Think animation + ControlNet outputs.
+**Description:** This is a video frame image provider + indexer/video creation nodes for hooking up to iterators and ranges and ControlNets and such for invokeAI node experimentation. Think animation + ControlNet outputs.
 
 **Node Link:** https://github.com/helix4u/load_video_frame
 
 **Example Node Graph:**  https://github.com/helix4u/load_video_frame/blob/main/Example_Workflow.json
 
 **Output Example:** 
-=======
-![Example animation](https://github.com/helix4u/load_video_frame/blob/main/testmp4_embed_converted.gif)
+
+<img src="https://raw.githubusercontent.com/helix4u/load_video_frame/main/testmp4_embed_converted.gif" width="500" />
 [Full mp4 of Example Output test.mp4](https://github.com/helix4u/load_video_frame/blob/main/test.mp4)
 
 --------------------------------
+### Make 3D
 
+**Description:** Create compelling 3D stereo images from 2D originals.
+
+**Node Link:** [https://gitlab.com/srcrr/shift3d/-/raw/main/make3d.py](https://gitlab.com/srcrr/shift3d)
+
+**Example Node Graph:**  https://gitlab.com/srcrr/shift3d/-/raw/main/example-workflow.json?ref_type=heads&inline=false
+
+**Output Examples** 
+
+<img src="https://gitlab.com/srcrr/shift3d/-/raw/main/example-1.png" width="300" />
+<img src="https://gitlab.com/srcrr/shift3d/-/raw/main/example-2.png" width="300" />
+
+--------------------------------
 ### Oobabooga
 
 **Description:** asks a local LLM running in Oobabooga's Text-Generation-Webui to write a prompt based on the user input.
 
 **Link:** https://github.com/sammyf/oobabooga-node
 
-
 **Example:**
 
 "describe a new mystical  creature in its natural environment"
@@ -99,7 +214,7 @@ Generated Prompt: An enchanted weapon will be usable by any character regardless
 "The mystical creature I am describing to you is called the "Glimmerwing". It is a majestic, iridescent being that inhabits the depths of the most enchanted forests and glimmering lakes. Its body is covered in shimmering scales that reflect every color of the rainbow, and it has delicate, translucent wings that sparkle like diamonds in the sunlight. The Glimmerwing's home is a crystal-clear lake, surrounded by towering trees with leaves that shimmer like jewels. In this serene environment, the Glimmerwing spends its days swimming gracefully through the water, chasing schools of glittering fish and playing with the gentle ripples of the lake's surface.
 As the sun sets, the Glimmerwing perches on a branch of one of the trees, spreading its wings to catch the last rays of light. The creature's scales glow softly, casting a rainbow of colors across the forest floor. The Glimmerwing sings a haunting melody, its voice echoing through the stillness of the night air. Its song is said to have the power to heal the sick and bring peace to troubled souls. Those who are lucky enough to hear the Glimmerwing's song are forever changed by its beauty and grace."
 
-![glimmerwing_small](https://github.com/sammyf/oobabooga-node/assets/42468608/cecdd820-93dd-4c35-abbf-607e001fb2ed)
+<img src="https://github.com/sammyf/oobabooga-node/assets/42468608/cecdd820-93dd-4c35-abbf-607e001fb2ed" width="300" />
 
 **Requirement**
 
@@ -107,98 +222,12 @@ a Text-Generation-Webui instance (might work remotely too, but I never tried it)
 
 **Note**
 
-This node works best with SDXL models, especially as the style can be described independantly of the LLM's output.
+This node works best with SDXL models, especially as the style can be described independently of the LLM's output.
 
 --------------------------------
-### Depth Map from Wavefront OBJ
-
-**Description:** Render depth maps from Wavefront .obj files (triangulated) using this simple 3D renderer utilizing numpy and matplotlib to compute and color the scene. There are simple parameters to change the FOV, camera position, and model orientation.
-
-To be imported, an .obj must use triangulated meshes, so make sure to enable that option if exporting from a 3D modeling program. This renderer makes each triangle a solid color based on its average depth, so it will cause anomalies if your .obj has large triangles. In Blender, the Remesh modifier can be helpful to subdivide a mesh into small pieces that work well given these limitations.
-
-**Node Link:** https://github.com/dwringer/depth-from-obj-node
-
-**Example Usage:**
-![depth from obj usage graph](https://raw.githubusercontent.com/dwringer/depth-from-obj-node/main/depth_from_obj_usage.jpg)
-
---------------------------------
-### Enhance Image (simple adjustments)
-
-**Description:** Boost or reduce color saturation, contrast, brightness, sharpness, or invert colors of any image at any stage with this simple wrapper for pillow [PIL]'s ImageEnhance module.
-
-Color inversion is toggled with a simple switch, while each of the four enhancer modes are activated by entering a value other than 1 in each corresponding input field. Values less than 1 will reduce the corresponding property, while values greater than 1 will enhance it.
-
-**Node Link:** https://github.com/dwringer/image-enhance-node
-
-**Example Usage:**
-![enhance image usage graph](https://raw.githubusercontent.com/dwringer/image-enhance-node/main/image_enhance_usage.jpg)
-
---------------------------------
-### Generative Grammar-Based Prompt Nodes
-
-**Description:** This set of 3 nodes generates prompts from simple user-defined grammar rules (loaded from custom files - examples provided below). The prompts are made by recursively expanding a special template string, replacing nonterminal "parts-of-speech" until no more nonterminal terms remain in the string.
-
-This includes 3 Nodes:
-- *Lookup Table from File* - loads a YAML file "prompt" section (or of a whole folder of YAML's) into a JSON-ified dictionary (Lookups output)
-- *Lookups Entry from Prompt* - places a single entry in a new Lookups output under the specified heading
-- *Prompt from Lookup Table* - uses a Collection of Lookups as grammar rules from which to randomly generate prompts.
-
-**Node Link:** https://github.com/dwringer/generative-grammar-prompt-nodes
-
-**Example Usage:**
-![lookups usage example graph](https://raw.githubusercontent.com/dwringer/generative-grammar-prompt-nodes/main/lookuptables_usage.jpg)
-
---------------------------------
-### Image and Mask Composition Pack
-
-**Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
-
-This includes 4 Nodes:
-- *Text Mask (simple 2D)* - create and position a white on black (or black on white) line of text using any font locally available to Invoke.
-- *Image Compositor* - Take a subject from an image with a flat backdrop and layer it on another image using a chroma key or flood select background removal.
-- *Offset Latents* - Offset a latents tensor in the vertical and/or horizontal dimensions, wrapping it around.
-- *Offset Image* - Offset an image in the vertical and/or horizontal dimensions, wrapping it around.
-
-**Node Link:** https://github.com/dwringer/composition-nodes
-
-**Example Usage:**
-![composition nodes usage graph](https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_nodes_usage.jpg)
-
---------------------------------
-### Size Stepper Nodes
-
-**Description:** This is a set of nodes for calculating the necessary size increments for doing upscaling workflows. Use the *Final Size & Orientation* node to enter your full size dimensions and orientation (portrait/landscape/random), then plug that and your initial generation dimensions into the *Ideal Size Stepper* and get 1, 2, or 3 intermediate pairs of dimensions for upscaling. Note this does not output the initial size or full size dimensions: the 1, 2, or 3 outputs of this node are only the intermediate sizes.
-
-A third node is included, *Random Switch (Integers)*, which is just a generic version of Final Size with no orientation selection.
-
-**Node Link:** https://github.com/dwringer/size-stepper-nodes
-
-**Example Usage:**
-![size stepper usage graph](https://raw.githubusercontent.com/dwringer/size-stepper-nodes/main/size_nodes_usage.jpg)
-
---------------------------------
-
-### Text font to Image
-
-**Description:** text font to text image node for InvokeAI, download a font to use (or if in font cache uses it from there), the text is always resized to the image size, but can control that with padding, optional 2nd line
-
-**Node Link:** https://github.com/mickr777/textfontimage
-
-**Output Examples**
-
-![a3609d48-d9b7-41f0-b280-063d857986fb](https://github.com/mickr777/InvokeAI/assets/115216705/c21b0af3-d9c6-4c16-9152-846a23effd36)
-
-Results after using the depth controlnet
-
-![9133eabb-bcda-4326-831e-1b641228b178](https://github.com/mickr777/InvokeAI/assets/115216705/915f1a53-968e-43eb-aa61-07cd8f1a733a)
-![4f9a3fa8-9be9-4236-8a3e-fcec66decd2a](https://github.com/mickr777/InvokeAI/assets/115216705/821ef89e-8a60-44f5-b94e-471a9d8690cc)
-![babd69c4-9d60-4a55-a834-5e8397f62610](https://github.com/mickr777/InvokeAI/assets/115216705/2befcb6d-49f4-4bfd-b5fc-1fee19274f89)
-
---------------------------------
-
 ### Prompt Tools 
 
-**Description:** A set of InvokeAI nodes that add general prompt manipulation tools.  These where written to accompany the PromptsFromFile node and other prompt generation nodes.
+**Description:** A set of InvokeAI nodes that add general prompt manipulation tools.  These were written to accompany the PromptsFromFile node and other prompt generation nodes.
 
 1. PromptJoin - Joins to prompts into one.
 2. PromptReplace - performs a search and replace on a prompt. With the option of using regex.
@@ -215,21 +244,83 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 **Node Link:** https://github.com/skunkworxdark/Prompt-tools-nodes
 
 --------------------------------
+### Retroize
 
+**Description:** Retroize is a collection of nodes for InvokeAI to "Retroize" images. Any image can be given a fresh coat of retro paint with these nodes, either from your gallery or from within the graph itself. It includes nodes to pixelize, quantize, palettize, and ditherize images; as well as to retrieve palettes from existing images.
+
+**Node Link:** https://github.com/Ar7ific1al/invokeai-retroizeinode/
+
+**Retroize Output Examples**
+
+<img src="https://github.com/Ar7ific1al/InvokeAI_nodes_retroize/assets/2306586/de8b4fa6-324c-4c2d-b36c-297600c73974" width="500" />
+
+--------------------------------
+### Size Stepper Nodes
+
+**Description:** This is a set of nodes for calculating the necessary size increments for doing upscaling workflows. Use the *Final Size & Orientation* node to enter your full size dimensions and orientation (portrait/landscape/random), then plug that and your initial generation dimensions into the *Ideal Size Stepper* and get 1, 2, or 3 intermediate pairs of dimensions for upscaling. Note this does not output the initial size or full size dimensions: the 1, 2, or 3 outputs of this node are only the intermediate sizes.
+
+A third node is included, *Random Switch (Integers)*, which is just a generic version of Final Size with no orientation selection.
+
+**Node Link:** https://github.com/dwringer/size-stepper-nodes
+
+**Example Usage:**
+</br><img src="https://raw.githubusercontent.com/dwringer/size-stepper-nodes/main/size_nodes_usage.jpg" width="500" />
+
+--------------------------------
+### Text font to Image
+
+**Description:** text font to text image node for InvokeAI, download a font to use (or if in font cache uses it from there), the text is always resized to the image size, but can control that with padding, optional 2nd line
+
+**Node Link:** https://github.com/mickr777/textfontimage
+
+**Output Examples**
+
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/c21b0af3-d9c6-4c16-9152-846a23effd36" width="300" />
+
+Results after using the depth controlnet
+
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/915f1a53-968e-43eb-aa61-07cd8f1a733a" width="300" />
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/821ef89e-8a60-44f5-b94e-471a9d8690cc" width="300" />
+<img src="https://github.com/mickr777/InvokeAI/assets/115216705/2befcb6d-49f4-4bfd-b5fc-1fee19274f89" width="300" />
+
+--------------------------------
+### Thresholding
+
+**Description:** This node generates masks for highlights, midtones, and shadows given an input image. You can optionally specify a blur for the lookup table used in making those masks from the source image.
+
+**Node Link:** https://github.com/JPPhoto/thresholding-node
+
+**Examples**
+
+Input:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c88ada13-fb3d-484c-a4fe-947b44712632" width="300" />
+
+Highlights/Midtones/Shadows:
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/727021c1-36ff-4ec8-90c8-105e00de986d" width="300" />
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0b721bfc-f051-404e-b905-2f16b824ddfe" width="300" />
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/04c1297f-1c88-42b6-a7df-dd090b976286" width="300" />
+
+Highlights/Midtones/Shadows (with LUT blur enabled):
+
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/19aa718a-70c1-4668-8169-d68f4bd13771" width="300" />
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0a440e43-697f-4d17-82ee-f287467df0a5" width="300" />
+<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0701fd0f-2ca7-4fe2-8613-2b52547bafce" width="300" />
+
+--------------------------------
 ### XY Image to Grid and Images to Grids nodes
 
 **Description:** Image to grid nodes and supporting tools.
 
-1. "Images To Grids" node - Takes a collection of images and creates a grid(s) of images. If there are more images than the size of a single grid then mutilple grids will be created until it runs out of images.
-2. "XYImage To Grid" node - Converts a collection of XYImages into a labeled Grid of images.  The XYImages collection has to be built using the supporoting nodes. See example node setups for more details.
-   
+1. "Images To Grids" node - Takes a collection of images and creates a grid(s) of images. If there are more images than the size of a single grid then multiple grids will be created until it runs out of images.
+2. "XYImage To Grid" node - Converts a collection of XYImages into a labeled Grid of images. The XYImages collection has to be built using the supporting nodes. See example node setups for more details.
 
 See full docs here: https://github.com/skunkworxdark/XYGrid_nodes/edit/main/README.md
 
 **Node Link:** https://github.com/skunkworxdark/XYGrid_nodes
 
 --------------------------------
-
 ### Example Node Template
 
 **Description:** This node allows you to do super cool things with InvokeAI.
@@ -240,7 +331,7 @@ See full docs here: https://github.com/skunkworxdark/XYGrid_nodes/edit/main/READ
 
 **Output Examples** 
 
-![Example Image](https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png){: style="height:115px;width:240px"}
+</br><img src="https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png" width="500" />
 
 
 ## Disclaimer

docs/nodes/defaultNodes.md

@@ -1,6 +1,6 @@
 # List of Default Nodes
 
-The table below contains a list of the default nodes shipped with InvokeAI and their descriptions. 
+The table below contains a list of the default nodes shipped with InvokeAI and their descriptions.
 
 | Node <img width=160 align="right"> | Function                                                                              |
 |: ---------------------------------- | :--------------------------------------------------------------------------------------|
@@ -17,11 +17,12 @@ The table below contains a list of the default nodes shipped with InvokeAI and t
 |Conditioning Primitive 			| A conditioning tensor primitive value|
 |Content Shuffle Processor 			| Applies content shuffle processing to image|
 |ControlNet 			| Collects ControlNet info to pass to other nodes|
-|OpenCV Inpaint 			| Simple inpaint using opencv.|
 |Denoise Latents 			| Denoises noisy latents to decodable images|
 |Divide Integers 			| Divides two numbers|
 |Dynamic Prompt 			| Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator|
-|Upscale (RealESRGAN) 			| Upscales an image using RealESRGAN.|
+|[FaceMask](./detailedNodes/faceTools.md#facemask) | Generates masks for faces in an image to use with Inpainting|
+|[FaceIdentifier](./detailedNodes/faceTools.md#faceidentifier)             | Identifies and labels faces in an image|
+|[FaceOff](./detailedNodes/faceTools.md#faceoff)             | Creates a new image that is a scaled bounding box with a mask on the face for Inpainting|
 |Float Math             | Perform basic math operations on two floats|
 |Float Primitive Collection 			| A collection of float primitive values|
 |Float Primitive 			| A float primitive value|
@@ -76,6 +77,7 @@ The table below contains a list of the default nodes shipped with InvokeAI and t
 |ONNX Prompt (Raw) 			| A node to process inputs and produce outputs. May use dependency injection in __init__ to receive providers.|
 |ONNX Text to Latents 			| Generates latents from conditionings.|
 |ONNX Model Loader 			| Loads a main model, outputting its submodels.|
+|OpenCV Inpaint 			| Simple inpaint using opencv.|
 |Openpose Processor 			| Applies Openpose processing to image|
 |PIDI Processor 			| Applies PIDI processing to image|
 |Prompts from File 			| Loads prompts from a text file|
@@ -97,5 +99,6 @@ The table below contains a list of the default nodes shipped with InvokeAI and t
 |String Primitive 			| A string primitive value|
 |Subtract Integers 			| Subtracts two numbers|
 |Tile Resample Processor 			| Tile resampler processor|
+|Upscale (RealESRGAN) 			| Upscales an image using RealESRGAN.|
 |VAE Loader 			| Loads a VAE model, outputting a VaeLoaderOutput|
 |Zoe (Depth) Processor 			| Applies Zoe depth processing to image|

docs/nodes/detailedNodes/faceTools.md

@@ -0,0 +1,154 @@
+# Face Nodes
+
+## FaceOff
+
+FaceOff mimics a user finding a face in an image and resizing the bounding box
+around the head in Canvas.
+
+Enter a face ID (found with FaceIdentifier) to choose which face to mask.
+
+Just as you would add more context inside the bounding box by making it larger
+in Canvas, the node gives you a padding input (in pixels) which will
+simultaneously add more context, and increase the resolution of the bounding box
+so the face remains the same size inside it.
+
+The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
+threshold a detected face must reach for it to be processed. Lowering this value
+may help if detection is failing. If the detected masks are imperfect and stray
+too far outside/inside of faces, the node gives you X & Y offsets to shrink/grow
+the masks by a multiplier.
+
+FaceOff will output the face in a bounded image, taking the face off of the
+original image for input into any node that accepts image inputs. The node also
+outputs a face mask with the dimensions of the bounded image. The X & Y outputs
+are for connecting to the X & Y inputs of the Paste Image node, which will place
+the bounded image back on the original image using these coordinates.
+
+###### Inputs/Outputs
+
+| Input              | Description                                                                                                                                                                              |
+| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Image              | Image for face detection                                                                                                                                                                 |
+| Face ID            | The face ID to process, numbered from 0. Multiple faces not supported. Find a face's ID with FaceIdentifier node.                                                                        |
+| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
+| X Offset           | X-axis offset of the mask                                                                                                                                                                |
+| Y Offset           | Y-axis offset of the mask                                                                                                                                                                |
+| Padding            | All-axis padding around the mask in pixels                                                                                                                                               |
+| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
+
+| Output        | Description                                      |
+| ------------- | ------------------------------------------------ |
+| Bounded Image | Original image bound, cropped, and resized       |
+| Width         | The width of the bounded image in pixels         |
+| Height        | The height of the bounded image in pixels        |
+| Mask          | The output mask                                  |
+| X             | The x coordinate of the bounding box's left side |
+| Y             | The y coordinate of the bounding box's top side  |
+
+## FaceMask
+
+FaceMask mimics a user drawing masks on faces in an image in Canvas.
+
+The "Face IDs" input allows the user to select specific faces to be masked.
+Leave empty to detect and mask all faces, or a comma-separated list for a
+specific combination of faces (ex: `1,2,4`). A single integer will detect and
+mask that specific face. Find face IDs with the FaceIdentifier node.
+
+The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
+threshold a detected face must reach for it to be processed. Lowering this value
+may help if detection is failing.
+
+If the detected masks are imperfect and stray too far outside/inside of faces,
+the node gives you X & Y offsets to shrink/grow the masks by a multiplier. All
+masks shrink/grow together by the X & Y offset values.
+
+By default, masks are created to change faces. When masks are inverted, they
+change surrounding areas, protecting faces.
+
+###### Inputs/Outputs
+
+| Input              | Description                                                                                                                                                                              |
+| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Image              | Image for face detection                                                                                                                                                                 |
+| Face IDs           | Comma-separated list of face ids to mask eg '0,2,7'. Numbered from 0. Leave empty to mask all. Find face IDs with FaceIdentifier node.                                                   |
+| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
+| X Offset           | X-axis offset of the mask                                                                                                                                                                |
+| Y Offset           | Y-axis offset of the mask                                                                                                                                                                |
+| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
+| Invert Mask        | Toggle to invert the face mask                                                                                                                                                           |
+
+| Output | Description                       |
+| ------ | --------------------------------- |
+| Image  | The original image                |
+| Width  | The width of the image in pixels  |
+| Height | The height of the image in pixels |
+| Mask   | The output face mask              |
+
+## FaceIdentifier
+
+FaceIdentifier outputs an image with detected face IDs printed in white numbers
+onto each face.
+
+Face IDs can then be used in FaceMask and FaceOff to selectively mask all, a
+specific combination, or single faces.
+
+The FaceIdentifier output image is generated for user reference, and isn't meant
+to be passed on to other image-processing nodes.
+
+The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
+threshold a detected face must reach for it to be processed. Lowering this value
+may help if detection is failing. If an image is changed in the slightest, run
+it through FaceIdentifier again to get updated FaceIDs.
+
+###### Inputs/Outputs
+
+| Input              | Description                                                                                                                                                                              |
+| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Image              | Image for face detection                                                                                                                                                                 |
+| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
+| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
+
+| Output | Description                                                                                      |
+| ------ | ------------------------------------------------------------------------------------------------ |
+| Image  | The original image with small face ID numbers printed in white onto each face for user reference |
+| Width  | The width of the original image in pixels                                                        |
+| Height | The height of the original image in pixels                                                       |
+
+## Tips
+
+- If not all target faces are being detected, activate Chunk to bypass full
+  image face detection and greatly improve detection success.
+- Final results will vary between full-image detection and chunking for faces
+  that are detectable by both due to the nature of the process. Try either to
+  your taste.
+- Be sure Minimum Confidence is set the same when using FaceIdentifier with
+  FaceOff/FaceMask.
+- For FaceOff, use the color correction node before faceplace to correct edges
+  being noticeable in the final image (see example screenshot).
+- Non-inpainting models may struggle to paint/generate correctly around faces.
+- If your face won't change the way you want it to no matter what you change,
+  consider that the change you're trying to make is too much at that resolution.
+  For example, if an image is only 512x768 total, the face might only be 128x128
+  or 256x256, much smaller than the 512x512 your SD1.5 model was probably
+  trained on. Try increasing the resolution of the image by upscaling or
+  resizing, add padding to increase the bounding box's resolution, or use an
+  image where the face takes up more pixels.
+- If the resulting face seems out of place pasted back on the original image
+  (ie. too large, not proportional), add more padding on the FaceOff node to
+  give inpainting more context. Context and good prompting are important to
+  keeping things proportional.
+- If you find the mask is too big/small and going too far outside/inside the
+  area you want to affect, adjust the x & y offsets to shrink/grow the mask area
+- Use a higher denoise start value to resemble aspects of the original face or
+  surroundings. Denoise start = 0 & denoise end = 1 will make something new,
+  while denoise start = 0.50 & denoise end = 1 will be 50% old and 50% new.
+- mediapipe isn't good at detecting faces with lots of face paint, hair covering
+  the face, etc. Anything that obstructs the face will likely result in no faces
+  being detected.
+- If you find your face isn't being detected, try lowering the minimum
+  confidence value from 0.5. This could result in false positives, however
+  (random areas being detected as faces and masked).
+- After altering an image and wanting to process a different face in the newly
+  altered image, run the altered image through FaceIdentifier again to see the
+  new Face IDs. MediaPipe will most likely detect faces in a different order
+  after an image has been changed in the slightest.

docs/nodes/exampleWorkflows.md

@@ -9,5 +9,6 @@ If you're interested in finding more workflows, checkout the [#share-your-workfl
 * [SD1.5 / SD2 Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/Text_to_Image.json)
 * [SDXL Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/SDXL_Text_to_Image.json)
 * [SDXL (with Refiner) Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/SDXL_Text_to_Image.json) 
-* [Tiled Upscaling with ControlNet](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/ESRGAN_img2img_upscale w_Canny_ControlNet.json)ß
-
+* [Tiled Upscaling with ControlNet](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/ESRGAN_img2img_upscale w_Canny_ControlNet.json)
+* [FaceMask](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/FaceMask.json)
+* [FaceOff with 2x Face Scaling](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/FaceOff_FaceScale2x.json)

installer/install.bat.in

@@ -1,7 +1,7 @@
 @echo off
 setlocal EnableExtensions EnableDelayedExpansion
 
-@rem This script requires the user to install Python 3.9 or higher. All other
+@rem This script requires the user to install Python 3.10 or higher. All other
 @rem requirements are downloaded as needed.
 
 @rem change to the script's directory
@@ -19,7 +19,7 @@ set INVOKEAI_VERSION=latest
 set INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
 set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
 set PYTHON_URL=https://www.python.org/downloads/windows/
-set MINIMUM_PYTHON_VERSION=3.9.0
+set MINIMUM_PYTHON_VERSION=3.10.0
 set PYTHON_URL=https://www.python.org/downloads/release/python-3109/
 
 set err_msg=An error has occurred and the script could not continue.
@@ -28,8 +28,7 @@ set err_msg=An error has occurred and the script could not continue.
 echo This script will install InvokeAI and its dependencies.
 echo.
 echo BEFORE YOU START PLEASE MAKE SURE TO DO THE FOLLOWING
-echo 1. Install python 3.9 or 3.10. Python version 3.11 and above are
-echo    not supported at the moment.
+echo 1. Install python 3.10 or 3.11. Python version 3.9 is no longer supported.
 echo 2. Double-click on the file WinLongPathsEnabled.reg in order to
 echo    enable long path support on your system.
 echo 3. Install the Visual C++ core libraries.
@@ -46,19 +45,19 @@ echo ***** Checking and Updating Python *****
 
 call python --version >.tmp1 2>.tmp2
 if %errorlevel% == 1 (
-   set err_msg=Please install Python 3.10. See %INSTRUCTIONS% for details.
+   set err_msg=Please install Python 3.10-11. See %INSTRUCTIONS% for details.
    goto err_exit
 )
 
 for /f "tokens=2" %%i in (.tmp1) do set python_version=%%i
 if "%python_version%" == "" (
-   set err_msg=No python was detected on your system. Please install Python version %MINIMUM_PYTHON_VERSION% or higher. We recommend Python 3.10.9 from %PYTHON_URL%
+   set err_msg=No python was detected on your system. Please install Python version %MINIMUM_PYTHON_VERSION% or higher. We recommend Python 3.10.12 from %PYTHON_URL%
    goto err_exit
 )
 
 call :compareVersions %MINIMUM_PYTHON_VERSION% %python_version%
 if %errorlevel% == 1 (
-   set err_msg=Your version of Python is too low. You need at least %MINIMUM_PYTHON_VERSION% but you have %python_version%. We recommend Python 3.10.9 from %PYTHON_URL%
+   set err_msg=Your version of Python is too low. You need at least %MINIMUM_PYTHON_VERSION% but you have %python_version%. We recommend Python 3.10.12 from %PYTHON_URL%
    goto err_exit
 )
 

installer/install.sh.in

@@ -8,10 +8,10 @@ cd $scriptdir
 
 function version { echo "$@" | awk -F. '{ printf("%d%03d%03d%03d\n", $1,$2,$3,$4); }'; }
 
-MINIMUM_PYTHON_VERSION=3.9.0
+MINIMUM_PYTHON_VERSION=3.10.0
 MAXIMUM_PYTHON_VERSION=3.11.100
 PYTHON=""
-for candidate in python3.11 python3.10 python3.9 python3 python ; do
+for candidate in python3.11 python3.10 python3 python ; do
     if ppath=`which $candidate`; then
         # when using `pyenv`, the executable for an inactive Python version will exist but will not be operational
         # we check that this found executable can actually run

installer/lib/installer.py

@@ -13,7 +13,7 @@ from pathlib import Path
 from tempfile import TemporaryDirectory
 from typing import Union
 
-SUPPORTED_PYTHON = ">=3.9.0,<=3.11.100"
+SUPPORTED_PYTHON = ">=3.10.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
 BOOTSTRAP_VENV_PREFIX = "invokeai-installer-tmp"
 
@@ -67,7 +67,6 @@ class Installer:
         # Cleaning up temporary directories on Windows results in a race condition
         # and a stack trace.
         # `ignore_cleanup_errors` was only added in Python 3.10
-        # users of Python 3.9 will see a gnarly stack trace on installer exit
         if OS == "Windows" and int(platform.python_version_tuple()[1]) >= 10:
             venv_dir = TemporaryDirectory(prefix=BOOTSTRAP_VENV_PREFIX, ignore_cleanup_errors=True)
         else:
@@ -139,13 +138,6 @@ class Installer:
         except shutil.SameFileError:
             venv.create(venv_dir, with_pip=True, symlinks=True)
 
-        # upgrade pip in Python 3.9 environments
-        if int(platform.python_version_tuple()[1]) == 9:
-            from plumbum import FG, local
-
-            pip = local[get_pip_from_venv(venv_dir)]
-            pip["install", "--upgrade", "pip"] & FG
-
         return venv_dir
 
     def install(
@@ -332,6 +324,7 @@ class InvokeAiInstance:
         Configure the InvokeAI runtime directory
         """
 
+        auto_install = False
         # set sys.argv to a consistent state
         new_argv = [sys.argv[0]]
         for i in range(1, len(sys.argv)):
@@ -340,13 +333,17 @@ class InvokeAiInstance:
                 new_argv.append(el)
                 new_argv.append(sys.argv[i + 1])
             elif el in ["-y", "--yes", "--yes-to-all"]:
-                new_argv.append(el)
+                auto_install = True
         sys.argv = new_argv
 
+        import messages
         import requests  # to catch download exceptions
-        from messages import introduction
 
-        introduction()
+        auto_install = auto_install or messages.user_wants_auto_configuration()
+        if auto_install:
+            sys.argv.append("--yes")
+        else:
+            messages.introduction()
 
         from invokeai.frontend.install.invokeai_configure import invokeai_configure
 

installer/lib/messages.py

@@ -7,7 +7,7 @@ import os
 import platform
 from pathlib import Path
 
-from prompt_toolkit import prompt
+from prompt_toolkit import HTML, prompt
 from prompt_toolkit.completion import PathCompleter
 from prompt_toolkit.validation import Validator
 from rich import box, print
@@ -65,17 +65,50 @@ def confirm_install(dest: Path) -> bool:
     if dest.exists():
         print(f":exclamation: Directory {dest} already exists :exclamation:")
         dest_confirmed = Confirm.ask(
-            ":stop_sign: Are you sure you want to (re)install in this location?",
+            ":stop_sign: (re)install in this location?",
             default=False,
         )
     else:
         print(f"InvokeAI will be installed in {dest}")
-        dest_confirmed = not Confirm.ask("Would you like to pick a different location?", default=False)
+        dest_confirmed = Confirm.ask("Use this location?", default=True)
     console.line()
 
     return dest_confirmed
 
 
+def user_wants_auto_configuration() -> bool:
+    """Prompt the user to choose between manual and auto configuration."""
+    console.rule("InvokeAI Configuration Section")
+    console.print(
+        Panel(
+            Group(
+                "\n".join(
+                    [
+                        "Libraries are installed and InvokeAI will now set up its root directory and configuration. Choose between:",
+                        "",
+                        "  * AUTOMATIC configuration:  install reasonable defaults and a minimal set of starter models.",
+                        "  * MANUAL configuration: manually inspect and adjust configuration options and pick from a larger set of starter models.",
+                        "",
+                        "Later you can fine tune your configuration by selecting option [6] 'Change InvokeAI startup options' from the invoke.bat/invoke.sh launcher script.",
+                    ]
+                ),
+            ),
+            box=box.MINIMAL,
+            padding=(1, 1),
+        )
+    )
+    choice = (
+        prompt(
+            HTML("Choose <b>&lt;a&gt;</b>utomatic or <b>&lt;m&gt;</b>anual configuration [a/m] (a): "),
+            validator=Validator.from_callable(
+                lambda n: n == "" or n.startswith(("a", "A", "m", "M")), error_message="Please select 'a' or 'm'"
+            ),
+        )
+        or "a"
+    )
+    return choice.lower().startswith("a")
+
+
 def dest_path(dest=None) -> Path:
     """
     Prompt the user for the destination path and create the path

installer/readme.txt

@@ -4,7 +4,7 @@ Project homepage: https://github.com/invoke-ai/InvokeAI
 
 Preparations:
 
-  You will need to install Python 3.9 or higher for this installer
+  You will need to install Python 3.10 or higher for this installer
   to work. Instructions are given here:
   https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
 
@@ -14,15 +14,15 @@ Preparations:
      python --version
 
   If all is well, it will print "Python 3.X.X", where the version number
-  is at least 3.9.*, and not higher than 3.11.*.
+  is at least 3.10.*, and not higher than 3.11.*.
 
   If this works, check the version of the Python package manager, pip:
 
      pip --version
 
   You should get a message that indicates that the pip package
-  installer was derived from Python 3.9 or 3.10. For example:
-  "pip 22.3.1 from /usr/bin/pip (python 3.9)"
+  installer was derived from Python 3.10 or 3.11. For example:
+  "pip 22.0.1 from /usr/bin/pip (python 3.10)"
 
 Long Paths on Windows:
 

installer/templates/invoke.bat.in

@@ -9,41 +9,37 @@ set INVOKEAI_ROOT=.
 :start
 echo Desired action:
 echo 1. Generate images with the browser-based interface
-echo 2. Explore InvokeAI nodes using a command-line interface
-echo 3. Run textual inversion training
-echo 4. Merge models (diffusers type only)
-echo 5. Download and install models
-echo 6. Change InvokeAI startup options
-echo 7. Re-run the configure script to fix a broken install or to complete a major upgrade
-echo 8. Open the developer console
-echo 9. Update InvokeAI
-echo 10. Run the InvokeAI image database maintenance script
-echo 11. Command-line help
+echo 2. Run textual inversion training
+echo 3. Merge models (diffusers type only)
+echo 4. Download and install models
+echo 5. Change InvokeAI startup options
+echo 6. Re-run the configure script to fix a broken install or to complete a major upgrade
+echo 7. Open the developer console
+echo 8. Update InvokeAI
+echo 9. Run the InvokeAI image database maintenance script
+echo 10. Command-line help
 echo Q - Quit
-set /P choice="Please enter 1-11, Q: [1] "
+set /P choice="Please enter 1-10, Q: [1] "
 if not defined choice set choice=1
 IF /I "%choice%" == "1" (
     echo Starting the InvokeAI browser-based UI..
     python .venv\Scripts\invokeai-web.exe %*
 ) ELSE IF /I "%choice%" == "2" (
-    echo Starting the InvokeAI command-line..
-    python .venv\Scripts\invokeai.exe %*
-) ELSE IF /I "%choice%" == "3" (
     echo Starting textual inversion training..
     python .venv\Scripts\invokeai-ti.exe --gui
-) ELSE IF /I "%choice%" == "4" (
+) ELSE IF /I "%choice%" == "3" (
     echo Starting model merging script..
     python .venv\Scripts\invokeai-merge.exe --gui
-) ELSE IF /I "%choice%" == "5" (
+) ELSE IF /I "%choice%" == "4" (
     echo Running invokeai-model-install...
     python .venv\Scripts\invokeai-model-install.exe
-) ELSE IF /I "%choice%" == "6" (
+) ELSE IF /I "%choice%" == "5" (
     echo Running invokeai-configure...
     python .venv\Scripts\invokeai-configure.exe --skip-sd-weight --skip-support-models
-) ELSE IF /I "%choice%" == "7" (
+) ELSE IF /I "%choice%" == "6" (
     echo Running invokeai-configure...
     python .venv\Scripts\invokeai-configure.exe --yes --skip-sd-weight
-) ELSE IF /I "%choice%" == "8" (
+) ELSE IF /I "%choice%" == "7" (
     echo Developer Console
     echo Python command is:
     where python
@@ -55,13 +51,13 @@ IF /I "%choice%" == "1" (
     echo *************************
     echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
     call cmd /k
-) ELSE IF /I "%choice%" == "9" (
+) ELSE IF /I "%choice%" == "8" (
    echo Running invokeai-update...
    python -m invokeai.frontend.install.invokeai_update
-) ELSE IF /I "%choice%" == "10" (
+) ELSE IF /I "%choice%" == "9" (
    echo Running the db maintenance script...
    python .venv\Scripts\invokeai-db-maintenance.exe
-) ELSE IF /I "%choice%" == "11" (
+) ELSE IF /I "%choice%" == "10" (
     echo Displaying command line help...
     python .venv\Scripts\invokeai-web.exe --help %*
     pause

installer/templates/invoke.sh.in

@@ -46,6 +46,9 @@ if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
+# Avoid glibc memory fragmentation. See invokeai/backend/model_management/README.md for details.
+export MALLOC_MMAP_THRESHOLD_=1048576
+
 # Primary function for the case statement to determine user input
 do_choice() {
     case $1 in
@@ -55,52 +58,47 @@ do_choice() {
         invokeai-web $PARAMS
         ;;
     2)
-        clear
-        printf "Explore InvokeAI nodes using a command-line interface\n"
-        invokeai $PARAMS
-        ;;
-    3)
         clear
         printf "Textual inversion training\n"
         invokeai-ti --gui $PARAMS
         ;;
-    4)
+    3)
         clear
         printf "Merge models (diffusers type only)\n"
         invokeai-merge --gui $PARAMS
         ;;
-    5)
+    4)
         clear
         printf "Download and install models\n"
         invokeai-model-install --root ${INVOKEAI_ROOT}
         ;;
-    6)
+    5)
         clear
         printf "Change InvokeAI startup options\n"
         invokeai-configure --root ${INVOKEAI_ROOT} --skip-sd-weights --skip-support-models
         ;;
-    7)
+    6)
         clear
         printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
         invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only --skip-sd-weights
         ;;
-    8)
+    7)
         clear
         printf "Open the developer console\n"
         file_name=$(basename "${BASH_SOURCE[0]}")
         bash --init-file "$file_name"
         ;;
-    9)
+    8)
         clear
         printf "Update InvokeAI\n"
         python -m invokeai.frontend.install.invokeai_update
         ;;
-    10)
+    9)
         clear
         printf "Running the db maintenance script\n"
         invokeai-db-maintenance --root ${INVOKEAI_ROOT}
         ;;
-    11)
+    10)
         clear
         printf "Command-line help\n"
         invokeai-web --help
@@ -118,16 +116,15 @@ do_choice() {
 do_dialog() {
     options=(
         1 "Generate images with a browser-based interface"
-        2 "Explore InvokeAI nodes using a command-line interface"
-        3 "Textual inversion training"
-        4 "Merge models (diffusers type only)"
-        5 "Download and install models"
-        6 "Change InvokeAI startup options"
-        7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
-        8 "Open the developer console"
-        9 "Update InvokeAI"
-	10 "Run the InvokeAI image database maintenance script"
-	11 "Command-line help"
+        2 "Textual inversion training"
+        3 "Merge models (diffusers type only)"
+        4 "Download and install models"
+        5 "Change InvokeAI startup options"
+        6 "Re-run the configure script to fix a broken install or to complete a major upgrade"
+        7 "Open the developer console"
+        8 "Update InvokeAI"
+	9 "Run the InvokeAI image database maintenance script"
+	10 "Command-line help"
     )
 
     choice=$(dialog --clear \
@@ -152,18 +149,17 @@ do_line_input() {
     printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
     printf "What would you like to do?\n"
     printf "1: Generate images using the browser-based interface\n"
-    printf "2: Explore InvokeAI nodes using the command-line interface\n"
-    printf "3: Run textual inversion training\n"
-    printf "4: Merge models (diffusers type only)\n"
-    printf "5: Download and install models\n"
-    printf "6: Change InvokeAI startup options\n"
-    printf "7: Re-run the configure script to fix a broken install\n"
-    printf "8: Open the developer console\n"
-    printf "9: Update InvokeAI\n"
-    printf "10: Run the InvokeAI image database maintenance script\n"
-    printf "11: Command-line help\n"
+    printf "2: Run textual inversion training\n"
+    printf "3: Merge models (diffusers type only)\n"
+    printf "4: Download and install models\n"
+    printf "5: Change InvokeAI startup options\n"
+    printf "6: Re-run the configure script to fix a broken install\n"
+    printf "7: Open the developer console\n"
+    printf "8: Update InvokeAI\n"
+    printf "9: Run the InvokeAI image database maintenance script\n"
+    printf "10: Command-line help\n"
     printf "Q: Quit\n\n"
-    read -p "Please enter 1-11, Q: [1] " yn
+    read -p "Please enter 1-10, Q: [1] " yn
     choice=${yn:='1'}
     do_choice $choice
     clear

invokeai/app/api/dependencies.py

@@ -1,35 +1,37 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-import sqlite3
 from logging import Logger
 
-from invokeai.app.services.board_image_record_storage import SqliteBoardImageRecordStorage
-from invokeai.app.services.board_images import BoardImagesService, BoardImagesServiceDependencies
-from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
-from invokeai.app.services.boards import BoardService, BoardServiceDependencies
-from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-from invokeai.app.services.images import ImageService, ImageServiceDependencies
-from invokeai.app.services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
-from invokeai.app.services.resource_name import SimpleNameService
-from invokeai.app.services.session_processor.session_processor_default import DefaultSessionProcessor
-from invokeai.app.services.session_queue.session_queue_sqlite import SqliteSessionQueue
-from invokeai.app.services.urls import LocalUrlService
+from invokeai.app.services.workflow_image_records.workflow_image_records_sqlite import SqliteWorkflowImageRecordsStorage
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
 
-from ..services.default_graphs import create_system_graphs
-from ..services.graph import GraphExecutionState, LibraryGraph
-from ..services.image_file_storage import DiskImageFileStorage
-from ..services.invocation_queue import MemoryInvocationQueue
+from ..services.board_image_records.board_image_records_sqlite import SqliteBoardImageRecordStorage
+from ..services.board_images.board_images_default import BoardImagesService
+from ..services.board_records.board_records_sqlite import SqliteBoardRecordStorage
+from ..services.boards.boards_default import BoardService
+from ..services.config import InvokeAIAppConfig
+from ..services.image_files.image_files_disk import DiskImageFileStorage
+from ..services.image_records.image_records_sqlite import SqliteImageRecordStorage
+from ..services.images.images_default import ImageService
+from ..services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
+from ..services.invocation_processor.invocation_processor_default import DefaultInvocationProcessor
+from ..services.invocation_queue.invocation_queue_memory import MemoryInvocationQueue
 from ..services.invocation_services import InvocationServices
-from ..services.invocation_stats import InvocationStatsService
+from ..services.invocation_stats.invocation_stats_default import InvocationStatsService
 from ..services.invoker import Invoker
-from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-from ..services.model_manager_service import ModelManagerService
-from ..services.processor import DefaultInvocationProcessor
-from ..services.sqlite import SqliteItemStorage
-from ..services.thread import lock
+from ..services.item_storage.item_storage_sqlite import SqliteItemStorage
+from ..services.latents_storage.latents_storage_disk import DiskLatentsStorage
+from ..services.latents_storage.latents_storage_forward_cache import ForwardCacheLatentsStorage
+from ..services.model_manager.model_manager_default import ModelManagerService
+from ..services.names.names_default import SimpleNameService
+from ..services.session_processor.session_processor_default import DefaultSessionProcessor
+from ..services.session_queue.session_queue_sqlite import SqliteSessionQueue
+from ..services.shared.default_graphs import create_system_graphs
+from ..services.shared.graph import GraphExecutionState, LibraryGraph
+from ..services.shared.sqlite import SqliteDatabase
+from ..services.urls.urls_default import LocalUrlService
+from ..services.workflow_records.workflow_records_sqlite import SqliteWorkflowRecordsStorage
 from .events import FastAPIEventService
 
 
@@ -63,100 +65,68 @@ class ApiDependencies:
         logger.info(f"Root directory = {str(config.root_path)}")
         logger.debug(f"Internet connectivity is {config.internet_available}")
 
-        events = FastAPIEventService(event_handler_id)
-
         output_folder = config.output_path
 
-        # TODO: build a file/path manager?
-        if config.use_memory_db:
-            db_location = ":memory:"
-        else:
-            db_path = config.db_path
-            db_path.parent.mkdir(parents=True, exist_ok=True)
-            db_location = str(db_path)
+        db = SqliteDatabase(config, logger)
 
-        logger.info(f"Using database at {db_location}")
-        db_conn = sqlite3.connect(db_location, check_same_thread=False)  # TODO: figure out a better threading solution
+        configuration = config
+        logger = logger
 
-        if config.log_sql:
-            db_conn.set_trace_callback(print)
-        db_conn.execute("PRAGMA foreign_keys = ON;")
-
-        graph_execution_manager = SqliteItemStorage[GraphExecutionState](
-            conn=db_conn, table_name="graph_executions", lock=lock
-        )
-
-        urls = LocalUrlService()
-        image_record_storage = SqliteImageRecordStorage(conn=db_conn, lock=lock)
-        image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
-        names = SimpleNameService()
+        board_image_records = SqliteBoardImageRecordStorage(db=db)
+        board_images = BoardImagesService()
+        board_records = SqliteBoardRecordStorage(db=db)
+        boards = BoardService()
+        events = FastAPIEventService(event_handler_id)
+        graph_execution_manager = SqliteItemStorage[GraphExecutionState](db=db, table_name="graph_executions")
+        graph_library = SqliteItemStorage[LibraryGraph](db=db, table_name="graphs")
+        image_files = DiskImageFileStorage(f"{output_folder}/images")
+        image_records = SqliteImageRecordStorage(db=db)
+        images = ImageService()
+        invocation_cache = MemoryInvocationCache(max_cache_size=config.node_cache_size)
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
-
-        board_record_storage = SqliteBoardRecordStorage(conn=db_conn, lock=lock)
-        board_image_record_storage = SqliteBoardImageRecordStorage(conn=db_conn, lock=lock)
-
-        boards = BoardService(
-            services=BoardServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                board_record_storage=board_record_storage,
-                image_record_storage=image_record_storage,
-                url=urls,
-                logger=logger,
-            )
-        )
-
-        board_images = BoardImagesService(
-            services=BoardImagesServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                board_record_storage=board_record_storage,
-                image_record_storage=image_record_storage,
-                url=urls,
-                logger=logger,
-            )
-        )
-
-        images = ImageService(
-            services=ImageServiceDependencies(
-                board_image_record_storage=board_image_record_storage,
-                image_record_storage=image_record_storage,
-                image_file_storage=image_file_storage,
-                url=urls,
-                logger=logger,
-                names=names,
-                graph_execution_manager=graph_execution_manager,
-            )
-        )
+        model_manager = ModelManagerService(config, logger)
+        names = SimpleNameService()
+        performance_statistics = InvocationStatsService()
+        processor = DefaultInvocationProcessor()
+        queue = MemoryInvocationQueue()
+        session_processor = DefaultSessionProcessor()
+        session_queue = SqliteSessionQueue(db=db)
+        urls = LocalUrlService()
+        workflow_image_records = SqliteWorkflowImageRecordsStorage(db=db)
+        workflow_records = SqliteWorkflowRecordsStorage(db=db)
 
         services = InvocationServices(
-            model_manager=ModelManagerService(config, logger),
-            events=events,
-            latents=latents,
-            images=images,
-            boards=boards,
+            board_image_records=board_image_records,
             board_images=board_images,
-            queue=MemoryInvocationQueue(),
-            graph_library=SqliteItemStorage[LibraryGraph](conn=db_conn, lock=lock, table_name="graphs"),
+            board_records=board_records,
+            boards=boards,
+            configuration=configuration,
+            events=events,
             graph_execution_manager=graph_execution_manager,
-            processor=DefaultInvocationProcessor(),
-            configuration=config,
-            performance_statistics=InvocationStatsService(graph_execution_manager),
+            graph_library=graph_library,
+            image_files=image_files,
+            image_records=image_records,
+            images=images,
+            invocation_cache=invocation_cache,
+            latents=latents,
             logger=logger,
-            session_queue=SqliteSessionQueue(conn=db_conn, lock=lock),
-            session_processor=DefaultSessionProcessor(),
-            invocation_cache=MemoryInvocationCache(max_cache_size=config.node_cache_size),
+            model_manager=model_manager,
+            names=names,
+            performance_statistics=performance_statistics,
+            processor=processor,
+            queue=queue,
+            session_processor=session_processor,
+            session_queue=session_queue,
+            urls=urls,
+            workflow_image_records=workflow_image_records,
+            workflow_records=workflow_records,
         )
 
         create_system_graphs(services.graph_library)
 
         ApiDependencies.invoker = Invoker(services)
 
-        try:
-            lock.acquire()
-            db_conn.execute("VACUUM;")
-            db_conn.commit()
-            logger.info("Cleaned database")
-        finally:
-            lock.release()
+        db.clean()
 
     @staticmethod
     def shutdown():

invokeai/app/api/events.py

@@ -7,7 +7,7 @@ from typing import Any
 
 from fastapi_events.dispatcher import dispatch
 
-from ..services.events import EventServiceBase
+from ..services.events.events_base import EventServiceBase
 
 
 class FastAPIEventService(EventServiceBase):

invokeai/app/api/routers/boards.py

@@ -4,9 +4,9 @@ from fastapi import Body, HTTPException, Path, Query
 from fastapi.routing import APIRouter
 from pydantic import BaseModel, Field
 
-from invokeai.app.services.board_record_storage import BoardChanges
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.board_record import BoardDTO
+from invokeai.app.services.board_records.board_records_common import BoardChanges
+from invokeai.app.services.boards.boards_common import BoardDTO
+from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 
 from ..dependencies import ApiDependencies
 

invokeai/app/api/routers/images.py

@@ -1,16 +1,17 @@
 import io
+import traceback
 from typing import Optional
 
 from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
 from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
 from PIL import Image
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, ValidationError
 
-from invokeai.app.invocations.metadata import ImageMetadata
-from invokeai.app.models.image import ImageCategory, ResourceOrigin
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.image_record import ImageDTO, ImageRecordChanges, ImageUrlsDTO
+from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator, WorkflowFieldValidator
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ImageRecordChanges, ResourceOrigin
+from invokeai.app.services.images.images_common import ImageDTO, ImageUrlsDTO
+from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 
 from ..dependencies import ApiDependencies
 
@@ -42,20 +43,41 @@ async def upload_image(
     crop_visible: Optional[bool] = Query(default=False, description="Whether to crop the image"),
 ) -> ImageDTO:
     """Uploads an image"""
-    if not file.content_type.startswith("image"):
+    if not file.content_type or not file.content_type.startswith("image"):
         raise HTTPException(status_code=415, detail="Not an image")
 
-    contents = await file.read()
+    metadata = None
+    workflow = None
 
+    contents = await file.read()
     try:
         pil_image = Image.open(io.BytesIO(contents))
         if crop_visible:
             bbox = pil_image.getbbox()
             pil_image = pil_image.crop(bbox)
     except Exception:
-        # Error opening the image
+        ApiDependencies.invoker.services.logger.error(traceback.format_exc())
         raise HTTPException(status_code=415, detail="Failed to read image")
 
+    # TODO: retain non-invokeai metadata on upload?
+    # attempt to parse metadata from image
+    metadata_raw = pil_image.info.get("invokeai_metadata", None)
+    if metadata_raw:
+        try:
+            metadata = MetadataFieldValidator.validate_json(metadata_raw)
+        except ValidationError:
+            ApiDependencies.invoker.services.logger.warn("Failed to parse metadata for uploaded image")
+            pass
+
+    # attempt to parse workflow from image
+    workflow_raw = pil_image.info.get("invokeai_workflow", None)
+    if workflow_raw is not None:
+        try:
+            workflow = WorkflowFieldValidator.validate_json(workflow_raw)
+        except ValidationError:
+            ApiDependencies.invoker.services.logger.warn("Failed to parse metadata for uploaded image")
+            pass
+
     try:
         image_dto = ApiDependencies.invoker.services.images.create(
             image=pil_image,
@@ -63,6 +85,8 @@ async def upload_image(
             image_category=image_category,
             session_id=session_id,
             board_id=board_id,
+            metadata=metadata,
+            workflow=workflow,
             is_intermediate=is_intermediate,
         )
 
@@ -71,6 +95,7 @@ async def upload_image(
 
         return image_dto
     except Exception:
+        ApiDependencies.invoker.services.logger.error(traceback.format_exc())
         raise HTTPException(status_code=500, detail="Failed to create image")
 
 
@@ -87,7 +112,7 @@ async def delete_image(
         pass
 
 
-@images_router.post("/clear-intermediates", operation_id="clear_intermediates")
+@images_router.delete("/intermediates", operation_id="clear_intermediates")
 async def clear_intermediates() -> int:
     """Clears all intermediates"""
 
@@ -99,6 +124,17 @@ async def clear_intermediates() -> int:
         pass
 
 
+@images_router.get("/intermediates", operation_id="get_intermediates_count")
+async def get_intermediates_count() -> int:
+    """Gets the count of intermediate images"""
+
+    try:
+        return ApiDependencies.invoker.services.images.get_intermediates_count()
+    except Exception:
+        raise HTTPException(status_code=500, detail="Failed to get intermediates")
+        pass
+
+
 @images_router.patch(
     "/i/{image_name}",
     operation_id="update_image",
@@ -135,11 +171,11 @@ async def get_image_dto(
 @images_router.get(
     "/i/{image_name}/metadata",
     operation_id="get_image_metadata",
-    response_model=ImageMetadata,
+    response_model=Optional[MetadataField],
 )
 async def get_image_metadata(
     image_name: str = Path(description="The name of image to get"),
-) -> ImageMetadata:
+) -> Optional[MetadataField]:
     """Gets an image's metadata"""
 
     try:
@@ -322,3 +358,20 @@ async def unstar_images_in_list(
         return ImagesUpdatedFromListResult(updated_image_names=updated_image_names)
     except Exception:
         raise HTTPException(status_code=500, detail="Failed to unstar images")
+
+
+class ImagesDownloaded(BaseModel):
+    response: Optional[str] = Field(
+        description="If defined, the message to display to the user when images begin downloading"
+    )
+
+
+@images_router.post("/download", operation_id="download_images_from_list", response_model=ImagesDownloaded)
+async def download_images_from_list(
+    image_names: list[str] = Body(description="The list of names of images to download", embed=True),
+    board_id: Optional[str] = Body(
+        default=None, description="The board from which image should be downloaded from", embed=True
+    ),
+) -> ImagesDownloaded:
+    # return ImagesDownloaded(response="Your images are downloading")
+    raise HTTPException(status_code=501, detail="Endpoint is not yet implemented")

invokeai/app/api/routers/models.py

@@ -2,11 +2,11 @@
 
 
 import pathlib
-from typing import List, Literal, Optional, Union
+from typing import Annotated, List, Literal, Optional, Union
 
 from fastapi import Body, Path, Query, Response
 from fastapi.routing import APIRouter
-from pydantic import BaseModel, parse_obj_as
+from pydantic import BaseModel, ConfigDict, Field, TypeAdapter
 from starlette.exceptions import HTTPException
 
 from invokeai.backend import BaseModelType, ModelType
@@ -23,8 +23,14 @@ from ..dependencies import ApiDependencies
 models_router = APIRouter(prefix="/v1/models", tags=["models"])
 
 UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+UpdateModelResponseValidator = TypeAdapter(UpdateModelResponse)
+
 ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ImportModelResponseValidator = TypeAdapter(ImportModelResponse)
+
 ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ConvertModelResponseValidator = TypeAdapter(ConvertModelResponse)
+
 MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 
@@ -32,6 +38,11 @@ ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 class ModelsList(BaseModel):
     models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
 
+    model_config = ConfigDict(use_enum_values=True)
+
+
+ModelsListValidator = TypeAdapter(ModelsList)
+
 
 @models_router.get(
     "/",
@@ -49,7 +60,7 @@ async def list_models(
             models_raw.extend(ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type))
     else:
         models_raw = ApiDependencies.invoker.services.model_manager.list_models(None, model_type)
-    models = parse_obj_as(ModelsList, {"models": models_raw})
+    models = ModelsListValidator.validate_python({"models": models_raw})
     return models
 
 
@@ -105,11 +116,14 @@ async def update_model(
                 info.path = new_info.get("path")
 
         # replace empty string values with None/null to avoid phenomenon of vae: ''
-        info_dict = info.dict()
+        info_dict = info.model_dump()
         info_dict = {x: info_dict[x] if info_dict[x] else None for x in info_dict.keys()}
 
         ApiDependencies.invoker.services.model_manager.update_model(
-            model_name=model_name, base_model=base_model, model_type=model_type, model_attributes=info_dict
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+            model_attributes=info_dict,
         )
 
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
@@ -117,7 +131,7 @@ async def update_model(
             base_model=base_model,
             model_type=model_type,
         )
-        model_response = parse_obj_as(UpdateModelResponse, model_raw)
+        model_response = UpdateModelResponseValidator.validate_python(model_raw)
     except ModelNotFoundException as e:
         raise HTTPException(status_code=404, detail=str(e))
     except ValueError as e:
@@ -146,18 +160,21 @@ async def update_model(
 async def import_model(
     location: str = Body(description="A model path, repo_id or URL to import"),
     prediction_type: Optional[Literal["v_prediction", "epsilon", "sample"]] = Body(
-        description="Prediction type for SDv2 checkpoint files", default="v_prediction"
+        description="Prediction type for SDv2 checkpoints and rare SDv1 checkpoints",
+        default=None,
     ),
 ) -> ImportModelResponse:
     """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
 
+    location = location.strip("\"' ")
     items_to_import = {location}
     prediction_types = {x.value: x for x in SchedulerPredictionType}
     logger = ApiDependencies.invoker.services.logger
 
     try:
         installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
-            items_to_import=items_to_import, prediction_type_helper=lambda x: prediction_types.get(prediction_type)
+            items_to_import=items_to_import,
+            prediction_type_helper=lambda x: prediction_types.get(prediction_type),
         )
         info = installed_models.get(location)
 
@@ -169,7 +186,7 @@ async def import_model(
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
             model_name=info.name, base_model=info.base_model, model_type=info.model_type
         )
-        return parse_obj_as(ImportModelResponse, model_raw)
+        return ImportModelResponseValidator.validate_python(model_raw)
 
     except ModelNotFoundException as e:
         logger.error(str(e))
@@ -203,13 +220,18 @@ async def add_model(
 
     try:
         ApiDependencies.invoker.services.model_manager.add_model(
-            info.model_name, info.base_model, info.model_type, model_attributes=info.dict()
+            info.model_name,
+            info.base_model,
+            info.model_type,
+            model_attributes=info.model_dump(),
         )
         logger.info(f"Successfully added {info.model_name}")
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=info.model_name, base_model=info.base_model, model_type=info.model_type
+            model_name=info.model_name,
+            base_model=info.base_model,
+            model_type=info.model_type,
         )
-        return parse_obj_as(ImportModelResponse, model_raw)
+        return ImportModelResponseValidator.validate_python(model_raw)
     except ModelNotFoundException as e:
         logger.error(str(e))
         raise HTTPException(status_code=404, detail=str(e))
@@ -221,7 +243,10 @@ async def add_model(
 @models_router.delete(
     "/{base_model}/{model_type}/{model_name}",
     operation_id="del_model",
-    responses={204: {"description": "Model deleted successfully"}, 404: {"description": "Model not found"}},
+    responses={
+        204: {"description": "Model deleted successfully"},
+        404: {"description": "Model not found"},
+    },
     status_code=204,
     response_model=None,
 )
@@ -277,7 +302,7 @@ async def convert_model(
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
             model_name, base_model=base_model, model_type=model_type
         )
-        response = parse_obj_as(ConvertModelResponse, model_raw)
+        response = ConvertModelResponseValidator.validate_python(model_raw)
     except ModelNotFoundException as e:
         raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found: {str(e)}")
     except ValueError as e:
@@ -300,7 +325,8 @@ async def search_for_models(
 ) -> List[pathlib.Path]:
     if not search_path.is_dir():
         raise HTTPException(
-            status_code=404, detail=f"The search path '{search_path}' does not exist or is not directory"
+            status_code=404,
+            detail=f"The search path '{search_path}' does not exist or is not directory",
         )
     return ApiDependencies.invoker.services.model_manager.search_for_models(search_path)
 
@@ -335,6 +361,26 @@ async def sync_to_config() -> bool:
     return True
 
 
+# There's some weird pydantic-fastapi behaviour that requires this to be a separate class
+# TODO: After a few updates, see if it works inside the route operation handler?
+class MergeModelsBody(BaseModel):
+    model_names: List[str] = Field(description="model name", min_length=2, max_length=3)
+    merged_model_name: Optional[str] = Field(description="Name of destination model")
+    alpha: Optional[float] = Field(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5)
+    interp: Optional[MergeInterpolationMethod] = Field(description="Interpolation method")
+    force: Optional[bool] = Field(
+        description="Force merging of models created with different versions of diffusers",
+        default=False,
+    )
+
+    merge_dest_directory: Optional[str] = Field(
+        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
+        default=None,
+    )
+
+    model_config = ConfigDict(protected_namespaces=())
+
+
 @models_router.put(
     "/merge/{base_model}",
     operation_id="merge_models",
@@ -347,31 +393,23 @@ async def sync_to_config() -> bool:
     response_model=MergeModelResponse,
 )
 async def merge_models(
+    body: Annotated[MergeModelsBody, Body(description="Model configuration", embed=True)],
     base_model: BaseModelType = Path(description="Base model"),
-    model_names: List[str] = Body(description="model name", min_items=2, max_items=3),
-    merged_model_name: Optional[str] = Body(description="Name of destination model"),
-    alpha: Optional[float] = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
-    interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method"),
-    force: Optional[bool] = Body(
-        description="Force merging of models created with different versions of diffusers", default=False
-    ),
-    merge_dest_directory: Optional[str] = Body(
-        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
-        default=None,
-    ),
 ) -> MergeModelResponse:
     """Convert a checkpoint model into a diffusers model"""
     logger = ApiDependencies.invoker.services.logger
     try:
-        logger.info(f"Merging models: {model_names} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
-        dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
+        logger.info(
+            f"Merging models: {body.model_names} into {body.merge_dest_directory or '<MODELS>'}/{body.merged_model_name}"
+        )
+        dest = pathlib.Path(body.merge_dest_directory) if body.merge_dest_directory else None
         result = ApiDependencies.invoker.services.model_manager.merge_models(
-            model_names,
-            base_model,
-            merged_model_name=merged_model_name or "+".join(model_names),
-            alpha=alpha,
-            interp=interp,
-            force=force,
+            model_names=body.model_names,
+            base_model=base_model,
+            merged_model_name=body.merged_model_name or "+".join(body.model_names),
+            alpha=body.alpha,
+            interp=body.interp,
+            force=body.force,
             merge_dest_directory=dest,
         )
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
@@ -379,9 +417,12 @@ async def merge_models(
             base_model=base_model,
             model_type=ModelType.Main,
         )
-        response = parse_obj_as(ConvertModelResponse, model_raw)
+        response = ConvertModelResponseValidator.validate_python(model_raw)
     except ModelNotFoundException:
-        raise HTTPException(status_code=404, detail=f"One or more of the models '{model_names}' not found")
+        raise HTTPException(
+            status_code=404,
+            detail=f"One or more of the models '{body.model_names}' not found",
+        )
     except ValueError as e:
         raise HTTPException(status_code=400, detail=str(e))
     return response

invokeai/app/api/routers/session_queue.py

@@ -12,15 +12,13 @@ from invokeai.app.services.session_queue.session_queue_common import (
     CancelByBatchIDsResult,
     ClearResult,
     EnqueueBatchResult,
-    EnqueueGraphResult,
     PruneResult,
     SessionQueueItem,
     SessionQueueItemDTO,
     SessionQueueStatus,
 )
-from invokeai.app.services.shared.models import CursorPaginatedResults
+from invokeai.app.services.shared.pagination import CursorPaginatedResults
 
-from ...services.graph import Graph
 from ..dependencies import ApiDependencies
 
 session_queue_router = APIRouter(prefix="/v1/queue", tags=["queue"])
@@ -33,23 +31,6 @@ class SessionQueueAndProcessorStatus(BaseModel):
     processor: SessionProcessorStatus
 
 
-@session_queue_router.post(
-    "/{queue_id}/enqueue_graph",
-    operation_id="enqueue_graph",
-    responses={
-        201: {"model": EnqueueGraphResult},
-    },
-)
-async def enqueue_graph(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-    graph: Graph = Body(description="The graph to enqueue"),
-    prepend: bool = Body(default=False, description="Whether or not to prepend this batch in the queue"),
-) -> EnqueueGraphResult:
-    """Enqueues a graph for single execution."""
-
-    return ApiDependencies.invoker.services.session_queue.enqueue_graph(queue_id=queue_id, graph=graph, prepend=prepend)
-
-
 @session_queue_router.post(
     "/{queue_id}/enqueue_batch",
     operation_id="enqueue_batch",

invokeai/app/api/routers/sessions.py

@@ -1,56 +1,50 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Annotated, Optional, Union
 
-from fastapi import Body, HTTPException, Path, Query, Response
+from fastapi import HTTPException, Path
 from fastapi.routing import APIRouter
-from pydantic.fields import Field
 
-# Importing * is bad karma but needed here for node detection
-from ...invocations import *  # noqa: F401 F403
-from ...invocations.baseinvocation import BaseInvocation
-from ...services.graph import Edge, EdgeConnection, Graph, GraphExecutionState, NodeAlreadyExecutedError
-from ...services.item_storage import PaginatedResults
+from ...services.shared.graph import GraphExecutionState
 from ..dependencies import ApiDependencies
 
 session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
 
 
-@session_router.post(
-    "/",
-    operation_id="create_session",
-    responses={
-        200: {"model": GraphExecutionState},
-        400: {"description": "Invalid json"},
-    },
-    deprecated=True,
-)
-async def create_session(
-    queue_id: str = Query(default="", description="The id of the queue to associate the session with"),
-    graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
-) -> GraphExecutionState:
-    """Creates a new session, optionally initializing it with an invocation graph"""
-    session = ApiDependencies.invoker.create_execution_state(queue_id=queue_id, graph=graph)
-    return session
+# @session_router.post(
+#     "/",
+#     operation_id="create_session",
+#     responses={
+#         200: {"model": GraphExecutionState},
+#         400: {"description": "Invalid json"},
+#     },
+#     deprecated=True,
+# )
+# async def create_session(
+#     queue_id: str = Query(default="", description="The id of the queue to associate the session with"),
+#     graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
+# ) -> GraphExecutionState:
+#     """Creates a new session, optionally initializing it with an invocation graph"""
+#     session = ApiDependencies.invoker.create_execution_state(queue_id=queue_id, graph=graph)
+#     return session
 
 
-@session_router.get(
-    "/",
-    operation_id="list_sessions",
-    responses={200: {"model": PaginatedResults[GraphExecutionState]}},
-    deprecated=True,
-)
-async def list_sessions(
-    page: int = Query(default=0, description="The page of results to get"),
-    per_page: int = Query(default=10, description="The number of results per page"),
-    query: str = Query(default="", description="The query string to search for"),
-) -> PaginatedResults[GraphExecutionState]:
-    """Gets a list of sessions, optionally searching"""
-    if query == "":
-        result = ApiDependencies.invoker.services.graph_execution_manager.list(page, per_page)
-    else:
-        result = ApiDependencies.invoker.services.graph_execution_manager.search(query, page, per_page)
-    return result
+# @session_router.get(
+#     "/",
+#     operation_id="list_sessions",
+#     responses={200: {"model": PaginatedResults[GraphExecutionState]}},
+#     deprecated=True,
+# )
+# async def list_sessions(
+#     page: int = Query(default=0, description="The page of results to get"),
+#     per_page: int = Query(default=10, description="The number of results per page"),
+#     query: str = Query(default="", description="The query string to search for"),
+# ) -> PaginatedResults[GraphExecutionState]:
+#     """Gets a list of sessions, optionally searching"""
+#     if query == "":
+#         result = ApiDependencies.invoker.services.graph_execution_manager.list(page, per_page)
+#     else:
+#         result = ApiDependencies.invoker.services.graph_execution_manager.search(query, page, per_page)
+#     return result
 
 
 @session_router.get(
@@ -60,7 +54,6 @@ async def list_sessions(
         200: {"model": GraphExecutionState},
         404: {"description": "Session not found"},
     },
-    deprecated=True,
 )
 async def get_session(
     session_id: str = Path(description="The id of the session to get"),
@@ -73,211 +66,211 @@ async def get_session(
         return session
 
 
-@session_router.post(
-    "/{session_id}/nodes",
-    operation_id="add_node",
-    responses={
-        200: {"model": str},
-        400: {"description": "Invalid node or link"},
-        404: {"description": "Session not found"},
-    },
-    deprecated=True,
-)
-async def add_node(
-    session_id: str = Path(description="The id of the session"),
-    node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
-        description="The node to add"
-    ),
-) -> str:
-    """Adds a node to the graph"""
-    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-    if session is None:
-        raise HTTPException(status_code=404)
+# @session_router.post(
+#     "/{session_id}/nodes",
+#     operation_id="add_node",
+#     responses={
+#         200: {"model": str},
+#         400: {"description": "Invalid node or link"},
+#         404: {"description": "Session not found"},
+#     },
+#     deprecated=True,
+# )
+# async def add_node(
+#     session_id: str = Path(description="The id of the session"),
+#     node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
+#         description="The node to add"
+#     ),
+# ) -> str:
+#     """Adds a node to the graph"""
+#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+#     if session is None:
+#         raise HTTPException(status_code=404)
 
-    try:
-        session.add_node(node)
-        ApiDependencies.invoker.services.graph_execution_manager.set(
-            session
-        )  # TODO: can this be done automatically, or add node through an API?
-        return session.id
-    except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
-    except IndexError:
-        raise HTTPException(status_code=400)
+#     try:
+#         session.add_node(node)
+#         ApiDependencies.invoker.services.graph_execution_manager.set(
+#             session
+#         )  # TODO: can this be done automatically, or add node through an API?
+#         return session.id
+#     except NodeAlreadyExecutedError:
+#         raise HTTPException(status_code=400)
+#     except IndexError:
+#         raise HTTPException(status_code=400)
 
 
-@session_router.put(
-    "/{session_id}/nodes/{node_path}",
-    operation_id="update_node",
-    responses={
-        200: {"model": GraphExecutionState},
-        400: {"description": "Invalid node or link"},
-        404: {"description": "Session not found"},
-    },
-    deprecated=True,
-)
-async def update_node(
-    session_id: str = Path(description="The id of the session"),
-    node_path: str = Path(description="The path to the node in the graph"),
-    node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
-        description="The new node"
-    ),
-) -> GraphExecutionState:
-    """Updates a node in the graph and removes all linked edges"""
-    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-    if session is None:
-        raise HTTPException(status_code=404)
+# @session_router.put(
+#     "/{session_id}/nodes/{node_path}",
+#     operation_id="update_node",
+#     responses={
+#         200: {"model": GraphExecutionState},
+#         400: {"description": "Invalid node or link"},
+#         404: {"description": "Session not found"},
+#     },
+#     deprecated=True,
+# )
+# async def update_node(
+#     session_id: str = Path(description="The id of the session"),
+#     node_path: str = Path(description="The path to the node in the graph"),
+#     node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
+#         description="The new node"
+#     ),
+# ) -> GraphExecutionState:
+#     """Updates a node in the graph and removes all linked edges"""
+#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+#     if session is None:
+#         raise HTTPException(status_code=404)
 
-    try:
-        session.update_node(node_path, node)
-        ApiDependencies.invoker.services.graph_execution_manager.set(
-            session
-        )  # TODO: can this be done automatically, or add node through an API?
-        return session
-    except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
-    except IndexError:
-        raise HTTPException(status_code=400)
+#     try:
+#         session.update_node(node_path, node)
+#         ApiDependencies.invoker.services.graph_execution_manager.set(
+#             session
+#         )  # TODO: can this be done automatically, or add node through an API?
+#         return session
+#     except NodeAlreadyExecutedError:
+#         raise HTTPException(status_code=400)
+#     except IndexError:
+#         raise HTTPException(status_code=400)
 
 
-@session_router.delete(
-    "/{session_id}/nodes/{node_path}",
-    operation_id="delete_node",
-    responses={
-        200: {"model": GraphExecutionState},
-        400: {"description": "Invalid node or link"},
-        404: {"description": "Session not found"},
-    },
-    deprecated=True,
-)
-async def delete_node(
-    session_id: str = Path(description="The id of the session"),
-    node_path: str = Path(description="The path to the node to delete"),
-) -> GraphExecutionState:
-    """Deletes a node in the graph and removes all linked edges"""
-    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-    if session is None:
-        raise HTTPException(status_code=404)
+# @session_router.delete(
+#     "/{session_id}/nodes/{node_path}",
+#     operation_id="delete_node",
+#     responses={
+#         200: {"model": GraphExecutionState},
+#         400: {"description": "Invalid node or link"},
+#         404: {"description": "Session not found"},
+#     },
+#     deprecated=True,
+# )
+# async def delete_node(
+#     session_id: str = Path(description="The id of the session"),
+#     node_path: str = Path(description="The path to the node to delete"),
+# ) -> GraphExecutionState:
+#     """Deletes a node in the graph and removes all linked edges"""
+#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+#     if session is None:
+#         raise HTTPException(status_code=404)
 
-    try:
-        session.delete_node(node_path)
-        ApiDependencies.invoker.services.graph_execution_manager.set(
-            session
-        )  # TODO: can this be done automatically, or add node through an API?
-        return session
-    except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
-    except IndexError:
-        raise HTTPException(status_code=400)
+#     try:
+#         session.delete_node(node_path)
+#         ApiDependencies.invoker.services.graph_execution_manager.set(
+#             session
+#         )  # TODO: can this be done automatically, or add node through an API?
+#         return session
+#     except NodeAlreadyExecutedError:
+#         raise HTTPException(status_code=400)
+#     except IndexError:
+#         raise HTTPException(status_code=400)
 
 
-@session_router.post(
-    "/{session_id}/edges",
-    operation_id="add_edge",
-    responses={
-        200: {"model": GraphExecutionState},
-        400: {"description": "Invalid node or link"},
-        404: {"description": "Session not found"},
-    },
-    deprecated=True,
-)
-async def add_edge(
-    session_id: str = Path(description="The id of the session"),
-    edge: Edge = Body(description="The edge to add"),
-) -> GraphExecutionState:
-    """Adds an edge to the graph"""
-    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-    if session is None:
-        raise HTTPException(status_code=404)
+# @session_router.post(
+#     "/{session_id}/edges",
+#     operation_id="add_edge",
+#     responses={
+#         200: {"model": GraphExecutionState},
+#         400: {"description": "Invalid node or link"},
+#         404: {"description": "Session not found"},
+#     },
+#     deprecated=True,
+# )
+# async def add_edge(
+#     session_id: str = Path(description="The id of the session"),
+#     edge: Edge = Body(description="The edge to add"),
+# ) -> GraphExecutionState:
+#     """Adds an edge to the graph"""
+#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+#     if session is None:
+#         raise HTTPException(status_code=404)
 
-    try:
-        session.add_edge(edge)
-        ApiDependencies.invoker.services.graph_execution_manager.set(
-            session
-        )  # TODO: can this be done automatically, or add node through an API?
-        return session
-    except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
-    except IndexError:
-        raise HTTPException(status_code=400)
+#     try:
+#         session.add_edge(edge)
+#         ApiDependencies.invoker.services.graph_execution_manager.set(
+#             session
+#         )  # TODO: can this be done automatically, or add node through an API?
+#         return session
+#     except NodeAlreadyExecutedError:
+#         raise HTTPException(status_code=400)
+#     except IndexError:
+#         raise HTTPException(status_code=400)
 
 
-# TODO: the edge being in the path here is really ugly, find a better solution
-@session_router.delete(
-    "/{session_id}/edges/{from_node_id}/{from_field}/{to_node_id}/{to_field}",
-    operation_id="delete_edge",
-    responses={
-        200: {"model": GraphExecutionState},
-        400: {"description": "Invalid node or link"},
-        404: {"description": "Session not found"},
-    },
-    deprecated=True,
-)
-async def delete_edge(
-    session_id: str = Path(description="The id of the session"),
-    from_node_id: str = Path(description="The id of the node the edge is coming from"),
-    from_field: str = Path(description="The field of the node the edge is coming from"),
-    to_node_id: str = Path(description="The id of the node the edge is going to"),
-    to_field: str = Path(description="The field of the node the edge is going to"),
-) -> GraphExecutionState:
-    """Deletes an edge from the graph"""
-    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-    if session is None:
-        raise HTTPException(status_code=404)
+# # TODO: the edge being in the path here is really ugly, find a better solution
+# @session_router.delete(
+#     "/{session_id}/edges/{from_node_id}/{from_field}/{to_node_id}/{to_field}",
+#     operation_id="delete_edge",
+#     responses={
+#         200: {"model": GraphExecutionState},
+#         400: {"description": "Invalid node or link"},
+#         404: {"description": "Session not found"},
+#     },
+#     deprecated=True,
+# )
+# async def delete_edge(
+#     session_id: str = Path(description="The id of the session"),
+#     from_node_id: str = Path(description="The id of the node the edge is coming from"),
+#     from_field: str = Path(description="The field of the node the edge is coming from"),
+#     to_node_id: str = Path(description="The id of the node the edge is going to"),
+#     to_field: str = Path(description="The field of the node the edge is going to"),
+# ) -> GraphExecutionState:
+#     """Deletes an edge from the graph"""
+#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+#     if session is None:
+#         raise HTTPException(status_code=404)
 
-    try:
-        edge = Edge(
-            source=EdgeConnection(node_id=from_node_id, field=from_field),
-            destination=EdgeConnection(node_id=to_node_id, field=to_field),
-        )
-        session.delete_edge(edge)
-        ApiDependencies.invoker.services.graph_execution_manager.set(
-            session
-        )  # TODO: can this be done automatically, or add node through an API?
-        return session
-    except NodeAlreadyExecutedError:
-        raise HTTPException(status_code=400)
-    except IndexError:
-        raise HTTPException(status_code=400)
+#     try:
+#         edge = Edge(
+#             source=EdgeConnection(node_id=from_node_id, field=from_field),
+#             destination=EdgeConnection(node_id=to_node_id, field=to_field),
+#         )
+#         session.delete_edge(edge)
+#         ApiDependencies.invoker.services.graph_execution_manager.set(
+#             session
+#         )  # TODO: can this be done automatically, or add node through an API?
+#         return session
+#     except NodeAlreadyExecutedError:
+#         raise HTTPException(status_code=400)
+#     except IndexError:
+#         raise HTTPException(status_code=400)
 
 
-@session_router.put(
-    "/{session_id}/invoke",
-    operation_id="invoke_session",
-    responses={
-        200: {"model": None},
-        202: {"description": "The invocation is queued"},
-        400: {"description": "The session has no invocations ready to invoke"},
-        404: {"description": "Session not found"},
-    },
-    deprecated=True,
-)
-async def invoke_session(
-    queue_id: str = Query(description="The id of the queue to associate the session with"),
-    session_id: str = Path(description="The id of the session to invoke"),
-    all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
-) -> Response:
-    """Invokes a session"""
-    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-    if session is None:
-        raise HTTPException(status_code=404)
+# @session_router.put(
+#     "/{session_id}/invoke",
+#     operation_id="invoke_session",
+#     responses={
+#         200: {"model": None},
+#         202: {"description": "The invocation is queued"},
+#         400: {"description": "The session has no invocations ready to invoke"},
+#         404: {"description": "Session not found"},
+#     },
+#     deprecated=True,
+# )
+# async def invoke_session(
+#     queue_id: str = Query(description="The id of the queue to associate the session with"),
+#     session_id: str = Path(description="The id of the session to invoke"),
+#     all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
+# ) -> Response:
+#     """Invokes a session"""
+#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+#     if session is None:
+#         raise HTTPException(status_code=404)
 
-    if session.is_complete():
-        raise HTTPException(status_code=400)
+#     if session.is_complete():
+#         raise HTTPException(status_code=400)
 
-    ApiDependencies.invoker.invoke(queue_id, session, invoke_all=all)
-    return Response(status_code=202)
+#     ApiDependencies.invoker.invoke(queue_id, session, invoke_all=all)
+#     return Response(status_code=202)
 
 
-@session_router.delete(
-    "/{session_id}/invoke",
-    operation_id="cancel_session_invoke",
-    responses={202: {"description": "The invocation is canceled"}},
-    deprecated=True,
-)
-async def cancel_session_invoke(
-    session_id: str = Path(description="The id of the session to cancel"),
-) -> Response:
-    """Invokes a session"""
-    ApiDependencies.invoker.cancel(session_id)
-    return Response(status_code=202)
+# @session_router.delete(
+#     "/{session_id}/invoke",
+#     operation_id="cancel_session_invoke",
+#     responses={202: {"description": "The invocation is canceled"}},
+#     deprecated=True,
+# )
+# async def cancel_session_invoke(
+#     session_id: str = Path(description="The id of the session to cancel"),
+# ) -> Response:
+#     """Invokes a session"""
+#     ApiDependencies.invoker.cancel(session_id)
+#     return Response(status_code=202)

invokeai/app/api/routers/utilities.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Optional, Union
 
 from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPromptGenerator
 from fastapi import Body
@@ -27,6 +27,7 @@ async def parse_dynamicprompts(
     combinatorial: bool = Body(default=True, description="Whether to use the combinatorial generator"),
 ) -> DynamicPromptsResponse:
     """Creates a batch process"""
+    generator: Union[RandomPromptGenerator, CombinatorialPromptGenerator]
     try:
         error: Optional[str] = None
         if combinatorial:

invokeai/app/api/routers/workflows.py

@@ -0,0 +1,20 @@
+from fastapi import APIRouter, Path
+
+from invokeai.app.api.dependencies import ApiDependencies
+from invokeai.app.invocations.baseinvocation import WorkflowField
+
+workflows_router = APIRouter(prefix="/v1/workflows", tags=["workflows"])
+
+
+@workflows_router.get(
+    "/i/{workflow_id}",
+    operation_id="get_workflow",
+    responses={
+        200: {"model": WorkflowField},
+    },
+)
+async def get_workflow(
+    workflow_id: str = Path(description="The workflow to get"),
+) -> WorkflowField:
+    """Gets a workflow"""
+    return ApiDependencies.invoker.services.workflow_records.get(workflow_id)

invokeai/app/api/sockets.py

@@ -5,7 +5,7 @@ from fastapi_events.handlers.local import local_handler
 from fastapi_events.typing import Event
 from socketio import ASGIApp, AsyncServer
 
-from ..services.events import EventServiceBase
+from ..services.events.events_base import EventServiceBase
 
 
 class SocketIO:
@@ -30,8 +30,8 @@ class SocketIO:
 
     async def _handle_sub_queue(self, sid, data, *args, **kwargs):
         if "queue_id" in data:
-            self.__sio.enter_room(sid, data["queue_id"])
+            await self.__sio.enter_room(sid, data["queue_id"])
 
     async def _handle_unsub_queue(self, sid, data, *args, **kwargs):
         if "queue_id" in data:
-            self.__sio.enter_room(sid, data["queue_id"])
+            await self.__sio.enter_room(sid, data["queue_id"])

invokeai/app/api_app.py

@@ -1,3 +1,7 @@
+from typing import Any
+
+from fastapi.responses import HTMLResponse
+
 from .services.config import InvokeAIAppConfig
 
 # parse_args() must be called before any other imports. if it is not called first, consumers of the config
@@ -8,23 +12,25 @@ app_config.parse_args()
 
 if True:  # hack to make flake8 happy with imports coming after setting up the config
     import asyncio
-    import logging
     import mimetypes
     import socket
     from inspect import signature
     from pathlib import Path
 
-    import torch
     import uvicorn
     from fastapi import FastAPI
     from fastapi.middleware.cors import CORSMiddleware
+    from fastapi.middleware.gzip import GZipMiddleware
     from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
     from fastapi.openapi.utils import get_openapi
+    from fastapi.responses import FileResponse
     from fastapi.staticfiles import StaticFiles
     from fastapi_events.handlers.local import local_handler
     from fastapi_events.middleware import EventHandlerASGIMiddleware
-    from pydantic.schema import schema
+    from pydantic.json_schema import models_json_schema
+    from torch.backends.mps import is_available as is_mps_available
 
+    # for PyCharm:
     # noinspection PyUnresolvedReferences
     import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
     import invokeai.frontend.web as web_dir
@@ -32,19 +38,27 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
 
     from ..backend.util.logging import InvokeAILogger
     from .api.dependencies import ApiDependencies
-    from .api.routers import app_info, board_images, boards, images, models, session_queue, sessions, utilities
+    from .api.routers import (
+        app_info,
+        board_images,
+        boards,
+        images,
+        models,
+        session_queue,
+        sessions,
+        utilities,
+        workflows,
+    )
     from .api.sockets import SocketIO
     from .invocations.baseinvocation import BaseInvocation, UIConfigBase, _InputField, _OutputField
 
-    if torch.backends.mps.is_available():
-        # noinspection PyUnresolvedReferences
+    if is_mps_available():
         import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
 
 
 app_config = InvokeAIAppConfig.get_config()
 app_config.parse_args()
 logger = InvokeAILogger.get_logger(config=app_config)
-
 # fix for windows mimetypes registry entries being borked
 # see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
 mimetypes.add_type("application/javascript", ".js")
@@ -52,7 +66,7 @@ mimetypes.add_type("text/css", ".css")
 
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
-app = FastAPI(title="Invoke AI", docs_url=None, redoc_url=None)
+app = FastAPI(title="Invoke AI", docs_url=None, redoc_url=None, separate_input_output_schemas=False)
 
 # Add event handler
 event_handler_id: int = id(app)
@@ -64,53 +78,45 @@ app.add_middleware(
 
 socket_io = SocketIO(app)
 
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=app_config.allow_origins,
+    allow_credentials=app_config.allow_credentials,
+    allow_methods=app_config.allow_methods,
+    allow_headers=app_config.allow_headers,
+)
+
+app.add_middleware(GZipMiddleware, minimum_size=1000)
+
 
 # Add startup event to load dependencies
 @app.on_event("startup")
-async def startup_event():
-    app.add_middleware(
-        CORSMiddleware,
-        allow_origins=app_config.allow_origins,
-        allow_credentials=app_config.allow_credentials,
-        allow_methods=app_config.allow_methods,
-        allow_headers=app_config.allow_headers,
-    )
-
+async def startup_event() -> None:
     ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
 
 
 # Shut down threads
 @app.on_event("shutdown")
-async def shutdown_event():
+async def shutdown_event() -> None:
     ApiDependencies.shutdown()
 
 
 # Include all routers
-# TODO: REMOVE
-# app.include_router(
-#     invocation.invocation_router,
-#     prefix = '/api')
-
 app.include_router(sessions.session_router, prefix="/api")
 
 app.include_router(utilities.utilities_router, prefix="/api")
-
 app.include_router(models.models_router, prefix="/api")
-
 app.include_router(images.images_router, prefix="/api")
-
 app.include_router(boards.boards_router, prefix="/api")
-
 app.include_router(board_images.board_images_router, prefix="/api")
-
 app.include_router(app_info.app_router, prefix="/api")
-
 app.include_router(session_queue.session_queue_router, prefix="/api")
+app.include_router(workflows.workflows_router, prefix="/api")
 
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?
-def custom_openapi():
+def custom_openapi() -> dict[str, Any]:
     if app.openapi_schema:
         return app.openapi_schema
     openapi_schema = get_openapi(
@@ -118,6 +124,7 @@ def custom_openapi():
         description="An API for invoking AI image operations",
         version="1.0.0",
         routes=app.routes,
+        separate_input_output_schemas=False,  # https://fastapi.tiangolo.com/how-to/separate-openapi-schemas/
     )
 
     # Add all outputs
@@ -128,29 +135,32 @@ def custom_openapi():
         output_type = signature(invoker.invoke).return_annotation
         output_types.add(output_type)
 
-    output_schemas = schema(output_types, ref_prefix="#/components/schemas/")
-    for schema_key, output_schema in output_schemas["definitions"].items():
-        output_schema["class"] = "output"
-        openapi_schema["components"]["schemas"][schema_key] = output_schema
-
+    output_schemas = models_json_schema(
+        models=[(o, "serialization") for o in output_types], ref_template="#/components/schemas/{model}"
+    )
+    for schema_key, output_schema in output_schemas[1]["$defs"].items():
         # TODO: note that we assume the schema_key here is the TYPE.__name__
         # This could break in some cases, figure out a better way to do it
         output_type_titles[schema_key] = output_schema["title"]
 
     # Add Node Editor UI helper schemas
-    ui_config_schemas = schema([UIConfigBase, _InputField, _OutputField], ref_prefix="#/components/schemas/")
-    for schema_key, ui_config_schema in ui_config_schemas["definitions"].items():
+    ui_config_schemas = models_json_schema(
+        [(UIConfigBase, "serialization"), (_InputField, "serialization"), (_OutputField, "serialization")],
+        ref_template="#/components/schemas/{model}",
+    )
+    for schema_key, ui_config_schema in ui_config_schemas[1]["$defs"].items():
         openapi_schema["components"]["schemas"][schema_key] = ui_config_schema
 
     # Add a reference to the output type to additionalProperties of the invoker schema
     for invoker in all_invocations:
         invoker_name = invoker.__name__
-        output_type = signature(invoker.invoke).return_annotation
+        output_type = signature(obj=invoker.invoke).return_annotation
         output_type_title = output_type_titles[output_type.__name__]
-        invoker_schema = openapi_schema["components"]["schemas"][invoker_name]
+        invoker_schema = openapi_schema["components"]["schemas"][f"{invoker_name}"]
         outputs_ref = {"$ref": f"#/components/schemas/{output_type_title}"}
         invoker_schema["output"] = outputs_ref
         invoker_schema["class"] = "invocation"
+        openapi_schema["components"]["schemas"][f"{output_type_title}"]["class"] = "output"
 
     from invokeai.backend.model_management.models import get_model_config_enums
 
@@ -161,7 +171,6 @@ def custom_openapi():
             # print(f"Config with name {name} already defined")
             continue
 
-        # "BaseModelType":{"title":"BaseModelType","description":"An enumeration.","enum":["sd-1","sd-2"],"type":"string"}
         openapi_schema["components"]["schemas"][name] = dict(
             title=name,
             description="An enumeration.",
@@ -173,36 +182,45 @@ def custom_openapi():
     return app.openapi_schema
 
 
-app.openapi = custom_openapi
-
-# Override API doc favicons
-app.mount("/static", StaticFiles(directory=Path(web_dir.__path__[0], "static/dream_web")), name="static")
+app.openapi = custom_openapi  # type: ignore [method-assign] # this is a valid assignment
 
 
 @app.get("/docs", include_in_schema=False)
-def overridden_swagger():
+def overridden_swagger() -> HTMLResponse:
     return get_swagger_ui_html(
-        openapi_url=app.openapi_url,
+        openapi_url=app.openapi_url,  # type: ignore [arg-type] # this is always a string
         title=app.title,
-        swagger_favicon_url="/static/favicon.ico",
+        swagger_favicon_url="/static/docs/favicon.ico",
     )
 
 
 @app.get("/redoc", include_in_schema=False)
-def overridden_redoc():
+def overridden_redoc() -> HTMLResponse:
     return get_redoc_html(
-        openapi_url=app.openapi_url,
+        openapi_url=app.openapi_url,  # type: ignore [arg-type] # this is always a string
         title=app.title,
-        redoc_favicon_url="/static/favicon.ico",
+        redoc_favicon_url="/static/docs/favicon.ico",
     )
 
 
-# Must mount *after* the other routes else it borks em
-app.mount("/", StaticFiles(directory=Path(web_dir.__path__[0], "dist"), html=True), name="ui")
+web_root_path = Path(list(web_dir.__path__)[0])
 
 
-def invoke_api():
-    def find_port(port: int):
+# Cannot add headers to StaticFiles, so we must serve index.html with a custom route
+# Add cache-control: no-store header to prevent caching of index.html, which leads to broken UIs at release
+@app.get("/", include_in_schema=False, name="ui_root")
+def get_index() -> FileResponse:
+    return FileResponse(Path(web_root_path, "dist/index.html"), headers={"Cache-Control": "no-store"})
+
+
+# # Must mount *after* the other routes else it borks em
+app.mount("/static", StaticFiles(directory=Path(web_root_path, "static/")), name="static")  # docs favicon is in here
+app.mount("/assets", StaticFiles(directory=Path(web_root_path, "dist/assets/")), name="assets")
+app.mount("/locales", StaticFiles(directory=Path(web_root_path, "dist/locales/")), name="locales")
+
+
+def invoke_api() -> None:
+    def find_port(port: int) -> int:
         """Find a port not in use starting at given port"""
         # Taken from https://waylonwalker.com/python-find-available-port/, thanks Waylon!
         # https://github.com/WaylonWalker
@@ -237,7 +255,7 @@ def invoke_api():
         app=app,
         host=app_config.host,
         port=port,
-        loop=loop,
+        loop="asyncio",
         log_level=app_config.log_level,
     )
     server = uvicorn.Server(config)

invokeai/app/cli/commands.py

@@ -1,313 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-import argparse
-from abc import ABC, abstractmethod
-from typing import Any, Callable, Iterable, Literal, Union, get_args, get_origin, get_type_hints
-
-import matplotlib.pyplot as plt
-import networkx as nx
-from pydantic import BaseModel, Field
-
-import invokeai.backend.util.logging as logger
-
-from ..invocations.baseinvocation import BaseInvocation
-from ..invocations.image import ImageField
-from ..services.graph import Edge, GraphExecutionState, LibraryGraph
-from ..services.invoker import Invoker
-
-
-def add_field_argument(command_parser, name: str, field, default_override=None):
-    default = (
-        default_override
-        if default_override is not None
-        else field.default
-        if field.default_factory is None
-        else field.default_factory()
-    )
-    if get_origin(field.type_) == Literal:
-        allowed_values = get_args(field.type_)
-        allowed_types = set()
-        for val in allowed_values:
-            allowed_types.add(type(val))
-        allowed_types_list = list(allowed_types)
-        field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
-
-        command_parser.add_argument(
-            f"--{name}",
-            dest=name,
-            type=field_type,
-            default=default,
-            choices=allowed_values,
-            help=field.field_info.description,
-        )
-    else:
-        command_parser.add_argument(
-            f"--{name}",
-            dest=name,
-            type=field.type_,
-            default=default,
-            help=field.field_info.description,
-        )
-
-
-def add_parsers(
-    subparsers,
-    commands: list[type],
-    command_field: str = "type",
-    exclude_fields: list[str] = ["id", "type"],
-    add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None,
-):
-    """Adds parsers for each command to the subparsers"""
-
-    # Create subparsers for each command
-    for command in commands:
-        hints = get_type_hints(command)
-        cmd_name = get_args(hints[command_field])[0]
-        command_parser = subparsers.add_parser(cmd_name, help=command.__doc__)
-
-        if add_arguments is not None:
-            add_arguments(command_parser)
-
-        # Convert all fields to arguments
-        fields = command.__fields__  # type: ignore
-        for name, field in fields.items():
-            if name in exclude_fields:
-                continue
-
-            add_field_argument(command_parser, name, field)
-
-
-def add_graph_parsers(
-    subparsers, graphs: list[LibraryGraph], add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None
-):
-    for graph in graphs:
-        command_parser = subparsers.add_parser(graph.name, help=graph.description)
-
-        if add_arguments is not None:
-            add_arguments(command_parser)
-
-        # Add arguments for inputs
-        for exposed_input in graph.exposed_inputs:
-            node = graph.graph.get_node(exposed_input.node_path)
-            field = node.__fields__[exposed_input.field]
-            default_override = getattr(node, exposed_input.field)
-            add_field_argument(command_parser, exposed_input.alias, field, default_override)
-
-
-class CliContext:
-    invoker: Invoker
-    session: GraphExecutionState
-    parser: argparse.ArgumentParser
-    defaults: dict[str, Any]
-    graph_nodes: dict[str, str]
-    nodes_added: list[str]
-
-    def __init__(self, invoker: Invoker, session: GraphExecutionState, parser: argparse.ArgumentParser):
-        self.invoker = invoker
-        self.session = session
-        self.parser = parser
-        self.defaults = dict()
-        self.graph_nodes = dict()
-        self.nodes_added = list()
-
-    def get_session(self):
-        self.session = self.invoker.services.graph_execution_manager.get(self.session.id)
-        return self.session
-
-    def reset(self):
-        self.session = self.invoker.create_execution_state()
-        self.graph_nodes = dict()
-        self.nodes_added = list()
-        # Leave defaults unchanged
-
-    def add_node(self, node: BaseInvocation):
-        self.get_session()
-        self.session.graph.add_node(node)
-        self.nodes_added.append(node.id)
-        self.invoker.services.graph_execution_manager.set(self.session)
-
-    def add_edge(self, edge: Edge):
-        self.get_session()
-        self.session.add_edge(edge)
-        self.invoker.services.graph_execution_manager.set(self.session)
-
-
-class ExitCli(Exception):
-    """Exception to exit the CLI"""
-
-    pass
-
-
-class BaseCommand(ABC, BaseModel):
-    """A CLI command"""
-
-    # All commands must include a type name like this:
-    # type: Literal['your_command_name'] = 'your_command_name'
-
-    @classmethod
-    def get_all_subclasses(cls):
-        subclasses = []
-        toprocess = [cls]
-        while len(toprocess) > 0:
-            next = toprocess.pop(0)
-            next_subclasses = next.__subclasses__()
-            subclasses.extend(next_subclasses)
-            toprocess.extend(next_subclasses)
-        return subclasses
-
-    @classmethod
-    def get_commands(cls):
-        return tuple(BaseCommand.get_all_subclasses())
-
-    @classmethod
-    def get_commands_map(cls):
-        # Get the type strings out of the literals and into a dictionary
-        return dict(map(lambda t: (get_args(get_type_hints(t)["type"])[0], t), BaseCommand.get_all_subclasses()))
-
-    @abstractmethod
-    def run(self, context: CliContext) -> None:
-        """Run the command. Raise ExitCli to exit."""
-        pass
-
-
-class ExitCommand(BaseCommand):
-    """Exits the CLI"""
-
-    type: Literal["exit"] = "exit"
-
-    def run(self, context: CliContext) -> None:
-        raise ExitCli()
-
-
-class HelpCommand(BaseCommand):
-    """Shows help"""
-
-    type: Literal["help"] = "help"
-
-    def run(self, context: CliContext) -> None:
-        context.parser.print_help()
-
-
-def get_graph_execution_history(
-    graph_execution_state: GraphExecutionState,
-) -> Iterable[str]:
-    """Gets the history of fully-executed invocations for a graph execution"""
-    return (n for n in reversed(graph_execution_state.executed_history) if n in graph_execution_state.graph.nodes)
-
-
-def get_invocation_command(invocation) -> str:
-    fields = invocation.__fields__.items()
-    type_hints = get_type_hints(type(invocation))
-    command = [invocation.type]
-    for name, field in fields:
-        if name in ["id", "type"]:
-            continue
-
-        # TODO: add links
-
-        # Skip image fields when serializing command
-        type_hint = type_hints.get(name) or None
-        if type_hint is ImageField or ImageField in get_args(type_hint):
-            continue
-
-        field_value = getattr(invocation, name)
-        field_default = field.default
-        if field_value != field_default:
-            if type_hint is str or str in get_args(type_hint):
-                command.append(f'--{name} "{field_value}"')
-            else:
-                command.append(f"--{name} {field_value}")
-
-    return " ".join(command)
-
-
-class HistoryCommand(BaseCommand):
-    """Shows the invocation history"""
-
-    type: Literal["history"] = "history"
-
-    # Inputs
-    # fmt: off
-    count: int = Field(default=5, gt=0, description="The number of history entries to show")
-    # fmt: on
-
-    def run(self, context: CliContext) -> None:
-        history = list(get_graph_execution_history(context.get_session()))
-        for i in range(min(self.count, len(history))):
-            entry_id = history[-1 - i]
-            entry = context.get_session().graph.get_node(entry_id)
-            logger.info(f"{entry_id}: {get_invocation_command(entry)}")
-
-
-class SetDefaultCommand(BaseCommand):
-    """Sets a default value for a field"""
-
-    type: Literal["default"] = "default"
-
-    # Inputs
-    # fmt: off
-    field: str = Field(description="The field to set the default for")
-    value: str = Field(description="The value to set the default to, or None to clear the default")
-    # fmt: on
-
-    def run(self, context: CliContext) -> None:
-        if self.value is None:
-            if self.field in context.defaults:
-                del context.defaults[self.field]
-        else:
-            context.defaults[self.field] = self.value
-
-
-class DrawGraphCommand(BaseCommand):
-    """Debugs a graph"""
-
-    type: Literal["draw_graph"] = "draw_graph"
-
-    def run(self, context: CliContext) -> None:
-        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
-        nxgraph = session.graph.nx_graph_flat()
-
-        # Draw the networkx graph
-        plt.figure(figsize=(20, 20))
-        pos = nx.spectral_layout(nxgraph)
-        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
-        nx.draw_networkx_edges(nxgraph, pos, width=2)
-        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
-        plt.axis("off")
-        plt.show()
-
-
-class DrawExecutionGraphCommand(BaseCommand):
-    """Debugs an execution graph"""
-
-    type: Literal["draw_xgraph"] = "draw_xgraph"
-
-    def run(self, context: CliContext) -> None:
-        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
-        nxgraph = session.execution_graph.nx_graph_flat()
-
-        # Draw the networkx graph
-        plt.figure(figsize=(20, 20))
-        pos = nx.spectral_layout(nxgraph)
-        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
-        nx.draw_networkx_edges(nxgraph, pos, width=2)
-        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
-        plt.axis("off")
-        plt.show()
-
-
-class SortedHelpFormatter(argparse.HelpFormatter):
-    def _iter_indented_subactions(self, action):
-        try:
-            get_subactions = action._get_subactions
-        except AttributeError:
-            pass
-        else:
-            self._indent()
-            if isinstance(action, argparse._SubParsersAction):
-                for subaction in sorted(get_subactions(), key=lambda x: x.dest):
-                    yield subaction
-            else:
-                for subaction in get_subactions():
-                    yield subaction
-                self._dedent()

invokeai/app/cli/completer.py

@@ -1,171 +0,0 @@
-"""
-Readline helper functions for cli_app.py
-You may import the global singleton `completer` to get access to the
-completer object.
-"""
-import atexit
-import readline
-import shlex
-from pathlib import Path
-from typing import Dict, List, Literal, get_args, get_origin, get_type_hints
-
-import invokeai.backend.util.logging as logger
-
-from ...backend import ModelManager
-from ..invocations.baseinvocation import BaseInvocation
-from ..services.invocation_services import InvocationServices
-from .commands import BaseCommand
-
-# singleton object, class variable
-completer = None
-
-
-class Completer(object):
-    def __init__(self, model_manager: ModelManager):
-        self.commands = self.get_commands()
-        self.matches = None
-        self.linebuffer = None
-        self.manager = model_manager
-        return
-
-    def complete(self, text, state):
-        """
-        Complete commands and switches fromm the node CLI command line.
-        Switches are determined in a context-specific manner.
-        """
-
-        buffer = readline.get_line_buffer()
-        if state == 0:
-            options = None
-            try:
-                current_command, current_switch = self.get_current_command(buffer)
-                options = self.get_command_options(current_command, current_switch)
-            except IndexError:
-                pass
-            options = options or list(self.parse_commands().keys())
-
-            if not text:  # first time
-                self.matches = options
-            else:
-                self.matches = [s for s in options if s and s.startswith(text)]
-
-        try:
-            match = self.matches[state]
-        except IndexError:
-            match = None
-        return match
-
-    @classmethod
-    def get_commands(self) -> List[object]:
-        """
-        Return a list of all the client commands and invocations.
-        """
-        return BaseCommand.get_commands() + BaseInvocation.get_invocations()
-
-    def get_current_command(self, buffer: str) -> tuple[str, str]:
-        """
-        Parse the readline buffer to find the most recent command and its switch.
-        """
-        if len(buffer) == 0:
-            return None, None
-        tokens = shlex.split(buffer)
-        command = None
-        switch = None
-        for t in tokens:
-            if t[0].isalpha():
-                if switch is None:
-                    command = t
-            else:
-                switch = t
-        # don't try to autocomplete switches that are already complete
-        if switch and buffer.endswith(" "):
-            switch = None
-        return command or "", switch or ""
-
-    def parse_commands(self) -> Dict[str, List[str]]:
-        """
-        Return a dict in which the keys are the command name
-        and the values are the parameters the command takes.
-        """
-        result = dict()
-        for command in self.commands:
-            hints = get_type_hints(command)
-            name = get_args(hints["type"])[0]
-            result.update({name: hints})
-        return result
-
-    def get_command_options(self, command: str, switch: str) -> List[str]:
-        """
-        Return all the parameters that can be passed to the command as
-        command-line switches. Returns None if the command is unrecognized.
-        """
-        parsed_commands = self.parse_commands()
-        if command not in parsed_commands:
-            return None
-
-        # handle switches in the format "-foo=bar"
-        argument = None
-        if switch and "=" in switch:
-            switch, argument = switch.split("=")
-
-        parameter = switch.strip("-")
-        if parameter in parsed_commands[command]:
-            if argument is None:
-                return self.get_parameter_options(parameter, parsed_commands[command][parameter])
-            else:
-                return [
-                    f"--{parameter}={x}"
-                    for x in self.get_parameter_options(parameter, parsed_commands[command][parameter])
-                ]
-        else:
-            return [f"--{x}" for x in parsed_commands[command].keys()]
-
-    def get_parameter_options(self, parameter: str, typehint) -> List[str]:
-        """
-        Given a parameter type (such as Literal), offers autocompletions.
-        """
-        if get_origin(typehint) == Literal:
-            return get_args(typehint)
-        if parameter == "model":
-            return self.manager.model_names()
-
-    def _pre_input_hook(self):
-        if self.linebuffer:
-            readline.insert_text(self.linebuffer)
-            readline.redisplay()
-            self.linebuffer = None
-
-
-def set_autocompleter(services: InvocationServices) -> Completer:
-    global completer
-
-    if completer:
-        return completer
-
-    completer = Completer(services.model_manager)
-
-    readline.set_completer(completer.complete)
-    try:
-        readline.set_auto_history(True)
-    except AttributeError:
-        # pyreadline3 does not have a set_auto_history() method
-        pass
-    readline.set_pre_input_hook(completer._pre_input_hook)
-    readline.set_completer_delims(" ")
-    readline.parse_and_bind("tab: complete")
-    readline.parse_and_bind("set print-completions-horizontally off")
-    readline.parse_and_bind("set page-completions on")
-    readline.parse_and_bind("set skip-completed-text on")
-    readline.parse_and_bind("set show-all-if-ambiguous on")
-
-    histfile = Path(services.configuration.root_dir / ".invoke_history")
-    try:
-        readline.read_history_file(histfile)
-        readline.set_history_length(1000)
-    except FileNotFoundError:
-        pass
-    except OSError:  # file likely corrupted
-        newname = f"{histfile}.old"
-        logger.error(f"Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}")
-        histfile.replace(Path(newname))
-    atexit.register(readline.write_history_file, histfile)

invokeai/app/cli_app.py

@@ -1,484 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
-
-from invokeai.app.services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
-
-from .services.config import InvokeAIAppConfig
-
-# parse_args() must be called before any other imports. if it is not called first, consumers of the config
-# which are imported/used before parse_args() is called will get the default config values instead of the
-# values from the command line or config file.
-
-if True:  # hack to make flake8 happy with imports coming after setting up the config
-    import argparse
-    import re
-    import shlex
-    import sqlite3
-    import sys
-    import time
-    from typing import Optional, Union, get_type_hints
-
-    import torch
-    from pydantic import BaseModel, ValidationError
-    from pydantic.fields import Field
-
-    import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
-    from invokeai.app.services.board_image_record_storage import SqliteBoardImageRecordStorage
-    from invokeai.app.services.board_images import BoardImagesService, BoardImagesServiceDependencies
-    from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
-    from invokeai.app.services.boards import BoardService, BoardServiceDependencies
-    from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-    from invokeai.app.services.images import ImageService, ImageServiceDependencies
-    from invokeai.app.services.invocation_stats import InvocationStatsService
-    from invokeai.app.services.resource_name import SimpleNameService
-    from invokeai.app.services.urls import LocalUrlService
-    from invokeai.backend.util.logging import InvokeAILogger
-    from invokeai.version.invokeai_version import __version__
-
-    from .cli.commands import BaseCommand, CliContext, ExitCli, SortedHelpFormatter, add_graph_parsers, add_parsers
-    from .cli.completer import set_autocompleter
-    from .invocations.baseinvocation import BaseInvocation
-    from .services.default_graphs import create_system_graphs, default_text_to_image_graph_id
-    from .services.events import EventServiceBase
-    from .services.graph import (
-        Edge,
-        EdgeConnection,
-        GraphExecutionState,
-        GraphInvocation,
-        LibraryGraph,
-        are_connection_types_compatible,
-    )
-    from .services.image_file_storage import DiskImageFileStorage
-    from .services.invocation_queue import MemoryInvocationQueue
-    from .services.invocation_services import InvocationServices
-    from .services.invoker import Invoker
-    from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-    from .services.model_manager_service import ModelManagerService
-    from .services.processor import DefaultInvocationProcessor
-    from .services.sqlite import SqliteItemStorage
-
-    if torch.backends.mps.is_available():
-        import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
-
-config = InvokeAIAppConfig.get_config()
-config.parse_args()
-logger = InvokeAILogger().get_logger(config=config)
-
-
-class CliCommand(BaseModel):
-    command: Union[BaseCommand.get_commands() + BaseInvocation.get_invocations()] = Field(discriminator="type")  # type: ignore
-
-
-class InvalidArgs(Exception):
-    pass
-
-
-def add_invocation_args(command_parser):
-    # Add linking capability
-    command_parser.add_argument(
-        "--link",
-        "-l",
-        action="append",
-        nargs=3,
-        help="A link in the format 'source_node source_field dest_field'. source_node can be relative to history (e.g. -1)",
-    )
-
-    command_parser.add_argument(
-        "--link_node",
-        "-ln",
-        action="append",
-        help="A link from all fields in the specified node. Node can be relative to history (e.g. -1)",
-    )
-
-
-def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
-    # Create invocation parser
-    parser = argparse.ArgumentParser(formatter_class=SortedHelpFormatter)
-
-    def exit(*args, **kwargs):
-        raise InvalidArgs
-
-    parser.exit = exit
-    subparsers = parser.add_subparsers(dest="type")
-
-    # Create subparsers for each invocation
-    invocations = BaseInvocation.get_all_subclasses()
-    add_parsers(subparsers, invocations, add_arguments=add_invocation_args)
-
-    # Create subparsers for each command
-    commands = BaseCommand.get_all_subclasses()
-    add_parsers(subparsers, commands, exclude_fields=["type"])
-
-    # Create subparsers for exposed CLI graphs
-    # TODO: add a way to identify these graphs
-    text_to_image = services.graph_library.get(default_text_to_image_graph_id)
-    add_graph_parsers(subparsers, [text_to_image], add_arguments=add_invocation_args)
-
-    return parser
-
-
-class NodeField:
-    alias: str
-    node_path: str
-    field: str
-    field_type: type
-
-    def __init__(self, alias: str, node_path: str, field: str, field_type: type):
-        self.alias = alias
-        self.node_path = node_path
-        self.field = field
-        self.field_type = field_type
-
-
-def fields_from_type_hints(hints: dict[str, type], node_path: str) -> dict[str, NodeField]:
-    return {k: NodeField(alias=k, node_path=node_path, field=k, field_type=v) for k, v in hints.items()}
-
-
-def get_node_input_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
-    """Gets the node field for the specified field alias"""
-    exposed_input = next(e for e in graph.exposed_inputs if e.alias == field_alias)
-    node_type = type(graph.graph.get_node(exposed_input.node_path))
-    return NodeField(
-        alias=exposed_input.alias,
-        node_path=f"{node_id}.{exposed_input.node_path}",
-        field=exposed_input.field,
-        field_type=get_type_hints(node_type)[exposed_input.field],
-    )
-
-
-def get_node_output_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
-    """Gets the node field for the specified field alias"""
-    exposed_output = next(e for e in graph.exposed_outputs if e.alias == field_alias)
-    node_type = type(graph.graph.get_node(exposed_output.node_path))
-    node_output_type = node_type.get_output_type()
-    return NodeField(
-        alias=exposed_output.alias,
-        node_path=f"{node_id}.{exposed_output.node_path}",
-        field=exposed_output.field,
-        field_type=get_type_hints(node_output_type)[exposed_output.field],
-    )
-
-
-def get_node_inputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
-    """Gets the inputs for the specified invocation from the context"""
-    node_type = type(invocation)
-    if node_type is not GraphInvocation:
-        return fields_from_type_hints(get_type_hints(node_type), invocation.id)
-    else:
-        graph: LibraryGraph = context.invoker.services.graph_library.get(context.graph_nodes[invocation.id])
-        return {e.alias: get_node_input_field(graph, e.alias, invocation.id) for e in graph.exposed_inputs}
-
-
-def get_node_outputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
-    """Gets the outputs for the specified invocation from the context"""
-    node_type = type(invocation)
-    if node_type is not GraphInvocation:
-        return fields_from_type_hints(get_type_hints(node_type.get_output_type()), invocation.id)
-    else:
-        graph: LibraryGraph = context.invoker.services.graph_library.get(context.graph_nodes[invocation.id])
-        return {e.alias: get_node_output_field(graph, e.alias, invocation.id) for e in graph.exposed_outputs}
-
-
-def generate_matching_edges(a: BaseInvocation, b: BaseInvocation, context: CliContext) -> list[Edge]:
-    """Generates all possible edges between two invocations"""
-    afields = get_node_outputs(a, context)
-    bfields = get_node_inputs(b, context)
-
-    matching_fields = set(afields.keys()).intersection(bfields.keys())
-
-    # Remove invalid fields
-    invalid_fields = set(["type", "id"])
-    matching_fields = matching_fields.difference(invalid_fields)
-
-    # Validate types
-    matching_fields = [
-        f for f in matching_fields if are_connection_types_compatible(afields[f].field_type, bfields[f].field_type)
-    ]
-
-    edges = [
-        Edge(
-            source=EdgeConnection(node_id=afields[alias].node_path, field=afields[alias].field),
-            destination=EdgeConnection(node_id=bfields[alias].node_path, field=bfields[alias].field),
-        )
-        for alias in matching_fields
-    ]
-    return edges
-
-
-class SessionError(Exception):
-    """Raised when a session error has occurred"""
-
-    pass
-
-
-def invoke_all(context: CliContext):
-    """Runs all invocations in the specified session"""
-    context.invoker.invoke(context.session, invoke_all=True)
-    while not context.get_session().is_complete():
-        # Wait some time
-        time.sleep(0.1)
-
-    # Print any errors
-    if context.session.has_error():
-        for n in context.session.errors:
-            context.invoker.services.logger.error(
-                f"Error in node {n} (source node {context.session.prepared_source_mapping[n]}): {context.session.errors[n]}"
-            )
-
-        raise SessionError()
-
-
-def invoke_cli():
-    logger.info(f"InvokeAI version {__version__}")
-    # get the optional list of invocations to execute on the command line
-    parser = config.get_parser()
-    parser.add_argument("commands", nargs="*")
-    invocation_commands = parser.parse_args().commands
-
-    # get the optional file to read commands from.
-    # Simplest is to use it for STDIN
-    if infile := config.from_file:
-        sys.stdin = open(infile, "r")
-
-    model_manager = ModelManagerService(config, logger)
-
-    events = EventServiceBase()
-    output_folder = config.output_path
-
-    # TODO: build a file/path manager?
-    if config.use_memory_db:
-        db_location = ":memory:"
-    else:
-        db_location = config.db_path
-        db_location.parent.mkdir(parents=True, exist_ok=True)
-
-    db_conn = sqlite3.connect(db_location, check_same_thread=False)  # TODO: figure out a better threading solution
-    logger.info(f'InvokeAI database location is "{db_location}"')
-
-    graph_execution_manager = SqliteItemStorage[GraphExecutionState](conn=db_conn, table_name="graph_executions")
-
-    urls = LocalUrlService()
-    image_record_storage = SqliteImageRecordStorage(conn=db_conn)
-    image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
-    names = SimpleNameService()
-
-    board_record_storage = SqliteBoardRecordStorage(conn=db_conn)
-    board_image_record_storage = SqliteBoardImageRecordStorage(conn=db_conn)
-
-    boards = BoardService(
-        services=BoardServiceDependencies(
-            board_image_record_storage=board_image_record_storage,
-            board_record_storage=board_record_storage,
-            image_record_storage=image_record_storage,
-            url=urls,
-            logger=logger,
-        )
-    )
-
-    board_images = BoardImagesService(
-        services=BoardImagesServiceDependencies(
-            board_image_record_storage=board_image_record_storage,
-            board_record_storage=board_record_storage,
-            image_record_storage=image_record_storage,
-            url=urls,
-            logger=logger,
-        )
-    )
-
-    images = ImageService(
-        services=ImageServiceDependencies(
-            board_image_record_storage=board_image_record_storage,
-            image_record_storage=image_record_storage,
-            image_file_storage=image_file_storage,
-            url=urls,
-            logger=logger,
-            names=names,
-            graph_execution_manager=graph_execution_manager,
-        )
-    )
-
-    services = InvocationServices(
-        model_manager=model_manager,
-        events=events,
-        latents=ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents")),
-        images=images,
-        boards=boards,
-        board_images=board_images,
-        queue=MemoryInvocationQueue(),
-        graph_library=SqliteItemStorage[LibraryGraph](conn=db_conn, table_name="graphs"),
-        graph_execution_manager=graph_execution_manager,
-        processor=DefaultInvocationProcessor(),
-        performance_statistics=InvocationStatsService(graph_execution_manager),
-        logger=logger,
-        configuration=config,
-        invocation_cache=MemoryInvocationCache(max_cache_size=config.node_cache_size),
-    )
-
-    system_graphs = create_system_graphs(services.graph_library)
-    system_graph_names = set([g.name for g in system_graphs])
-    set_autocompleter(services)
-
-    invoker = Invoker(services)
-    session: GraphExecutionState = invoker.create_execution_state()
-    parser = get_command_parser(services)
-
-    re_negid = re.compile("^-[0-9]+$")
-
-    # Uncomment to print out previous sessions at startup
-    # print(services.session_manager.list())
-
-    context = CliContext(invoker, session, parser)
-    set_autocompleter(services)
-
-    command_line_args_exist = len(invocation_commands) > 0
-    done = False
-
-    while not done:
-        try:
-            if command_line_args_exist:
-                cmd_input = invocation_commands.pop(0)
-                done = len(invocation_commands) == 0
-            else:
-                cmd_input = input("invoke> ")
-        except (KeyboardInterrupt, EOFError):
-            # Ctrl-c exits
-            break
-
-        try:
-            # Refresh the state of the session
-            # history = list(get_graph_execution_history(context.session))
-            history = list(reversed(context.nodes_added))
-
-            # Split the command for piping
-            cmds = cmd_input.split("|")
-            start_id = len(context.nodes_added)
-            current_id = start_id
-            new_invocations = list()
-            for cmd in cmds:
-                if cmd is None or cmd.strip() == "":
-                    raise InvalidArgs("Empty command")
-
-                # Parse args to create invocation
-                args = vars(context.parser.parse_args(shlex.split(cmd.strip())))
-
-                # Override defaults
-                for field_name, field_default in context.defaults.items():
-                    if field_name in args:
-                        args[field_name] = field_default
-
-                # Parse invocation
-                command: CliCommand = None  # type:ignore
-                system_graph: Optional[LibraryGraph] = None
-                if args["type"] in system_graph_names:
-                    system_graph = next(filter(lambda g: g.name == args["type"], system_graphs))
-                    invocation = GraphInvocation(graph=system_graph.graph, id=str(current_id))
-                    for exposed_input in system_graph.exposed_inputs:
-                        if exposed_input.alias in args:
-                            node = invocation.graph.get_node(exposed_input.node_path)
-                            field = exposed_input.field
-                            setattr(node, field, args[exposed_input.alias])
-                    command = CliCommand(command=invocation)
-                    context.graph_nodes[invocation.id] = system_graph.id
-                else:
-                    args["id"] = current_id
-                    command = CliCommand(command=args)
-
-                if command is None:
-                    continue
-
-                # Run any CLI commands immediately
-                if isinstance(command.command, BaseCommand):
-                    # Invoke all current nodes to preserve operation order
-                    invoke_all(context)
-
-                    # Run the command
-                    command.command.run(context)
-                    continue
-
-                # TODO: handle linking with library graphs
-                # Pipe previous command output (if there was a previous command)
-                edges: list[Edge] = list()
-                if len(history) > 0 or current_id != start_id:
-                    from_id = history[0] if current_id == start_id else str(current_id - 1)
-                    from_node = (
-                        next(filter(lambda n: n[0].id == from_id, new_invocations))[0]
-                        if current_id != start_id
-                        else context.session.graph.get_node(from_id)
-                    )
-                    matching_edges = generate_matching_edges(from_node, command.command, context)
-                    edges.extend(matching_edges)
-
-                # Parse provided links
-                if "link_node" in args and args["link_node"]:
-                    for link in args["link_node"]:
-                        node_id = link
-                        if re_negid.match(node_id):
-                            node_id = str(current_id + int(node_id))
-
-                        link_node = context.session.graph.get_node(node_id)
-                        matching_edges = generate_matching_edges(link_node, command.command, context)
-                        matching_destinations = [e.destination for e in matching_edges]
-                        edges = [e for e in edges if e.destination not in matching_destinations]
-                        edges.extend(matching_edges)
-
-                if "link" in args and args["link"]:
-                    for link in args["link"]:
-                        edges = [
-                            e
-                            for e in edges
-                            if e.destination.node_id != command.command.id or e.destination.field != link[2]
-                        ]
-
-                        node_id = link[0]
-                        if re_negid.match(node_id):
-                            node_id = str(current_id + int(node_id))
-
-                        # TODO: handle missing input/output
-                        node_output = get_node_outputs(context.session.graph.get_node(node_id), context)[link[1]]
-                        node_input = get_node_inputs(command.command, context)[link[2]]
-
-                        edges.append(
-                            Edge(
-                                source=EdgeConnection(node_id=node_output.node_path, field=node_output.field),
-                                destination=EdgeConnection(node_id=node_input.node_path, field=node_input.field),
-                            )
-                        )
-
-                new_invocations.append((command.command, edges))
-
-                current_id = current_id + 1
-
-                # Add the node to the session
-                context.add_node(command.command)
-                for edge in edges:
-                    print(edge)
-                    context.add_edge(edge)
-
-            # Execute all remaining nodes
-            invoke_all(context)
-
-        except InvalidArgs:
-            invoker.services.logger.warning('Invalid command, use "help" to list commands')
-            continue
-
-        except ValidationError:
-            invoker.services.logger.warning('Invalid command arguments, run "<command> --help" for summary')
-
-        except SessionError:
-            # Start a new session
-            invoker.services.logger.warning("Session error: creating a new session")
-            context.reset()
-
-        except ExitCli:
-            break
-
-        except SystemExit:
-            continue
-
-    invoker.stop()
-
-
-if __name__ == "__main__":
-    if config.version:
-        print(f"InvokeAI version {__version__}")
-    else:
-        invoke_cli()

invokeai/app/invocations/__init__.py

@@ -1,8 +1,28 @@
-import os
+import shutil
+import sys
+from importlib.util import module_from_spec, spec_from_file_location
+from pathlib import Path
 
-__all__ = []
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
 
-dirname = os.path.dirname(os.path.abspath(__file__))
-for f in os.listdir(dirname):
-    if f != "__init__.py" and os.path.isfile("%s/%s" % (dirname, f)) and f[-3:] == ".py":
-        __all__.append(f[:-3])
+custom_nodes_path = Path(InvokeAIAppConfig.get_config().custom_nodes_path.absolute())
+custom_nodes_path.mkdir(parents=True, exist_ok=True)
+
+custom_nodes_init_path = str(custom_nodes_path / "__init__.py")
+custom_nodes_readme_path = str(custom_nodes_path / "README.md")
+
+# copy our custom nodes __init__.py to the custom nodes directory
+shutil.copy(Path(__file__).parent / "custom_nodes/init.py", custom_nodes_init_path)
+shutil.copy(Path(__file__).parent / "custom_nodes/README.md", custom_nodes_readme_path)
+
+# Import custom nodes, see https://docs.python.org/3/library/importlib.html#importing-programmatically
+spec = spec_from_file_location("custom_nodes", custom_nodes_init_path)
+if spec is None or spec.loader is None:
+    raise RuntimeError(f"Could not load custom nodes from {custom_nodes_init_path}")
+module = module_from_spec(spec)
+sys.modules[spec.name] = module
+spec.loader.exec_module(module)
+
+# add core nodes to __all__
+python_files = filter(lambda f: not f.name.startswith("_"), Path(__file__).parent.glob("*.py"))
+__all__ = list(f.stem for f in python_files)  # type: ignore

invokeai/app/invocations/baseinvocation.py

@@ -2,33 +2,21 @@
 
 from __future__ import annotations
 
-import json
+import inspect
 import re
 from abc import ABC, abstractmethod
 from enum import Enum
 from inspect import signature
-from typing import (
-    TYPE_CHECKING,
-    AbstractSet,
-    Any,
-    Callable,
-    ClassVar,
-    Literal,
-    Mapping,
-    Optional,
-    Type,
-    TypeVar,
-    Union,
-    get_args,
-    get_type_hints,
-)
+from types import UnionType
+from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union
 
 import semver
-from pydantic import BaseModel, Field, validator
-from pydantic.fields import ModelField, Undefined
-from pydantic.typing import NoArgAnyCallable
+from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter, create_model
+from pydantic.fields import FieldInfo, _Unset
+from pydantic_core import PydanticUndefined
 
-from invokeai.app.services.config.invokeai_config import InvokeAIAppConfig
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.util.misc import uuid_string
 
 if TYPE_CHECKING:
     from ..services.invocation_services import InvocationServices
@@ -38,6 +26,10 @@ class InvalidVersionError(ValueError):
     pass
 
 
+class InvalidFieldError(TypeError):
+    pass
+
+
 class FieldDescriptions:
     denoising_start = "When to start denoising, expressed a percentage of total steps"
     denoising_end = "When to stop denoising, expressed a percentage of total steps"
@@ -68,10 +60,16 @@ class FieldDescriptions:
     height = "Height of output (px)"
     control = "ControlNet(s) to apply"
     ip_adapter = "IP-Adapter to apply"
+    t2i_adapter = "T2I-Adapter(s) to apply"
     denoised_latents = "Denoised latents tensor"
     latents = "Latents tensor"
     strength = "Strength of denoising (proportional to steps)"
-    core_metadata = "Optional core metadata to be written to image"
+    metadata = "Optional metadata to be saved with the image"
+    metadata_collection = "Collection of Metadata"
+    metadata_item_polymorphic = "A single metadata item or collection of metadata items"
+    metadata_item_label = "Label for this metadata item"
+    metadata_item_value = "The value for this metadata item (may be any type)"
+    workflow = "Optional workflow to be saved with the image"
     interp_mode = "Interpolation mode"
     torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
     fp32 = "Whether or not to use full float32 precision"
@@ -91,6 +89,9 @@ class FieldDescriptions:
     board = "The board to save the image to"
     image = "The image to process"
     tile_size = "Tile size"
+    inclusive_low = "The inclusive low value"
+    exclusive_high = "The exclusive high value"
+    decimal_places = "The number of decimal places to round to"
 
 
 class Input(str, Enum):
@@ -175,8 +176,12 @@ class UIType(str, Enum):
     Scheduler = "Scheduler"
     WorkflowField = "WorkflowField"
     IsIntermediate = "IsIntermediate"
-    MetadataField = "MetadataField"
     BoardField = "BoardField"
+    Any = "Any"
+    MetadataItem = "MetadataItem"
+    MetadataItemCollection = "MetadataItemCollection"
+    MetadataItemPolymorphic = "MetadataItemPolymorphic"
+    MetadataDict = "MetadataDict"
     # endregion
 
 
@@ -207,6 +212,11 @@ class _InputField(BaseModel):
     ui_choice_labels: Optional[dict[str, str]]
     item_default: Optional[Any]
 
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
 
 class _OutputField(BaseModel):
     """
@@ -220,34 +230,36 @@ class _OutputField(BaseModel):
     ui_type: Optional[UIType]
     ui_order: Optional[int]
 
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+def get_type(klass: BaseModel) -> str:
+    """Helper function to get an invocation or invocation output's type. This is the default value of the `type` field."""
+    return klass.model_fields["type"].default
+
 
 def InputField(
-    *args: Any,
-    default: Any = Undefined,
-    default_factory: Optional[NoArgAnyCallable] = None,
-    alias: Optional[str] = None,
-    title: Optional[str] = None,
-    description: Optional[str] = None,
-    exclude: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
-    include: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
-    const: Optional[bool] = None,
-    gt: Optional[float] = None,
-    ge: Optional[float] = None,
-    lt: Optional[float] = None,
-    le: Optional[float] = None,
-    multiple_of: Optional[float] = None,
-    allow_inf_nan: Optional[bool] = None,
-    max_digits: Optional[int] = None,
-    decimal_places: Optional[int] = None,
-    min_items: Optional[int] = None,
-    max_items: Optional[int] = None,
-    unique_items: Optional[bool] = None,
-    min_length: Optional[int] = None,
-    max_length: Optional[int] = None,
-    allow_mutation: bool = True,
-    regex: Optional[str] = None,
-    discriminator: Optional[str] = None,
-    repr: bool = True,
+    # copied from pydantic's Field
+    default: Any = _Unset,
+    default_factory: Callable[[], Any] | None = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
     input: Input = Input.Any,
     ui_type: Optional[UIType] = None,
     ui_component: Optional[UIComponent] = None,
@@ -255,7 +267,6 @@ def InputField(
     ui_order: Optional[int] = None,
     ui_choice_labels: Optional[dict[str, str]] = None,
     item_default: Optional[Any] = None,
-    **kwargs: Any,
 ) -> Any:
     """
     Creates an input field for an invocation.
@@ -285,18 +296,27 @@ def InputField(
     : param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
 
     : param bool item_default: [None] Specifies the default item value, if this is a collection input. \
-      Ignored for non-collection fields..
+      Ignored for non-collection fields.
     """
-    return Field(
-        *args,
+
+    json_schema_extra_: dict[str, Any] = dict(
+        input=input,
+        ui_type=ui_type,
+        ui_component=ui_component,
+        ui_hidden=ui_hidden,
+        ui_order=ui_order,
+        item_default=item_default,
+        ui_choice_labels=ui_choice_labels,
+        _field_kind="input",
+    )
+
+    field_args = dict(
         default=default,
         default_factory=default_factory,
-        alias=alias,
         title=title,
         description=description,
-        exclude=exclude,
-        include=include,
-        const=const,
+        pattern=pattern,
+        strict=strict,
         gt=gt,
         ge=ge,
         lt=lt,
@@ -305,57 +325,92 @@ def InputField(
         allow_inf_nan=allow_inf_nan,
         max_digits=max_digits,
         decimal_places=decimal_places,
-        min_items=min_items,
-        max_items=max_items,
-        unique_items=unique_items,
         min_length=min_length,
         max_length=max_length,
-        allow_mutation=allow_mutation,
-        regex=regex,
-        discriminator=discriminator,
-        repr=repr,
-        input=input,
-        ui_type=ui_type,
-        ui_component=ui_component,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        item_default=item_default,
-        ui_choice_labels=ui_choice_labels,
-        **kwargs,
+    )
+
+    """
+    Invocation definitions have their fields typed correctly for their `invoke()` functions.
+    This typing is often more specific than the actual invocation definition requires, because
+    fields may have values provided only by connections.
+
+    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
+
+    `image` is required during the call to `invoke()`, but when the python class is instantiated,
+    the field may not be present. This is fine, because that image field will be provided by a
+    an ancestor node that outputs the image.
+
+    So we'd like to type that `image` field as `Optional[ImageField]`. If we do that, however, then
+    we need to handle a lot of extra logic in the `invoke()` function to check if the field has a
+    value or not. This is very tedious.
+
+    Ideally, the invocation definition would be able to specify that the field is required during
+    invocation, but optional during instantiation. So the field would be typed as `image: ImageField`,
+    but when calling the `invoke()` function, we raise an error if the field is not present.
+
+    To do this, we need to do a bit of fanagling to make the pydantic field optional, and then do
+    extra validation when calling `invoke()`.
+
+    There is some additional logic here to cleaning create the pydantic field via the wrapper.
+    """
+
+    # Filter out field args not provided
+    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
+
+    if (default is not PydanticUndefined) and (default_factory is not PydanticUndefined):
+        raise ValueError("Cannot specify both default and default_factory")
+
+    # because we are manually making fields optional, we need to store the original required bool for reference later
+    if default is PydanticUndefined and default_factory is PydanticUndefined:
+        json_schema_extra_.update(dict(orig_required=True))
+    else:
+        json_schema_extra_.update(dict(orig_required=False))
+
+    # make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
+    if (input is Input.Any or input is Input.Connection) and default_factory is PydanticUndefined:
+        default_ = None if default is PydanticUndefined else default
+        provided_args.update(dict(default=default_))
+        if default is not PydanticUndefined:
+            # before invoking, we'll grab the original default value and set it on the field if the field wasn't provided a value
+            json_schema_extra_.update(dict(default=default))
+            json_schema_extra_.update(dict(orig_default=default))
+    elif default is not PydanticUndefined and default_factory is PydanticUndefined:
+        default_ = default
+        provided_args.update(dict(default=default_))
+        json_schema_extra_.update(dict(orig_default=default_))
+    elif default_factory is not PydanticUndefined:
+        provided_args.update(dict(default_factory=default_factory))
+        # TODO: cannot serialize default_factory...
+        # json_schema_extra_.update(dict(orig_default_factory=default_factory))
+
+    return Field(
+        **provided_args,
+        json_schema_extra=json_schema_extra_,
     )
 
 
 def OutputField(
-    *args: Any,
-    default: Any = Undefined,
-    default_factory: Optional[NoArgAnyCallable] = None,
-    alias: Optional[str] = None,
-    title: Optional[str] = None,
-    description: Optional[str] = None,
-    exclude: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
-    include: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
-    const: Optional[bool] = None,
-    gt: Optional[float] = None,
-    ge: Optional[float] = None,
-    lt: Optional[float] = None,
-    le: Optional[float] = None,
-    multiple_of: Optional[float] = None,
-    allow_inf_nan: Optional[bool] = None,
-    max_digits: Optional[int] = None,
-    decimal_places: Optional[int] = None,
-    min_items: Optional[int] = None,
-    max_items: Optional[int] = None,
-    unique_items: Optional[bool] = None,
-    min_length: Optional[int] = None,
-    max_length: Optional[int] = None,
-    allow_mutation: bool = True,
-    regex: Optional[str] = None,
-    discriminator: Optional[str] = None,
-    repr: bool = True,
+    # copied from pydantic's Field
+    default: Any = _Unset,
+    default_factory: Callable[[], Any] | None = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
     ui_type: Optional[UIType] = None,
     ui_hidden: bool = False,
     ui_order: Optional[int] = None,
-    **kwargs: Any,
 ) -> Any:
     """
     Creates an output field for an invocation output.
@@ -375,15 +430,12 @@ def OutputField(
     : param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
     """
     return Field(
-        *args,
         default=default,
         default_factory=default_factory,
-        alias=alias,
         title=title,
         description=description,
-        exclude=exclude,
-        include=include,
-        const=const,
+        pattern=pattern,
+        strict=strict,
         gt=gt,
         ge=ge,
         lt=lt,
@@ -392,19 +444,14 @@ def OutputField(
         allow_inf_nan=allow_inf_nan,
         max_digits=max_digits,
         decimal_places=decimal_places,
-        min_items=min_items,
-        max_items=max_items,
-        unique_items=unique_items,
         min_length=min_length,
         max_length=max_length,
-        allow_mutation=allow_mutation,
-        regex=regex,
-        discriminator=discriminator,
-        repr=repr,
-        ui_type=ui_type,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        **kwargs,
+        json_schema_extra=dict(
+            ui_type=ui_type,
+            ui_hidden=ui_hidden,
+            ui_order=ui_order,
+            _field_kind="output",
+        ),
     )
 
 
@@ -418,7 +465,13 @@ class UIConfigBase(BaseModel):
     title: Optional[str] = Field(default=None, description="The node's display name")
     category: Optional[str] = Field(default=None, description="The node's category")
     version: Optional[str] = Field(
-        default=None, description='The node\'s version. Should be a valid semver string e.g. "1.0.0" or "3.8.13".'
+        default=None,
+        description='The node\'s version. Should be a valid semver string e.g. "1.0.0" or "3.8.13".',
+    )
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
     )
 
 
@@ -453,23 +506,39 @@ class BaseInvocationOutput(BaseModel):
     All invocation outputs must use the `@invocation_output` decorator to provide their unique type.
     """
 
-    @classmethod
-    def get_all_subclasses_tuple(cls):
-        subclasses = []
-        toprocess = [cls]
-        while len(toprocess) > 0:
-            next = toprocess.pop(0)
-            next_subclasses = next.__subclasses__()
-            subclasses.extend(next_subclasses)
-            toprocess.extend(next_subclasses)
-        return tuple(subclasses)
+    _output_classes: ClassVar[set[BaseInvocationOutput]] = set()
 
-    class Config:
-        @staticmethod
-        def schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
-            if "required" not in schema or not isinstance(schema["required"], list):
-                schema["required"] = list()
-            schema["required"].extend(["type"])
+    @classmethod
+    def register_output(cls, output: BaseInvocationOutput) -> None:
+        cls._output_classes.add(output)
+
+    @classmethod
+    def get_outputs(cls) -> Iterable[BaseInvocationOutput]:
+        return cls._output_classes
+
+    @classmethod
+    def get_outputs_union(cls) -> UnionType:
+        outputs_union = Union[tuple(cls._output_classes)]  # type: ignore [valid-type]
+        return outputs_union  # type: ignore [return-value]
+
+    @classmethod
+    def get_output_types(cls) -> Iterable[str]:
+        return map(lambda i: get_type(i), BaseInvocationOutput.get_outputs())
+
+    @staticmethod
+    def json_schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
+        # Because we use a pydantic Literal field with default value for the invocation type,
+        # it will be typed as optional in the OpenAPI schema. Make it required manually.
+        if "required" not in schema or not isinstance(schema["required"], list):
+            schema["required"] = list()
+        schema["required"].extend(["type"])
+
+    model_config = ConfigDict(
+        protected_namespaces=(),
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+        json_schema_extra=json_schema_extra,
+    )
 
 
 class RequiredConnectionException(Exception):
@@ -488,110 +557,94 @@ class MissingInputException(Exception):
 
 class BaseInvocation(ABC, BaseModel):
     """
-    A node to process inputs and produce outputs.
-    May use dependency injection in __init__ to receive providers.
-
     All invocations must use the `@invocation` decorator to provide their unique type.
     """
 
+    _invocation_classes: ClassVar[set[BaseInvocation]] = set()
+
     @classmethod
-    def get_all_subclasses(cls):
+    def register_invocation(cls, invocation: BaseInvocation) -> None:
+        cls._invocation_classes.add(invocation)
+
+    @classmethod
+    def get_invocations_union(cls) -> UnionType:
+        invocations_union = Union[tuple(cls._invocation_classes)]  # type: ignore [valid-type]
+        return invocations_union  # type: ignore [return-value]
+
+    @classmethod
+    def get_invocations(cls) -> Iterable[BaseInvocation]:
         app_config = InvokeAIAppConfig.get_config()
-        subclasses = []
-        toprocess = [cls]
-        while len(toprocess) > 0:
-            next = toprocess.pop(0)
-            next_subclasses = next.__subclasses__()
-            subclasses.extend(next_subclasses)
-            toprocess.extend(next_subclasses)
-        allowed_invocations = []
-        for sc in subclasses:
+        allowed_invocations: set[BaseInvocation] = set()
+        for sc in cls._invocation_classes:
+            invocation_type = get_type(sc)
             is_in_allowlist = (
-                sc.__fields__.get("type").default in app_config.allow_nodes
-                if isinstance(app_config.allow_nodes, list)
-                else True
+                invocation_type in app_config.allow_nodes if isinstance(app_config.allow_nodes, list) else True
             )
-
             is_in_denylist = (
-                sc.__fields__.get("type").default in app_config.deny_nodes
-                if isinstance(app_config.deny_nodes, list)
-                else False
+                invocation_type in app_config.deny_nodes if isinstance(app_config.deny_nodes, list) else False
             )
-
             if is_in_allowlist and not is_in_denylist:
-                allowed_invocations.append(sc)
+                allowed_invocations.add(sc)
         return allowed_invocations
 
     @classmethod
-    def get_invocations(cls):
-        return tuple(BaseInvocation.get_all_subclasses())
-
-    @classmethod
-    def get_invocations_map(cls):
+    def get_invocations_map(cls) -> dict[str, BaseInvocation]:
         # Get the type strings out of the literals and into a dictionary
         return dict(
             map(
-                lambda t: (get_args(get_type_hints(t)["type"])[0], t),
-                BaseInvocation.get_all_subclasses(),
+                lambda i: (get_type(i), i),
+                BaseInvocation.get_invocations(),
             )
         )
 
     @classmethod
-    def get_output_type(cls):
+    def get_invocation_types(cls) -> Iterable[str]:
+        return map(lambda i: get_type(i), BaseInvocation.get_invocations())
+
+    @classmethod
+    def get_output_type(cls) -> BaseInvocationOutput:
         return signature(cls.invoke).return_annotation
 
-    class Config:
-        validate_assignment = True
-        validate_all = True
-
-        @staticmethod
-        def schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
-            uiconfig = getattr(model_class, "UIConfig", None)
-            if uiconfig and hasattr(uiconfig, "title"):
-                schema["title"] = uiconfig.title
-            if uiconfig and hasattr(uiconfig, "tags"):
-                schema["tags"] = uiconfig.tags
-            if uiconfig and hasattr(uiconfig, "category"):
-                schema["category"] = uiconfig.category
-            if uiconfig and hasattr(uiconfig, "version"):
-                schema["version"] = uiconfig.version
-            if "required" not in schema or not isinstance(schema["required"], list):
-                schema["required"] = list()
-            schema["required"].extend(["type", "id"])
+    @staticmethod
+    def json_schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
+        # Add the various UI-facing attributes to the schema. These are used to build the invocation templates.
+        uiconfig = getattr(model_class, "UIConfig", None)
+        if uiconfig and hasattr(uiconfig, "title"):
+            schema["title"] = uiconfig.title
+        if uiconfig and hasattr(uiconfig, "tags"):
+            schema["tags"] = uiconfig.tags
+        if uiconfig and hasattr(uiconfig, "category"):
+            schema["category"] = uiconfig.category
+        if uiconfig and hasattr(uiconfig, "version"):
+            schema["version"] = uiconfig.version
+        if "required" not in schema or not isinstance(schema["required"], list):
+            schema["required"] = list()
+        schema["required"].extend(["type", "id"])
 
     @abstractmethod
     def invoke(self, context: InvocationContext) -> BaseInvocationOutput:
         """Invoke with provided context and return outputs."""
         pass
 
-    def __init__(self, **data):
-        # nodes may have required fields, that can accept input from connections
-        # on instantiation of the model, we need to exclude these from validation
-        restore = dict()
-        try:
-            field_names = list(self.__fields__.keys())
-            for field_name in field_names:
-                # if the field is required and may get its value from a connection, exclude it from validation
-                field = self.__fields__[field_name]
-                _input = field.field_info.extra.get("input", None)
-                if _input in [Input.Connection, Input.Any] and field.required:
-                    if field_name not in data:
-                        restore[field_name] = self.__fields__.pop(field_name)
-            # instantiate the node, which will validate the data
-            super().__init__(**data)
-        finally:
-            # restore the removed fields
-            for field_name, field in restore.items():
-                self.__fields__[field_name] = field
-
     def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
-        for field_name, field in self.__fields__.items():
-            _input = field.field_info.extra.get("input", None)
-            if field.required and not hasattr(self, field_name):
-                if _input == Input.Connection:
-                    raise RequiredConnectionException(self.__fields__["type"].default, field_name)
-                elif _input == Input.Any:
-                    raise MissingInputException(self.__fields__["type"].default, field_name)
+        for field_name, field in self.model_fields.items():
+            if not field.json_schema_extra or callable(field.json_schema_extra):
+                # something has gone terribly awry, we should always have this and it should be a dict
+                continue
+
+            # Here we handle the case where the field is optional in the pydantic class, but required
+            # in the `invoke()` method.
+
+            orig_default = field.json_schema_extra.get("orig_default", PydanticUndefined)
+            orig_required = field.json_schema_extra.get("orig_required", True)
+            input_ = field.json_schema_extra.get("input", None)
+            if orig_default is not PydanticUndefined and not hasattr(self, field_name):
+                setattr(self, field_name, orig_default)
+            if orig_required and orig_default is PydanticUndefined and getattr(self, field_name) is None:
+                if input_ == Input.Connection:
+                    raise RequiredConnectionException(self.model_fields["type"].default, field_name)
+                elif input_ == Input.Any:
+                    raise MissingInputException(self.model_fields["type"].default, field_name)
 
         # skip node cache codepath if it's disabled
         if context.services.configuration.node_cache_size == 0:
@@ -614,35 +667,96 @@ class BaseInvocation(ABC, BaseModel):
             return self.invoke(context)
 
     def get_type(self) -> str:
-        return self.__fields__["type"].default
+        return self.model_fields["type"].default
 
     id: str = Field(
-        description="The id of this instance of an invocation. Must be unique among all instances of invocations."
+        default_factory=uuid_string,
+        description="The id of this instance of an invocation. Must be unique among all instances of invocations.",
+        json_schema_extra=dict(_field_kind="internal"),
     )
-    is_intermediate: bool = InputField(
-        default=False, description="Whether or not this is an intermediate invocation.", ui_type=UIType.IsIntermediate
+    is_intermediate: bool = Field(
+        default=False,
+        description="Whether or not this is an intermediate invocation.",
+        json_schema_extra=dict(ui_type=UIType.IsIntermediate, _field_kind="internal"),
     )
-    workflow: Optional[str] = InputField(
-        default=None,
-        description="The workflow to save with the image",
-        ui_type=UIType.WorkflowField,
+    use_cache: bool = Field(
+        default=True, description="Whether or not to use the cache", json_schema_extra=dict(_field_kind="internal")
     )
-    use_cache: bool = InputField(default=True, description="Whether or not to use the cache")
-
-    @validator("workflow", pre=True)
-    def validate_workflow_is_json(cls, v):
-        if v is None:
-            return None
-        try:
-            json.loads(v)
-        except json.decoder.JSONDecodeError:
-            raise ValueError("Workflow must be valid JSON")
-        return v
 
     UIConfig: ClassVar[Type[UIConfigBase]]
 
+    model_config = ConfigDict(
+        protected_namespaces=(),
+        validate_assignment=True,
+        json_schema_extra=json_schema_extra,
+        json_schema_serialization_defaults_required=True,
+        coerce_numbers_to_str=True,
+    )
 
-GenericBaseInvocation = TypeVar("GenericBaseInvocation", bound=BaseInvocation)
+
+TBaseInvocation = TypeVar("TBaseInvocation", bound=BaseInvocation)
+
+
+RESERVED_INPUT_FIELD_NAMES = {
+    "id",
+    "is_intermediate",
+    "use_cache",
+    "type",
+    "workflow",
+    "metadata",
+}
+
+RESERVED_OUTPUT_FIELD_NAMES = {"type"}
+
+
+class _Model(BaseModel):
+    pass
+
+
+# Get all pydantic model attrs, methods, etc
+RESERVED_PYDANTIC_FIELD_NAMES = set(map(lambda m: m[0], inspect.getmembers(_Model())))
+
+
+def validate_fields(model_fields: dict[str, FieldInfo], model_type: str) -> None:
+    """
+    Validates the fields of an invocation or invocation output:
+    - must not override any pydantic reserved fields
+    - must be created via `InputField`, `OutputField`, or be an internal field defined in this file
+    """
+    for name, field in model_fields.items():
+        if name in RESERVED_PYDANTIC_FIELD_NAMES:
+            raise InvalidFieldError(f'Invalid field name "{name}" on "{model_type}" (reserved by pydantic)')
+
+        field_kind = (
+            # _field_kind is defined via InputField(), OutputField() or by one of the internal fields defined in this file
+            field.json_schema_extra.get("_field_kind", None)
+            if field.json_schema_extra
+            else None
+        )
+
+        # must have a field_kind
+        if field_kind is None or field_kind not in {"input", "output", "internal"}:
+            raise InvalidFieldError(
+                f'Invalid field definition for "{name}" on "{model_type}" (maybe it\'s not an InputField or OutputField?)'
+            )
+
+        if field_kind == "input" and name in RESERVED_INPUT_FIELD_NAMES:
+            raise InvalidFieldError(f'Invalid field name "{name}" on "{model_type}" (reserved input field name)')
+
+        if field_kind == "output" and name in RESERVED_OUTPUT_FIELD_NAMES:
+            raise InvalidFieldError(f'Invalid field name "{name}" on "{model_type}" (reserved output field name)')
+
+        # internal fields *must* be in the reserved list
+        if (
+            field_kind == "internal"
+            and name not in RESERVED_INPUT_FIELD_NAMES
+            and name not in RESERVED_OUTPUT_FIELD_NAMES
+        ):
+            raise InvalidFieldError(
+                f'Invalid field name "{name}" on "{model_type}" (internal field without reserved name)'
+            )
+
+    return None
 
 
 def invocation(
@@ -652,9 +766,9 @@ def invocation(
     category: Optional[str] = None,
     version: Optional[str] = None,
     use_cache: Optional[bool] = True,
-) -> Callable[[Type[GenericBaseInvocation]], Type[GenericBaseInvocation]]:
+) -> Callable[[Type[TBaseInvocation]], Type[TBaseInvocation]]:
     """
-    Adds metadata to an invocation.
+    Registers an invocation.
 
     :param str invocation_type: The type of the invocation. Must be unique among all invocations.
     :param Optional[str] title: Adds a title to the invocation. Use if the auto-generated title isn't quite right. Defaults to None.
@@ -664,12 +778,17 @@ def invocation(
     :param Optional[bool] use_cache: Whether or not to use the invocation cache. Defaults to True. The user may override this in the workflow editor.
     """
 
-    def wrapper(cls: Type[GenericBaseInvocation]) -> Type[GenericBaseInvocation]:
+    def wrapper(cls: Type[TBaseInvocation]) -> Type[TBaseInvocation]:
         # Validate invocation types on creation of invocation classes
         # TODO: ensure unique?
         if re.compile(r"^\S+$").match(invocation_type) is None:
             raise ValueError(f'"invocation_type" must consist of non-whitespace characters, got "{invocation_type}"')
 
+        if invocation_type in BaseInvocation.get_invocation_types():
+            raise ValueError(f'Invocation type "{invocation_type}" already exists')
+
+        validate_fields(cls.model_fields, invocation_type)
+
         # Add OpenAPI schema extras
         uiconf_name = cls.__qualname__ + ".UIConfig"
         if not hasattr(cls, "UIConfig") or cls.UIConfig.__qualname__ != uiconf_name:
@@ -687,59 +806,114 @@ def invocation(
                 raise InvalidVersionError(f'Invalid version string for node "{invocation_type}": "{version}"') from e
             cls.UIConfig.version = version
         if use_cache is not None:
-            cls.__fields__["use_cache"].default = use_cache
+            cls.model_fields["use_cache"].default = use_cache
+
+        # Add the invocation type to the model.
+
+        # You'd be tempted to just add the type field and rebuild the model, like this:
+        # cls.model_fields.update(type=FieldInfo.from_annotated_attribute(Literal[invocation_type], invocation_type))
+        # cls.model_rebuild() or cls.model_rebuild(force=True)
+
+        # Unfortunately, because the `GraphInvocation` uses a forward ref in its `graph` field's annotation, this does
+        # not work. Instead, we have to create a new class with the type field and patch the original class with it.
 
-        # Add the invocation type to the pydantic model of the invocation
         invocation_type_annotation = Literal[invocation_type]  # type: ignore
-        invocation_type_field = ModelField.infer(
-            name="type",
-            value=invocation_type,
-            annotation=invocation_type_annotation,
-            class_validators=None,
-            config=cls.__config__,
+        invocation_type_field = Field(
+            title="type", default=invocation_type, json_schema_extra=dict(_field_kind="internal")
         )
-        cls.__fields__.update({"type": invocation_type_field})
-        # to support 3.9, 3.10 and 3.11, as described in https://docs.python.org/3/howto/annotations.html
-        if annotations := cls.__dict__.get("__annotations__", None):
-            annotations.update({"type": invocation_type_annotation})
+
+        docstring = cls.__doc__
+        cls = create_model(
+            cls.__qualname__,
+            __base__=cls,
+            __module__=cls.__module__,
+            type=(invocation_type_annotation, invocation_type_field),
+        )
+        cls.__doc__ = docstring
+
+        # TODO: how to type this correctly? it's typed as ModelMetaclass, a private class in pydantic
+        BaseInvocation.register_invocation(cls)  # type: ignore
+
         return cls
 
     return wrapper
 
 
-GenericBaseInvocationOutput = TypeVar("GenericBaseInvocationOutput", bound=BaseInvocationOutput)
+TBaseInvocationOutput = TypeVar("TBaseInvocationOutput", bound=BaseInvocationOutput)
 
 
 def invocation_output(
     output_type: str,
-) -> Callable[[Type[GenericBaseInvocationOutput]], Type[GenericBaseInvocationOutput]]:
+) -> Callable[[Type[TBaseInvocationOutput]], Type[TBaseInvocationOutput]]:
     """
     Adds metadata to an invocation output.
 
     :param str output_type: The type of the invocation output. Must be unique among all invocation outputs.
     """
 
-    def wrapper(cls: Type[GenericBaseInvocationOutput]) -> Type[GenericBaseInvocationOutput]:
+    def wrapper(cls: Type[TBaseInvocationOutput]) -> Type[TBaseInvocationOutput]:
         # Validate output types on creation of invocation output classes
         # TODO: ensure unique?
         if re.compile(r"^\S+$").match(output_type) is None:
             raise ValueError(f'"output_type" must consist of non-whitespace characters, got "{output_type}"')
 
-        # Add the output type to the pydantic model of the invocation output
-        output_type_annotation = Literal[output_type]  # type: ignore
-        output_type_field = ModelField.infer(
-            name="type",
-            value=output_type,
-            annotation=output_type_annotation,
-            class_validators=None,
-            config=cls.__config__,
-        )
-        cls.__fields__.update({"type": output_type_field})
+        if output_type in BaseInvocationOutput.get_output_types():
+            raise ValueError(f'Invocation type "{output_type}" already exists')
 
-        # to support 3.9, 3.10 and 3.11, as described in https://docs.python.org/3/howto/annotations.html
-        if annotations := cls.__dict__.get("__annotations__", None):
-            annotations.update({"type": output_type_annotation})
+        validate_fields(cls.model_fields, output_type)
+
+        # Add the output type to the model.
+
+        output_type_annotation = Literal[output_type]  # type: ignore
+        output_type_field = Field(title="type", default=output_type, json_schema_extra=dict(_field_kind="internal"))
+
+        docstring = cls.__doc__
+        cls = create_model(
+            cls.__qualname__,
+            __base__=cls,
+            __module__=cls.__module__,
+            type=(output_type_annotation, output_type_field),
+        )
+        cls.__doc__ = docstring
+
+        BaseInvocationOutput.register_output(cls)  # type: ignore # TODO: how to type this correctly?
 
         return cls
 
     return wrapper
+
+
+class WorkflowField(RootModel):
+    """
+    Pydantic model for workflows with custom root of type dict[str, Any].
+    Workflows are stored without a strict schema.
+    """
+
+    root: dict[str, Any] = Field(description="The workflow")
+
+
+WorkflowFieldValidator = TypeAdapter(WorkflowField)
+
+
+class WithWorkflow(BaseModel):
+    workflow: Optional[WorkflowField] = Field(
+        default=None, description=FieldDescriptions.workflow, json_schema_extra=dict(_field_kind="internal")
+    )
+
+
+class MetadataField(RootModel):
+    """
+    Pydantic model for metadata with custom root of type dict[str, Any].
+    Metadata is stored without a strict schema.
+    """
+
+    root: dict[str, Any] = Field(description="The metadata")
+
+
+MetadataFieldValidator = TypeAdapter(MetadataField)
+
+
+class WithMetadata(BaseModel):
+    metadata: Optional[MetadataField] = Field(
+        default=None, description=FieldDescriptions.metadata, json_schema_extra=dict(_field_kind="internal")
+    )

invokeai/app/invocations/collections.py

@@ -2,7 +2,7 @@
 
 
 import numpy as np
-from pydantic import validator
+from pydantic import ValidationInfo, field_validator
 
 from invokeai.app.invocations.primitives import IntegerCollectionOutput
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
@@ -20,9 +20,9 @@ class RangeInvocation(BaseInvocation):
     stop: int = InputField(default=10, description="The stop of the range")
     step: int = InputField(default=1, description="The step of the range")
 
-    @validator("stop")
-    def stop_gt_start(cls, v, values):
-        if "start" in values and v <= values["start"]:
+    @field_validator("stop")
+    def stop_gt_start(cls, v: int, info: ValidationInfo):
+        if "start" in info.data and v <= info.data["start"]:
             raise ValueError("stop must be greater than start")
         return v
 

invokeai/app/invocations/compel.py

@@ -1,6 +1,6 @@
 import re
 from dataclasses import dataclass
-from typing import List, Union
+from typing import List, Optional, Union
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
@@ -43,7 +43,13 @@ class ConditioningFieldData:
 #    PerpNeg = "perp_neg"
 
 
-@invocation("compel", title="Prompt", tags=["prompt", "compel"], category="conditioning", version="1.0.0")
+@invocation(
+    "compel",
+    title="Prompt",
+    tags=["prompt", "compel"],
+    category="conditioning",
+    version="1.0.0",
+)
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
 
@@ -61,17 +67,19 @@ class CompelInvocation(BaseInvocation):
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.dict(),
+            **self.clip.tokenizer.model_dump(),
             context=context,
         )
         text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.dict(),
+            **self.clip.text_encoder.model_dump(),
             context=context,
         )
 
         def _lora_loader():
             for lora in self.clip.loras:
-                lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
+                lora_info = context.services.model_manager.get_model(
+                    **lora.model_dump(exclude={"weight"}), context=context
+                )
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
@@ -160,11 +168,11 @@ class SDXLPromptInvocationBase:
         zero_on_empty: bool,
     ):
         tokenizer_info = context.services.model_manager.get_model(
-            **clip_field.tokenizer.dict(),
+            **clip_field.tokenizer.model_dump(),
             context=context,
         )
         text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.dict(),
+            **clip_field.text_encoder.model_dump(),
             context=context,
         )
 
@@ -172,7 +180,11 @@ class SDXLPromptInvocationBase:
         if prompt == "" and zero_on_empty:
             cpu_text_encoder = text_encoder_info.context.model
             c = torch.zeros(
-                (1, cpu_text_encoder.config.max_position_embeddings, cpu_text_encoder.config.hidden_size),
+                (
+                    1,
+                    cpu_text_encoder.config.max_position_embeddings,
+                    cpu_text_encoder.config.hidden_size,
+                ),
                 dtype=text_encoder_info.context.cache.precision,
             )
             if get_pooled:
@@ -186,7 +198,9 @@ class SDXLPromptInvocationBase:
 
         def _lora_loader():
             for lora in clip_field.loras:
-                lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
+                lora_info = context.services.model_manager.get_model(
+                    **lora.model_dump(exclude={"weight"}), context=context
+                )
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
@@ -273,8 +287,16 @@ class SDXLPromptInvocationBase:
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
 
-    prompt: str = InputField(default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea)
-    style: str = InputField(default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea)
+    prompt: str = InputField(
+        default="",
+        description=FieldDescriptions.compel_prompt,
+        ui_component=UIComponent.Textarea,
+    )
+    style: str = InputField(
+        default="",
+        description=FieldDescriptions.compel_prompt,
+        ui_component=UIComponent.Textarea,
+    )
     original_width: int = InputField(default=1024, description="")
     original_height: int = InputField(default=1024, description="")
     crop_top: int = InputField(default=0, description="")
@@ -310,7 +332,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 [
                     c1,
                     torch.zeros(
-                        (c1.shape[0], c2.shape[1] - c1.shape[1], c1.shape[2]), device=c1.device, dtype=c1.dtype
+                        (c1.shape[0], c2.shape[1] - c1.shape[1], c1.shape[2]),
+                        device=c1.device,
+                        dtype=c1.dtype,
                     ),
                 ],
                 dim=1,
@@ -321,7 +345,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 [
                     c2,
                     torch.zeros(
-                        (c2.shape[0], c1.shape[1] - c2.shape[1], c2.shape[2]), device=c2.device, dtype=c2.dtype
+                        (c2.shape[0], c1.shape[1] - c2.shape[1], c2.shape[2]),
+                        device=c2.device,
+                        dtype=c2.dtype,
                     ),
                 ],
                 dim=1,
@@ -359,7 +385,9 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
     """Parse prompt using compel package to conditioning."""
 
     style: str = InputField(
-        default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea
+        default="",
+        description=FieldDescriptions.compel_prompt,
+        ui_component=UIComponent.Textarea,
     )  # TODO: ?
     original_width: int = InputField(default=1024, description="")
     original_height: int = InputField(default=1024, description="")
@@ -403,10 +431,16 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 class ClipSkipInvocationOutput(BaseInvocationOutput):
     """Clip skip node output"""
 
-    clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
+    clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
-@invocation("clip_skip", title="CLIP Skip", tags=["clipskip", "clip", "skip"], category="conditioning", version="1.0.0")
+@invocation(
+    "clip_skip",
+    title="CLIP Skip",
+    tags=["clipskip", "clip", "skip"],
+    category="conditioning",
+    version="1.0.0",
+)
 class ClipSkipInvocation(BaseInvocation):
     """Skip layers in clip text_encoder model."""
 
@@ -421,7 +455,9 @@ class ClipSkipInvocation(BaseInvocation):
 
 
 def get_max_token_count(
-    tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction], truncate_if_too_long=False
+    tokenizer,
+    prompt: Union[FlattenedPrompt, Blend, Conjunction],
+    truncate_if_too_long=False,
 ) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt

invokeai/app/invocations/controlnet_image_processors.py

@@ -2,7 +2,7 @@
 # initial implementation by Gregg Helt, 2023
 # heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
 from builtins import bool, float
-from typing import Dict, List, Literal, Optional, Union
+from typing import Dict, List, Literal, Union
 
 import cv2
 import numpy as np
@@ -24,12 +24,12 @@ from controlnet_aux import (
 )
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
-from pydantic import BaseModel, Field, validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator
 
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 
 from ...backend.model_management import BaseModelType
-from ..models.image import ImageCategory, ResourceOrigin
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -38,6 +38,8 @@ from .baseinvocation import (
     InputField,
     InvocationContext,
     OutputField,
+    WithMetadata,
+    WithWorkflow,
     invocation,
     invocation_output,
 )
@@ -57,6 +59,8 @@ class ControlNetModelField(BaseModel):
     model_name: str = Field(description="Name of the ControlNet model")
     base_model: BaseModelType = Field(description="Base model")
 
+    model_config = ConfigDict(protected_namespaces=())
+
 
 class ControlField(BaseModel):
     image: ImageField = Field(description="The control image")
@@ -71,7 +75,7 @@ class ControlField(BaseModel):
     control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
     resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
 
-    @validator("control_weight")
+    @field_validator("control_weight")
     def validate_control_weight(cls, v):
         """Validate that all control weights in the valid range"""
         if isinstance(v, list):
@@ -124,15 +128,13 @@ class ControlNetInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "image_processor", title="Base Image Processor", tags=["controlnet"], category="controlnet", version="1.0.0"
-)
-class ImageProcessorInvocation(BaseInvocation):
+# This invocation exists for other invocations to subclass it - do not register with @invocation!
+class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Base class for invocations that preprocess images for ControlNet"""
 
     image: ImageField = InputField(description="The image to process")
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         # superclass just passes through image without processing
         return image
 
@@ -150,6 +152,7 @@ class ImageProcessorInvocation(BaseInvocation):
             session_id=context.graph_execution_state_id,
             node_id=self.id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -393,9 +396,9 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
 
     detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
     image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-    h: Optional[int] = InputField(default=512, ge=0, description="Content shuffle `h` parameter")
-    w: Optional[int] = InputField(default=512, ge=0, description="Content shuffle `w` parameter")
-    f: Optional[int] = InputField(default=256, ge=0, description="Content shuffle `f` parameter")
+    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")
 
     def run_processor(self, image):
         content_shuffle_processor = ContentShuffleDetector()
@@ -575,14 +578,14 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
 
     def run_processor(self, image: Image.Image):
         image = image.convert("RGB")
-        image = np.array(image, dtype=np.uint8)
-        height, width = image.shape[:2]
+        np_image = np.array(image, dtype=np.uint8)
+        height, width = np_image.shape[:2]
 
         width_tile_size = min(self.color_map_tile_size, width)
         height_tile_size = min(self.color_map_tile_size, height)
 
         color_map = cv2.resize(
-            image,
+            np_image,
             (width // width_tile_size, height // height_tile_size),
             interpolation=cv2.INTER_CUBIC,
         )

invokeai/app/invocations/custom_nodes/README.md

@@ -0,0 +1,51 @@
+# Custom Nodes / Node Packs
+
+Copy your node packs to this directory.
+
+When nodes are added or changed, you must restart the app to see the changes.
+
+## Directory Structure
+
+For a node pack to be loaded, it must be placed in a directory alongside this
+file. Here's an example structure:
+
+```py
+.
+├── __init__.py # Invoke-managed custom node loader
+│
+├── cool_node
+│   ├── __init__.py # see example below
+│   └── cool_node.py
+│
+└── my_node_pack
+    ├── __init__.py # see example below
+    ├── tasty_node.py
+    ├── bodacious_node.py
+    ├── utils.py
+    └── extra_nodes
+        └── fancy_node.py
+```
+
+## Node Pack `__init__.py`
+
+Each node pack must have an `__init__.py` file that imports its nodes.
+
+The structure of each node or node pack is otherwise not important.
+
+Here are examples, based on the example directory structure.
+
+### `cool_node/__init__.py`
+
+```py
+from .cool_node import CoolInvocation
+```
+
+### `my_node_pack/__init__.py`
+
+```py
+from .tasty_node import TastyInvocation
+from .bodacious_node import BodaciousInvocation
+from .extra_nodes.fancy_node import FancyInvocation
+```
+
+Only nodes imported in the `__init__.py` file are loaded.

invokeai/app/invocations/custom_nodes/init.py

@@ -0,0 +1,51 @@
+"""
+Invoke-managed custom node loader. See README.md for more information.
+"""
+
+import sys
+from importlib.util import module_from_spec, spec_from_file_location
+from pathlib import Path
+
+from invokeai.backend.util.logging import InvokeAILogger
+
+logger = InvokeAILogger.get_logger()
+loaded_count = 0
+
+
+for d in Path(__file__).parent.iterdir():
+    # skip files
+    if not d.is_dir():
+        continue
+
+    # skip hidden directories
+    if d.name.startswith("_") or d.name.startswith("."):
+        continue
+
+    # skip directories without an `__init__.py`
+    init = d / "__init__.py"
+    if not init.exists():
+        continue
+
+    module_name = init.parent.stem
+
+    # skip if already imported
+    if module_name in globals():
+        continue
+
+    # we have a legit module to import
+    spec = spec_from_file_location(module_name, init.absolute())
+
+    if spec is None or spec.loader is None:
+        logger.warn(f"Could not load {init}")
+        continue
+
+    module = module_from_spec(spec)
+    sys.modules[spec.name] = module
+    spec.loader.exec_module(module)
+
+    loaded_count += 1
+
+    del init, module_name
+
+
+logger.info(f"Loaded {loaded_count} modules from {Path(__file__).parent}")

invokeai/app/invocations/cv.py

@@ -6,13 +6,13 @@ import numpy
 from PIL import Image, ImageOps
 
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.models.image import ImageCategory, ResourceOrigin
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
 
 
 @invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.0.0")
-class CvInpaintInvocation(BaseInvocation):
+class CvInpaintInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Simple inpaint using opencv."""
 
     image: ImageField = InputField(description="The image to inpaint")

invokeai/app/invocations/facetools.py

@@ -0,0 +1,726 @@
+import math
+import re
+from pathlib import Path
+from typing import Optional, TypedDict
+
+import cv2
+import numpy as np
+from mediapipe.python.solutions.face_mesh import FaceMesh  # type: ignore[import]
+from PIL import Image, ImageDraw, ImageFilter, ImageFont, ImageOps
+from PIL.Image import Image as ImageType
+from pydantic import field_validator
+
+import invokeai.assets.fonts as font_assets
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    InputField,
+    InvocationContext,
+    OutputField,
+    WithMetadata,
+    WithWorkflow,
+    invocation,
+    invocation_output,
+)
+from invokeai.app.invocations.primitives import ImageField, ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+
+
+@invocation_output("face_mask_output")
+class FaceMaskOutput(ImageOutput):
+    """Base class for FaceMask output"""
+
+    mask: ImageField = OutputField(description="The output mask")
+
+
+@invocation_output("face_off_output")
+class FaceOffOutput(ImageOutput):
+    """Base class for FaceOff Output"""
+
+    mask: ImageField = OutputField(description="The output mask")
+    x: int = OutputField(description="The x coordinate of the bounding box's left side")
+    y: int = OutputField(description="The y coordinate of the bounding box's top side")
+
+
+class FaceResultData(TypedDict):
+    image: ImageType
+    mask: ImageType
+    x_center: float
+    y_center: float
+    mesh_width: int
+    mesh_height: int
+    chunk_x_offset: int
+    chunk_y_offset: int
+
+
+class FaceResultDataWithId(FaceResultData):
+    face_id: int
+
+
+class ExtractFaceData(TypedDict):
+    bounded_image: ImageType
+    bounded_mask: ImageType
+    x_min: int
+    y_min: int
+    x_max: int
+    y_max: int
+
+
+class FaceMaskResult(TypedDict):
+    image: ImageType
+    mask: ImageType
+
+
+def create_white_image(w: int, h: int) -> ImageType:
+    return Image.new("L", (w, h), color=255)
+
+
+def create_black_image(w: int, h: int) -> ImageType:
+    return Image.new("L", (w, h), color=0)
+
+
+FONT_SIZE = 32
+FONT_STROKE_WIDTH = 4
+
+
+def coalesce_faces(face1: FaceResultData, face2: FaceResultData) -> FaceResultData:
+    face1_x_offset = face1["chunk_x_offset"] - min(face1["chunk_x_offset"], face2["chunk_x_offset"])
+    face2_x_offset = face2["chunk_x_offset"] - min(face1["chunk_x_offset"], face2["chunk_x_offset"])
+    face1_y_offset = face1["chunk_y_offset"] - min(face1["chunk_y_offset"], face2["chunk_y_offset"])
+    face2_y_offset = face2["chunk_y_offset"] - min(face1["chunk_y_offset"], face2["chunk_y_offset"])
+
+    new_im_width = (
+        max(face1["image"].width, face2["image"].width)
+        + max(face1["chunk_x_offset"], face2["chunk_x_offset"])
+        - min(face1["chunk_x_offset"], face2["chunk_x_offset"])
+    )
+    new_im_height = (
+        max(face1["image"].height, face2["image"].height)
+        + max(face1["chunk_y_offset"], face2["chunk_y_offset"])
+        - min(face1["chunk_y_offset"], face2["chunk_y_offset"])
+    )
+    pil_image = Image.new(mode=face1["image"].mode, size=(new_im_width, new_im_height))
+    pil_image.paste(face1["image"], (face1_x_offset, face1_y_offset))
+    pil_image.paste(face2["image"], (face2_x_offset, face2_y_offset))
+
+    # Mask images are always from the origin
+    new_mask_im_width = max(face1["mask"].width, face2["mask"].width)
+    new_mask_im_height = max(face1["mask"].height, face2["mask"].height)
+    mask_pil = create_white_image(new_mask_im_width, new_mask_im_height)
+    black_image = create_black_image(face1["mask"].width, face1["mask"].height)
+    mask_pil.paste(black_image, (0, 0), ImageOps.invert(face1["mask"]))
+    black_image = create_black_image(face2["mask"].width, face2["mask"].height)
+    mask_pil.paste(black_image, (0, 0), ImageOps.invert(face2["mask"]))
+
+    new_face = FaceResultData(
+        image=pil_image,
+        mask=mask_pil,
+        x_center=max(face1["x_center"], face2["x_center"]),
+        y_center=max(face1["y_center"], face2["y_center"]),
+        mesh_width=max(face1["mesh_width"], face2["mesh_width"]),
+        mesh_height=max(face1["mesh_height"], face2["mesh_height"]),
+        chunk_x_offset=max(face1["chunk_x_offset"], face2["chunk_x_offset"]),
+        chunk_y_offset=max(face2["chunk_y_offset"], face2["chunk_y_offset"]),
+    )
+    return new_face
+
+
+def prepare_faces_list(
+    face_result_list: list[FaceResultData],
+) -> list[FaceResultDataWithId]:
+    """Deduplicates a list of faces, adding IDs to them."""
+    deduped_faces: list[FaceResultData] = []
+
+    if len(face_result_list) == 0:
+        return list()
+
+    for candidate in face_result_list:
+        should_add = True
+        candidate_x_center = candidate["x_center"]
+        candidate_y_center = candidate["y_center"]
+        for idx, face in enumerate(deduped_faces):
+            face_center_x = face["x_center"]
+            face_center_y = face["y_center"]
+            face_radius_w = face["mesh_width"] / 2
+            face_radius_h = face["mesh_height"] / 2
+            # Determine if the center of the candidate_face is inside the ellipse of the added face
+            # p < 1 -> Inside
+            # p = 1 -> Exactly on the ellipse
+            # p > 1 -> Outside
+            p = (math.pow((candidate_x_center - face_center_x), 2) / math.pow(face_radius_w, 2)) + (
+                math.pow((candidate_y_center - face_center_y), 2) / math.pow(face_radius_h, 2)
+            )
+
+            if p < 1:  # Inside of the already-added face's radius
+                deduped_faces[idx] = coalesce_faces(face, candidate)
+                should_add = False
+                break
+
+        if should_add is True:
+            deduped_faces.append(candidate)
+
+    sorted_faces = sorted(deduped_faces, key=lambda x: x["y_center"])
+    sorted_faces = sorted(sorted_faces, key=lambda x: x["x_center"])
+
+    # add face_id for reference
+    sorted_faces_with_ids: list[FaceResultDataWithId] = []
+    face_id_counter = 0
+    for face in sorted_faces:
+        sorted_faces_with_ids.append(
+            FaceResultDataWithId(
+                **face,
+                face_id=face_id_counter,
+            )
+        )
+        face_id_counter += 1
+
+    return sorted_faces_with_ids
+
+
+def generate_face_box_mask(
+    context: InvocationContext,
+    minimum_confidence: float,
+    x_offset: float,
+    y_offset: float,
+    pil_image: ImageType,
+    chunk_x_offset: int = 0,
+    chunk_y_offset: int = 0,
+    draw_mesh: bool = True,
+) -> list[FaceResultData]:
+    result = []
+    mask_pil = None
+
+    # Convert the PIL image to a NumPy array.
+    np_image = np.array(pil_image, dtype=np.uint8)
+
+    # Check if the input image has four channels (RGBA).
+    if np_image.shape[2] == 4:
+        # Convert RGBA to RGB by removing the alpha channel.
+        np_image = np_image[:, :, :3]
+
+    # Create a FaceMesh object for face landmark detection and mesh generation.
+    face_mesh = FaceMesh(
+        max_num_faces=999,
+        min_detection_confidence=minimum_confidence,
+        min_tracking_confidence=minimum_confidence,
+    )
+
+    # Detect the face landmarks and mesh in the input image.
+    results = face_mesh.process(np_image)
+
+    # Check if any face is detected.
+    if results.multi_face_landmarks:  # type: ignore # this are via protobuf and not typed
+        # Search for the face_id in the detected faces.
+        for face_id, face_landmarks in enumerate(results.multi_face_landmarks):  # type: ignore #this are via protobuf and not typed
+            # Get the bounding box of the face mesh.
+            x_coordinates = [landmark.x for landmark in face_landmarks.landmark]
+            y_coordinates = [landmark.y for landmark in face_landmarks.landmark]
+            x_min, x_max = min(x_coordinates), max(x_coordinates)
+            y_min, y_max = min(y_coordinates), max(y_coordinates)
+
+            # Calculate the width and height of the face mesh.
+            mesh_width = int((x_max - x_min) * np_image.shape[1])
+            mesh_height = int((y_max - y_min) * np_image.shape[0])
+
+            # Get the center of the face.
+            x_center = np.mean([landmark.x * np_image.shape[1] for landmark in face_landmarks.landmark])
+            y_center = np.mean([landmark.y * np_image.shape[0] for landmark in face_landmarks.landmark])
+
+            face_landmark_points = np.array(
+                [
+                    [landmark.x * np_image.shape[1], landmark.y * np_image.shape[0]]
+                    for landmark in face_landmarks.landmark
+                ]
+            )
+
+            # Apply the scaling offsets to the face landmark points with a multiplier.
+            scale_multiplier = 0.2
+            x_center = np.mean(face_landmark_points[:, 0])
+            y_center = np.mean(face_landmark_points[:, 1])
+
+            if draw_mesh:
+                x_scaled = face_landmark_points[:, 0] + scale_multiplier * x_offset * (
+                    face_landmark_points[:, 0] - x_center
+                )
+                y_scaled = face_landmark_points[:, 1] + scale_multiplier * y_offset * (
+                    face_landmark_points[:, 1] - y_center
+                )
+
+                convex_hull = cv2.convexHull(np.column_stack((x_scaled, y_scaled)).astype(np.int32))
+
+                # Generate a binary face mask using the face mesh.
+                mask_image = np.ones(np_image.shape[:2], dtype=np.uint8) * 255
+                cv2.fillConvexPoly(mask_image, convex_hull, 0)
+
+                # Convert the binary mask image to a PIL Image.
+                init_mask_pil = Image.fromarray(mask_image, mode="L")
+                w, h = init_mask_pil.size
+                mask_pil = create_white_image(w + chunk_x_offset, h + chunk_y_offset)
+                mask_pil.paste(init_mask_pil, (chunk_x_offset, chunk_y_offset))
+
+            x_center = float(x_center)
+            y_center = float(y_center)
+            face = FaceResultData(
+                image=pil_image,
+                mask=mask_pil or create_white_image(*pil_image.size),
+                x_center=x_center + chunk_x_offset,
+                y_center=y_center + chunk_y_offset,
+                mesh_width=mesh_width,
+                mesh_height=mesh_height,
+                chunk_x_offset=chunk_x_offset,
+                chunk_y_offset=chunk_y_offset,
+            )
+
+            result.append(face)
+
+    return result
+
+
+def extract_face(
+    context: InvocationContext,
+    image: ImageType,
+    face: FaceResultData,
+    padding: int,
+) -> ExtractFaceData:
+    mask = face["mask"]
+    center_x = face["x_center"]
+    center_y = face["y_center"]
+    mesh_width = face["mesh_width"]
+    mesh_height = face["mesh_height"]
+
+    # Determine the minimum size of the square crop
+    min_size = min(mask.width, mask.height)
+
+    # Calculate the crop boundaries for the output image and mask.
+    mesh_width += 128 + padding  # add pixels to account for mask variance
+    mesh_height += 128 + padding  # add pixels to account for mask variance
+    crop_size = min(
+        max(mesh_width, mesh_height, 128), min_size
+    )  # Choose the smaller of the two (given value or face mask size)
+    if crop_size > 128:
+        crop_size = (crop_size + 7) // 8 * 8  # Ensure crop side is multiple of 8
+
+    # Calculate the actual crop boundaries within the bounds of the original image.
+    x_min = int(center_x - crop_size / 2)
+    y_min = int(center_y - crop_size / 2)
+    x_max = int(center_x + crop_size / 2)
+    y_max = int(center_y + crop_size / 2)
+
+    # Adjust the crop boundaries to stay within the original image's dimensions
+    if x_min < 0:
+        context.services.logger.warning("FaceTools --> -X-axis padding reached image edge.")
+        x_max -= x_min
+        x_min = 0
+    elif x_max > mask.width:
+        context.services.logger.warning("FaceTools --> +X-axis padding reached image edge.")
+        x_min -= x_max - mask.width
+        x_max = mask.width
+
+    if y_min < 0:
+        context.services.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
+        y_max -= y_min
+        y_min = 0
+    elif y_max > mask.height:
+        context.services.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
+        y_min -= y_max - mask.height
+        y_max = mask.height
+
+    # Ensure the crop is square and adjust the boundaries if needed
+    if x_max - x_min != crop_size:
+        context.services.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
+        diff = crop_size - (x_max - x_min)
+        x_min -= diff // 2
+        x_max += diff - diff // 2
+
+    if y_max - y_min != crop_size:
+        context.services.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
+        diff = crop_size - (y_max - y_min)
+        y_min -= diff // 2
+        y_max += diff - diff // 2
+
+    context.services.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
+
+    # Crop the output image to the specified size with the center of the face mesh as the center.
+    mask = mask.crop((x_min, y_min, x_max, y_max))
+    bounded_image = image.crop((x_min, y_min, x_max, y_max))
+
+    # blur mask edge by small radius
+    mask = mask.filter(ImageFilter.GaussianBlur(radius=2))
+
+    return ExtractFaceData(
+        bounded_image=bounded_image,
+        bounded_mask=mask,
+        x_min=x_min,
+        y_min=y_min,
+        x_max=x_max,
+        y_max=y_max,
+    )
+
+
+def get_faces_list(
+    context: InvocationContext,
+    image: ImageType,
+    should_chunk: bool,
+    minimum_confidence: float,
+    x_offset: float,
+    y_offset: float,
+    draw_mesh: bool = True,
+) -> list[FaceResultDataWithId]:
+    result = []
+
+    # Generate the face box mask and get the center of the face.
+    if not should_chunk:
+        context.services.logger.info("FaceTools --> Attempting full image face detection.")
+        result = generate_face_box_mask(
+            context=context,
+            minimum_confidence=minimum_confidence,
+            x_offset=x_offset,
+            y_offset=y_offset,
+            pil_image=image,
+            chunk_x_offset=0,
+            chunk_y_offset=0,
+            draw_mesh=draw_mesh,
+        )
+    if should_chunk or len(result) == 0:
+        context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
+        width, height = image.size
+        image_chunks = []
+        x_offsets = []
+        y_offsets = []
+        result = []
+
+        # If width == height, there's nothing more we can do... otherwise...
+        if width > height:
+            # Landscape - slice the image horizontally
+            fx = 0.0
+            steps = int(width * 2 / height) + 1
+            increment = (width - height) / (steps - 1)
+            while fx <= (width - height):
+                x = int(fx)
+                image_chunks.append(image.crop((x, 0, x + height, height)))
+                x_offsets.append(x)
+                y_offsets.append(0)
+                fx += increment
+                context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
+        elif height > width:
+            # Portrait - slice the image vertically
+            fy = 0.0
+            steps = int(height * 2 / width) + 1
+            increment = (height - width) / (steps - 1)
+            while fy <= (height - width):
+                y = int(fy)
+                image_chunks.append(image.crop((0, y, width, y + width)))
+                x_offsets.append(0)
+                y_offsets.append(y)
+                fy += increment
+                context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
+
+        for idx in range(len(image_chunks)):
+            context.services.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
+            result = result + generate_face_box_mask(
+                context=context,
+                minimum_confidence=minimum_confidence,
+                x_offset=x_offset,
+                y_offset=y_offset,
+                pil_image=image_chunks[idx],
+                chunk_x_offset=x_offsets[idx],
+                chunk_y_offset=y_offsets[idx],
+                draw_mesh=draw_mesh,
+            )
+
+        if len(result) == 0:
+            # Give up
+            context.services.logger.warning(
+                "FaceTools --> No face detected in chunked input image. Passing through original image."
+            )
+
+    all_faces = prepare_faces_list(result)
+
+    return all_faces
+
+
+@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.0.2")
+class FaceOffInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+    """Bound, extract, and mask a face from an image using MediaPipe detection"""
+
+    image: ImageField = InputField(description="Image for face detection")
+    face_id: int = InputField(
+        default=0,
+        ge=0,
+        description="The face ID to process, numbered from 0. Multiple faces not supported. Find a face's ID with FaceIdentifier node.",
+    )
+    minimum_confidence: float = InputField(
+        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
+    )
+    x_offset: float = InputField(default=0.0, description="X-axis offset of the mask")
+    y_offset: float = InputField(default=0.0, description="Y-axis offset of the mask")
+    padding: int = InputField(default=0, description="All-axis padding around the mask in pixels")
+    chunk: bool = InputField(
+        default=False,
+        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
+    )
+
+    def faceoff(self, context: InvocationContext, image: ImageType) -> Optional[ExtractFaceData]:
+        all_faces = get_faces_list(
+            context=context,
+            image=image,
+            should_chunk=self.chunk,
+            minimum_confidence=self.minimum_confidence,
+            x_offset=self.x_offset,
+            y_offset=self.y_offset,
+            draw_mesh=True,
+        )
+
+        if len(all_faces) == 0:
+            context.services.logger.warning("FaceOff --> No faces detected. Passing through original image.")
+            return None
+
+        if self.face_id > len(all_faces) - 1:
+            context.services.logger.warning(
+                f"FaceOff --> Face ID {self.face_id} is outside of the number of faces detected ({len(all_faces)}). Passing through original image."
+            )
+            return None
+
+        face_data = extract_face(context=context, image=image, face=all_faces[self.face_id], padding=self.padding)
+        # Convert the input image to RGBA mode to ensure it has an alpha channel.
+        face_data["bounded_image"] = face_data["bounded_image"].convert("RGBA")
+
+        return face_data
+
+    def invoke(self, context: InvocationContext) -> FaceOffOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+        result = self.faceoff(context=context, image=image)
+
+        if result is None:
+            result_image = image
+            result_mask = create_white_image(*image.size)
+            x = 0
+            y = 0
+        else:
+            result_image = result["bounded_image"]
+            result_mask = result["bounded_mask"]
+            x = result["x_min"]
+            y = result["y_min"]
+
+        image_dto = context.services.images.create(
+            image=result_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            workflow=self.workflow,
+        )
+
+        mask_dto = context.services.images.create(
+            image=result_mask,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.MASK,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        output = FaceOffOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+            mask=ImageField(image_name=mask_dto.image_name),
+            x=x,
+            y=y,
+        )
+
+        return output
+
+
+@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.0.2")
+class FaceMaskInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+    """Face mask creation using mediapipe face detection"""
+
+    image: ImageField = InputField(description="Image to face detect")
+    face_ids: str = InputField(
+        default="",
+        description="Comma-separated list of face ids to mask eg '0,2,7'. Numbered from 0. Leave empty to mask all. Find face IDs with FaceIdentifier node.",
+    )
+    minimum_confidence: float = InputField(
+        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
+    )
+    x_offset: float = InputField(default=0.0, description="Offset for the X-axis of the face mask")
+    y_offset: float = InputField(default=0.0, description="Offset for the Y-axis of the face mask")
+    chunk: bool = InputField(
+        default=False,
+        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
+    )
+    invert_mask: bool = InputField(default=False, description="Toggle to invert the mask")
+
+    @field_validator("face_ids")
+    def validate_comma_separated_ints(cls, v) -> str:
+        comma_separated_ints_regex = re.compile(r"^\d*(,\d+)*$")
+        if comma_separated_ints_regex.match(v) is None:
+            raise ValueError('Face IDs must be a comma-separated list of integers (e.g. "1,2,3")')
+        return v
+
+    def facemask(self, context: InvocationContext, image: ImageType) -> FaceMaskResult:
+        all_faces = get_faces_list(
+            context=context,
+            image=image,
+            should_chunk=self.chunk,
+            minimum_confidence=self.minimum_confidence,
+            x_offset=self.x_offset,
+            y_offset=self.y_offset,
+            draw_mesh=True,
+        )
+
+        mask_pil = create_white_image(*image.size)
+
+        id_range = list(range(0, len(all_faces)))
+        ids_to_extract = id_range
+        if self.face_ids != "":
+            parsed_face_ids = [int(id) for id in self.face_ids.split(",")]
+            # get requested face_ids that are in range
+            intersected_face_ids = set(parsed_face_ids) & set(id_range)
+
+            if len(intersected_face_ids) == 0:
+                id_range_str = ",".join([str(id) for id in id_range])
+                context.services.logger.warning(
+                    f"Face IDs must be in range of detected faces - requested {self.face_ids}, detected {id_range_str}. Passing through original image."
+                )
+                return FaceMaskResult(
+                    image=image,  # original image
+                    mask=mask_pil,  # white mask
+                )
+
+            ids_to_extract = list(intersected_face_ids)
+
+        for face_id in ids_to_extract:
+            face_data = extract_face(context=context, image=image, face=all_faces[face_id], padding=0)
+            face_mask_pil = face_data["bounded_mask"]
+            x_min = face_data["x_min"]
+            y_min = face_data["y_min"]
+            x_max = face_data["x_max"]
+            y_max = face_data["y_max"]
+
+            mask_pil.paste(
+                create_black_image(x_max - x_min, y_max - y_min),
+                box=(x_min, y_min),
+                mask=ImageOps.invert(face_mask_pil),
+            )
+
+        if self.invert_mask:
+            mask_pil = ImageOps.invert(mask_pil)
+
+        # Create an RGBA image with transparency
+        image = image.convert("RGBA")
+
+        return FaceMaskResult(
+            image=image,
+            mask=mask_pil,
+        )
+
+    def invoke(self, context: InvocationContext) -> FaceMaskOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+        result = self.facemask(context=context, image=image)
+
+        image_dto = context.services.images.create(
+            image=result["image"],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            workflow=self.workflow,
+        )
+
+        mask_dto = context.services.images.create(
+            image=result["mask"],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.MASK,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        output = FaceMaskOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+            mask=ImageField(image_name=mask_dto.image_name),
+        )
+
+        return output
+
+
+@invocation(
+    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.0.2"
+)
+class FaceIdentifierInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+    """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
+
+    image: ImageField = InputField(description="Image to face detect")
+    minimum_confidence: float = InputField(
+        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
+    )
+    chunk: bool = InputField(
+        default=False,
+        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
+    )
+
+    def faceidentifier(self, context: InvocationContext, image: ImageType) -> ImageType:
+        image = image.copy()
+
+        all_faces = get_faces_list(
+            context=context,
+            image=image,
+            should_chunk=self.chunk,
+            minimum_confidence=self.minimum_confidence,
+            x_offset=0,
+            y_offset=0,
+            draw_mesh=False,
+        )
+
+        # Note - font may be found either in the repo if running an editable install, or in the venv if running a package install
+        font_path = [x for x in [Path(y, "inter/Inter-Regular.ttf") for y in font_assets.__path__] if x.exists()]
+        font = ImageFont.truetype(font_path[0].as_posix(), FONT_SIZE)
+
+        # Paste face IDs on the output image
+        draw = ImageDraw.Draw(image)
+        for face in all_faces:
+            x_coord = face["x_center"]
+            y_coord = face["y_center"]
+            text = str(face["face_id"])
+            # get bbox of the text so we can center the id on the face
+            _, _, bbox_w, bbox_h = draw.textbbox(xy=(0, 0), text=text, font=font, stroke_width=FONT_STROKE_WIDTH)
+            x = x_coord - bbox_w / 2
+            y = y_coord - bbox_h / 2
+            draw.text(
+                xy=(x, y),
+                text=str(text),
+                fill=(255, 255, 255, 255),
+                font=font,
+                stroke_width=FONT_STROKE_WIDTH,
+                stroke_fill=(0, 0, 0, 255),
+            )
+
+        # Create an RGBA image with transparency
+        image = image.convert("RGBA")
+
+        return image
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+        result_image = self.faceidentifier(context=context, image=image)
+
+        image_dto = context.services.images.create(
+            image=result_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            workflow=self.workflow,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/image.py

@@ -5,15 +5,23 @@ from typing import Literal, Optional
 
 import cv2
 import numpy
-from PIL import Image, ImageChops, ImageFilter, ImageOps
+from PIL import Image, ImageChops, ImageFilter, ImageOps, ImageDraw
 
-from invokeai.app.invocations.metadata import CoreMetadata
 from invokeai.app.invocations.primitives import BoardField, ColorField, ImageField, ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 
-from ..models.image import ImageCategory, ResourceOrigin
-from .baseinvocation import BaseInvocation, FieldDescriptions, Input, InputField, InvocationContext, invocation
+from .baseinvocation import (
+    BaseInvocation,
+    FieldDescriptions,
+    Input,
+    InputField,
+    InvocationContext,
+    WithMetadata,
+    WithWorkflow,
+    invocation,
+)
 
 
 @invocation("show_image", title="Show Image", tags=["image"], category="image", version="1.0.0")
@@ -37,7 +45,7 @@ class ShowImageInvocation(BaseInvocation):
 
 
 @invocation("blank_image", title="Blank Image", tags=["image"], category="image", version="1.0.0")
-class BlankImageInvocation(BaseInvocation):
+class BlankImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Creates a blank image and forwards it to the pipeline"""
 
     width: int = InputField(default=512, description="The width of the image")
@@ -55,6 +63,135 @@ class BlankImageInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
+            workflow=self.workflow,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+@invocation("gradient_image", title="Gradient Image", tags=["gradient", "image"], category="image", version="1.0.0")
+class GradientImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+    """Creates a variety of gradient images and forwards them to the pipeline"""
+
+    width: int = InputField(default=512, description="The width of the image")
+    height: int = InputField(default=512, description="The height of the image")
+    mode: Literal["linear", "radial", "noise", "conical", "diamond"] = InputField(
+        default="linear", description="The type of gradient"
+    )
+    color1: ColorField = InputField(
+        default=ColorField(r=0, g=0, b=0, a=255), description="The starting color of the gradient"
+    )
+    color2: ColorField = InputField(
+        default=ColorField(r=255, g=255, b=255, a=255), description="The ending color of the gradient"
+    )
+    orientation_angle: float = InputField(default=0.0, description="The orientation angle of the gradient in degrees")
+
+    def _generate_linear_gradient(self) -> Image.Image:
+        image = Image.new("RGBA", (self.width, self.height), self.color1.tuple())
+        draw = ImageDraw.Draw(image)
+        for i in range(self.width):
+            blended_color = (
+                int(self.color1.r + (self.color2.r - self.color1.r) * (i / self.width)),
+                int(self.color1.g + (self.color2.g - self.color1.g) * (i / self.width)),
+                int(self.color1.b + (self.color2.b - self.color1.b) * (i / self.width)),
+                int(self.color1.a + (self.color2.a - self.color1.a) * (i / self.width)),
+            )
+            draw.line([(i, 0), (i, self.height)], fill=blended_color)
+
+        image = image.rotate(self.orientation_angle, expand=True)
+
+        return image
+
+    def _generate_radial_gradient(self) -> Image.Image:
+        image = Image.new("RGBA", (self.width, self.height), self.color1.tuple())
+        draw = ImageDraw.Draw(image)
+        max_radius = int(((self.width**2) + (self.height**2)) ** 0.5 / 2)
+        center_x, center_y = self.width // 2, self.height // 2
+
+        for r in range(max_radius):
+            blended_color = (
+                int(self.color1.r + (self.color2.r - self.color1.r) * (r / max_radius)),
+                int(self.color1.g + (self.color2.g - self.color1.g) * (r / max_radius)),
+                int(self.color1.b + (self.color2.b - self.color1.b) * (r / max_radius)),
+                int(self.color1.a + (self.color2.a - self.color1.a) * (r / max_radius)),
+            )
+            draw.ellipse((center_x - r, center_y - r, center_x + r, center_y + r), outline=blended_color, width=1)
+        return image
+
+    def _generate_noise_gradient(self) -> Image.Image:
+        img_array = numpy.zeros((self.height, self.width, 4), dtype=numpy.uint8)
+        random_factors = numpy.random.rand(self.height, self.width, 4)
+
+        for i, color in enumerate(["r", "g", "b", "a"]):
+            img_array[..., i] = (
+                getattr(self.color1, color)
+                + (getattr(self.color2, color) - getattr(self.color1, color)) * random_factors[..., i]
+            )
+
+        image = Image.fromarray(img_array.astype("uint8"), "RGBA")
+        return image
+
+    def _generate_conical_gradient(self) -> Image.Image:
+        image = Image.new("RGBA", (self.width, self.height))
+        pixels = image.load()
+        center_x, center_y = self.width // 2, self.height // 2
+
+        for x in range(self.width):
+            for y in range(self.height):
+                angle = int((180 / numpy.pi) * numpy.arctan2(y - center_y, x - center_x)) % 360
+                blended_color = (
+                    int(self.color1.r + (self.color2.r - self.color1.r) * (angle / 360)),
+                    int(self.color1.g + (self.color2.g - self.color1.g) * (angle / 360)),
+                    int(self.color1.b + (self.color2.b - self.color1.b) * (angle / 360)),
+                    int(self.color1.a + (self.color2.a - self.color1.a) * (angle / 360)),
+                )
+                pixels[x, y] = blended_color
+
+        return image
+
+    def _generate_diamond_gradient(self) -> Image.Image:
+        image = Image.new("RGBA", (self.width, self.height))
+        pixels = image.load()
+        center_x, center_y = self.width // 2, self.height // 2
+
+        for x in range(self.width):
+            for y in range(self.height):
+                distance = abs(x - center_x) + abs(y - center_y)
+                max_distance = self.width // 2 + self.height // 2
+                blended_color = (
+                    int(self.color1.r + (self.color2.r - self.color1.r) * (distance / max_distance)),
+                    int(self.color1.g + (self.color2.g - self.color1.g) * (distance / max_distance)),
+                    int(self.color1.b + (self.color2.b - self.color1.b) * (distance / max_distance)),
+                    int(self.color1.a + (self.color2.a - self.color1.a) * (distance / max_distance)),
+                )
+                pixels[x, y] = blended_color
+
+        return image
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        gradient_method_map = {
+            "linear": self._generate_linear_gradient,
+            "radial": self._generate_radial_gradient,
+            "noise": self._generate_noise_gradient,
+            "conical": self._generate_conical_gradient,
+            "diamond": self._generate_diamond_gradient,
+        }
+
+        image = gradient_method_map.get(self.mode)()
+
+        image_dto = context.services.images.create(
+            image=image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -66,7 +203,7 @@ class BlankImageInvocation(BaseInvocation):
 
 
 @invocation("img_crop", title="Crop Image", tags=["image", "crop"], category="image", version="1.0.0")
-class ImageCropInvocation(BaseInvocation):
+class ImageCropInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Crops an image to a specified box. The box can be outside of the image."""
 
     image: ImageField = InputField(description="The image to crop")
@@ -88,6 +225,7 @@ class ImageCropInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -99,7 +237,7 @@ class ImageCropInvocation(BaseInvocation):
 
 
 @invocation("img_paste", title="Paste Image", tags=["image", "paste"], category="image", version="1.0.1")
-class ImagePasteInvocation(BaseInvocation):
+class ImagePasteInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Pastes an image into another image."""
 
     base_image: ImageField = InputField(description="The base image")
@@ -141,6 +279,7 @@ class ImagePasteInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -152,7 +291,7 @@ class ImagePasteInvocation(BaseInvocation):
 
 
 @invocation("tomask", title="Mask from Alpha", tags=["image", "mask"], category="image", version="1.0.0")
-class MaskFromAlphaInvocation(BaseInvocation):
+class MaskFromAlphaInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Extracts the alpha channel of an image as a mask."""
 
     image: ImageField = InputField(description="The image to create the mask from")
@@ -172,6 +311,7 @@ class MaskFromAlphaInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -183,7 +323,7 @@ class MaskFromAlphaInvocation(BaseInvocation):
 
 
 @invocation("img_mul", title="Multiply Images", tags=["image", "multiply"], category="image", version="1.0.0")
-class ImageMultiplyInvocation(BaseInvocation):
+class ImageMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Multiplies two images together using `PIL.ImageChops.multiply()`."""
 
     image1: ImageField = InputField(description="The first image to multiply")
@@ -202,6 +342,7 @@ class ImageMultiplyInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -216,7 +357,7 @@ IMAGE_CHANNELS = Literal["A", "R", "G", "B"]
 
 
 @invocation("img_chan", title="Extract Image Channel", tags=["image", "channel"], category="image", version="1.0.0")
-class ImageChannelInvocation(BaseInvocation):
+class ImageChannelInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Gets a channel from an image."""
 
     image: ImageField = InputField(description="The image to get the channel from")
@@ -234,6 +375,7 @@ class ImageChannelInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -248,7 +390,7 @@ IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F
 
 
 @invocation("img_conv", title="Convert Image Mode", tags=["image", "convert"], category="image", version="1.0.0")
-class ImageConvertInvocation(BaseInvocation):
+class ImageConvertInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Converts an image to a different mode."""
 
     image: ImageField = InputField(description="The image to convert")
@@ -266,6 +408,7 @@ class ImageConvertInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -277,7 +420,7 @@ class ImageConvertInvocation(BaseInvocation):
 
 
 @invocation("img_blur", title="Blur Image", tags=["image", "blur"], category="image", version="1.0.0")
-class ImageBlurInvocation(BaseInvocation):
+class ImageBlurInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Blurs an image"""
 
     image: ImageField = InputField(description="The image to blur")
@@ -300,6 +443,7 @@ class ImageBlurInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -331,16 +475,13 @@ PIL_RESAMPLING_MAP = {
 
 
 @invocation("img_resize", title="Resize Image", tags=["image", "resize"], category="image", version="1.0.0")
-class ImageResizeInvocation(BaseInvocation):
+class ImageResizeInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Resizes an image to specific dimensions"""
 
     image: ImageField = InputField(description="The image to resize")
     width: int = InputField(default=512, gt=0, description="The width to resize to (px)")
     height: int = InputField(default=512, gt=0, description="The height to resize to (px)")
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
-    metadata: Optional[CoreMetadata] = InputField(
-        default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
-    )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
@@ -359,7 +500,7 @@ class ImageResizeInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -371,7 +512,7 @@ class ImageResizeInvocation(BaseInvocation):
 
 
 @invocation("img_scale", title="Scale Image", tags=["image", "scale"], category="image", version="1.0.0")
-class ImageScaleInvocation(BaseInvocation):
+class ImageScaleInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Scales an image by a factor"""
 
     image: ImageField = InputField(description="The image to scale")
@@ -401,6 +542,7 @@ class ImageScaleInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -412,7 +554,7 @@ class ImageScaleInvocation(BaseInvocation):
 
 
 @invocation("img_lerp", title="Lerp Image", tags=["image", "lerp"], category="image", version="1.0.0")
-class ImageLerpInvocation(BaseInvocation):
+class ImageLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Linear interpolation of all pixels of an image"""
 
     image: ImageField = InputField(description="The image to lerp")
@@ -434,6 +576,7 @@ class ImageLerpInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -445,7 +588,7 @@ class ImageLerpInvocation(BaseInvocation):
 
 
 @invocation("img_ilerp", title="Inverse Lerp Image", tags=["image", "ilerp"], category="image", version="1.0.0")
-class ImageInverseLerpInvocation(BaseInvocation):
+class ImageInverseLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Inverse linear interpolation of all pixels of an image"""
 
     image: ImageField = InputField(description="The image to lerp")
@@ -456,7 +599,7 @@ class ImageInverseLerpInvocation(BaseInvocation):
         image = context.services.images.get_pil_image(self.image.image_name)
 
         image_arr = numpy.asarray(image, dtype=numpy.float32)
-        image_arr = numpy.minimum(numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1) * 255
+        image_arr = numpy.minimum(numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1) * 255  # type: ignore [assignment]
 
         ilerp_image = Image.fromarray(numpy.uint8(image_arr))
 
@@ -467,6 +610,7 @@ class ImageInverseLerpInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -478,13 +622,10 @@ class ImageInverseLerpInvocation(BaseInvocation):
 
 
 @invocation("img_nsfw", title="Blur NSFW Image", tags=["image", "nsfw"], category="image", version="1.0.0")
-class ImageNSFWBlurInvocation(BaseInvocation):
+class ImageNSFWBlurInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Add blur to NSFW-flagged images"""
 
     image: ImageField = InputField(description="The image to check")
-    metadata: Optional[CoreMetadata] = InputField(
-        default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
-    )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
@@ -505,7 +646,7 @@ class ImageNSFWBlurInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -515,7 +656,7 @@ class ImageNSFWBlurInvocation(BaseInvocation):
             height=image_dto.height,
         )
 
-    def _get_caution_img(self) -> Image:
+    def _get_caution_img(self) -> Image.Image:
         import invokeai.app.assets.images as image_assets
 
         caution = Image.open(Path(image_assets.__path__[0]) / "caution.png")
@@ -523,16 +664,17 @@ class ImageNSFWBlurInvocation(BaseInvocation):
 
 
 @invocation(
-    "img_watermark", title="Add Invisible Watermark", tags=["image", "watermark"], category="image", version="1.0.0"
+    "img_watermark",
+    title="Add Invisible Watermark",
+    tags=["image", "watermark"],
+    category="image",
+    version="1.0.0",
 )
-class ImageWatermarkInvocation(BaseInvocation):
+class ImageWatermarkInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Add an invisible watermark to an image"""
 
     image: ImageField = InputField(description="The image to check")
     text: str = InputField(default="InvokeAI", description="Watermark text")
-    metadata: Optional[CoreMetadata] = InputField(
-        default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
-    )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
@@ -544,7 +686,7 @@ class ImageWatermarkInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -556,7 +698,7 @@ class ImageWatermarkInvocation(BaseInvocation):
 
 
 @invocation("mask_edge", title="Mask Edge", tags=["image", "mask", "inpaint"], category="image", version="1.0.0")
-class MaskEdgeInvocation(BaseInvocation):
+class MaskEdgeInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Applies an edge mask to an image"""
 
     image: ImageField = InputField(description="The image to apply the mask to")
@@ -590,6 +732,7 @@ class MaskEdgeInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -601,9 +744,13 @@ class MaskEdgeInvocation(BaseInvocation):
 
 
 @invocation(
-    "mask_combine", title="Combine Masks", tags=["image", "mask", "multiply"], category="image", version="1.0.0"
+    "mask_combine",
+    title="Combine Masks",
+    tags=["image", "mask", "multiply"],
+    category="image",
+    version="1.0.0",
 )
-class MaskCombineInvocation(BaseInvocation):
+class MaskCombineInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Combine two masks together by multiplying them using `PIL.ImageChops.multiply()`."""
 
     mask1: ImageField = InputField(description="The first mask to combine")
@@ -622,6 +769,7 @@ class MaskCombineInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -633,7 +781,7 @@ class MaskCombineInvocation(BaseInvocation):
 
 
 @invocation("color_correct", title="Color Correct", tags=["image", "color"], category="image", version="1.0.0")
-class ColorCorrectInvocation(BaseInvocation):
+class ColorCorrectInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """
     Shifts the colors of a target image to match the reference image, optionally
     using a mask to only color-correct certain regions of the target image.
@@ -732,6 +880,7 @@ class ColorCorrectInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -743,7 +892,7 @@ class ColorCorrectInvocation(BaseInvocation):
 
 
 @invocation("img_hue_adjust", title="Adjust Image Hue", tags=["image", "hue"], category="image", version="1.0.0")
-class ImageHueAdjustmentInvocation(BaseInvocation):
+class ImageHueAdjustmentInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Adjusts the Hue of an image."""
 
     image: ImageField = InputField(description="The image to adjust")
@@ -771,6 +920,7 @@ class ImageHueAdjustmentInvocation(BaseInvocation):
             node_id=self.id,
             is_intermediate=self.is_intermediate,
             session_id=context.graph_execution_state_id,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -846,7 +996,7 @@ CHANNEL_FORMATS = {
     category="image",
     version="1.0.0",
 )
-class ImageChannelOffsetInvocation(BaseInvocation):
+class ImageChannelOffsetInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Add or subtract a value from a specific color channel of an image."""
 
     image: ImageField = InputField(description="The image to adjust")
@@ -880,6 +1030,7 @@ class ImageChannelOffsetInvocation(BaseInvocation):
             node_id=self.id,
             is_intermediate=self.is_intermediate,
             session_id=context.graph_execution_state_id,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -916,7 +1067,7 @@ class ImageChannelOffsetInvocation(BaseInvocation):
     category="image",
     version="1.0.0",
 )
-class ImageChannelMultiplyInvocation(BaseInvocation):
+class ImageChannelMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Scale a specific color channel of an image."""
 
     image: ImageField = InputField(description="The image to adjust")
@@ -956,6 +1107,7 @@ class ImageChannelMultiplyInvocation(BaseInvocation):
             is_intermediate=self.is_intermediate,
             session_id=context.graph_execution_state_id,
             workflow=self.workflow,
+            metadata=self.metadata,
         )
 
         return ImageOutput(
@@ -975,16 +1127,11 @@ class ImageChannelMultiplyInvocation(BaseInvocation):
     version="1.0.1",
     use_cache=False,
 )
-class SaveImageInvocation(BaseInvocation):
+class SaveImageInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Saves an image. Unlike an image primitive, this invocation stores a copy of the image."""
 
     image: ImageField = InputField(description=FieldDescriptions.image)
-    board: Optional[BoardField] = InputField(default=None, description=FieldDescriptions.board, input=Input.Direct)
-    metadata: CoreMetadata = InputField(
-        default=None,
-        description=FieldDescriptions.core_metadata,
-        ui_hidden=True,
-    )
+    board: BoardField = InputField(default=None, description=FieldDescriptions.board, input=Input.Direct)
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
@@ -997,7 +1144,7 @@ class SaveImageInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 

invokeai/app/invocations/infill.py

@@ -7,13 +7,13 @@ import numpy as np
 from PIL import Image, ImageOps
 
 from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
 from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
 from invokeai.backend.image_util.lama import LaMA
 from invokeai.backend.image_util.patchmatch import PatchMatch
 
-from ..models.image import ImageCategory, ResourceOrigin
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
 from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
 
 
@@ -119,7 +119,7 @@ def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int]
 
 
 @invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
-class InfillColorInvocation(BaseInvocation):
+class InfillColorInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Infills transparent areas of an image with a solid color"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -143,6 +143,7 @@ class InfillColorInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -154,7 +155,7 @@ class InfillColorInvocation(BaseInvocation):
 
 
 @invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
-class InfillTileInvocation(BaseInvocation):
+class InfillTileInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Infills transparent areas of an image with tiles of the image"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -179,6 +180,7 @@ class InfillTileInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -192,7 +194,7 @@ class InfillTileInvocation(BaseInvocation):
 @invocation(
     "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0"
 )
-class InfillPatchMatchInvocation(BaseInvocation):
+class InfillPatchMatchInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -232,6 +234,7 @@ class InfillPatchMatchInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -243,7 +246,7 @@ class InfillPatchMatchInvocation(BaseInvocation):
 
 
 @invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
-class LaMaInfillInvocation(BaseInvocation):
+class LaMaInfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Infills transparent areas of an image using the LaMa model"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -260,6 +263,8 @@ class LaMaInfillInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
+            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -270,7 +275,7 @@ class LaMaInfillInvocation(BaseInvocation):
 
 
 @invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint")
-class CV2InfillInvocation(BaseInvocation):
+class CV2InfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -287,6 +292,8 @@ class CV2InfillInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
+            workflow=self.workflow,
         )
 
         return ImageOutput(

invokeai/app/invocations/ip_adapter.py

@@ -2,7 +2,7 @@ import os
 from builtins import float
 from typing import List, Union
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -25,14 +25,18 @@ class IPAdapterModelField(BaseModel):
     model_name: str = Field(description="Name of the IP-Adapter model")
     base_model: BaseModelType = Field(description="Base model")
 
+    model_config = ConfigDict(protected_namespaces=())
+
 
 class CLIPVisionModelField(BaseModel):
     model_name: str = Field(description="Name of the CLIP Vision image encoder model")
     base_model: BaseModelType = Field(description="Base model (usually 'Any')")
 
+    model_config = ConfigDict(protected_namespaces=())
+
 
 class IPAdapterField(BaseModel):
-    image: ImageField = Field(description="The IP-Adapter image prompt.")
+    image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
     ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
     image_encoder_model: CLIPVisionModelField = Field(description="The name of the CLIP image encoder model.")
     weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
@@ -51,19 +55,19 @@ class IPAdapterOutput(BaseInvocationOutput):
     ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.0.0")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.0")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
     # Inputs
-    image: ImageField = InputField(description="The IP-Adapter image prompt.")
+    image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).")
     ip_adapter_model: IPAdapterModelField = InputField(
         description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
     )
 
     # weight: float = InputField(default=1.0, description="The weight of the IP-Adapter.", ui_type=UIType.Float)
     weight: Union[float, List[float]] = InputField(
-        default=1, ge=0, description="The weight given to the IP-Adapter", ui_type=UIType.Float, title="Weight"
+        default=1, ge=-1, description="The weight given to the IP-Adapter", ui_type=UIType.Float, title="Weight"
     )
 
     begin_step_percent: float = InputField(

invokeai/app/invocations/latent.py

@@ -10,7 +10,7 @@ import torch
 import torchvision.transforms as T
 from diffusers import AutoencoderKL, AutoencoderTiny
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.models import UNet2DConditionModel
+from diffusers.models.adapter import FullAdapterXL, T2IAdapter
 from diffusers.models.attention_processor import (
     AttnProcessor2_0,
     LoRAAttnProcessor2_0,
@@ -19,11 +19,10 @@ from diffusers.models.attention_processor import (
 )
 from diffusers.schedulers import DPMSolverSDEScheduler
 from diffusers.schedulers import SchedulerMixin as Scheduler
-from pydantic import validator
+from pydantic import field_validator
 from torchvision.transforms.functional import resize as tv_resize
 
 from invokeai.app.invocations.ip_adapter import IPAdapterField
-from invokeai.app.invocations.metadata import CoreMetadata
 from invokeai.app.invocations.primitives import (
     DenoiseMaskField,
     DenoiseMaskOutput,
@@ -33,6 +32,8 @@ from invokeai.app.invocations.primitives import (
     LatentsOutput,
     build_latents_output,
 )
+from invokeai.app.invocations.t2i_adapter import T2IAdapterField
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
@@ -47,12 +48,12 @@ from ...backend.stable_diffusion.diffusers_pipeline import (
     ControlNetData,
     IPAdapterData,
     StableDiffusionGeneratorPipeline,
+    T2IAdapterData,
     image_resized_to_grid_as_tensor,
 )
 from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
 from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
 from ...backend.util.devices import choose_precision, choose_torch_device
-from ..models.image import ImageCategory, ResourceOrigin
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -62,6 +63,8 @@ from .baseinvocation import (
     InvocationContext,
     OutputField,
     UIType,
+    WithMetadata,
+    WithWorkflow,
     invocation,
     invocation_output,
 )
@@ -82,12 +85,20 @@ class SchedulerOutput(BaseInvocationOutput):
     scheduler: SAMPLER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
 
 
-@invocation("scheduler", title="Scheduler", tags=["scheduler"], category="latents", version="1.0.0")
+@invocation(
+    "scheduler",
+    title="Scheduler",
+    tags=["scheduler"],
+    category="latents",
+    version="1.0.0",
+)
 class SchedulerInvocation(BaseInvocation):
     """Selects a scheduler."""
 
     scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler
+        default="euler",
+        description=FieldDescriptions.scheduler,
+        ui_type=UIType.Scheduler,
     )
 
     def invoke(self, context: InvocationContext) -> SchedulerOutput:
@@ -95,7 +106,11 @@ class SchedulerInvocation(BaseInvocation):
 
 
 @invocation(
-    "create_denoise_mask", title="Create Denoise Mask", tags=["mask", "denoise"], category="latents", version="1.0.0"
+    "create_denoise_mask",
+    title="Create Denoise Mask",
+    tags=["mask", "denoise"],
+    category="latents",
+    version="1.0.0",
 )
 class CreateDenoiseMaskInvocation(BaseInvocation):
     """Creates mask for denoising model run."""
@@ -104,7 +119,11 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
     image: Optional[ImageField] = InputField(default=None, description="Image which will be masked", ui_order=1)
     mask: ImageField = InputField(description="The mask to use when pasting", ui_order=2)
     tiled: bool = InputField(default=False, description=FieldDescriptions.tiled, ui_order=3)
-    fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32, ui_order=4)
+    fp32: bool = InputField(
+        default=DEFAULT_PRECISION == "float32",
+        description=FieldDescriptions.fp32,
+        ui_order=4,
+    )
 
     def prep_mask_tensor(self, mask_image):
         if mask_image.mode != "L":
@@ -132,7 +151,7 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
 
         if image is not None:
             vae_info = context.services.model_manager.get_model(
-                **self.vae.vae.dict(),
+                **self.vae.vae.model_dump(),
                 context=context,
             )
 
@@ -165,7 +184,7 @@ def get_scheduler(
 ) -> Scheduler:
     scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
     orig_scheduler_info = context.services.model_manager.get_model(
-        **scheduler_info.dict(),
+        **scheduler_info.model_dump(),
         context=context,
     )
     with orig_scheduler_info as orig_scheduler:
@@ -196,7 +215,7 @@ def get_scheduler(
     title="Denoise Latents",
     tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
     category="latents",
-    version="1.1.0",
+    version="1.4.0",
 )
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
@@ -207,31 +226,64 @@ class DenoiseLatentsInvocation(BaseInvocation):
     negative_conditioning: ConditioningField = InputField(
         description=FieldDescriptions.negative_cond, input=Input.Connection, ui_order=1
     )
-    noise: Optional[LatentsField] = InputField(description=FieldDescriptions.noise, input=Input.Connection, ui_order=3)
+    noise: Optional[LatentsField] = InputField(
+        default=None,
+        description=FieldDescriptions.noise,
+        input=Input.Connection,
+        ui_order=3,
+    )
     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"
     )
-    denoising_start: float = InputField(default=0.0, ge=0, le=1, description=FieldDescriptions.denoising_start)
+    denoising_start: float = InputField(
+        default=0.0,
+        ge=0,
+        le=1,
+        description=FieldDescriptions.denoising_start,
+    )
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
     scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler
+        default="euler",
+        description=FieldDescriptions.scheduler,
+        ui_type=UIType.Scheduler,
     )
-    unet: UNetField = InputField(description=FieldDescriptions.unet, input=Input.Connection, title="UNet", ui_order=2)
-    control: Union[ControlField, list[ControlField]] = InputField(
+    unet: UNetField = InputField(
+        description=FieldDescriptions.unet,
+        input=Input.Connection,
+        title="UNet",
+        ui_order=2,
+    )
+    control: Optional[Union[ControlField, list[ControlField]]] = InputField(
         default=None,
         input=Input.Connection,
         ui_order=5,
     )
-    ip_adapter: Optional[IPAdapterField] = InputField(
-        description=FieldDescriptions.ip_adapter, title="IP-Adapter", default=None, input=Input.Connection, ui_order=6
+    ip_adapter: Optional[Union[IPAdapterField, list[IPAdapterField]]] = InputField(
+        description=FieldDescriptions.ip_adapter,
+        title="IP-Adapter",
+        default=None,
+        input=Input.Connection,
+        ui_order=6,
+    )
+    t2i_adapter: Optional[Union[T2IAdapterField, list[T2IAdapterField]]] = InputField(
+        description=FieldDescriptions.t2i_adapter,
+        title="T2I-Adapter",
+        default=None,
+        input=Input.Connection,
+        ui_order=7,
+    )
+    latents: Optional[LatentsField] = InputField(
+        default=None, description=FieldDescriptions.latents, input=Input.Connection
     )
-    latents: Optional[LatentsField] = InputField(description=FieldDescriptions.latents, input=Input.Connection)
     denoise_mask: Optional[DenoiseMaskField] = InputField(
-        default=None, description=FieldDescriptions.mask, input=Input.Connection, ui_order=7
+        default=None,
+        description=FieldDescriptions.mask,
+        input=Input.Connection,
+        ui_order=8,
     )
 
-    @validator("cfg_scale")
+    @field_validator("cfg_scale")
     def ge_one(cls, v):
         """validate that all cfg_scale values are >= 1"""
         if isinstance(v, list):
@@ -254,7 +306,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
-            node=self.dict(),
+            node=self.model_dump(),
             source_node_id=source_node_id,
             base_model=base_model,
         )
@@ -404,52 +456,156 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def prep_ip_adapter_data(
         self,
         context: InvocationContext,
-        ip_adapter: Optional[IPAdapterField],
+        ip_adapter: Optional[Union[IPAdapterField, list[IPAdapterField]]],
         conditioning_data: ConditioningData,
-        unet: UNet2DConditionModel,
         exit_stack: ExitStack,
-    ) -> Optional[IPAdapterData]:
+    ) -> Optional[list[IPAdapterData]]:
         """If IP-Adapter is enabled, then this function loads the requisite models, and adds the image prompt embeddings
         to the `conditioning_data` (in-place).
         """
         if ip_adapter is None:
             return None
 
-        image_encoder_model_info = context.services.model_manager.get_model(
-            model_name=ip_adapter.image_encoder_model.model_name,
-            model_type=ModelType.CLIPVision,
-            base_model=ip_adapter.image_encoder_model.base_model,
-            context=context,
-        )
+        # ip_adapter could be a list or a single IPAdapterField. Normalize to a list here.
+        if not isinstance(ip_adapter, list):
+            ip_adapter = [ip_adapter]
 
-        ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
-            context.services.model_manager.get_model(
-                model_name=ip_adapter.ip_adapter_model.model_name,
-                model_type=ModelType.IPAdapter,
-                base_model=ip_adapter.ip_adapter_model.base_model,
+        if len(ip_adapter) == 0:
+            return None
+
+        ip_adapter_data_list = []
+        conditioning_data.ip_adapter_conditioning = []
+        for single_ip_adapter in ip_adapter:
+            ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
+                context.services.model_manager.get_model(
+                    model_name=single_ip_adapter.ip_adapter_model.model_name,
+                    model_type=ModelType.IPAdapter,
+                    base_model=single_ip_adapter.ip_adapter_model.base_model,
+                    context=context,
+                )
+            )
+
+            image_encoder_model_info = context.services.model_manager.get_model(
+                model_name=single_ip_adapter.image_encoder_model.model_name,
+                model_type=ModelType.CLIPVision,
+                base_model=single_ip_adapter.image_encoder_model.base_model,
                 context=context,
             )
-        )
 
-        input_image = context.services.images.get_pil_image(ip_adapter.image.image_name)
+            # `single_ip_adapter.image` could be a list or a single ImageField. Normalize to a list here.
+            single_ipa_images = single_ip_adapter.image
+            if not isinstance(single_ipa_images, list):
+                single_ipa_images = [single_ipa_images]
 
-        # TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
-        # models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
-        with image_encoder_model_info as image_encoder_model:
-            # Get image embeddings from CLIP and ImageProjModel.
-            image_prompt_embeds, uncond_image_prompt_embeds = ip_adapter_model.get_image_embeds(
-                input_image, image_encoder_model
-            )
-            conditioning_data.ip_adapter_conditioning = IPAdapterConditioningInfo(
-                image_prompt_embeds, uncond_image_prompt_embeds
+            single_ipa_images = [context.services.images.get_pil_image(image.image_name) for image in single_ipa_images]
+
+            # TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
+            # models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
+            with image_encoder_model_info as image_encoder_model:
+                # Get image embeddings from CLIP and ImageProjModel.
+                image_prompt_embeds, uncond_image_prompt_embeds = ip_adapter_model.get_image_embeds(
+                    single_ipa_images, image_encoder_model
+                )
+
+                conditioning_data.ip_adapter_conditioning.append(
+                    IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds)
+                )
+
+            ip_adapter_data_list.append(
+                IPAdapterData(
+                    ip_adapter_model=ip_adapter_model,
+                    weight=single_ip_adapter.weight,
+                    begin_step_percent=single_ip_adapter.begin_step_percent,
+                    end_step_percent=single_ip_adapter.end_step_percent,
+                )
             )
 
-        return IPAdapterData(
-            ip_adapter_model=ip_adapter_model,
-            weight=ip_adapter.weight,
-            begin_step_percent=ip_adapter.begin_step_percent,
-            end_step_percent=ip_adapter.end_step_percent,
-        )
+        return ip_adapter_data_list
+
+    def run_t2i_adapters(
+        self,
+        context: InvocationContext,
+        t2i_adapter: Optional[Union[T2IAdapterField, list[T2IAdapterField]]],
+        latents_shape: list[int],
+        do_classifier_free_guidance: bool,
+    ) -> Optional[list[T2IAdapterData]]:
+        if t2i_adapter is None:
+            return None
+
+        # Handle the possibility that t2i_adapter could be a list or a single T2IAdapterField.
+        if isinstance(t2i_adapter, T2IAdapterField):
+            t2i_adapter = [t2i_adapter]
+
+        if len(t2i_adapter) == 0:
+            return None
+
+        t2i_adapter_data = []
+        for t2i_adapter_field in t2i_adapter:
+            t2i_adapter_model_info = context.services.model_manager.get_model(
+                model_name=t2i_adapter_field.t2i_adapter_model.model_name,
+                model_type=ModelType.T2IAdapter,
+                base_model=t2i_adapter_field.t2i_adapter_model.base_model,
+                context=context,
+            )
+            image = context.services.images.get_pil_image(t2i_adapter_field.image.image_name)
+
+            # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
+            if t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusion1:
+                max_unet_downscale = 8
+            elif t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusionXL:
+                max_unet_downscale = 4
+            else:
+                raise ValueError(
+                    f"Unexpected T2I-Adapter base model type: '{t2i_adapter_field.t2i_adapter_model.base_model}'."
+                )
+
+            t2i_adapter_model: T2IAdapter
+            with t2i_adapter_model_info as t2i_adapter_model:
+                total_downscale_factor = t2i_adapter_model.total_downscale_factor
+                if isinstance(t2i_adapter_model.adapter, FullAdapterXL):
+                    # HACK(ryand): Work around a bug in FullAdapterXL. This is being addressed upstream in diffusers by
+                    # this PR: https://github.com/huggingface/diffusers/pull/5134.
+                    total_downscale_factor = total_downscale_factor // 2
+
+                # Resize the T2I-Adapter input image.
+                # We select the resize dimensions so that after the T2I-Adapter's total_downscale_factor is applied, the
+                # result will match the latent image's dimensions after max_unet_downscale is applied.
+                t2i_input_height = latents_shape[2] // max_unet_downscale * total_downscale_factor
+                t2i_input_width = latents_shape[3] // max_unet_downscale * total_downscale_factor
+
+                # Note: We have hard-coded `do_classifier_free_guidance=False`. This is because we only want to prepare
+                # a single image. If CFG is enabled, we will duplicate the resultant tensor after applying the
+                # T2I-Adapter model.
+                #
+                # Note: We re-use the `prepare_control_image(...)` from ControlNet for T2I-Adapter, because it has many
+                # of the same requirements (e.g. preserving binary masks during resize).
+                t2i_image = prepare_control_image(
+                    image=image,
+                    do_classifier_free_guidance=False,
+                    width=t2i_input_width,
+                    height=t2i_input_height,
+                    num_channels=t2i_adapter_model.config.in_channels,
+                    device=t2i_adapter_model.device,
+                    dtype=t2i_adapter_model.dtype,
+                    resize_mode=t2i_adapter_field.resize_mode,
+                )
+
+                adapter_state = t2i_adapter_model(t2i_image)
+
+            if do_classifier_free_guidance:
+                for idx, value in enumerate(adapter_state):
+                    adapter_state[idx] = torch.cat([value] * 2, dim=0)
+
+            t2i_adapter_data.append(
+                T2IAdapterData(
+                    adapter_state=adapter_state,
+                    weight=t2i_adapter_field.weight,
+                    begin_step_percent=t2i_adapter_field.begin_step_percent,
+                    end_step_percent=t2i_adapter_field.end_step_percent,
+                )
+            )
+
+        return t2i_adapter_data
 
     # original idea by https://github.com/AmericanPresidentJimmyCarter
     # TODO: research more for second order schedulers timesteps
@@ -522,6 +678,15 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
             mask, masked_latents = self.prep_inpaint_mask(context, latents)
 
+            # TODO(ryand): I have hard-coded `do_classifier_free_guidance=True` to mirror the behaviour of ControlNets,
+            # below. Investigate whether this is appropriate.
+            t2i_adapter_data = self.run_t2i_adapters(
+                context,
+                self.t2i_adapter,
+                latents.shape,
+                do_classifier_free_guidance=True,
+            )
+
             # Get the source node id (we are invoking the prepared node)
             graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
             source_node_id = graph_execution_state.prepared_source_mapping[self.id]
@@ -532,7 +697,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             def _lora_loader():
                 for lora in self.unet.loras:
                     lora_info = context.services.model_manager.get_model(
-                        **lora.dict(exclude={"weight"}),
+                        **lora.model_dump(exclude={"weight"}),
                         context=context,
                     )
                     yield (lora_info.context.model, lora.weight)
@@ -540,7 +705,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 return
 
             unet_info = context.services.model_manager.get_model(
-                **self.unet.unet.dict(),
+                **self.unet.unet.model_dump(),
                 context=context,
             )
             with (
@@ -580,7 +745,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     context=context,
                     ip_adapter=self.ip_adapter,
                     conditioning_data=conditioning_data,
-                    unet=unet,
                     exit_stack=exit_stack,
                 )
 
@@ -592,7 +756,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     denoising_end=self.denoising_end,
                 )
 
-                result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
+                (
+                    result_latents,
+                    result_attention_map_saver,
+                ) = pipeline.latents_from_embeddings(
                     latents=latents,
                     timesteps=timesteps,
                     init_timestep=init_timestep,
@@ -602,8 +769,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     masked_latents=masked_latents,
                     num_inference_steps=num_inference_steps,
                     conditioning_data=conditioning_data,
-                    control_data=controlnet_data,  # list[ControlNetData],
-                    ip_adapter_data=ip_adapter_data,  # IPAdapterData,
+                    control_data=controlnet_data,
+                    ip_adapter_data=ip_adapter_data,
+                    t2i_adapter_data=t2i_adapter_data,
                     callback=step_callback,
                 )
 
@@ -619,9 +787,13 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
 
 @invocation(
-    "l2i", title="Latents to Image", tags=["latents", "image", "vae", "l2i"], category="latents", version="1.0.0"
+    "l2i",
+    title="Latents to Image",
+    tags=["latents", "image", "vae", "l2i"],
+    category="latents",
+    version="1.0.0",
 )
-class LatentsToImageInvocation(BaseInvocation):
+class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Generates an image from latents."""
 
     latents: LatentsField = InputField(
@@ -634,18 +806,13 @@ class LatentsToImageInvocation(BaseInvocation):
     )
     tiled: bool = InputField(default=False, description=FieldDescriptions.tiled)
     fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
-    metadata: CoreMetadata = InputField(
-        default=None,
-        description=FieldDescriptions.core_metadata,
-        ui_hidden=True,
-    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ImageOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
         vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.dict(),
+            **self.vae.vae.model_dump(),
             context=context,
         )
 
@@ -707,7 +874,7 @@ class LatentsToImageInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -721,7 +888,13 @@ class LatentsToImageInvocation(BaseInvocation):
 LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
 
 
-@invocation("lresize", title="Resize Latents", tags=["latents", "resize"], category="latents", version="1.0.0")
+@invocation(
+    "lresize",
+    title="Resize Latents",
+    tags=["latents", "resize"],
+    category="latents",
+    version="1.0.0",
+)
 class ResizeLatentsInvocation(BaseInvocation):
     """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
 
@@ -767,7 +940,13 @@ class ResizeLatentsInvocation(BaseInvocation):
         return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
-@invocation("lscale", title="Scale Latents", tags=["latents", "resize"], category="latents", version="1.0.0")
+@invocation(
+    "lscale",
+    title="Scale Latents",
+    tags=["latents", "resize"],
+    category="latents",
+    version="1.0.0",
+)
 class ScaleLatentsInvocation(BaseInvocation):
     """Scales latents by a given factor."""
 
@@ -806,7 +985,11 @@ class ScaleLatentsInvocation(BaseInvocation):
 
 
 @invocation(
-    "i2l", title="Image to Latents", tags=["latents", "image", "vae", "i2l"], category="latents", version="1.0.0"
+    "i2l",
+    title="Image to Latents",
+    tags=["latents", "image", "vae", "i2l"],
+    category="latents",
+    version="1.0.0",
 )
 class ImageToLatentsInvocation(BaseInvocation):
     """Encodes an image into latents."""
@@ -870,7 +1053,7 @@ class ImageToLatentsInvocation(BaseInvocation):
         image = context.services.images.get_pil_image(self.image.image_name)
 
         vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.dict(),
+            **self.vae.vae.model_dump(),
             context=context,
         )
 
@@ -898,7 +1081,13 @@ class ImageToLatentsInvocation(BaseInvocation):
         return vae.encode(image_tensor).latents
 
 
-@invocation("lblend", title="Blend Latents", tags=["latents", "blend"], category="latents", version="1.0.0")
+@invocation(
+    "lblend",
+    title="Blend Latents",
+    tags=["latents", "blend"],
+    category="latents",
+    version="1.0.0",
+)
 class BlendLatentsInvocation(BaseInvocation):
     """Blend two latents using a given alpha. Latents must have same size."""
 

invokeai/app/invocations/math.py

@@ -3,7 +3,7 @@
 from typing import Literal
 
 import numpy as np
-from pydantic import validator
+from pydantic import ValidationInfo, field_validator
 
 from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
 
@@ -65,13 +65,34 @@ class DivideInvocation(BaseInvocation):
 class RandomIntInvocation(BaseInvocation):
     """Outputs a single random integer."""
 
-    low: int = InputField(default=0, description="The inclusive low value")
-    high: int = InputField(default=np.iinfo(np.int32).max, description="The exclusive high value")
+    low: int = InputField(default=0, description=FieldDescriptions.inclusive_low)
+    high: int = InputField(default=np.iinfo(np.int32).max, description=FieldDescriptions.exclusive_high)
 
     def invoke(self, context: InvocationContext) -> IntegerOutput:
         return IntegerOutput(value=np.random.randint(self.low, self.high))
 
 
+@invocation(
+    "rand_float",
+    title="Random Float",
+    tags=["math", "float", "random"],
+    category="math",
+    version="1.0.1",
+    use_cache=False,
+)
+class RandomFloatInvocation(BaseInvocation):
+    """Outputs a single random float"""
+
+    low: float = InputField(default=0.0, description=FieldDescriptions.inclusive_low)
+    high: float = InputField(default=1.0, description=FieldDescriptions.exclusive_high)
+    decimals: int = InputField(default=2, description=FieldDescriptions.decimal_places)
+
+    def invoke(self, context: InvocationContext) -> FloatOutput:
+        random_float = np.random.uniform(self.low, self.high)
+        rounded_float = round(random_float, self.decimals)
+        return FloatOutput(value=rounded_float)
+
+
 @invocation(
     "float_to_int",
     title="Float To Integer",
@@ -164,13 +185,13 @@ class IntegerMathInvocation(BaseInvocation):
     a: int = InputField(default=0, description=FieldDescriptions.num_1)
     b: int = InputField(default=0, description=FieldDescriptions.num_2)
 
-    @validator("b")
-    def no_unrepresentable_results(cls, v, values):
-        if values["operation"] == "DIV" and v == 0:
+    @field_validator("b")
+    def no_unrepresentable_results(cls, v: int, info: ValidationInfo):
+        if info.data["operation"] == "DIV" and v == 0:
             raise ValueError("Cannot divide by zero")
-        elif values["operation"] == "MOD" and v == 0:
+        elif info.data["operation"] == "MOD" and v == 0:
             raise ValueError("Cannot divide by zero")
-        elif values["operation"] == "EXP" and v < 0:
+        elif info.data["operation"] == "EXP" and v < 0:
             raise ValueError("Result of exponentiation is not an integer")
         return v
 
@@ -238,13 +259,13 @@ class FloatMathInvocation(BaseInvocation):
     a: float = InputField(default=0, description=FieldDescriptions.num_1)
     b: float = InputField(default=0, description=FieldDescriptions.num_2)
 
-    @validator("b")
-    def no_unrepresentable_results(cls, v, values):
-        if values["operation"] == "DIV" and v == 0:
+    @field_validator("b")
+    def no_unrepresentable_results(cls, v: float, info: ValidationInfo):
+        if info.data["operation"] == "DIV" and v == 0:
             raise ValueError("Cannot divide by zero")
-        elif values["operation"] == "EXP" and values["a"] == 0 and v < 0:
+        elif info.data["operation"] == "EXP" and info.data["a"] == 0 and v < 0:
             raise ValueError("Cannot raise zero to a negative power")
-        elif values["operation"] == "EXP" and type(values["a"] ** v) is complex:
+        elif info.data["operation"] == "EXP" and type(info.data["a"] ** v) is complex:
             raise ValueError("Root operation resulted in a complex number")
         return v
 

invokeai/app/invocations/metadata.py

@@ -1,129 +1,151 @@
-from typing import Optional
+from typing import Any, Literal, Optional, Union
 
-from pydantic import Field
+from pydantic import BaseModel, ConfigDict, Field
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
+    FieldDescriptions,
     InputField,
     InvocationContext,
+    MetadataField,
     OutputField,
+    UIType,
     invocation,
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import ControlField
+from invokeai.app.invocations.ip_adapter import IPAdapterModelField
 from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
-from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
+from invokeai.app.invocations.primitives import ImageField
+from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 
 from ...version import __version__
 
 
-class LoRAMetadataField(BaseModelExcludeNull):
-    """LoRA metadata for an image generated in InvokeAI."""
-
-    lora: LoRAModelField = Field(description="The LoRA model")
-    weight: float = Field(description="The weight of the LoRA model")
+class MetadataItemField(BaseModel):
+    label: str = Field(description=FieldDescriptions.metadata_item_label)
+    value: Any = Field(description=FieldDescriptions.metadata_item_value)
 
 
-class CoreMetadata(BaseModelExcludeNull):
-    """Core generation metadata for an image generated in InvokeAI."""
+class LoRAMetadataField(BaseModel):
+    """LoRA Metadata Field"""
 
-    app_version: str = Field(default=__version__, description="The version of InvokeAI used to generate this image")
-    generation_mode: str = Field(
+    lora: LoRAModelField = Field(description=FieldDescriptions.lora_model)
+    weight: float = Field(description=FieldDescriptions.lora_weight)
+
+
+class IPAdapterMetadataField(BaseModel):
+    """IP Adapter Field, minus the CLIP Vision Encoder model"""
+
+    image: ImageField = Field(description="The IP-Adapter image prompt.")
+    ip_adapter_model: IPAdapterModelField = Field(
+        description="The IP-Adapter model.",
+    )
+    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)")
+
+
+@invocation_output("metadata_item_output")
+class MetadataItemOutput(BaseInvocationOutput):
+    """Metadata Item Output"""
+
+    item: MetadataItemField = OutputField(description="Metadata Item")
+
+
+@invocation("metadata_item", title="Metadata Item", tags=["metadata"], category="metadata", version="1.0.0")
+class MetadataItemInvocation(BaseInvocation):
+    """Used to create an arbitrary metadata item. Provide "label" and make a connection to "value" to store that data as the value."""
+
+    label: str = InputField(description=FieldDescriptions.metadata_item_label)
+    value: Any = InputField(description=FieldDescriptions.metadata_item_value, ui_type=UIType.Any)
+
+    def invoke(self, context: InvocationContext) -> MetadataItemOutput:
+        return MetadataItemOutput(item=MetadataItemField(label=self.label, value=self.value))
+
+
+@invocation_output("metadata_output")
+class MetadataOutput(BaseInvocationOutput):
+    metadata: MetadataField = OutputField(description="Metadata Dict")
+
+
+@invocation("metadata", title="Metadata", tags=["metadata"], category="metadata", version="1.0.0")
+class MetadataInvocation(BaseInvocation):
+    """Takes a MetadataItem or collection of MetadataItems and outputs a MetadataDict."""
+
+    items: Union[list[MetadataItemField], MetadataItemField] = InputField(
+        description=FieldDescriptions.metadata_item_polymorphic
+    )
+
+    def invoke(self, context: InvocationContext) -> MetadataOutput:
+        if isinstance(self.items, MetadataItemField):
+            # single metadata item
+            data = {self.items.label: self.items.value}
+        else:
+            # collection of metadata items
+            data = {item.label: item.value for item in self.items}
+
+        # add app version
+        data.update({"app_version": __version__})
+        return MetadataOutput(metadata=MetadataField.model_validate(data))
+
+
+@invocation("merge_metadata", title="Metadata Merge", tags=["metadata"], category="metadata", version="1.0.0")
+class MergeMetadataInvocation(BaseInvocation):
+    """Merged a collection of MetadataDict into a single MetadataDict."""
+
+    collection: list[MetadataField] = InputField(description=FieldDescriptions.metadata_collection)
+
+    def invoke(self, context: InvocationContext) -> MetadataOutput:
+        data = {}
+        for item in self.collection:
+            data.update(item.model_dump())
+
+        return MetadataOutput(metadata=MetadataField.model_validate(data))
+
+
+GENERATION_MODES = Literal[
+    "txt2img", "img2img", "inpaint", "outpaint", "sdxl_txt2img", "sdxl_img2img", "sdxl_inpaint", "sdxl_outpaint"
+]
+
+
+@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.0.0")
+class CoreMetadataInvocation(BaseInvocation):
+    """Collects core generation metadata into a MetadataField"""
+
+    generation_mode: Optional[GENERATION_MODES] = InputField(
+        default=None,
         description="The generation mode that output this image",
     )
-    created_by: Optional[str] = Field(description="The name of the creator of the image")
-    positive_prompt: str = Field(description="The positive prompt parameter")
-    negative_prompt: str = Field(description="The negative prompt parameter")
-    width: int = Field(description="The width parameter")
-    height: int = Field(description="The height parameter")
-    seed: int = Field(description="The seed used for noise generation")
-    rand_device: str = Field(description="The device used for random number generation")
-    cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
-    steps: int = Field(description="The number of steps used for inference")
-    scheduler: str = Field(description="The scheduler used for inference")
-    clip_skip: Optional[int] = Field(
+    positive_prompt: Optional[str] = InputField(default=None, description="The positive prompt parameter")
+    negative_prompt: Optional[str] = InputField(default=None, description="The negative prompt parameter")
+    width: Optional[int] = InputField(default=None, description="The width parameter")
+    height: Optional[int] = InputField(default=None, description="The height parameter")
+    seed: Optional[int] = InputField(default=None, description="The seed used for noise generation")
+    rand_device: Optional[str] = InputField(default=None, description="The device used for random number generation")
+    cfg_scale: Optional[float] = InputField(default=None, description="The classifier-free guidance scale parameter")
+    steps: Optional[int] = InputField(default=None, description="The number of steps used for inference")
+    scheduler: Optional[str] = InputField(default=None, description="The scheduler used for inference")
+    seamless_x: Optional[bool] = InputField(default=None, description="Whether seamless tiling was used on the X axis")
+    seamless_y: Optional[bool] = InputField(default=None, description="Whether seamless tiling was used on the Y axis")
+    clip_skip: Optional[int] = InputField(
         default=None,
         description="The number of skipped CLIP layers",
     )
-    model: MainModelField = Field(description="The main model used for inference")
-    controlnets: list[ControlField] = Field(description="The ControlNets used for inference")
-    loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
-    vae: Optional[VAEModelField] = Field(
-        default=None,
-        description="The VAE used for decoding, if the main model's default was not used",
+    model: Optional[MainModelField] = InputField(default=None, description="The main model used for inference")
+    controlnets: Optional[list[ControlField]] = InputField(
+        default=None, description="The ControlNets used for inference"
     )
-
-    # Latents-to-Latents
-    strength: Optional[float] = Field(
-        default=None,
-        description="The strength used for latents-to-latents",
+    ipAdapters: Optional[list[IPAdapterMetadataField]] = InputField(
+        default=None, description="The IP Adapters used for inference"
     )
-    init_image: Optional[str] = Field(default=None, description="The name of the initial image")
-
-    # SDXL
-    positive_style_prompt: Optional[str] = Field(default=None, description="The positive style prompt parameter")
-    negative_style_prompt: Optional[str] = Field(default=None, description="The negative style prompt parameter")
-
-    # SDXL Refiner
-    refiner_model: Optional[MainModelField] = Field(default=None, description="The SDXL Refiner model used")
-    refiner_cfg_scale: Optional[float] = Field(
-        default=None,
-        description="The classifier-free guidance scale parameter used for the refiner",
+    t2iAdapters: Optional[list[T2IAdapterField]] = InputField(
+        default=None, description="The IP Adapters used for inference"
     )
-    refiner_steps: Optional[int] = Field(default=None, description="The number of steps used for the refiner")
-    refiner_scheduler: Optional[str] = Field(default=None, description="The scheduler used for the refiner")
-    refiner_positive_aesthetic_score: Optional[float] = Field(
-        default=None, description="The aesthetic score used for the refiner"
-    )
-    refiner_negative_aesthetic_score: Optional[float] = Field(
-        default=None, description="The aesthetic score used for the refiner"
-    )
-    refiner_start: Optional[float] = Field(default=None, description="The start value used for refiner denoising")
-
-
-class ImageMetadata(BaseModelExcludeNull):
-    """An image's generation metadata"""
-
-    metadata: Optional[dict] = Field(
-        default=None,
-        description="The image's core metadata, if it was created in the Linear or Canvas UI",
-    )
-    graph: Optional[dict] = Field(default=None, description="The graph that created the image")
-
-
-@invocation_output("metadata_accumulator_output")
-class MetadataAccumulatorOutput(BaseInvocationOutput):
-    """The output of the MetadataAccumulator node"""
-
-    metadata: CoreMetadata = OutputField(description="The core metadata for the image")
-
-
-@invocation(
-    "metadata_accumulator", title="Metadata Accumulator", tags=["metadata"], category="metadata", version="1.0.0"
-)
-class MetadataAccumulatorInvocation(BaseInvocation):
-    """Outputs a Core Metadata Object"""
-
-    generation_mode: str = InputField(
-        description="The generation mode that output this image",
-    )
-    positive_prompt: str = InputField(description="The positive prompt parameter")
-    negative_prompt: str = InputField(description="The negative prompt parameter")
-    width: int = InputField(description="The width parameter")
-    height: int = InputField(description="The height parameter")
-    seed: int = InputField(description="The seed used for noise generation")
-    rand_device: str = InputField(description="The device used for random number generation")
-    cfg_scale: float = InputField(description="The classifier-free guidance scale parameter")
-    steps: int = InputField(description="The number of steps used for inference")
-    scheduler: str = InputField(description="The scheduler used for inference")
-    clip_skip: Optional[int] = Field(
-        default=None,
-        description="The number of skipped CLIP layers",
-    )
-    model: MainModelField = InputField(description="The main model used for inference")
-    controlnets: list[ControlField] = InputField(description="The ControlNets used for inference")
-    loras: list[LoRAMetadataField] = InputField(description="The LoRAs used for inference")
+    loras: Optional[list[LoRAMetadataField]] = InputField(default=None, description="The LoRAs used for inference")
     strength: Optional[float] = InputField(
         default=None,
         description="The strength used for latents-to-latents",
@@ -137,6 +159,20 @@ class MetadataAccumulatorInvocation(BaseInvocation):
         description="The VAE used for decoding, if the main model's default was not used",
     )
 
+    # High resolution fix metadata.
+    hrf_width: Optional[int] = InputField(
+        default=None,
+        description="The high resolution fix height and width multipler.",
+    )
+    hrf_height: Optional[int] = InputField(
+        default=None,
+        description="The high resolution fix height and width multipler.",
+    )
+    hrf_strength: Optional[float] = InputField(
+        default=None,
+        description="The high resolution fix img2img strength used in the upscale pass.",
+    )
+
     # SDXL
     positive_style_prompt: Optional[str] = InputField(
         default=None,
@@ -177,7 +213,13 @@ class MetadataAccumulatorInvocation(BaseInvocation):
         description="The start value used for refiner denoising",
     )
 
-    def invoke(self, context: InvocationContext) -> MetadataAccumulatorOutput:
+    def invoke(self, context: InvocationContext) -> MetadataOutput:
         """Collects and outputs a CoreMetadata object"""
 
-        return MetadataAccumulatorOutput(metadata=CoreMetadata(**self.dict()))
+        return MetadataOutput(
+            metadata=MetadataField.model_validate(
+                self.model_dump(exclude_none=True, exclude={"id", "type", "is_intermediate", "use_cache"})
+            )
+        )
+
+    model_config = ConfigDict(extra="allow")

invokeai/app/invocations/model.py

@@ -1,7 +1,7 @@
 import copy
 from typing import List, Optional
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field
 
 from ...backend.model_management import BaseModelType, ModelType, SubModelType
 from .baseinvocation import (
@@ -24,6 +24,8 @@ class ModelInfo(BaseModel):
     model_type: ModelType = Field(description="Info to load submodel")
     submodel: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
 
+    model_config = ConfigDict(protected_namespaces=())
+
 
 class LoraInfo(ModelInfo):
     weight: float = Field(description="Lora's weight which to use when apply to model")
@@ -65,6 +67,8 @@ class MainModelField(BaseModel):
     base_model: BaseModelType = Field(description="Base model")
     model_type: ModelType = Field(description="Model Type")
 
+    model_config = ConfigDict(protected_namespaces=())
+
 
 class LoRAModelField(BaseModel):
     """LoRA model field"""
@@ -72,8 +76,16 @@ class LoRAModelField(BaseModel):
     model_name: str = Field(description="Name of the LoRA model")
     base_model: BaseModelType = Field(description="Base model")
 
+    model_config = ConfigDict(protected_namespaces=())
 
-@invocation("main_model_loader", title="Main Model", tags=["model"], category="model", version="1.0.0")
+
+@invocation(
+    "main_model_loader",
+    title="Main Model",
+    tags=["model"],
+    category="model",
+    version="1.0.0",
+)
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
 
@@ -180,10 +192,16 @@ class LoraLoaderInvocation(BaseInvocation):
     lora: LoRAModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
     weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
     unet: Optional[UNetField] = InputField(
-        default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
+        default=None,
+        description=FieldDescriptions.unet,
+        input=Input.Connection,
+        title="UNet",
     )
     clip: Optional[ClipField] = InputField(
-        default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP"
+        default=None,
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+        title="CLIP",
     )
 
     def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
@@ -244,20 +262,35 @@ class SDXLLoraLoaderOutput(BaseInvocationOutput):
     clip2: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 2")
 
 
-@invocation("sdxl_lora_loader", title="SDXL LoRA", tags=["lora", "model"], category="model", version="1.0.0")
+@invocation(
+    "sdxl_lora_loader",
+    title="SDXL LoRA",
+    tags=["lora", "model"],
+    category="model",
+    version="1.0.0",
+)
 class SDXLLoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
     lora: LoRAModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
     weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
     unet: Optional[UNetField] = InputField(
-        default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
+        default=None,
+        description=FieldDescriptions.unet,
+        input=Input.Connection,
+        title="UNet",
     )
     clip: Optional[ClipField] = InputField(
-        default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1"
+        default=None,
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+        title="CLIP 1",
     )
     clip2: Optional[ClipField] = InputField(
-        default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2"
+        default=None,
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+        title="CLIP 2",
     )
 
     def invoke(self, context: InvocationContext) -> SDXLLoraLoaderOutput:
@@ -330,6 +363,8 @@ class VAEModelField(BaseModel):
     model_name: str = Field(description="Name of the model")
     base_model: BaseModelType = Field(description="Base model")
 
+    model_config = ConfigDict(protected_namespaces=())
+
 
 @invocation_output("vae_loader_output")
 class VaeLoaderOutput(BaseInvocationOutput):
@@ -343,7 +378,10 @@ class VaeLoaderInvocation(BaseInvocation):
     """Loads a VAE model, outputting a VaeLoaderOutput"""
 
     vae_model: VAEModelField = InputField(
-        description=FieldDescriptions.vae_model, input=Input.Direct, ui_type=UIType.VaeModel, title="VAE"
+        description=FieldDescriptions.vae_model,
+        input=Input.Direct,
+        ui_type=UIType.VaeModel,
+        title="VAE",
     )
 
     def invoke(self, context: InvocationContext) -> VaeLoaderOutput:
@@ -372,19 +410,31 @@ class VaeLoaderInvocation(BaseInvocation):
 class SeamlessModeOutput(BaseInvocationOutput):
     """Modified Seamless Model output"""
 
-    unet: Optional[UNetField] = OutputField(description=FieldDescriptions.unet, title="UNet")
-    vae: Optional[VaeField] = OutputField(description=FieldDescriptions.vae, title="VAE")
+    unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
+    vae: Optional[VaeField] = OutputField(default=None, description=FieldDescriptions.vae, title="VAE")
 
 
-@invocation("seamless", title="Seamless", tags=["seamless", "model"], category="model", version="1.0.0")
+@invocation(
+    "seamless",
+    title="Seamless",
+    tags=["seamless", "model"],
+    category="model",
+    version="1.0.0",
+)
 class SeamlessModeInvocation(BaseInvocation):
     """Applies the seamless transformation to the Model UNet and VAE."""
 
     unet: Optional[UNetField] = InputField(
-        default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
+        default=None,
+        description=FieldDescriptions.unet,
+        input=Input.Connection,
+        title="UNet",
     )
     vae: Optional[VaeField] = InputField(
-        default=None, description=FieldDescriptions.vae_model, input=Input.Connection, title="VAE"
+        default=None,
+        description=FieldDescriptions.vae_model,
+        input=Input.Connection,
+        title="VAE",
     )
     seamless_y: bool = InputField(default=True, input=Input.Any, description="Specify whether Y axis is seamless")
     seamless_x: bool = InputField(default=True, input=Input.Any, description="Specify whether X axis is seamless")

invokeai/app/invocations/noise.py

@@ -2,7 +2,7 @@
 
 
 import torch
-from pydantic import validator
+from pydantic import field_validator
 
 from invokeai.app.invocations.latent import LatentsField
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
@@ -65,7 +65,7 @@ Nodes
 class NoiseOutput(BaseInvocationOutput):
     """Invocation noise output"""
 
-    noise: LatentsField = OutputField(default=None, description=FieldDescriptions.noise)
+    noise: LatentsField = OutputField(description=FieldDescriptions.noise)
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
@@ -78,7 +78,13 @@ def build_noise_output(latents_name: str, latents: torch.Tensor, seed: int):
     )
 
 
-@invocation("noise", title="Noise", tags=["latents", "noise"], category="latents", version="1.0.0")
+@invocation(
+    "noise",
+    title="Noise",
+    tags=["latents", "noise"],
+    category="latents",
+    version="1.0.0",
+)
 class NoiseInvocation(BaseInvocation):
     """Generates latent noise."""
 
@@ -105,7 +111,7 @@ class NoiseInvocation(BaseInvocation):
         description="Use CPU for noise generation (for reproducible results across platforms)",
     )
 
-    @validator("seed", pre=True)
+    @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 v % (SEED_MAX + 1)

invokeai/app/invocations/onnx.py

@@ -4,23 +4,22 @@ import inspect
 import re
 
 # from contextlib import ExitStack
-from typing import List, Literal, Optional, Union
+from typing import List, Literal, Union
 
 import numpy as np
 import torch
 from diffusers.image_processor import VaeImageProcessor
-from pydantic import BaseModel, Field, validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator
 from tqdm import tqdm
 
-from invokeai.app.invocations.metadata import CoreMetadata
 from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput, ImageField, ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend import BaseModelType, ModelType, SubModelType
 
 from ...backend.model_management import ONNXModelPatcher
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.util import choose_torch_device
-from ..models.image import ImageCategory, ResourceOrigin
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -31,6 +30,8 @@ from .baseinvocation import (
     OutputField,
     UIComponent,
     UIType,
+    WithMetadata,
+    WithWorkflow,
     invocation,
     invocation_output,
 )
@@ -63,14 +64,17 @@ class ONNXPromptInvocation(BaseInvocation):
 
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.dict(),
+            **self.clip.tokenizer.model_dump(),
         )
         text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.dict(),
+            **self.clip.text_encoder.model_dump(),
         )
         with tokenizer_info as orig_tokenizer, text_encoder_info as text_encoder:  # , ExitStack() as stack:
             loras = [
-                (context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight)
+                (
+                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
+                    lora.weight,
+                )
                 for lora in self.clip.loras
             ]
 
@@ -175,14 +179,14 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
         description=FieldDescriptions.unet,
         input=Input.Connection,
     )
-    control: Optional[Union[ControlField, list[ControlField]]] = InputField(
+    control: Union[ControlField, list[ControlField]] = InputField(
         default=None,
         description=FieldDescriptions.control,
     )
     # seamless:   bool = InputField(default=False, description="Whether or not to generate an image that can tile without seams", )
     # seamless_axes: str = InputField(default="", description="The axes to tile the image on, 'x' and/or 'y'")
 
-    @validator("cfg_scale")
+    @field_validator("cfg_scale")
     def ge_one(cls, v):
         """validate that all cfg_scale values are >= 1"""
         if isinstance(v, list):
@@ -241,7 +245,7 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
             stable_diffusion_step_callback(
                 context=context,
                 intermediate_state=intermediate_state,
-                node=self.dict(),
+                node=self.model_dump(),
                 source_node_id=source_node_id,
             )
 
@@ -254,12 +258,15 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
                 eta=0.0,
             )
 
-        unet_info = context.services.model_manager.get_model(**self.unet.unet.dict())
+        unet_info = context.services.model_manager.get_model(**self.unet.unet.model_dump())
 
         with unet_info as unet:  # , ExitStack() as stack:
             # loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
             loras = [
-                (context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight)
+                (
+                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
+                    lora.weight,
+                )
                 for lora in self.unet.loras
             ]
 
@@ -321,7 +328,7 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
     category="image",
     version="1.0.0",
 )
-class ONNXLatentsToImageInvocation(BaseInvocation):
+class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     """Generates an image from latents."""
 
     latents: LatentsField = InputField(
@@ -332,11 +339,6 @@ class ONNXLatentsToImageInvocation(BaseInvocation):
         description=FieldDescriptions.vae,
         input=Input.Connection,
     )
-    metadata: Optional[CoreMetadata] = InputField(
-        default=None,
-        description=FieldDescriptions.core_metadata,
-        ui_hidden=True,
-    )
     # tiled: bool = InputField(default=False, description="Decode latents by overlaping tiles(less memory consumption)")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -346,7 +348,7 @@ class ONNXLatentsToImageInvocation(BaseInvocation):
             raise Exception(f"Expected vae_decoder, found: {self.vae.vae.model_type}")
 
         vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.dict(),
+            **self.vae.vae.model_dump(),
         )
 
         # clear memory as vae decode can request a lot
@@ -375,7 +377,7 @@ class ONNXLatentsToImageInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -403,6 +405,8 @@ class OnnxModelField(BaseModel):
     base_model: BaseModelType = Field(description="Base model")
     model_type: ModelType = Field(description="Model Type")
 
+    model_config = ConfigDict(protected_namespaces=())
+
 
 @invocation("onnx_model_loader", title="ONNX Main Model", tags=["onnx", "model"], category="model", version="1.0.0")
 class OnnxModelLoaderInvocation(BaseInvocation):

invokeai/app/invocations/param_easing.py

@@ -44,13 +44,22 @@ from invokeai.app.invocations.primitives import FloatCollectionOutput
 from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
 
 
-@invocation("float_range", title="Float Range", tags=["math", "range"], category="math", version="1.0.0")
+@invocation(
+    "float_range",
+    title="Float Range",
+    tags=["math", "range"],
+    category="math",
+    version="1.0.0",
+)
 class FloatLinearRangeInvocation(BaseInvocation):
     """Creates a range"""
 
     start: float = InputField(default=5, description="The first value of the range")
     stop: float = InputField(default=10, description="The last value of the range")
-    steps: int = InputField(default=30, description="number of values to interpolate over (including start and stop)")
+    steps: int = InputField(
+        default=30,
+        description="number of values to interpolate over (including start and stop)",
+    )
 
     def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
         param_list = list(np.linspace(self.start, self.stop, self.steps))
@@ -95,7 +104,13 @@ EASING_FUNCTION_KEYS = Literal[tuple(list(EASING_FUNCTIONS_MAP.keys()))]
 
 
 # actually I think for now could just use CollectionOutput (which is list[Any]
-@invocation("step_param_easing", title="Step Param Easing", tags=["step", "easing"], category="step", version="1.0.0")
+@invocation(
+    "step_param_easing",
+    title="Step Param Easing",
+    tags=["step", "easing"],
+    category="step",
+    version="1.0.0",
+)
 class StepParamEasingInvocation(BaseInvocation):
     """Experimental per-step parameter easing for denoising steps"""
 
@@ -159,7 +174,9 @@ class StepParamEasingInvocation(BaseInvocation):
                 context.services.logger.debug("base easing duration: " + str(base_easing_duration))
             even_num_steps = num_easing_steps % 2 == 0  # even number of steps
             easing_function = easing_class(
-                start=self.start_value, end=self.end_value, duration=base_easing_duration - 1
+                start=self.start_value,
+                end=self.end_value,
+                duration=base_easing_duration - 1,
             )
             base_easing_vals = list()
             for step_index in range(base_easing_duration):
@@ -199,7 +216,11 @@ class StepParamEasingInvocation(BaseInvocation):
         #
 
         else:  # no mirroring (default)
-            easing_function = easing_class(start=self.start_value, end=self.end_value, duration=num_easing_steps - 1)
+            easing_function = easing_class(
+                start=self.start_value,
+                end=self.end_value,
+                duration=num_easing_steps - 1,
+            )
             for step_index in range(num_easing_steps):
                 step_val = easing_function.ease(step_index)
                 easing_list.append(step_val)

invokeai/app/invocations/primitives.py

@@ -251,7 +251,9 @@ class ImageCollectionOutput(BaseInvocationOutput):
 
 
 @invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.0")
-class ImageInvocation(BaseInvocation):
+class ImageInvocation(
+    BaseInvocation,
+):
     """An image primitive value"""
 
     image: ImageField = InputField(description="The image to load")

invokeai/app/invocations/prompt.py

@@ -3,7 +3,7 @@ from typing import Optional, Union
 
 import numpy as np
 from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPromptGenerator
-from pydantic import validator
+from pydantic import field_validator
 
 from invokeai.app.invocations.primitives import StringCollectionOutput
 
@@ -21,7 +21,10 @@ from .baseinvocation import BaseInvocation, InputField, InvocationContext, UICom
 class DynamicPromptInvocation(BaseInvocation):
     """Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator"""
 
-    prompt: str = InputField(description="The prompt to parse with dynamicprompts", ui_component=UIComponent.Textarea)
+    prompt: str = InputField(
+        description="The prompt to parse with dynamicprompts",
+        ui_component=UIComponent.Textarea,
+    )
     max_prompts: int = InputField(default=1, description="The number of prompts to generate")
     combinatorial: bool = InputField(default=False, description="Whether to use the combinatorial generator")
 
@@ -36,21 +39,31 @@ class DynamicPromptInvocation(BaseInvocation):
         return StringCollectionOutput(collection=prompts)
 
 
-@invocation("prompt_from_file", title="Prompts from File", tags=["prompt", "file"], category="prompt", version="1.0.0")
+@invocation(
+    "prompt_from_file",
+    title="Prompts from File",
+    tags=["prompt", "file"],
+    category="prompt",
+    version="1.0.0",
+)
 class PromptsFromFileInvocation(BaseInvocation):
     """Loads prompts from a text file"""
 
     file_path: str = InputField(description="Path to prompt text file")
     pre_prompt: Optional[str] = InputField(
-        default=None, description="String to prepend to each prompt", ui_component=UIComponent.Textarea
+        default=None,
+        description="String to prepend to each prompt",
+        ui_component=UIComponent.Textarea,
     )
     post_prompt: Optional[str] = InputField(
-        default=None, description="String to append to each prompt", ui_component=UIComponent.Textarea
+        default=None,
+        description="String to append to each prompt",
+        ui_component=UIComponent.Textarea,
     )
     start_line: int = InputField(default=1, ge=1, description="Line in the file to start start from")
     max_prompts: int = InputField(default=1, ge=0, description="Max lines to read from file (0=all)")
 
-    @validator("file_path")
+    @field_validator("file_path")
     def file_path_exists(cls, v):
         if not exists(v):
             raise ValueError(FileNotFoundError)
@@ -79,6 +92,10 @@ class PromptsFromFileInvocation(BaseInvocation):
 
     def invoke(self, context: InvocationContext) -> StringCollectionOutput:
         prompts = self.promptsFromFile(
-            self.file_path, self.pre_prompt, self.post_prompt, self.start_line, self.max_prompts
+            self.file_path,
+            self.pre_prompt,
+            self.post_prompt,
+            self.start_line,
+            self.max_prompts,
         )
         return StringCollectionOutput(collection=prompts)

invokeai/app/invocations/t2i_adapter.py

@@ -0,0 +1,85 @@
+from typing import Union
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    FieldDescriptions,
+    Input,
+    InputField,
+    InvocationContext,
+    OutputField,
+    UIType,
+    invocation,
+    invocation_output,
+)
+from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESIZE_VALUES
+from invokeai.app.invocations.primitives import ImageField
+from invokeai.backend.model_management.models.base import BaseModelType
+
+
+class T2IAdapterModelField(BaseModel):
+    model_name: str = Field(description="Name of the T2I-Adapter model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
+
+
+class T2IAdapterField(BaseModel):
+    image: ImageField = Field(description="The T2I-Adapter image prompt.")
+    t2i_adapter_model: T2IAdapterModelField = Field(description="The T2I-Adapter model to use.")
+    weight: Union[float, list[float]] = Field(default=1, description="The weight given to the T2I-Adapter")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the T2I-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the T2I-Adapter is last applied (% of total steps)"
+    )
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+
+
+@invocation_output("t2i_adapter_output")
+class T2IAdapterOutput(BaseInvocationOutput):
+    t2i_adapter: T2IAdapterField = OutputField(description=FieldDescriptions.t2i_adapter, title="T2I Adapter")
+
+
+@invocation(
+    "t2i_adapter", title="T2I-Adapter", tags=["t2i_adapter", "control"], category="t2i_adapter", version="1.0.0"
+)
+class T2IAdapterInvocation(BaseInvocation):
+    """Collects T2I-Adapter info to pass to other nodes."""
+
+    # Inputs
+    image: ImageField = InputField(description="The IP-Adapter image prompt.")
+    t2i_adapter_model: T2IAdapterModelField = InputField(
+        description="The T2I-Adapter model.",
+        title="T2I-Adapter Model",
+        input=Input.Direct,
+        ui_order=-1,
+    )
+    weight: Union[float, list[float]] = InputField(
+        default=1, ge=0, description="The weight given to the T2I-Adapter", ui_type=UIType.Float, title="Weight"
+    )
+    begin_step_percent: float = InputField(
+        default=0, ge=-1, le=2, description="When the T2I-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = InputField(
+        default=1, ge=0, le=1, description="When the T2I-Adapter is last applied (% of total steps)"
+    )
+    resize_mode: CONTROLNET_RESIZE_VALUES = InputField(
+        default="just_resize",
+        description="The resize mode applied to the T2I-Adapter input image so that it matches the target output size.",
+    )
+
+    def invoke(self, context: InvocationContext) -> T2IAdapterOutput:
+        return T2IAdapterOutput(
+            t2i_adapter=T2IAdapterField(
+                image=self.image,
+                t2i_adapter_model=self.t2i_adapter_model,
+                weight=self.weight,
+                begin_step_percent=self.begin_step_percent,
+                end_step_percent=self.end_step_percent,
+                resize_mode=self.resize_mode,
+            )
+        )

invokeai/app/invocations/upscale.py

@@ -4,14 +4,17 @@ from typing import Literal
 
 import cv2 as cv
 import numpy as np
+import torch
 from basicsr.archs.rrdbnet_arch import RRDBNet
 from PIL import Image
+from pydantic import ConfigDict
 from realesrgan import RealESRGANer
 
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.models.image import ImageCategory, ResourceOrigin
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.backend.util.devices import choose_torch_device
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
 
 # TODO: Populate this from disk?
 # TODO: Use model manager to load?
@@ -22,13 +25,21 @@ ESRGAN_MODELS = Literal[
     "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="1.0.0")
-class ESRGANInvocation(BaseInvocation):
+
+@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.1.0")
+class ESRGANInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     """Upscales an image using RealESRGAN."""
 
     image: ImageField = InputField(description="The input image")
     model_name: ESRGAN_MODELS = InputField(default="RealESRGAN_x4plus.pth", description="The Real-ESRGAN model to use")
+    tile_size: int = InputField(
+        default=400, ge=0, description="Tile size for tiled ESRGAN upscaling (0=tiling disabled)"
+    )
+
+    model_config = ConfigDict(protected_namespaces=())
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
@@ -86,9 +97,11 @@ class ESRGANInvocation(BaseInvocation):
             model_path=str(models_path / esrgan_model_path),
             model=rrdbnet_model,
             half=False,
+            tile=self.tile_size,
         )
 
         # prepare image - Real-ESRGAN uses cv2 internally, and cv2 uses BGR vs RGB for PIL
+        # TODO: This strips the alpha... is that okay?
         cv_image = cv.cvtColor(np.array(image.convert("RGB")), cv.COLOR_RGB2BGR)
 
         # We can pass an `outscale` value here, but it just resizes the image by that factor after
@@ -99,6 +112,10 @@ class ESRGANInvocation(BaseInvocation):
         # back to PIL
         pil_image = Image.fromarray(cv.cvtColor(upscaled_image, cv.COLOR_BGR2RGB)).convert("RGBA")
 
+        torch.cuda.empty_cache()
+        if choose_torch_device() == torch.device("mps"):
+            mps.empty_cache()
+
         image_dto = context.services.images.create(
             image=pil_image,
             image_origin=ResourceOrigin.INTERNAL,
@@ -106,6 +123,7 @@ class ESRGANInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
+            metadata=self.metadata,
             workflow=self.workflow,
         )
 

invokeai/app/models/exceptions.py

@@ -1,4 +0,0 @@
-class CanceledException(Exception):
-    """Execution canceled by user."""
-
-    pass

invokeai/app/models/image.py

@@ -1,71 +0,0 @@
-from enum import Enum
-
-from pydantic import BaseModel, Field
-
-from invokeai.app.util.metaenum import MetaEnum
-
-
-class ProgressImage(BaseModel):
-    """The progress image sent intermittently during processing"""
-
-    width: int = Field(description="The effective width of the image in pixels")
-    height: int = Field(description="The effective height of the image in pixels")
-    dataURL: str = Field(description="The image data as a b64 data URL")
-
-
-class ResourceOrigin(str, Enum, metaclass=MetaEnum):
-    """The origin of a resource (eg image).
-
-    - INTERNAL: The resource was created by the application.
-    - EXTERNAL: The resource was not created by the application.
-    This may be a user-initiated upload, or an internal application upload (eg Canvas init image).
-    """
-
-    INTERNAL = "internal"
-    """The resource was created by the application."""
-    EXTERNAL = "external"
-    """The resource was not created by the application.
-    This may be a user-initiated upload, or an internal application upload (eg Canvas init image).
-    """
-
-
-class InvalidOriginException(ValueError):
-    """Raised when a provided value is not a valid ResourceOrigin.
-
-    Subclasses `ValueError`.
-    """
-
-    def __init__(self, message="Invalid resource origin."):
-        super().__init__(message)
-
-
-class ImageCategory(str, Enum, metaclass=MetaEnum):
-    """The category of an image.
-
-    - GENERAL: The image is an output, init image, or otherwise an image without a specialized purpose.
-    - MASK: The image is a mask image.
-    - CONTROL: The image is a ControlNet control image.
-    - USER: The image is a user-provide image.
-    - OTHER: The image is some other type of image with a specialized purpose. To be used by external nodes.
-    """
-
-    GENERAL = "general"
-    """GENERAL: The image is an output, init image, or otherwise an image without a specialized purpose."""
-    MASK = "mask"
-    """MASK: The image is a mask image."""
-    CONTROL = "control"
-    """CONTROL: The image is a ControlNet control image."""
-    USER = "user"
-    """USER: The image is a user-provide image."""
-    OTHER = "other"
-    """OTHER: The image is some other type of image with a specialized purpose. To be used by external nodes."""
-
-
-class InvalidImageCategoryException(ValueError):
-    """Raised when a provided value is not a valid ImageCategory.
-
-    Subclasses `ValueError`.
-    """
-
-    def __init__(self, message="Invalid image category."):
-        super().__init__(message)

invokeai/app/services/board_image_records/board_image_records_base.py

@@ -0,0 +1,47 @@
+from abc import ABC, abstractmethod
+from typing import Optional
+
+
+class BoardImageRecordStorageBase(ABC):
+    """Abstract base class for the one-to-many board-image relationship record storage."""
+
+    @abstractmethod
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        """Adds an image to a board."""
+        pass
+
+    @abstractmethod
+    def remove_image_from_board(
+        self,
+        image_name: str,
+    ) -> None:
+        """Removes an image from a board."""
+        pass
+
+    @abstractmethod
+    def get_all_board_image_names_for_board(
+        self,
+        board_id: str,
+    ) -> list[str]:
+        """Gets all board images for a board, as a list of the image names."""
+        pass
+
+    @abstractmethod
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        """Gets an image's board id, if it has one."""
+        pass
+
+    @abstractmethod
+    def get_image_count_for_board(
+        self,
+        board_id: str,
+    ) -> int:
+        """Gets the number of images for a board."""
+        pass

invokeai/app/services/board_image_records/board_image_records_sqlite.py

@@ -1,69 +1,24 @@
 import sqlite3
 import threading
-from abc import ABC, abstractmethod
 from typing import Optional, cast
 
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.image_record import ImageRecord, deserialize_image_record
+from invokeai.app.services.image_records.image_records_common import ImageRecord, deserialize_image_record
+from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+from invokeai.app.services.shared.sqlite import SqliteDatabase
 
-
-class BoardImageRecordStorageBase(ABC):
-    """Abstract base class for the one-to-many board-image relationship record storage."""
-
-    @abstractmethod
-    def add_image_to_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        """Adds an image to a board."""
-        pass
-
-    @abstractmethod
-    def remove_image_from_board(
-        self,
-        image_name: str,
-    ) -> None:
-        """Removes an image from a board."""
-        pass
-
-    @abstractmethod
-    def get_all_board_image_names_for_board(
-        self,
-        board_id: str,
-    ) -> list[str]:
-        """Gets all board images for a board, as a list of the image names."""
-        pass
-
-    @abstractmethod
-    def get_board_for_image(
-        self,
-        image_name: str,
-    ) -> Optional[str]:
-        """Gets an image's board id, if it has one."""
-        pass
-
-    @abstractmethod
-    def get_image_count_for_board(
-        self,
-        board_id: str,
-    ) -> int:
-        """Gets the number of images for a board."""
-        pass
+from .board_image_records_base import BoardImageRecordStorageBase
 
 
 class SqliteBoardImageRecordStorage(BoardImageRecordStorageBase):
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
-    _lock: threading.Lock
+    _lock: threading.RLock
 
-    def __init__(self, conn: sqlite3.Connection, lock: threading.Lock) -> None:
+    def __init__(self, db: SqliteDatabase) -> None:
         super().__init__()
-        self._conn = conn
-        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
-        self._conn.row_factory = sqlite3.Row
+        self._lock = db.lock
+        self._conn = db.conn
         self._cursor = self._conn.cursor()
-        self._lock = lock
 
         try:
             self._lock.acquire()

invokeai/app/services/board_images.py

@@ -1,112 +0,0 @@
-from abc import ABC, abstractmethod
-from logging import Logger
-from typing import Optional
-
-from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
-from invokeai.app.services.board_record_storage import BoardRecord, BoardRecordStorageBase
-from invokeai.app.services.image_record_storage import ImageRecordStorageBase
-from invokeai.app.services.models.board_record import BoardDTO
-from invokeai.app.services.urls import UrlServiceBase
-
-
-class BoardImagesServiceABC(ABC):
-    """High-level service for board-image relationship management."""
-
-    @abstractmethod
-    def add_image_to_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        """Adds an image to a board."""
-        pass
-
-    @abstractmethod
-    def remove_image_from_board(
-        self,
-        image_name: str,
-    ) -> None:
-        """Removes an image from a board."""
-        pass
-
-    @abstractmethod
-    def get_all_board_image_names_for_board(
-        self,
-        board_id: str,
-    ) -> list[str]:
-        """Gets all board images for a board, as a list of the image names."""
-        pass
-
-    @abstractmethod
-    def get_board_for_image(
-        self,
-        image_name: str,
-    ) -> Optional[str]:
-        """Gets an image's board id, if it has one."""
-        pass
-
-
-class BoardImagesServiceDependencies:
-    """Service dependencies for the BoardImagesService."""
-
-    board_image_records: BoardImageRecordStorageBase
-    board_records: BoardRecordStorageBase
-    image_records: ImageRecordStorageBase
-    urls: UrlServiceBase
-    logger: Logger
-
-    def __init__(
-        self,
-        board_image_record_storage: BoardImageRecordStorageBase,
-        image_record_storage: ImageRecordStorageBase,
-        board_record_storage: BoardRecordStorageBase,
-        url: UrlServiceBase,
-        logger: Logger,
-    ):
-        self.board_image_records = board_image_record_storage
-        self.image_records = image_record_storage
-        self.board_records = board_record_storage
-        self.urls = url
-        self.logger = logger
-
-
-class BoardImagesService(BoardImagesServiceABC):
-    _services: BoardImagesServiceDependencies
-
-    def __init__(self, services: BoardImagesServiceDependencies):
-        self._services = services
-
-    def add_image_to_board(
-        self,
-        board_id: str,
-        image_name: str,
-    ) -> None:
-        self._services.board_image_records.add_image_to_board(board_id, image_name)
-
-    def remove_image_from_board(
-        self,
-        image_name: str,
-    ) -> None:
-        self._services.board_image_records.remove_image_from_board(image_name)
-
-    def get_all_board_image_names_for_board(
-        self,
-        board_id: str,
-    ) -> list[str]:
-        return self._services.board_image_records.get_all_board_image_names_for_board(board_id)
-
-    def get_board_for_image(
-        self,
-        image_name: str,
-    ) -> Optional[str]:
-        board_id = self._services.board_image_records.get_board_for_image(image_name)
-        return board_id
-
-
-def board_record_to_dto(board_record: BoardRecord, cover_image_name: Optional[str], image_count: int) -> BoardDTO:
-    """Converts a board record to a board DTO."""
-    return BoardDTO(
-        **board_record.dict(exclude={"cover_image_name"}),
-        cover_image_name=cover_image_name,
-        image_count=image_count,
-    )

invokeai/app/services/board_images/board_images_base.py

@@ -0,0 +1,39 @@
+from abc import ABC, abstractmethod
+from typing import Optional
+
+
+class BoardImagesServiceABC(ABC):
+    """High-level service for board-image relationship management."""
+
+    @abstractmethod
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        """Adds an image to a board."""
+        pass
+
+    @abstractmethod
+    def remove_image_from_board(
+        self,
+        image_name: str,
+    ) -> None:
+        """Removes an image from a board."""
+        pass
+
+    @abstractmethod
+    def get_all_board_image_names_for_board(
+        self,
+        board_id: str,
+    ) -> list[str]:
+        """Gets all board images for a board, as a list of the image names."""
+        pass
+
+    @abstractmethod
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        """Gets an image's board id, if it has one."""
+        pass

invokeai/app/services/board_images/board_images_default.py

@@ -0,0 +1,38 @@
+from typing import Optional
+
+from invokeai.app.services.invoker import Invoker
+
+from .board_images_base import BoardImagesServiceABC
+
+
+class BoardImagesService(BoardImagesServiceABC):
+    __invoker: Invoker
+
+    def start(self, invoker: Invoker) -> None:
+        self.__invoker = invoker
+
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        self.__invoker.services.board_image_records.add_image_to_board(board_id, image_name)
+
+    def remove_image_from_board(
+        self,
+        image_name: str,
+    ) -> None:
+        self.__invoker.services.board_image_records.remove_image_from_board(image_name)
+
+    def get_all_board_image_names_for_board(
+        self,
+        board_id: str,
+    ) -> list[str]:
+        return self.__invoker.services.board_image_records.get_all_board_image_names_for_board(board_id)
+
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        board_id = self.__invoker.services.board_image_records.get_board_for_image(image_name)
+        return board_id

invokeai/app/services/board_records/board_records_base.py

@@ -0,0 +1,55 @@
+from abc import ABC, abstractmethod
+
+from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+
+from .board_records_common import BoardChanges, BoardRecord
+
+
+class BoardRecordStorageBase(ABC):
+    """Low-level service responsible for interfacing with the board record store."""
+
+    @abstractmethod
+    def delete(self, board_id: str) -> None:
+        """Deletes a board record."""
+        pass
+
+    @abstractmethod
+    def save(
+        self,
+        board_name: str,
+    ) -> BoardRecord:
+        """Saves a board record."""
+        pass
+
+    @abstractmethod
+    def get(
+        self,
+        board_id: str,
+    ) -> BoardRecord:
+        """Gets a board record."""
+        pass
+
+    @abstractmethod
+    def update(
+        self,
+        board_id: str,
+        changes: BoardChanges,
+    ) -> BoardRecord:
+        """Updates a board record."""
+        pass
+
+    @abstractmethod
+    def get_many(
+        self,
+        offset: int = 0,
+        limit: int = 10,
+    ) -> OffsetPaginatedResults[BoardRecord]:
+        """Gets many board records."""
+        pass
+
+    @abstractmethod
+    def get_all(
+        self,
+    ) -> list[BoardRecord]:
+        """Gets all board records."""
+        pass

invokeai/app/services/board_records/board_records_common.py

@@ -1,7 +1,7 @@
 from datetime import datetime
 from typing import Optional, Union
 
-from pydantic import Field
+from pydantic import BaseModel, Field
 
 from invokeai.app.util.misc import get_iso_timestamp
 from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
@@ -18,21 +18,12 @@ class BoardRecord(BaseModelExcludeNull):
     """The created timestamp of the image."""
     updated_at: Union[datetime, str] = Field(description="The updated timestamp of the board.")
     """The updated timestamp of the image."""
-    deleted_at: Union[datetime, str, None] = Field(description="The deleted timestamp of the board.")
+    deleted_at: Optional[Union[datetime, str]] = Field(default=None, description="The deleted timestamp of the board.")
     """The updated timestamp of the image."""
-    cover_image_name: Optional[str] = Field(description="The name of the cover image of the board.")
+    cover_image_name: Optional[str] = Field(default=None, description="The name of the cover image of the board.")
     """The name of the cover image of the board."""
 
 
-class BoardDTO(BoardRecord):
-    """Deserialized board record with cover image URL and image count."""
-
-    cover_image_name: Optional[str] = Field(description="The name of the board's cover image.")
-    """The URL of the thumbnail of the most recent image in the board."""
-    image_count: int = Field(description="The number of images in the board.")
-    """The number of images in the board."""
-
-
 def deserialize_board_record(board_dict: dict) -> BoardRecord:
     """Deserializes a board record."""
 
@@ -53,3 +44,29 @@ def deserialize_board_record(board_dict: dict) -> BoardRecord:
         updated_at=updated_at,
         deleted_at=deleted_at,
     )
+
+
+class BoardChanges(BaseModel, extra="forbid"):
+    board_name: Optional[str] = Field(default=None, description="The board's new name.")
+    cover_image_name: Optional[str] = Field(default=None, description="The name of the board's new cover image.")
+
+
+class BoardRecordNotFoundException(Exception):
+    """Raised when an board record is not found."""
+
+    def __init__(self, message="Board record not found"):
+        super().__init__(message)
+
+
+class BoardRecordSaveException(Exception):
+    """Raised when an board record cannot be saved."""
+
+    def __init__(self, message="Board record not saved"):
+        super().__init__(message)
+
+
+class BoardRecordDeleteException(Exception):
+    """Raised when an board record cannot be deleted."""
+
+    def __init__(self, message="Board record not deleted"):
+        super().__init__(message)

invokeai/app/services/board_records/board_records_sqlite.py

@@ -1,103 +1,32 @@
 import sqlite3
 import threading
-from abc import ABC, abstractmethod
-from typing import Optional, Union, cast
+from typing import Union, cast
 
-from pydantic import BaseModel, Extra, Field
-
-from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.board_record import BoardRecord, deserialize_board_record
+from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+from invokeai.app.services.shared.sqlite import SqliteDatabase
 from invokeai.app.util.misc import uuid_string
 
-
-class BoardChanges(BaseModel, extra=Extra.forbid):
-    board_name: Optional[str] = Field(description="The board's new name.")
-    cover_image_name: Optional[str] = Field(description="The name of the board's new cover image.")
-
-
-class BoardRecordNotFoundException(Exception):
-    """Raised when an board record is not found."""
-
-    def __init__(self, message="Board record not found"):
-        super().__init__(message)
-
-
-class BoardRecordSaveException(Exception):
-    """Raised when an board record cannot be saved."""
-
-    def __init__(self, message="Board record not saved"):
-        super().__init__(message)
-
-
-class BoardRecordDeleteException(Exception):
-    """Raised when an board record cannot be deleted."""
-
-    def __init__(self, message="Board record not deleted"):
-        super().__init__(message)
-
-
-class BoardRecordStorageBase(ABC):
-    """Low-level service responsible for interfacing with the board record store."""
-
-    @abstractmethod
-    def delete(self, board_id: str) -> None:
-        """Deletes a board record."""
-        pass
-
-    @abstractmethod
-    def save(
-        self,
-        board_name: str,
-    ) -> BoardRecord:
-        """Saves a board record."""
-        pass
-
-    @abstractmethod
-    def get(
-        self,
-        board_id: str,
-    ) -> BoardRecord:
-        """Gets a board record."""
-        pass
-
-    @abstractmethod
-    def update(
-        self,
-        board_id: str,
-        changes: BoardChanges,
-    ) -> BoardRecord:
-        """Updates a board record."""
-        pass
-
-    @abstractmethod
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-    ) -> OffsetPaginatedResults[BoardRecord]:
-        """Gets many board records."""
-        pass
-
-    @abstractmethod
-    def get_all(
-        self,
-    ) -> list[BoardRecord]:
-        """Gets all board records."""
-        pass
+from .board_records_base import BoardRecordStorageBase
+from .board_records_common import (
+    BoardChanges,
+    BoardRecord,
+    BoardRecordDeleteException,
+    BoardRecordNotFoundException,
+    BoardRecordSaveException,
+    deserialize_board_record,
+)
 
 
 class SqliteBoardRecordStorage(BoardRecordStorageBase):
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
-    _lock: threading.Lock
+    _lock: threading.RLock
 
-    def __init__(self, conn: sqlite3.Connection, lock: threading.Lock) -> None:
+    def __init__(self, db: SqliteDatabase) -> None:
         super().__init__()
-        self._conn = conn
-        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
-        self._conn.row_factory = sqlite3.Row
+        self._lock = db.lock
+        self._conn = db.conn
         self._cursor = self._conn.cursor()
-        self._lock = lock
 
         try:
             self._lock.acquire()

invokeai/app/services/boards.py

@@ -1,158 +0,0 @@
-from abc import ABC, abstractmethod
-from logging import Logger
-
-from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
-from invokeai.app.services.board_images import board_record_to_dto
-from invokeai.app.services.board_record_storage import BoardChanges, BoardRecordStorageBase
-from invokeai.app.services.image_record_storage import ImageRecordStorageBase, OffsetPaginatedResults
-from invokeai.app.services.models.board_record import BoardDTO
-from invokeai.app.services.urls import UrlServiceBase
-
-
-class BoardServiceABC(ABC):
-    """High-level service for board management."""
-
-    @abstractmethod
-    def create(
-        self,
-        board_name: str,
-    ) -> BoardDTO:
-        """Creates a board."""
-        pass
-
-    @abstractmethod
-    def get_dto(
-        self,
-        board_id: str,
-    ) -> BoardDTO:
-        """Gets a board."""
-        pass
-
-    @abstractmethod
-    def update(
-        self,
-        board_id: str,
-        changes: BoardChanges,
-    ) -> BoardDTO:
-        """Updates a board."""
-        pass
-
-    @abstractmethod
-    def delete(
-        self,
-        board_id: str,
-    ) -> None:
-        """Deletes a board."""
-        pass
-
-    @abstractmethod
-    def get_many(
-        self,
-        offset: int = 0,
-        limit: int = 10,
-    ) -> OffsetPaginatedResults[BoardDTO]:
-        """Gets many boards."""
-        pass
-
-    @abstractmethod
-    def get_all(
-        self,
-    ) -> list[BoardDTO]:
-        """Gets all boards."""
-        pass
-
-
-class BoardServiceDependencies:
-    """Service dependencies for the BoardService."""
-
-    board_image_records: BoardImageRecordStorageBase
-    board_records: BoardRecordStorageBase
-    image_records: ImageRecordStorageBase
-    urls: UrlServiceBase
-    logger: Logger
-
-    def __init__(
-        self,
-        board_image_record_storage: BoardImageRecordStorageBase,
-        image_record_storage: ImageRecordStorageBase,
-        board_record_storage: BoardRecordStorageBase,
-        url: UrlServiceBase,
-        logger: Logger,
-    ):
-        self.board_image_records = board_image_record_storage
-        self.image_records = image_record_storage
-        self.board_records = board_record_storage
-        self.urls = url
-        self.logger = logger
-
-
-class BoardService(BoardServiceABC):
-    _services: BoardServiceDependencies
-
-    def __init__(self, services: BoardServiceDependencies):
-        self._services = services
-
-    def create(
-        self,
-        board_name: str,
-    ) -> BoardDTO:
-        board_record = self._services.board_records.save(board_name)
-        return board_record_to_dto(board_record, None, 0)
-
-    def get_dto(self, board_id: str) -> BoardDTO:
-        board_record = self._services.board_records.get(board_id)
-        cover_image = self._services.image_records.get_most_recent_image_for_board(board_record.board_id)
-        if cover_image:
-            cover_image_name = cover_image.image_name
-        else:
-            cover_image_name = None
-        image_count = self._services.board_image_records.get_image_count_for_board(board_id)
-        return board_record_to_dto(board_record, cover_image_name, image_count)
-
-    def update(
-        self,
-        board_id: str,
-        changes: BoardChanges,
-    ) -> BoardDTO:
-        board_record = self._services.board_records.update(board_id, changes)
-        cover_image = self._services.image_records.get_most_recent_image_for_board(board_record.board_id)
-        if cover_image:
-            cover_image_name = cover_image.image_name
-        else:
-            cover_image_name = None
-
-        image_count = self._services.board_image_records.get_image_count_for_board(board_id)
-        return board_record_to_dto(board_record, cover_image_name, image_count)
-
-    def delete(self, board_id: str) -> None:
-        self._services.board_records.delete(board_id)
-
-    def get_many(self, offset: int = 0, limit: int = 10) -> OffsetPaginatedResults[BoardDTO]:
-        board_records = self._services.board_records.get_many(offset, limit)
-        board_dtos = []
-        for r in board_records.items:
-            cover_image = self._services.image_records.get_most_recent_image_for_board(r.board_id)
-            if cover_image:
-                cover_image_name = cover_image.image_name
-            else:
-                cover_image_name = None
-
-            image_count = self._services.board_image_records.get_image_count_for_board(r.board_id)
-            board_dtos.append(board_record_to_dto(r, cover_image_name, image_count))
-
-        return OffsetPaginatedResults[BoardDTO](items=board_dtos, offset=offset, limit=limit, total=len(board_dtos))
-
-    def get_all(self) -> list[BoardDTO]:
-        board_records = self._services.board_records.get_all()
-        board_dtos = []
-        for r in board_records:
-            cover_image = self._services.image_records.get_most_recent_image_for_board(r.board_id)
-            if cover_image:
-                cover_image_name = cover_image.image_name
-            else:
-                cover_image_name = None
-
-            image_count = self._services.board_image_records.get_image_count_for_board(r.board_id)
-            board_dtos.append(board_record_to_dto(r, cover_image_name, image_count))
-
-        return board_dtos