feat(nodes): WIP restricted invocation context

Upgrade pydantic and fastapi to latest.

- pydantic~=2.4.2
- fastapi~=103.2
- fastapi-events~=0.9.1

**Big Changes**

There are a number of logic changes needed to support pydantic v2. Most changes are very simple, like using the new methods to serialized and deserialize models, but there are a few more complex changes.

**Invocations**

The biggest change relates to invocation creation, instantiation and validation.

Because pydantic v2 moves all validation logic into the rust pydantic-core, we may no longer directly stick our fingers into the validation pie.

Previously, we (ab)used models and fields to allow invocation fields to be optional at instantiation, but required when `invoke()` is called. We directly manipulated the fields and invocation models when calling `invoke()`.

With pydantic v2, this is much more involved. Changes to the python wrapper do not propagate down to the rust validation logic - you have to rebuild the model. This causes problem with concurrent access to the invocation classes and is not a free operation.

This logic has been totally refactored and we do not need to change the model any more. The details are in `baseinvocation.py`, in the `InputField` function and `BaseInvocation.invoke_internal()` method.

In the end, this implementation is cleaner.

**Invocation Fields**

In pydantic v2, you can no longer directly add or remove fields from a model.

Previously, we did this to add the `type` field to invocations.

**Invocation Decorators**

With pydantic v2, we instead use the imperative `create_model()` API to create a new model with the additional field. This is done in `baseinvocation.py` in the `invocation()` wrapper.

A similar technique is used for `invocation_output()`.

**Minor Changes**

There are a number of minor changes around the pydantic v2 models API.

**Protected `model_` Namespace**

All models' pydantic-provided methods and attributes are prefixed with `model_` and this is considered a protected namespace. This causes some conflict, because "model" means something to us, and we have a ton of pydantic models with attributes starting with "model_".

Forunately, there are no direct conflicts. However, in any pydantic model where we define an attribute or method that starts with "model_", we must tell set the protected namespaces to an empty tuple.

```py
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=())
```

**Model Serialization**

Pydantic models no longer have `Model.dict()` or `Model.json()`.

Instead, we use `Model.model_dump()` or `Model.model_dump_json()`.

**Model Deserialization**

Pydantic models no longer have `Model.parse_obj()` or `Model.parse_raw()`, and there are no `parse_raw_as()` or `parse_obj_as()` functions.

Instead, you need to create a `TypeAdapter` object to parse python objects or JSON into a model.

```py
adapter_graph = TypeAdapter(Graph)
deserialized_graph_from_json = adapter_graph.validate_json(graph_json)
deserialized_graph_from_dict = adapter_graph.validate_python(graph_dict)
```

**Field Customisation**

Pydantic `Field`s no longer accept arbitrary args.

Now, you must put all additional arbitrary args in a `json_schema_extra` arg on the field.

**Schema Customisation**

FastAPI and pydantic schema generation now follows the OpenAPI version 3.1 spec.

This necessitates two changes:
- Our schema customization logic has been revised
- Schema parsing to build node templates has been revised

The specific aren't important, but this does present additional surface area for bugs.

**Performance Improvements**

Pydantic v2 is a full rewrite with a rust backend. This offers a substantial performance improvement (pydantic claims 5x to 50x depending on the task). We'll notice this the most during serialization and deserialization of sessions/graphs, which happens very very often - a couple times per node.

I haven't done any benchmarks, but anecdotally, graph execution is much faster. Also, very larges graphs - like with massive iterators - are much, much faster.

.gitignore

@@ -1,5 +1,8 @@
 .idea/
 
+# ignore the Anaconda/Miniconda installer used while building Docker image
+anaconda.sh
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -133,10 +136,12 @@ celerybeat.pid
 
 # Environments
 .env
-.venv*
+.venv
 env/
 venv/
 ENV/
+env.bak/
+venv.bak/
 
 # Spyder project settings
 .spyderproject
@@ -181,6 +186,11 @@ 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 3.10 through 3.11 installed on your machine. Earlier or
+You must have Python 3.9 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

@@ -1,15 +1,13 @@
 ## Make a copy of this file named `.env` and fill in the values below.
-## Any environment variables supported by InvokeAI can be specified here,
-## in addition to the examples below.
+## Any environment variables supported by InvokeAI can be specified here.
 
 # 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=
 
-# Get this value from your HuggingFace account settings page.
-# HUGGING_FACE_HUB_TOKEN=
+HUGGINGFACE_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:23.04 AS builder
+FROM library/ubuntu:22.04 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-venv \
+        python3.10-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/cu121"; \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu118"; \
     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:23.04 AS runtime
+FROM library/ubuntu:22.04 AS runtime
 
 ARG DEBIAN_FRONTEND=noninteractive
 ENV PYTHONUNBUFFERED=1
@@ -85,7 +85,6 @@ RUN apt update && apt install -y --no-install-recommends \
         iotop \
         bzip2 \
         gosu \
-        magic-wormhole \
         libglib2.0-0 \
         libgl1-mesa-glx \
         python3-venv \
@@ -95,6 +94,10 @@ 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
@@ -117,7 +120,9 @@ 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"
 
-RUN mkdir -p ${INVOKEAI_ROOT} && chown -R 1000:1000 ${INVOKEAI_ROOT}
+# 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}
 
 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://docs.docker.com/compose/install/linux/#install-using-the-repository).
+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).
     - 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)
@@ -20,6 +20,7 @@ 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.
@@ -41,22 +42,20 @@ 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 (values are optional, but setting `INVOKEAI_ROOT` is highly recommended):
+Example (most values are optional):
 
-```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.yml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
+See the `docker compose.yaml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
 
 ### Reconfigure the runtime directory
 
@@ -64,7 +63,7 @@ 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
@@ -72,7 +71,7 @@ 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=ubuntu
+USER=invoke
 usermod -u ${USER_ID} ${USER} 1>/dev/null
 
 configure() {

docker/run.sh

@@ -1,11 +1,8 @@
 #!/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/INSTALLATION.md).
+  [Installation](installation/index.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](deprecated/VARIATIONS.md)
+- Support image variations (see [VARIATIONS](features/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/contribution_guides/development.md

@@ -45,5 +45,5 @@ For backend related work, please reach out to **@blessedcoolant**, **@lstein**,
 
 ## **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/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](VARIATIONS.md). |
-| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](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](../features/VARIATIONS.md). |
+| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](../features/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/features/CONCEPTS.md

@@ -28,9 +28,8 @@ 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 legacy 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 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 [6] in the launcher, "Re-run the
+configuration script again -- option [7] in the launcher, "Re-run the
 configure script".
 
 #### Reading Environment Variables

docs/features/CONTROLNET.md

@@ -17,6 +17,9 @@ 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
@@ -24,21 +27,35 @@ 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.
 
-#### Installation
+
+#### Models
 
 InvokeAI provides access to a series of ControlNet models that provide
-different effects or styles in your generated images.
+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.
 
-To install ControlNet Models:
+***InvokeAI does not currently support checkpoint-format
+ControlNets. These come in the form of a single file with the
+extension `.safetensors`.***
 
-1. The easiest way to install them is
+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
 to use the InvokeAI model installer application. Use the
-`invoke.sh`/`invoke.bat` launcher to select item [4] and then navigate
+`invoke.sh`/`invoke.bat` launcher to select item [5] 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. 
-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"
+repo_ids in the "Additional models" textbox:
 
+![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
@@ -46,17 +63,6 @@ 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**:
@@ -127,30 +133,6 @@ Start/End  - 0 represents the start of the generation, 1 represents the end. The
 
 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
 
@@ -158,13 +140,13 @@ Additionally, each  section can be expanded with the "Show Advanced" button in o
 
 ![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)
+![IP-Adapter + IMG2IMG](https://github.com/tencent-ailab/IP-Adapter/blob/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.  
+1. Through the command line interface launched from the invoke.sh / invoke.bat scripts, option [5] to download models.
+2. Through the Model Manager UI with models from the *Tools* section of [www.models.invoke.ai](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

docs/features/MODEL_MERGING.md

@@ -16,10 +16,9 @@ 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
-  "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.
+  `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.
 
 * 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 [7]). Users who are
+console" from the launcher (`invoke.bat` menu item [8]). 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 [3]. Call
+This is the model merge script, the same as launcher option [4]. 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 [2]. Call it with `--gui` to run the interactive console-based
+option [3]. 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 [4]. If called without arguments, it will launch the
+option [5]. 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 [8] to update to a new version of InvokeAI. It takes no
+menu item [9] to update to a new version of InvokeAI. It takes no
 command-line arguments.
 
 ## **invokeai-metadata**

docs/features/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](../features/OTHER.md#thresholding-and-perlin-noise-initialization-options)
+Also be aware of the [Perlin Noise](OTHER.md#thresholding-and-perlin-noise-initialization-options)
 feature, which provides another way of introducing variability into your
 image generation requests.

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.
+Use a seed image to build new creations in the CLI.
 
 ## Model Management
 

docs/help/gettingStartedWithAI.md

@@ -57,9 +57,7 @@ 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 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!
+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!
 
 - *Models that contain “inpainting” in the name are designed for use with the inpainting feature of the Unified Canvas*
 

docs/index.md

@@ -143,6 +143,7 @@ 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)
@@ -165,8 +166,10 @@ still a work in progress, but coming soon.
 
 ### Command-Line Interface Retired
 
-All "invokeai" command-line interfaces have been retired as of version
-3.4.
+The original "invokeai" command-line interface has been retired. The
+`invokeai` command will now launch a new command-line client that can
+be used by developers to create and test nodes. It is not intended to
+be used for routine image generation or manipulation.
 
 To 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 `3.10.*` or `3.11.*` you meet
+    number. If it is version `3.9.*`, `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
-        3.10.12](https://www.python.org/downloads/release/python-3109/),
+        3.10.9](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 3.10 through 3.11
+    version 3.9 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 3.10 through 3.11. The rest of the install
+1.  Please make sure you are using Python 3.9 through 3.11. The rest of the install
     procedure depends on this and will not work with other versions:
 
     ```bash

docs/installation/040_INSTALL_DOCKER.md

@@ -4,31 +4,30 @@ title: Installing with Docker
 
 # :fontawesome-brands-docker: Docker
 
-!!! warning "macOS and AMD GPU Users"
+!!! warning "For most users"
 
-    We highly recommend to Install InvokeAI locally using [these instructions](INSTALLATION.md),
-    because Docker containers can not access the GPU on macOS.
+    We highly recommend to Install InvokeAI locally using [these instructions](INSTALLATION.md)
 
-!!! warning "AMD GPU Users"
+!!! tip "For developers"
 
-    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 container-related development tasks or for enabling easy
+    deployment to other environments (on-premises or cloud), follow these
+    instructions.
 
-!!! 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)
+    For general use, install locally to leverage your machine's GPU.
 
 ## Why containers?
 
-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.
+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.
 
-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.
+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.
 
 Developers on Apple silicon (M1/M2): You
 [can't access your GPU cores from Docker containers](https://github.com/pytorch/pytorch/issues/81224)
@@ -37,16 +36,6 @@ 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
@@ -69,33 +58,222 @@ a token and copy it, since you will need in for the next step.
 
 ### Setup
 
-Set up your environmnent variables. In the `docker` directory, make a copy of `env.sample` and name it `.env`. Make changes as necessary.
+Set the fork you want to use and other variables.
 
-Any environment variables supported by InvokeAI can be set here - please see the [CONFIGURATION](../features/CONFIGURATION.md) for further detail.
+!!! tip
 
-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.
+    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:
 
 <figure markdown>
 
 | Environment-Variable <img width="220" align="right"/> | Default value <img width="360" align="right"/> | Description                                                                                                                                                                                       |
 | ----------------------------------------------------- | ---------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `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.
+| `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                                                                                                                                                   |
 
 </figure>
 
 #### Build the Image
 
-Use the standard `docker compose build` command from within the `docker` directory.
+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:
 
-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
+```bash
+./docker/build.sh
+```
+
+The build Script not only builds the container, but also creates the docker
+volume if not existing yet.
 
 #### Run the Container
 
-Use the standard `docker compose up` command, and generally the `docker compose` [CLI](https://docs.docker.com/compose/reference/) as usual.
+After the build process is done, you can run the container via the provided
+`docker/run.sh` script
 
-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)
+```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
+```

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 [4] "Download and install
+From the `invoke` launcher, choose option [5] "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

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -59,7 +59,8 @@ Prior to installing PyPatchMatch, you need to take the following steps:
    `from patchmatch import patch_match`: It should look like the following:
 
     ```py
-    Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] on linux
+    Python 3.9.5 (default, Nov 23 2021, 15:27:38)
+    [GCC 9.3.0] 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](../020_INSTALL_MANUAL.md) for a manual process for doing
+        Please look [here](../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](../../deprecated/CLI.md#model-selection-and-importation). The
+        Client](../../features/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](../../deprecated/CLI.md#model-selection-and-importation). The
+    Client](../../features/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](../../deprecated/CLI.md) documentation.
+[Command-Line Interface](../../features/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](../020_INSTALL_MANUAL.md) for a manual process for doing the
+          Please look [here](../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](../../deprecated/CLI.md#model-selection-and-importation). The
+        Client](../../features/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/communityNodes.md

@@ -9,7 +9,6 @@ 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
-    + [Average Images](#average-images)
     + [Depth Map from Wavefront OBJ](#depth-map-from-wavefront-obj)
     + [Film Grain](#film-grain)
     + [Generative Grammar-Based Prompt Nodes](#generative-grammar-based-prompt-nodes)
@@ -34,13 +33,6 @@ To use a community workflow, download the the `.json` node graph file and load i
 - [Help](#help)
 
 
---------------------------------
-### Average Images
-
-**Description:** This node takes in a collection of images of the same size and averages them as output. It converts everything to RGB mode first.
-
-**Node Link:** https://github.com/JPPhoto/average-images-node
-
 --------------------------------
 ### Depth Map from Wavefront OBJ
 
@@ -185,8 +177,12 @@ This includes 15 Nodes:
 
 **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:** 
-<img src="https://raw.githubusercontent.com/helix4u/load_video_frame/main/_git_assets/testmp4_embed_converted.gif" width="500" />
+
+<img src="https://github.com/helix4u/load_video_frame/blob/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

installer/install.bat.in

@@ -1,7 +1,7 @@
 @echo off
 setlocal EnableExtensions EnableDelayedExpansion
 
-@rem This script requires the user to install Python 3.10 or higher. All other
+@rem This script requires the user to install Python 3.9 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=3.10.0
+set MINIMUM_PYTHON_VERSION=3.9.0
 set PYTHON_URL=https://www.python.org/downloads/release/python-3109/
 
 set err_msg=An error has occurred and the script could not continue.
@@ -28,7 +28,8 @@ 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 3.10 or 3.11. Python version 3.9 is no longer supported.
+echo 1. Install python 3.9 or 3.10. Python version 3.11 and above are
+echo    not supported at the moment.
 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.
@@ -45,19 +46,19 @@ echo ***** Checking and Updating Python *****
 
 call python --version >.tmp1 2>.tmp2
 if %errorlevel% == 1 (
-   set err_msg=Please install Python 3.10-11. See %INSTRUCTIONS% for details.
+   set err_msg=Please install Python 3.10. 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 3.10.12 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 3.10.9 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 3.10.12 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 3.10.9 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=3.10.0
+MINIMUM_PYTHON_VERSION=3.9.0
 MAXIMUM_PYTHON_VERSION=3.11.100
 PYTHON=""
-for candidate in python3.11 python3.10 python3 python ; do
+for candidate in python3.11 python3.10 python3.9 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 = ">=3.10.0,<=3.11.100"
+SUPPORTED_PYTHON = ">=3.9.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
 BOOTSTRAP_VENV_PREFIX = "invokeai-installer-tmp"
 
@@ -67,6 +67,7 @@ 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:
@@ -138,6 +139,13 @@ 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(

installer/readme.txt

@@ -4,7 +4,7 @@ Project homepage: https://github.com/invoke-ai/InvokeAI
 
 Preparations:
 
-  You will need to install Python 3.10 or higher for this installer
+  You will need to install Python 3.9 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 3.10.*, and not higher than 3.11.*.
+  is at least 3.9.*, 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 3.10 or 3.11. For example:
-  "pip 22.0.1 from /usr/bin/pip (python 3.10)"
+  installer was derived from Python 3.9 or 3.10. For example:
+  "pip 22.3.1 from /usr/bin/pip (python 3.9)"
 
 Long Paths on Windows:
 

installer/templates/invoke.bat.in

@@ -9,37 +9,41 @@ set INVOKEAI_ROOT=.
 :start
 echo Desired action:
 echo 1. Generate images with the browser-based interface
-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 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 Q - Quit
-set /P choice="Please enter 1-10, Q: [1] "
+set /P choice="Please enter 1-11, 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%" == "3" (
+) ELSE IF /I "%choice%" == "4" (
     echo Starting model merging script..
     python .venv\Scripts\invokeai-merge.exe --gui
-) ELSE IF /I "%choice%" == "4" (
+) ELSE IF /I "%choice%" == "5" (
     echo Running invokeai-model-install...
     python .venv\Scripts\invokeai-model-install.exe
-) 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%" == "6" (
     echo Running invokeai-configure...
-    python .venv\Scripts\invokeai-configure.exe --yes --skip-sd-weight
+    python .venv\Scripts\invokeai-configure.exe --skip-sd-weight --skip-support-models
 ) ELSE IF /I "%choice%" == "7" (
+    echo Running invokeai-configure...
+    python .venv\Scripts\invokeai-configure.exe --yes --skip-sd-weight
+) ELSE IF /I "%choice%" == "8" (
     echo Developer Console
     echo Python command is:
     where python
@@ -51,13 +55,13 @@ 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%" == "8" (
+) ELSE IF /I "%choice%" == "9" (
    echo Running invokeai-update...
    python -m invokeai.frontend.install.invokeai_update
-) ELSE IF /I "%choice%" == "9" (
+) ELSE IF /I "%choice%" == "10" (
    echo Running the db maintenance script...
    python .venv\Scripts\invokeai-db-maintenance.exe
-) ELSE IF /I "%choice%" == "10" (
+) ELSE IF /I "%choice%" == "11" (
     echo Displaying command line help...
     python .venv\Scripts\invokeai-web.exe --help %*
     pause

installer/templates/invoke.sh.in

@@ -58,47 +58,52 @@ 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
         ;;
-    3)
+    4)
         clear
         printf "Merge models (diffusers type only)\n"
         invokeai-merge --gui $PARAMS
         ;;
-    4)
+    5)
         clear
         printf "Download and install models\n"
         invokeai-model-install --root ${INVOKEAI_ROOT}
         ;;
-    5)
+    6)
         clear
         printf "Change InvokeAI startup options\n"
         invokeai-configure --root ${INVOKEAI_ROOT} --skip-sd-weights --skip-support-models
         ;;
-    6)
+    7)
         clear
         printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
         invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only --skip-sd-weights
         ;;
-    7)
+    8)
         clear
         printf "Open the developer console\n"
         file_name=$(basename "${BASH_SOURCE[0]}")
         bash --init-file "$file_name"
         ;;
-    8)
+    9)
         clear
         printf "Update InvokeAI\n"
         python -m invokeai.frontend.install.invokeai_update
         ;;
-    9)
+    10)
         clear
         printf "Running the db maintenance script\n"
         invokeai-db-maintenance --root ${INVOKEAI_ROOT}
         ;;
-    10)
+    11)
         clear
         printf "Command-line help\n"
         invokeai-web --help
@@ -116,15 +121,16 @@ do_choice() {
 do_dialog() {
     options=(
         1 "Generate images with a browser-based interface"
-        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"
+        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"
     )
 
     choice=$(dialog --clear \
@@ -149,17 +155,18 @@ do_line_input() {
     printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
     printf "What would you like to do?\n"
     printf "1: Generate images using the browser-based interface\n"
-    printf "2: Run textual inversion training\n"
-    printf "3: Merge models (diffusers type only)\n"
-    printf "4: Download and install models\n"
-    printf "5: Change InvokeAI startup options\n"
-    printf "6: Re-run the configure script to fix a broken install\n"
-    printf "7: Open the developer console\n"
-    printf "8: Update InvokeAI\n"
-    printf "9: Run the InvokeAI image database maintenance script\n"
-    printf "10: Command-line help\n"
+    printf "2: Explore InvokeAI nodes using the command-line interface\n"
+    printf "3: Run textual inversion training\n"
+    printf "4: Merge models (diffusers type only)\n"
+    printf "5: Download and install models\n"
+    printf "6: Change InvokeAI startup options\n"
+    printf "7: Re-run the configure script to fix a broken install\n"
+    printf "8: Open the developer console\n"
+    printf "9: Update InvokeAI\n"
+    printf "10: Run the InvokeAI image database maintenance script\n"
+    printf "11: Command-line help\n"
     printf "Q: Quit\n\n"
-    read -p "Please enter 1-10, Q: [1] " yn
+    read -p "Please enter 1-11, Q: [1] " yn
     choice=${yn:='1'}
     do_choice $choice
     clear

invokeai/app/api/dependencies.py

@@ -2,7 +2,6 @@
 
 from logging import Logger
 
-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__
 
@@ -31,7 +30,6 @@ 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
 
 
@@ -92,8 +90,6 @@ class ApiDependencies:
         session_processor = DefaultSessionProcessor()
         session_queue = SqliteSessionQueue(db=db)
         urls = LocalUrlService()
-        workflow_image_records = SqliteWorkflowImageRecordsStorage(db=db)
-        workflow_records = SqliteWorkflowRecordsStorage(db=db)
 
         services = InvocationServices(
             board_image_records=board_image_records,
@@ -118,8 +114,6 @@ class ApiDependencies:
             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)

invokeai/app/api/routers/images.py

@@ -1,14 +1,13 @@
 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, ValidationError
+from pydantic import BaseModel, Field
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator, WorkflowFieldValidator
+from invokeai.app.invocations.metadata import ImageMetadata
 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
@@ -46,38 +45,17 @@ async def upload_image(
     if not file.content_type or not file.content_type.startswith("image"):
         raise HTTPException(status_code=415, detail="Not an image")
 
-    metadata = None
-    workflow = None
-
     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:
-        ApiDependencies.invoker.services.logger.error(traceback.format_exc())
+        # Error opening the image
         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,
@@ -85,8 +63,6 @@ async def upload_image(
             image_category=image_category,
             session_id=session_id,
             board_id=board_id,
-            metadata=metadata,
-            workflow=workflow,
             is_intermediate=is_intermediate,
         )
 
@@ -95,7 +71,6 @@ 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")
 
 
@@ -112,7 +87,7 @@ async def delete_image(
         pass
 
 
-@images_router.delete("/intermediates", operation_id="clear_intermediates")
+@images_router.post("/clear-intermediates", operation_id="clear_intermediates")
 async def clear_intermediates() -> int:
     """Clears all intermediates"""
 
@@ -124,17 +99,6 @@ 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",
@@ -171,11 +135,11 @@ async def get_image_dto(
 @images_router.get(
     "/i/{image_name}/metadata",
     operation_id="get_image_metadata",
-    response_model=Optional[MetadataField],
+    response_model=ImageMetadata,
 )
 async def get_image_metadata(
     image_name: str = Path(description="The name of image to get"),
-) -> Optional[MetadataField]:
+) -> ImageMetadata:
     """Gets an image's metadata"""
 
     try:

invokeai/app/api/routers/models.py

@@ -23,13 +23,13 @@ from ..dependencies import ApiDependencies
 models_router = APIRouter(prefix="/v1/models", tags=["models"])
 
 UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-UpdateModelResponseValidator = TypeAdapter(UpdateModelResponse)
+update_models_response_adapter = TypeAdapter(UpdateModelResponse)
 
 ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelResponseValidator = TypeAdapter(ImportModelResponse)
+import_models_response_adapter = TypeAdapter(ImportModelResponse)
 
 ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ConvertModelResponseValidator = TypeAdapter(ConvertModelResponse)
+convert_models_response_adapter = TypeAdapter(ConvertModelResponse)
 
 MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
@@ -41,7 +41,7 @@ class ModelsList(BaseModel):
     model_config = ConfigDict(use_enum_values=True)
 
 
-ModelsListValidator = TypeAdapter(ModelsList)
+models_list_adapter = TypeAdapter(ModelsList)
 
 
 @models_router.get(
@@ -60,7 +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 = ModelsListValidator.validate_python({"models": models_raw})
+    models = models_list_adapter.validate_python({"models": models_raw})
     return models
 
 
@@ -131,7 +131,7 @@ async def update_model(
             base_model=base_model,
             model_type=model_type,
         )
-        model_response = UpdateModelResponseValidator.validate_python(model_raw)
+        model_response = update_models_response_adapter.validate_python(model_raw)
     except ModelNotFoundException as e:
         raise HTTPException(status_code=404, detail=str(e))
     except ValueError as e:
@@ -186,7 +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 ImportModelResponseValidator.validate_python(model_raw)
+        return import_models_response_adapter.validate_python(model_raw)
 
     except ModelNotFoundException as e:
         logger.error(str(e))
@@ -231,7 +231,7 @@ async def add_model(
             base_model=info.base_model,
             model_type=info.model_type,
         )
-        return ImportModelResponseValidator.validate_python(model_raw)
+        return import_models_response_adapter.validate_python(model_raw)
     except ModelNotFoundException as e:
         logger.error(str(e))
         raise HTTPException(status_code=404, detail=str(e))
@@ -302,7 +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 = ConvertModelResponseValidator.validate_python(model_raw)
+        response = convert_models_response_adapter.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:
@@ -417,7 +417,7 @@ async def merge_models(
             base_model=base_model,
             model_type=ModelType.Main,
         )
-        response = ConvertModelResponseValidator.validate_python(model_raw)
+        response = convert_models_response_adapter.validate_python(model_raw)
     except ModelNotFoundException:
         raise HTTPException(
             status_code=404,

invokeai/app/api/routers/session_queue.py

@@ -12,11 +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.graph import Graph
 from invokeai.app.services.shared.pagination import CursorPaginatedResults
 
 from ..dependencies import ApiDependencies
@@ -31,6 +33,23 @@ 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

@@ -1,50 +1,57 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+from typing import Annotated, Optional, Union
 
-from fastapi import HTTPException, Path
+from fastapi import Body, HTTPException, Path, Query, Response
 from fastapi.routing import APIRouter
+from pydantic.fields import Field
 
-from ...services.shared.graph import GraphExecutionState
+from invokeai.app.services.shared.pagination import PaginatedResults
+
+# Importing * is bad karma but needed here for node detection
+from ...invocations import *  # noqa: F401 F403
+from ...invocations.baseinvocation import BaseInvocation
+from ...services.shared.graph import Edge, EdgeConnection, Graph, GraphExecutionState, NodeAlreadyExecutedError
 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(
@@ -54,6 +61,7 @@ session_router = APIRouter(prefix="/v1/sessions", tags=["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"),
@@ -66,211 +74,211 @@ 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/workflows.py

@@ -1,20 +0,0 @@
-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_app.py

@@ -1,7 +1,3 @@
-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
@@ -17,20 +13,17 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
     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.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
@@ -38,27 +31,19 @@ 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,
-        workflows,
-    )
+    from .api.routers import app_info, board_images, boards, images, models, session_queue, utilities
     from .api.sockets import SocketIO
     from .invocations.baseinvocation import BaseInvocation, UIConfigBase, _InputField, _OutputField
 
-    if is_mps_available():
+    if torch.backends.mps.is_available():
+        # noinspection PyUnresolvedReferences
         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")
@@ -86,37 +71,40 @@ app.add_middleware(
     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() -> None:
+async def startup_event():
     ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
 
 
 # Shut down threads
 @app.on_event("shutdown")
-async def shutdown_event() -> None:
+async def shutdown_event():
     ApiDependencies.shutdown()
 
 
 # Include all routers
-app.include_router(sessions.session_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() -> dict[str, Any]:
+def custom_openapi():
     if app.openapi_schema:
         return app.openapi_schema
     openapi_schema = get_openapi(
@@ -171,6 +159,7 @@ def custom_openapi() -> dict[str, Any]:
             # 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.",
@@ -184,43 +173,34 @@ def custom_openapi() -> dict[str, Any]:
 
 app.openapi = custom_openapi  # type: ignore [method-assign] # this is a valid assignment
 
+# Override API doc favicons
+app.mount("/static", StaticFiles(directory=Path(web_dir.__path__[0], "static/dream_web")), name="static")
+
 
 @app.get("/docs", include_in_schema=False)
-def overridden_swagger() -> HTMLResponse:
+def overridden_swagger():
     return get_swagger_ui_html(
-        openapi_url=app.openapi_url,  # type: ignore [arg-type] # this is always a string
+        openapi_url=app.openapi_url,
         title=app.title,
-        swagger_favicon_url="/static/docs/favicon.ico",
+        swagger_favicon_url="/static/favicon.ico",
     )
 
 
 @app.get("/redoc", include_in_schema=False)
-def overridden_redoc() -> HTMLResponse:
+def overridden_redoc():
     return get_redoc_html(
-        openapi_url=app.openapi_url,  # type: ignore [arg-type] # this is always a string
+        openapi_url=app.openapi_url,
         title=app.title,
-        redoc_favicon_url="/static/docs/favicon.ico",
+        redoc_favicon_url="/static/favicon.ico",
     )
 
 
-web_root_path = Path(list(web_dir.__path__)[0])
+# Must mount *after* the other routes else it borks em
+app.mount("/", StaticFiles(directory=Path(web_dir.__path__[0], "dist"), html=True), name="ui")
 
 
-# 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:
+def invoke_api():
+    def find_port(port: 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
@@ -255,7 +235,7 @@ def invoke_api() -> None:
         app=app,
         host=app_config.host,
         port=port,
-        loop="asyncio",
+        loop=loop,
         log_level=app_config.log_level,
     )
     server = uvicorn.Server(config)

invokeai/app/cli/commands.py

@@ -0,0 +1,312 @@
+# 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.annotation) == Literal:
+        allowed_values = get_args(field.annotation)
+        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.description,
+        )
+    else:
+        command_parser.add_argument(
+            f"--{name}",
+            dest=name,
+            type=field.annotation,
+            default=default,
+            help=field.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:
+
+    @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

@@ -0,0 +1,171 @@
+"""
+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

@@ -0,0 +1,484 @@
+# 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

@@ -1,28 +1,8 @@
-import shutil
-import sys
-from importlib.util import module_from_spec, spec_from_file_location
-from pathlib import Path
+import os
 
-from invokeai.app.services.config.config_default import InvokeAIAppConfig
+__all__ = []
 
-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
+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])

invokeai/app/invocations/baseinvocation.py

@@ -2,21 +2,27 @@
 
 from __future__ import annotations
 
-import inspect
+import json
 import re
 from abc import ABC, abstractmethod
 from enum import Enum
 from inspect import signature
 from types import UnionType
-from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union
+from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Protocol, Type, TypeVar, Union
 
 import semver
-from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter, create_model
-from pydantic.fields import FieldInfo, _Unset
+from PIL.Image import Image as ImageType
+from pydantic import BaseModel, ConfigDict, Field, create_model, field_validator
+from pydantic.fields import _Unset
 from pydantic_core import PydanticUndefined
+import torch
 
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.services.invocation_processor.invocation_processor_common import ProgressImage
 from invokeai.app.util.misc import uuid_string
+from invokeai.backend.model_management.model_manager import ModelInfo
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
 
 if TYPE_CHECKING:
     from ..services.invocation_services import InvocationServices
@@ -26,10 +32,6 @@ 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"
@@ -64,12 +66,7 @@ class FieldDescriptions:
     denoised_latents = "Denoised latents tensor"
     latents = "Latents tensor"
     strength = "Strength of denoising (proportional to steps)"
-    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"
+    core_metadata = "Optional core metadata to be written to 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"
@@ -176,12 +173,8 @@ 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
 
 
@@ -307,7 +300,6 @@ def InputField(
         ui_order=ui_order,
         item_default=item_default,
         ui_choice_labels=ui_choice_labels,
-        _field_kind="input",
     )
 
     field_args = dict(
@@ -450,7 +442,6 @@ def OutputField(
             ui_type=ui_type,
             ui_hidden=ui_hidden,
             ui_order=ui_order,
-            _field_kind="output",
         ),
     )
 
@@ -475,7 +466,123 @@ class UIConfigBase(BaseModel):
     )
 
 
+class GetImage(Protocol):
+    def __call__(self, name: str) -> ImageType:
+        ...
+
+
+class SaveImage(Protocol):
+    def __call__(self, image: ImageType, category: ImageCategory = ImageCategory.GENERAL) -> str:
+        ...
+
+
+class GetLatents(Protocol):
+    def __call__(self, name: str) -> torch.Tensor:
+        ...
+
+
+class SaveLatents(Protocol):
+    def __call__(self, latents: torch.Tensor) -> str:
+        ...
+
+
+class GetConditioning(Protocol):
+    def __call__(self, name: str) -> torch.Tensor:
+        ...
+
+
+class SaveConditioning(Protocol):
+    def __call__(self, conditioning: torch.Tensor) -> str:
+        ...
+
+
+class IsCanceled(Protocol):
+    def __call__(self) -> bool:
+        ...
+
+
+class EmitDenoisingProgress(Protocol):
+    def __call__(self, progress_image: ProgressImage, step: int, order: int, total_steps: int) -> None:
+        ...
+
+
+class GetModel(Protocol):
+    def __call__(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: Optional[SubModelType] = None,
+    ) -> ModelInfo:
+        ...
+
+
+class ModelExists(Protocol):
+    def __call__(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ) -> bool:
+        ...
+
+
 class InvocationContext:
+    def __init__(
+        self,
+        # context
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
+        source_node_id: str,
+        # methods
+        get_image: GetImage,
+        save_image: SaveImage,
+        get_latents: GetLatents,
+        save_latents: SaveLatents,
+        get_conditioning: GetConditioning,
+        save_conditioning: SaveConditioning,
+        is_canceled: IsCanceled,
+        get_model: GetModel,
+        emit_denoising_progress: EmitDenoisingProgress,
+        model_exists: ModelExists,
+        # services
+        config: InvokeAIAppConfig,
+    ) -> None:
+        # context
+        self.queue_id = queue_id
+        self.queue_item_id = queue_item_id
+        self.queue_batch_id = queue_batch_id
+        self.graph_execution_state_id = graph_execution_state_id
+        self.source_node_id = source_node_id
+
+        # resource methods
+        self.get_image = get_image
+        self.save_image = save_image
+        self.get_latents = get_latents
+        self.save_latents = save_latents
+        self.get_conditioning = get_conditioning
+        self.save_conditioning = save_conditioning
+
+        # execution state
+        self.is_canceled = is_canceled
+
+        # models
+        self.get_model = get_model
+        self.model_exists = model_exists
+
+        # events
+        self.emit_denoising_progress = emit_denoising_progress
+
+        # services
+        self.config = config
+
+        # misc
+        self.categories = ImageCategory
+
+
+class AppInvocationContext:
     """Initialized and provided to on execution of invocations."""
 
     services: InvocationServices
@@ -483,6 +590,7 @@ class InvocationContext:
     queue_id: str
     queue_item_id: int
     queue_batch_id: str
+    source_node_id: str
 
     def __init__(
         self,
@@ -491,12 +599,113 @@ class InvocationContext:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
+        source_node_id: str,
     ):
         self.services = services
         self.graph_execution_state_id = graph_execution_state_id
         self.queue_id = queue_id
         self.queue_item_id = queue_item_id
         self.queue_batch_id = queue_batch_id
+        self.source_node_id = source_node_id
+
+    def get_restricted_context(self, invocation: BaseInvocation) -> InvocationContext:
+        def get_image(name: str) -> ImageType:
+            return self.services.images.get_pil_image(name)
+
+        def save_image(image: ImageType, category: ImageCategory = ImageCategory.GENERAL) -> str:
+            metadata = getattr(invocation, "metadata")
+            workflow = getattr(invocation, "workflow")
+
+            image_dto = self.services.images.create(
+                image=image,
+                image_origin=ResourceOrigin.INTERNAL,
+                image_category=category,
+                session_id=self.graph_execution_state_id,
+                node_id=invocation.id,
+                is_intermediate=invocation.is_intermediate,
+                metadata=metadata.model_dump() if metadata else None,
+                workflow=workflow,
+            )
+            return image_dto.image_name
+
+        def get_latents(name: str) -> torch.Tensor:
+            return self.services.latents.get(name)
+
+        def save_latents(latents: torch.Tensor) -> str:
+            name = f"{self.graph_execution_state_id}__{invocation.id}"
+            self.services.latents.save(name=name, data=latents)
+            return name
+
+        def get_conditioning(name: str) -> torch.Tensor:
+            return self.services.latents.get(name)
+
+        def save_conditioning(conditioning: torch.Tensor) -> str:
+            name = f"{self.graph_execution_state_id}__{invocation.id}_conditioning"
+            self.services.latents.save(name=name, data=conditioning)
+            return name
+
+        def is_canceled() -> bool:
+            return self.services.queue.is_canceled(self.graph_execution_state_id)
+
+        def get_model(
+            model_name: str,
+            base_model: BaseModelType,
+            model_type: ModelType,
+            submodel: Optional[SubModelType] = None,
+        ) -> ModelInfo:
+            return self.services.model_manager.get_model(
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+                queue_id=self.queue_id,
+                queue_item_id=self.queue_item_id,
+                queue_batch_id=self.queue_batch_id,
+                graph_execution_state_id=self.graph_execution_state_id,
+            )
+
+        def model_exists(
+            model_name: str,
+            base_model: BaseModelType,
+            model_type: ModelType,
+        ) -> bool:
+            return self.services.model_manager.model_exists(model_name, base_model, model_type)
+
+        def emit_denoising_progress(progress_image: ProgressImage, step: int, order: int, total_steps: int) -> None:
+            self.services.events.emit_generator_progress(
+                queue_id=self.queue_id,
+                queue_item_id=self.queue_item_id,
+                queue_batch_id=self.queue_batch_id,
+                graph_execution_state_id=self.graph_execution_state_id,
+                node=invocation.model_dump(),
+                source_node_id=self.source_node_id,
+                progress_image=progress_image,
+                step=step,
+                order=order,
+                total_steps=total_steps,
+            )
+
+        return InvocationContext(
+            # context
+            queue_id=self.queue_id,
+            queue_item_id=self.queue_item_id,
+            queue_batch_id=self.queue_batch_id,
+            graph_execution_state_id=self.graph_execution_state_id,
+            source_node_id=self.source_node_id,
+            # methods
+            get_image=get_image,
+            save_image=save_image,
+            get_latents=get_latents,
+            save_latents=save_latents,
+            get_conditioning=get_conditioning,
+            save_conditioning=save_conditioning,
+            is_canceled=is_canceled,
+            emit_denoising_progress=emit_denoising_progress,
+            get_model=get_model,
+            model_exists=model_exists,
+            # services
+            config=self.services.configuration,
+        )
 
 
 class BaseInvocationOutput(BaseModel):
@@ -534,7 +743,6 @@ class BaseInvocationOutput(BaseModel):
         schema["required"].extend(["type"])
 
     model_config = ConfigDict(
-        protected_namespaces=(),
         validate_assignment=True,
         json_schema_serialization_defaults_required=True,
         json_schema_extra=json_schema_extra,
@@ -557,6 +765,9 @@ 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.
     """
 
@@ -626,7 +837,7 @@ class BaseInvocation(ABC, BaseModel):
         """Invoke with provided context and return outputs."""
         pass
 
-    def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
+    def invoke_internal(self, context: AppInvocationContext) -> BaseInvocationOutput:
         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
@@ -648,7 +859,7 @@ class BaseInvocation(ABC, BaseModel):
 
         # skip node cache codepath if it's disabled
         if context.services.configuration.node_cache_size == 0:
-            return self.invoke(context)
+            return self.invoke(context.get_restricted_context(invocation=self))
 
         output: BaseInvocationOutput
         if self.use_cache:
@@ -656,7 +867,7 @@ class BaseInvocation(ABC, BaseModel):
             cached_value = context.services.invocation_cache.get(key)
             if cached_value is None:
                 context.services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
-                output = self.invoke(context)
+                output = self.invoke(context.get_restricted_context(invocation=self))
                 context.services.invocation_cache.save(key, output)
                 return output
             else:
@@ -664,7 +875,7 @@ class BaseInvocation(ABC, BaseModel):
                 return cached_value
         else:
             context.services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
-            return self.invoke(context)
+            return self.invoke(context.get_restricted_context(invocation=self))
 
     def get_type(self) -> str:
         return self.model_fields["type"].default
@@ -672,93 +883,46 @@ class BaseInvocation(ABC, BaseModel):
     id: str = Field(
         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 = Field(
+    is_intermediate: Optional[bool] = Field(
         default=False,
         description="Whether or not this is an intermediate invocation.",
-        json_schema_extra=dict(ui_type=UIType.IsIntermediate, _field_kind="internal"),
+        json_schema_extra=dict(ui_type=UIType.IsIntermediate),
     )
-    use_cache: bool = Field(
-        default=True, description="Whether or not to use the cache", json_schema_extra=dict(_field_kind="internal")
+    workflow: Optional[str] = Field(
+        default=None,
+        description="The workflow to save with the image",
+        json_schema_extra=dict(ui_type=UIType.WorkflowField),
     )
+    use_cache: Optional[bool] = Field(
+        default=True,
+        description="Whether or not to use the cache",
+    )
+
+    @field_validator("workflow", mode="before")
+    @classmethod
+    def validate_workflow_is_json(cls, v):
+        """We don't have a workflow schema in the backend, so we just check that it's valid JSON"""
+        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,
     )
 
 
 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(
     invocation_type: str,
     title: Optional[str] = None,
@@ -768,7 +932,7 @@ def invocation(
     use_cache: Optional[bool] = True,
 ) -> Callable[[Type[TBaseInvocation]], Type[TBaseInvocation]]:
     """
-    Registers an invocation.
+    Adds metadata to 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.
@@ -787,8 +951,6 @@ def invocation(
         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:
@@ -819,7 +981,8 @@ def invocation(
 
         invocation_type_annotation = Literal[invocation_type]  # type: ignore
         invocation_type_field = Field(
-            title="type", default=invocation_type, json_schema_extra=dict(_field_kind="internal")
+            title="type",
+            default=invocation_type,
         )
 
         docstring = cls.__doc__
@@ -860,12 +1023,13 @@ def invocation_output(
         if output_type in BaseInvocationOutput.get_output_types():
             raise ValueError(f'Invocation type "{output_type}" already exists')
 
-        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"))
+        output_type_field = Field(
+            title="type",
+            default=output_type,
+        )
 
         docstring = cls.__doc__
         cls = create_model(
@@ -883,37 +1047,4 @@ def invocation_output(
     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")
-    )
+GenericBaseModel = TypeVar("GenericBaseModel", bound=BaseModel)

invokeai/app/invocations/compel.py

@@ -66,25 +66,21 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
+        tokenizer_info = context.get_model(
             **self.clip.tokenizer.model_dump(),
-            context=context,
         )
-        text_encoder_info = context.services.model_manager.get_model(
+        text_encoder_info = context.get_model(
             **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.model_dump(exclude={"weight"}), context=context
-                )
+                lora_info = context.get_model(**lora.model_dump(exclude={"weight"}))
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
-        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
         ti_list = []
         for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
@@ -93,11 +89,10 @@ class CompelInvocation(BaseInvocation):
                 ti_list.append(
                     (
                         name,
-                        context.services.model_manager.get_model(
+                        context.get_model(
                             model_name=name,
                             base_model=self.clip.text_encoder.base_model,
                             model_type=ModelType.TextualInversion,
-                            context=context,
                         ).context.model,
                     )
                 )
@@ -126,7 +121,7 @@ class CompelInvocation(BaseInvocation):
 
             conjunction = Compel.parse_prompt_string(self.prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.log_tokenization:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
             c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
@@ -147,8 +142,7 @@ class CompelInvocation(BaseInvocation):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.save_conditioning(conditioning_data)
 
         return ConditioningOutput(
             conditioning=ConditioningField(

invokeai/app/invocations/controlnet_image_processors.py

@@ -38,8 +38,6 @@ from .baseinvocation import (
     InputField,
     InvocationContext,
     OutputField,
-    WithMetadata,
-    WithWorkflow,
     invocation,
     invocation_output,
 )
@@ -129,12 +127,12 @@ class ControlNetInvocation(BaseInvocation):
 
 
 # This invocation exists for other invocations to subclass it - do not register with @invocation!
-class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+class ImageProcessorInvocation(BaseInvocation):
     """Base class for invocations that preprocess images for ControlNet"""
 
     image: ImageField = InputField(description="The image to process")
 
-    def run_processor(self, image: Image.Image) -> Image.Image:
+    def run_processor(self, image):
         # superclass just passes through image without processing
         return image
 
@@ -152,7 +150,6 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithWorkflow):
             session_id=context.graph_execution_state_id,
             node_id=self.id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 

invokeai/app/invocations/custom_nodes/README.md

@@ -1,51 +0,0 @@
-# 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

@@ -1,51 +0,0 @@
-"""
-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

@@ -8,11 +8,11 @@ from PIL import Image, ImageOps
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
 
 
 @invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.0.0")
-class CvInpaintInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+class CvInpaintInvocation(BaseInvocation):
     """Simple inpaint using opencv."""
 
     image: ImageField = InputField(description="The image to inpaint")

invokeai/app/invocations/facetools.py

@@ -16,8 +16,6 @@ from invokeai.app.invocations.baseinvocation import (
     InputField,
     InvocationContext,
     OutputField,
-    WithMetadata,
-    WithWorkflow,
     invocation,
     invocation_output,
 )
@@ -439,7 +437,7 @@ def get_faces_list(
 
 
 @invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.0.2")
-class FaceOffInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class FaceOffInvocation(BaseInvocation):
     """Bound, extract, and mask a face from an image using MediaPipe detection"""
 
     image: ImageField = InputField(description="Image for face detection")
@@ -533,7 +531,7 @@ class FaceOffInvocation(BaseInvocation, WithWorkflow, WithMetadata):
 
 
 @invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.0.2")
-class FaceMaskInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class FaceMaskInvocation(BaseInvocation):
     """Face mask creation using mediapipe face detection"""
 
     image: ImageField = InputField(description="Image to face detect")
@@ -652,7 +650,7 @@ class FaceMaskInvocation(BaseInvocation, WithWorkflow, WithMetadata):
 @invocation(
     "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.0.2"
 )
-class FaceIdentifierInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class FaceIdentifierInvocation(BaseInvocation):
     """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
 
     image: ImageField = InputField(description="Image to face detect")

invokeai/app/invocations/image.py

@@ -7,21 +7,13 @@ import cv2
 import numpy
 from PIL import Image, ImageChops, ImageFilter, ImageOps
 
+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 .baseinvocation import (
-    BaseInvocation,
-    FieldDescriptions,
-    Input,
-    InputField,
-    InvocationContext,
-    WithMetadata,
-    WithWorkflow,
-    invocation,
-)
+from .baseinvocation import BaseInvocation, FieldDescriptions, Input, InputField, InvocationContext, invocation
 
 
 @invocation("show_image", title="Show Image", tags=["image"], category="image", version="1.0.0")
@@ -44,8 +36,14 @@ class ShowImageInvocation(BaseInvocation):
         )
 
 
-@invocation("blank_image", title="Blank Image", tags=["image"], category="image", version="1.0.0")
-class BlankImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+@invocation(
+    "blank_image",
+    title="Blank Image",
+    tags=["image"],
+    category="image",
+    version="1.0.0",
+)
+class BlankImageInvocation(BaseInvocation):
     """Creates a blank image and forwards it to the pipeline"""
 
     width: int = InputField(default=512, description="The width of the image")
@@ -63,7 +61,6 @@ class BlankImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -74,8 +71,14 @@ class BlankImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
         )
 
 
-@invocation("img_crop", title="Crop Image", tags=["image", "crop"], category="image", version="1.0.0")
-class ImageCropInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "img_crop",
+    title="Crop Image",
+    tags=["image", "crop"],
+    category="image",
+    version="1.0.0",
+)
+class ImageCropInvocation(BaseInvocation):
     """Crops an image to a specified box. The box can be outside of the image."""
 
     image: ImageField = InputField(description="The image to crop")
@@ -97,7 +100,6 @@ class ImageCropInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -108,8 +110,14 @@ class ImageCropInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("img_paste", title="Paste Image", tags=["image", "paste"], category="image", version="1.0.1")
-class ImagePasteInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "img_paste",
+    title="Paste Image",
+    tags=["image", "paste"],
+    category="image",
+    version="1.0.1",
+)
+class ImagePasteInvocation(BaseInvocation):
     """Pastes an image into another image."""
 
     base_image: ImageField = InputField(description="The base image")
@@ -151,7 +159,6 @@ class ImagePasteInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -162,8 +169,14 @@ class ImagePasteInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("tomask", title="Mask from Alpha", tags=["image", "mask"], category="image", version="1.0.0")
-class MaskFromAlphaInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "tomask",
+    title="Mask from Alpha",
+    tags=["image", "mask"],
+    category="image",
+    version="1.0.0",
+)
+class MaskFromAlphaInvocation(BaseInvocation):
     """Extracts the alpha channel of an image as a mask."""
 
     image: ImageField = InputField(description="The image to create the mask from")
@@ -183,7 +196,6 @@ class MaskFromAlphaInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -194,8 +206,14 @@ class MaskFromAlphaInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("img_mul", title="Multiply Images", tags=["image", "multiply"], category="image", version="1.0.0")
-class ImageMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "img_mul",
+    title="Multiply Images",
+    tags=["image", "multiply"],
+    category="image",
+    version="1.0.0",
+)
+class ImageMultiplyInvocation(BaseInvocation):
     """Multiplies two images together using `PIL.ImageChops.multiply()`."""
 
     image1: ImageField = InputField(description="The first image to multiply")
@@ -214,7 +232,6 @@ class ImageMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -228,8 +245,14 @@ class ImageMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata):
 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, WithWorkflow, WithMetadata):
+@invocation(
+    "img_chan",
+    title="Extract Image Channel",
+    tags=["image", "channel"],
+    category="image",
+    version="1.0.0",
+)
+class ImageChannelInvocation(BaseInvocation):
     """Gets a channel from an image."""
 
     image: ImageField = InputField(description="The image to get the channel from")
@@ -247,7 +270,6 @@ class ImageChannelInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -261,8 +283,14 @@ class ImageChannelInvocation(BaseInvocation, WithWorkflow, WithMetadata):
 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, WithWorkflow, WithMetadata):
+@invocation(
+    "img_conv",
+    title="Convert Image Mode",
+    tags=["image", "convert"],
+    category="image",
+    version="1.0.0",
+)
+class ImageConvertInvocation(BaseInvocation):
     """Converts an image to a different mode."""
 
     image: ImageField = InputField(description="The image to convert")
@@ -280,7 +308,6 @@ class ImageConvertInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -291,8 +318,14 @@ class ImageConvertInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("img_blur", title="Blur Image", tags=["image", "blur"], category="image", version="1.0.0")
-class ImageBlurInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "img_blur",
+    title="Blur Image",
+    tags=["image", "blur"],
+    category="image",
+    version="1.0.0",
+)
+class ImageBlurInvocation(BaseInvocation):
     """Blurs an image"""
 
     image: ImageField = InputField(description="The image to blur")
@@ -315,7 +348,6 @@ class ImageBlurInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -346,17 +378,26 @@ PIL_RESAMPLING_MAP = {
 }
 
 
-@invocation("img_resize", title="Resize Image", tags=["image", "resize"], category="image", version="1.0.0")
-class ImageResizeInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+@invocation(
+    "img_resize",
+    title="Resize Image",
+    tags=["image", "resize"],
+    category="image",
+    version="1.0.0",
+)
+class ImageResizeInvocation(BaseInvocation):
     """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)
+        image = context.get_image(self.image.image_name)
 
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
@@ -365,26 +406,23 @@ class ImageResizeInvocation(BaseInvocation, WithMetadata, WithWorkflow):
             resample=resample_mode,
         )
 
-        image_dto = context.services.images.create(
-            image=resize_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=self.workflow,
-        )
+        image_name = context.save_image(image=resize_image)
 
         return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+            image=ImageField(image_name=image_name),
+            width=resize_image.width,
+            height=resize_image.height,
         )
 
 
-@invocation("img_scale", title="Scale Image", tags=["image", "scale"], category="image", version="1.0.0")
-class ImageScaleInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+@invocation(
+    "img_scale",
+    title="Scale Image",
+    tags=["image", "scale"],
+    category="image",
+    version="1.0.0",
+)
+class ImageScaleInvocation(BaseInvocation):
     """Scales an image by a factor"""
 
     image: ImageField = InputField(description="The image to scale")
@@ -414,7 +452,6 @@ class ImageScaleInvocation(BaseInvocation, WithMetadata, WithWorkflow):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -425,8 +462,14 @@ class ImageScaleInvocation(BaseInvocation, WithMetadata, WithWorkflow):
         )
 
 
-@invocation("img_lerp", title="Lerp Image", tags=["image", "lerp"], category="image", version="1.0.0")
-class ImageLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "img_lerp",
+    title="Lerp Image",
+    tags=["image", "lerp"],
+    category="image",
+    version="1.0.0",
+)
+class ImageLerpInvocation(BaseInvocation):
     """Linear interpolation of all pixels of an image"""
 
     image: ImageField = InputField(description="The image to lerp")
@@ -448,7 +491,6 @@ class ImageLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -459,8 +501,14 @@ class ImageLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("img_ilerp", title="Inverse Lerp Image", tags=["image", "ilerp"], category="image", version="1.0.0")
-class ImageInverseLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "img_ilerp",
+    title="Inverse Lerp Image",
+    tags=["image", "ilerp"],
+    category="image",
+    version="1.0.0",
+)
+class ImageInverseLerpInvocation(BaseInvocation):
     """Inverse linear interpolation of all pixels of an image"""
 
     image: ImageField = InputField(description="The image to lerp")
@@ -482,7 +530,6 @@ class ImageInverseLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -493,11 +540,20 @@ class ImageInverseLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("img_nsfw", title="Blur NSFW Image", tags=["image", "nsfw"], category="image", version="1.0.0")
-class ImageNSFWBlurInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+@invocation(
+    "img_nsfw",
+    title="Blur NSFW Image",
+    tags=["image", "nsfw"],
+    category="image",
+    version="1.0.0",
+)
+class ImageNSFWBlurInvocation(BaseInvocation):
     """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)
@@ -518,7 +574,7 @@ class ImageNSFWBlurInvocation(BaseInvocation, WithMetadata, WithWorkflow):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
+            metadata=self.metadata.model_dump() if self.metadata else None,
             workflow=self.workflow,
         )
 
@@ -542,11 +598,14 @@ class ImageNSFWBlurInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     category="image",
     version="1.0.0",
 )
-class ImageWatermarkInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+class ImageWatermarkInvocation(BaseInvocation):
     """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)
@@ -558,7 +617,7 @@ class ImageWatermarkInvocation(BaseInvocation, WithMetadata, WithWorkflow):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
+            metadata=self.metadata.model_dump() if self.metadata else None,
             workflow=self.workflow,
         )
 
@@ -569,8 +628,14 @@ class ImageWatermarkInvocation(BaseInvocation, WithMetadata, WithWorkflow):
         )
 
 
-@invocation("mask_edge", title="Mask Edge", tags=["image", "mask", "inpaint"], category="image", version="1.0.0")
-class MaskEdgeInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "mask_edge",
+    title="Mask Edge",
+    tags=["image", "mask", "inpaint"],
+    category="image",
+    version="1.0.0",
+)
+class MaskEdgeInvocation(BaseInvocation):
     """Applies an edge mask to an image"""
 
     image: ImageField = InputField(description="The image to apply the mask to")
@@ -604,7 +669,6 @@ class MaskEdgeInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -622,7 +686,7 @@ class MaskEdgeInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     category="image",
     version="1.0.0",
 )
-class MaskCombineInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class MaskCombineInvocation(BaseInvocation):
     """Combine two masks together by multiplying them using `PIL.ImageChops.multiply()`."""
 
     mask1: ImageField = InputField(description="The first mask to combine")
@@ -641,7 +705,6 @@ class MaskCombineInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -652,8 +715,14 @@ class MaskCombineInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("color_correct", title="Color Correct", tags=["image", "color"], category="image", version="1.0.0")
-class ColorCorrectInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "color_correct",
+    title="Color Correct",
+    tags=["image", "color"],
+    category="image",
+    version="1.0.0",
+)
+class ColorCorrectInvocation(BaseInvocation):
     """
     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.
@@ -752,7 +821,6 @@ class ColorCorrectInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -763,8 +831,14 @@ class ColorCorrectInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("img_hue_adjust", title="Adjust Image Hue", tags=["image", "hue"], category="image", version="1.0.0")
-class ImageHueAdjustmentInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation(
+    "img_hue_adjust",
+    title="Adjust Image Hue",
+    tags=["image", "hue"],
+    category="image",
+    version="1.0.0",
+)
+class ImageHueAdjustmentInvocation(BaseInvocation):
     """Adjusts the Hue of an image."""
 
     image: ImageField = InputField(description="The image to adjust")
@@ -792,7 +866,6 @@ class ImageHueAdjustmentInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             is_intermediate=self.is_intermediate,
             session_id=context.graph_execution_state_id,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -868,7 +941,7 @@ CHANNEL_FORMATS = {
     category="image",
     version="1.0.0",
 )
-class ImageChannelOffsetInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class ImageChannelOffsetInvocation(BaseInvocation):
     """Add or subtract a value from a specific color channel of an image."""
 
     image: ImageField = InputField(description="The image to adjust")
@@ -902,7 +975,6 @@ class ImageChannelOffsetInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             is_intermediate=self.is_intermediate,
             session_id=context.graph_execution_state_id,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -939,7 +1011,7 @@ class ImageChannelOffsetInvocation(BaseInvocation, WithWorkflow, WithMetadata):
     category="image",
     version="1.0.0",
 )
-class ImageChannelMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class ImageChannelMultiplyInvocation(BaseInvocation):
     """Scale a specific color channel of an image."""
 
     image: ImageField = InputField(description="The image to adjust")
@@ -979,7 +1051,6 @@ class ImageChannelMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata)
             is_intermediate=self.is_intermediate,
             session_id=context.graph_execution_state_id,
             workflow=self.workflow,
-            metadata=self.metadata,
         )
 
         return ImageOutput(
@@ -999,11 +1070,16 @@ class ImageChannelMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata)
     version="1.0.1",
     use_cache=False,
 )
-class SaveImageInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class SaveImageInvocation(BaseInvocation):
     """Saves an image. Unlike an image primitive, this invocation stores a copy of the image."""
 
     image: ImageField = InputField(description=FieldDescriptions.image)
-    board: BoardField = InputField(default=None, description=FieldDescriptions.board, input=Input.Direct)
+    board: Optional[BoardField] = InputField(default=None, description=FieldDescriptions.board, input=Input.Direct)
+    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)
@@ -1016,7 +1092,7 @@ class SaveImageInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
+            metadata=self.metadata.model_dump() if self.metadata else None,
             workflow=self.workflow,
         )
 

invokeai/app/invocations/infill.py

@@ -13,7 +13,7 @@ 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 .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, 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, WithWorkflow, WithMetadata):
+class InfillColorInvocation(BaseInvocation):
     """Infills transparent areas of an image with a solid color"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -143,7 +143,6 @@ class InfillColorInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -155,7 +154,7 @@ class InfillColorInvocation(BaseInvocation, WithWorkflow, WithMetadata):
 
 
 @invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
-class InfillTileInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class InfillTileInvocation(BaseInvocation):
     """Infills transparent areas of an image with tiles of the image"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -180,7 +179,6 @@ class InfillTileInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -194,7 +192,7 @@ class InfillTileInvocation(BaseInvocation, WithWorkflow, WithMetadata):
 @invocation(
     "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0"
 )
-class InfillPatchMatchInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class InfillPatchMatchInvocation(BaseInvocation):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -234,7 +232,6 @@ class InfillPatchMatchInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 
@@ -246,7 +243,7 @@ class InfillPatchMatchInvocation(BaseInvocation, WithWorkflow, WithMetadata):
 
 
 @invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
-class LaMaInfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class LaMaInfillInvocation(BaseInvocation):
     """Infills transparent areas of an image using the LaMa model"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -263,8 +260,6 @@ class LaMaInfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -274,8 +269,8 @@ class LaMaInfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
         )
 
 
-@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint")
-class CV2InfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
+class CV2InfillInvocation(BaseInvocation):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -292,8 +287,6 @@ class CV2InfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             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

@@ -36,7 +36,7 @@ class CLIPVisionModelField(BaseModel):
 
 
 class IPAdapterField(BaseModel):
-    image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
+    image: ImageField = Field(description="The IP-Adapter image prompt.")
     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")
@@ -55,12 +55,12 @@ 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="1.1.0")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.0.0")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
     # Inputs
-    image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).")
+    image: ImageField = InputField(description="The IP-Adapter image prompt.")
     ip_adapter_model: IPAdapterModelField = InputField(
         description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
     )

invokeai/app/invocations/latent.py

@@ -23,6 +23,7 @@ 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,
@@ -63,8 +64,6 @@ from .baseinvocation import (
     InvocationContext,
     OutputField,
     UIType,
-    WithMetadata,
-    WithWorkflow,
     invocation,
     invocation_output,
 )
@@ -183,9 +182,8 @@ def get_scheduler(
     seed: int,
 ) -> Scheduler:
     scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
-    orig_scheduler_info = context.services.model_manager.get_model(
+    orig_scheduler_info = context.get_model(
         **scheduler_info.model_dump(),
-        context=context,
     )
     with orig_scheduler_info as orig_scheduler:
         scheduler_config = orig_scheduler.config
@@ -215,7 +213,7 @@ def get_scheduler(
     title="Denoise Latents",
     tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
     category="latents",
-    version="1.4.0",
+    version="1.3.0",
 )
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
@@ -299,15 +297,12 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def dispatch_progress(
         self,
         context: InvocationContext,
-        source_node_id: str,
         intermediate_state: PipelineIntermediateState,
         base_model: BaseModelType,
     ) -> None:
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
-            node=self.model_dump(),
-            source_node_id=source_node_id,
             base_model=base_model,
         )
 
@@ -318,11 +313,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         unet,
         seed,
     ) -> ConditioningData:
-        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        positive_cond_data = context.get_conditioning(self.positive_conditioning.conditioning_name)
         c = positive_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
         extra_conditioning_info = c.extra_conditioning
 
-        negative_cond_data = context.services.latents.get(self.negative_conditioning.conditioning_name)
+        negative_cond_data = context.get_conditioning(self.negative_conditioning.conditioning_name)
         uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
 
         conditioning_data = ConditioningData(
@@ -409,17 +404,16 @@ class DenoiseLatentsInvocation(BaseInvocation):
         controlnet_data = []
         for control_info in control_list:
             control_model = exit_stack.enter_context(
-                context.services.model_manager.get_model(
+                context.get_model(
                     model_name=control_info.control_model.model_name,
                     model_type=ModelType.ControlNet,
                     base_model=control_info.control_model.base_model,
-                    context=context,
                 )
             )
 
             # control_models.append(control_model)
             control_image_field = control_info.image
-            input_image = context.services.images.get_pil_image(control_image_field.image_name)
+            input_image = context.get_image(control_image_field.image_name)
             # self.image.image_type, self.image.image_name
             # FIXME: still need to test with different widths, heights, devices, dtypes
             #        and add in batch_size, num_images_per_prompt?
@@ -477,36 +471,29 @@ class DenoiseLatentsInvocation(BaseInvocation):
         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(
+                context.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(
+            image_encoder_model_info = context.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,
             )
 
-            # `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]
-
-            single_ipa_images = [context.services.images.get_pil_image(image.image_name) for image in single_ipa_images]
+            input_image = context.get_image(single_ip_adapter.image.image_name)
 
             # 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
-                )
-
+                (
+                    image_prompt_embeds,
+                    uncond_image_prompt_embeds,
+                ) = ip_adapter_model.get_image_embeds(input_image, image_encoder_model)
                 conditioning_data.ip_adapter_conditioning.append(
                     IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds)
                 )
@@ -541,13 +528,12 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
-            t2i_adapter_model_info = context.services.model_manager.get_model(
+            t2i_adapter_model_info = context.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)
+            image = context.get_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:
@@ -657,11 +643,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
             seed = None
             noise = None
             if self.noise is not None:
-                noise = context.services.latents.get(self.noise.latents_name)
+                noise = context.get_latents(self.noise.latents_name)
                 seed = self.noise.seed
 
             if self.latents is not None:
-                latents = context.services.latents.get(self.latents.latents_name)
+                latents = context.get_latents(self.latents.latents_name)
                 if seed is None:
                     seed = self.latents.seed
 
@@ -687,26 +673,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 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]
-
             def step_callback(state: PipelineIntermediateState):
-                self.dispatch_progress(context, source_node_id, state, self.unet.unet.base_model)
+                self.dispatch_progress(context, state, self.unet.unet.base_model)
 
             def _lora_loader():
                 for lora in self.unet.loras:
-                    lora_info = context.services.model_manager.get_model(
+                    lora_info = context.get_model(
                         **lora.model_dump(exclude={"weight"}),
-                        context=context,
                     )
                     yield (lora_info.context.model, lora.weight)
                     del lora_info
                 return
 
-            unet_info = context.services.model_manager.get_model(
+            unet_info = context.get_model(
                 **self.unet.unet.model_dump(),
-                context=context,
             )
             with (
                 ExitStack() as exit_stack,
@@ -781,9 +761,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
             if choose_torch_device() == torch.device("mps"):
                 mps.empty_cache()
 
-            name = f"{context.graph_execution_state_id}__{self.id}"
-            context.services.latents.save(name, result_latents)
-        return build_latents_output(latents_name=name, latents=result_latents, seed=seed)
+            latents_name = context.save_latents(result_latents)
+        return build_latents_output(latents_name=latents_name, latents=result_latents, seed=seed)
 
 
 @invocation(
@@ -793,7 +772,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     category="latents",
     version="1.0.0",
 )
-class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+class LatentsToImageInvocation(BaseInvocation):
     """Generates an image from latents."""
 
     latents: LatentsField = InputField(
@@ -806,14 +785,18 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
     )
     tiled: bool = InputField(default=False, description=FieldDescriptions.tiled)
     fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
+    metadata: Optional[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)
+        latents = context.get_latents(self.latents.latents_name)
 
-        vae_info = context.services.model_manager.get_model(
+        vae_info = context.get_model(
             **self.vae.vae.model_dump(),
-            context=context,
         )
 
         with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
@@ -843,7 +826,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
                 vae.to(dtype=torch.float16)
                 latents = latents.half()
 
-            if self.tiled or context.services.configuration.tiled_decode:
+            if self.tiled or context.config.tiled_decode:
                 vae.enable_tiling()
             else:
                 vae.disable_tiling()
@@ -867,21 +850,12 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
         if choose_torch_device() == torch.device("mps"):
             mps.empty_cache()
 
-        image_dto = context.services.images.create(
-            image=image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=self.workflow,
-        )
+        image_name = context.save_image(image, category=context.categories.GENERAL)
 
         return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
+            image=ImageField(image_name=image_name),
+            width=image.width,
+            height=image.height,
         )
 
 

invokeai/app/invocations/math.py

@@ -3,7 +3,7 @@
 from typing import Literal
 
 import numpy as np
-from pydantic import ValidationInfo, field_validator
+from pydantic import field_validator
 
 from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
 
@@ -186,12 +186,12 @@ class IntegerMathInvocation(BaseInvocation):
     b: int = InputField(default=0, description=FieldDescriptions.num_2)
 
     @field_validator("b")
-    def no_unrepresentable_results(cls, v: int, info: ValidationInfo):
-        if info.data["operation"] == "DIV" and v == 0:
+    def no_unrepresentable_results(cls, v, values):
+        if values["operation"] == "DIV" and v == 0:
             raise ValueError("Cannot divide by zero")
-        elif info.data["operation"] == "MOD" and v == 0:
+        elif values["operation"] == "MOD" and v == 0:
             raise ValueError("Cannot divide by zero")
-        elif info.data["operation"] == "EXP" and v < 0:
+        elif values["operation"] == "EXP" and v < 0:
             raise ValueError("Result of exponentiation is not an integer")
         return v
 
@@ -260,12 +260,12 @@ class FloatMathInvocation(BaseInvocation):
     b: float = InputField(default=0, description=FieldDescriptions.num_2)
 
     @field_validator("b")
-    def no_unrepresentable_results(cls, v: float, info: ValidationInfo):
-        if info.data["operation"] == "DIV" and v == 0:
+    def no_unrepresentable_results(cls, v, values):
+        if values["operation"] == "DIV" and v == 0:
             raise ValueError("Cannot divide by zero")
-        elif info.data["operation"] == "EXP" and info.data["a"] == 0 and v < 0:
+        elif values["operation"] == "EXP" and values["a"] == 0 and v < 0:
             raise ValueError("Cannot raise zero to a negative power")
-        elif info.data["operation"] == "EXP" and type(info.data["a"] ** v) is complex:
+        elif values["operation"] == "EXP" and type(values["a"] ** v) is complex:
             raise ValueError("Root operation resulted in a complex number")
         return v
 

invokeai/app/invocations/metadata.py

@@ -1,16 +1,13 @@
-from typing import Any, Literal, Optional, Union
+from typing import Optional
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import Field
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    FieldDescriptions,
     InputField,
     InvocationContext,
-    MetadataField,
     OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
@@ -19,104 +16,116 @@ from invokeai.app.invocations.ip_adapter import IPAdapterModelField
 from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
+from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
 
 from ...version import __version__
 
 
-class MetadataItemField(BaseModel):
-    label: str = Field(description=FieldDescriptions.metadata_item_label)
-    value: Any = Field(description=FieldDescriptions.metadata_item_value)
+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 LoRAMetadataField(BaseModel):
-    """LoRA Metadata 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"""
-
+class IPAdapterMetadataField(BaseModelExcludeNull):
     image: ImageField = Field(description="The IP-Adapter image prompt.")
-    ip_adapter_model: IPAdapterModelField = Field(
-        description="The IP-Adapter model.",
+    ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
+    weight: float = Field(description="The weight of the IP-Adapter model")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
     )
-    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
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
 
-    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))
+class CoreMetadata(BaseModelExcludeNull):
+    """Core generation metadata for an image generated in InvokeAI."""
+
+    app_version: str = Field(default=__version__, description="The version of InvokeAI used to generate this image")
+    generation_mode: Optional[str] = Field(
+        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: Optional[str] = Field(default=None, description="The positive prompt parameter")
+    negative_prompt: Optional[str] = Field(default=None, description="The negative prompt parameter")
+    width: Optional[int] = Field(default=None, description="The width parameter")
+    height: Optional[int] = Field(default=None, description="The height parameter")
+    seed: Optional[int] = Field(default=None, description="The seed used for noise generation")
+    rand_device: Optional[str] = Field(default=None, description="The device used for random number generation")
+    cfg_scale: Optional[float] = Field(default=None, description="The classifier-free guidance scale parameter")
+    steps: Optional[int] = Field(default=None, description="The number of steps used for inference")
+    scheduler: Optional[str] = Field(default=None, description="The scheduler used for inference")
+    clip_skip: Optional[int] = Field(
+        default=None,
+        description="The number of skipped CLIP layers",
+    )
+    model: Optional[MainModelField] = Field(default=None, description="The main model used for inference")
+    controlnets: Optional[list[ControlField]] = Field(default=None, description="The ControlNets used for inference")
+    ipAdapters: Optional[list[IPAdapterMetadataField]] = Field(
+        default=None, description="The IP Adapters used for inference"
+    )
+    t2iAdapters: Optional[list[T2IAdapterField]] = Field(default=None, description="The IP Adapters used for inference")
+    loras: Optional[list[LoRAMetadataField]] = Field(default=None, 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",
+    )
+
+    # Latents-to-Latents
+    strength: Optional[float] = Field(
+        default=None,
+        description="The strength used for latents-to-latents",
+    )
+    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",
+    )
+    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")
 
 
-@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."""
+class ImageMetadata(BaseModelExcludeNull):
+    """An image's generation metadata"""
 
-    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))
+    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")
 
 
-GENERATION_MODES = Literal[
-    "txt2img", "img2img", "inpaint", "outpaint", "sdxl_txt2img", "sdxl_img2img", "sdxl_inpaint", "sdxl_outpaint"
-]
+@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("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.0.0")
-class CoreMetadataInvocation(BaseInvocation):
-    """Collects core generation metadata into a MetadataField"""
+@invocation(
+    "metadata_accumulator", title="Metadata Accumulator", tags=["metadata"], category="metadata", version="1.0.0"
+)
+class MetadataAccumulatorInvocation(BaseInvocation):
+    """Outputs a Core Metadata Object"""
 
-    generation_mode: Optional[GENERATION_MODES] = InputField(
+    generation_mode: Optional[str] = InputField(
         default=None,
         description="The generation mode that output this image",
     )
@@ -129,8 +138,6 @@ class CoreMetadataInvocation(BaseInvocation):
     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",
@@ -213,13 +220,7 @@ class CoreMetadataInvocation(BaseInvocation):
         description="The start value used for refiner denoising",
     )
 
-    def invoke(self, context: InvocationContext) -> MetadataOutput:
+    def invoke(self, context: InvocationContext) -> MetadataAccumulatorOutput:
         """Collects and outputs a CoreMetadata object"""
 
-        return MetadataOutput(
-            metadata=MetadataField.model_validate(
-                self.model_dump(exclude_none=True, exclude={"id", "type", "is_intermediate", "use_cache"})
-            )
-        )
-
-    model_config = ConfigDict(extra="allow")
+        return MetadataAccumulatorOutput(metadata=CoreMetadata(**self.model_dump()))

invokeai/app/invocations/model.py

@@ -98,7 +98,7 @@ class MainModelLoaderInvocation(BaseInvocation):
         model_type = ModelType.Main
 
         # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
+        if not context.model_exists(
             model_name=model_name,
             base_model=base_model,
             model_type=model_type,

invokeai/app/invocations/noise.py

@@ -124,6 +124,5 @@ class NoiseInvocation(BaseInvocation):
             seed=self.seed,
             use_cpu=self.use_cpu,
         )
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, noise)
-        return build_noise_output(latents_name=name, latents=noise, seed=self.seed)
+        latents_name = context.save_latents(noise)
+        return build_noise_output(latents_name=latents_name, latents=noise, seed=self.seed)

invokeai/app/invocations/onnx.py

@@ -4,7 +4,7 @@ import inspect
 import re
 
 # from contextlib import ExitStack
-from typing import List, Literal, Union
+from typing import List, Literal, Optional, Union
 
 import numpy as np
 import torch
@@ -12,6 +12,7 @@ from diffusers.image_processor import VaeImageProcessor
 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
@@ -30,8 +31,6 @@ from .baseinvocation import (
     OutputField,
     UIComponent,
     UIType,
-    WithMetadata,
-    WithWorkflow,
     invocation,
     invocation_output,
 )
@@ -328,7 +327,7 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
     category="image",
     version="1.0.0",
 )
-class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
+class ONNXLatentsToImageInvocation(BaseInvocation):
     """Generates an image from latents."""
 
     latents: LatentsField = InputField(
@@ -339,6 +338,11 @@ class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
         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:
@@ -377,7 +381,7 @@ class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
+            metadata=self.metadata.model_dump() if self.metadata else None,
             workflow=self.workflow,
         )
 

invokeai/app/invocations/primitives.py

@@ -251,9 +251,7 @@ 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/upscale.py

@@ -14,7 +14,7 @@ from invokeai.app.invocations.primitives import ImageField, ImageOutput
 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, WithMetadata, WithWorkflow, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
 
 # TODO: Populate this from disk?
 # TODO: Use model manager to load?
@@ -30,7 +30,7 @@ if choose_torch_device() == torch.device("mps"):
 
 
 @invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.1.0")
-class ESRGANInvocation(BaseInvocation, WithWorkflow, WithMetadata):
+class ESRGANInvocation(BaseInvocation):
     """Upscales an image using RealESRGAN."""
 
     image: ImageField = InputField(description="The input image")
@@ -123,7 +123,6 @@ class ESRGANInvocation(BaseInvocation, WithWorkflow, WithMetadata):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
             workflow=self.workflow,
         )
 

invokeai/app/services/config/config_default.py

@@ -243,7 +243,6 @@ class InvokeAIAppConfig(InvokeAISettings):
     db_dir              : Optional[Path] = Field(default=Path('databases'), description='Path to InvokeAI databases directory', json_schema_extra=Categories.Paths)
     outdir              : Optional[Path] = Field(default=Path('outputs'), description='Default folder for output images', json_schema_extra=Categories.Paths)
     use_memory_db       : bool = Field(default=False, description='Use in-memory database for storing image metadata', json_schema_extra=Categories.Paths)
-    custom_nodes_dir    : Path = Field(default=Path('nodes'), description='Path to directory for custom nodes', json_schema_extra=Categories.Paths)
     from_file           : Optional[Path] = Field(default=None, description='Take command input from the indicated file (command-line client only)', json_schema_extra=Categories.Paths)
 
     # LOGGING
@@ -411,13 +410,6 @@ class InvokeAIAppConfig(InvokeAISettings):
         """
         return self._resolve(self.models_dir)
 
-    @property
-    def custom_nodes_path(self) -> Path:
-        """
-        Path to the custom nodes directory
-        """
-        return self._resolve(self.custom_nodes_dir)
-
     # the following methods support legacy calls leftover from the Globals era
     @property
     def full_precision(self) -> bool:

invokeai/app/services/image_files/image_files_base.py

@@ -4,8 +4,6 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField, WorkflowField
-
 
 class ImageFileStorageBase(ABC):
     """Low-level service responsible for storing and retrieving image files."""
@@ -32,8 +30,8 @@ class ImageFileStorageBase(ABC):
         self,
         image: PILImageType,
         image_name: str,
-        metadata: Optional[MetadataField] = None,
-        workflow: Optional[WorkflowField] = None,
+        metadata: Optional[dict] = None,
+        workflow: Optional[str] = None,
         thumbnail_size: int = 256,
     ) -> None:
         """Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image name, thumbnail name, and created timestamp."""

invokeai/app/services/image_files/image_files_disk.py

@@ -1,4 +1,5 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+import json
 from pathlib import Path
 from queue import Queue
 from typing import Dict, Optional, Union
@@ -7,7 +8,6 @@ from PIL import Image, PngImagePlugin
 from PIL.Image import Image as PILImageType
 from send2trash import send2trash
 
-from invokeai.app.invocations.baseinvocation import MetadataField, WorkflowField
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
 
@@ -55,8 +55,8 @@ class DiskImageFileStorage(ImageFileStorageBase):
         self,
         image: PILImageType,
         image_name: str,
-        metadata: Optional[MetadataField] = None,
-        workflow: Optional[WorkflowField] = None,
+        metadata: Optional[dict] = None,
+        workflow: Optional[str] = None,
         thumbnail_size: int = 256,
     ) -> None:
         try:
@@ -65,10 +65,20 @@ class DiskImageFileStorage(ImageFileStorageBase):
 
             pnginfo = PngImagePlugin.PngInfo()
 
-            if metadata is not None:
-                pnginfo.add_text("invokeai_metadata", metadata.model_dump_json())
-            if workflow is not None:
-                pnginfo.add_text("invokeai_workflow", workflow.model_dump_json())
+            if metadata is not None or workflow is not None:
+                if metadata is not None:
+                    pnginfo.add_text("invokeai_metadata", json.dumps(metadata))
+                if workflow is not None:
+                    pnginfo.add_text("invokeai_workflow", workflow)
+            else:
+                # For uploaded images, we want to retain metadata. PIL strips it on save; manually add it back
+                # TODO: retain non-invokeai metadata on save...
+                original_metadata = image.info.get("invokeai_metadata", None)
+                if original_metadata is not None:
+                    pnginfo.add_text("invokeai_metadata", original_metadata)
+                original_workflow = image.info.get("invokeai_workflow", None)
+                if original_workflow is not None:
+                    pnginfo.add_text("invokeai_workflow", original_workflow)
 
             image.save(
                 image_path,

invokeai/app/services/image_records/image_records_base.py

@@ -2,7 +2,6 @@ from abc import ABC, abstractmethod
 from datetime import datetime
 from typing import Optional
 
-from invokeai.app.invocations.metadata import MetadataField
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 
 from .image_records_common import ImageCategory, ImageRecord, ImageRecordChanges, ResourceOrigin
@@ -19,7 +18,7 @@ class ImageRecordStorageBase(ABC):
         pass
 
     @abstractmethod
-    def get_metadata(self, image_name: str) -> Optional[MetadataField]:
+    def get_metadata(self, image_name: str) -> Optional[dict]:
         """Gets an image's metadata'."""
         pass
 
@@ -62,11 +61,6 @@ class ImageRecordStorageBase(ABC):
         """Deletes all intermediate image records, returning a list of deleted image names."""
         pass
 
-    @abstractmethod
-    def get_intermediates_count(self) -> int:
-        """Gets a count of all intermediate images."""
-        pass
-
     @abstractmethod
     def save(
         self,
@@ -79,7 +73,7 @@ class ImageRecordStorageBase(ABC):
         starred: Optional[bool] = False,
         session_id: Optional[str] = None,
         node_id: Optional[str] = None,
-        metadata: Optional[MetadataField] = None,
+        metadata: Optional[dict] = None,
     ) -> datetime:
         """Saves an image record."""
         pass

invokeai/app/services/image_records/image_records_sqlite.py

@@ -1,9 +1,9 @@
+import json
 import sqlite3
 import threading
 from datetime import datetime
 from typing import Optional, Union, cast
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 from invokeai.app.services.shared.sqlite import SqliteDatabase
 
@@ -141,26 +141,22 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
 
         return deserialize_image_record(dict(result))
 
-    def get_metadata(self, image_name: str) -> Optional[MetadataField]:
+    def get_metadata(self, image_name: str) -> Optional[dict]:
         try:
             self._lock.acquire()
 
             self._cursor.execute(
                 """--sql
-                SELECT metadata FROM images
+                SELECT images.metadata FROM images
                 WHERE image_name = ?;
                 """,
                 (image_name,),
             )
 
             result = cast(Optional[sqlite3.Row], self._cursor.fetchone())
-
-            if not result:
-                raise ImageRecordNotFoundException
-
-            as_dict = dict(result)
-            metadata_raw = cast(Optional[str], as_dict.get("metadata", None))
-            return MetadataFieldValidator.validate_json(metadata_raw) if metadata_raw is not None else None
+            if not result or not result[0]:
+                return None
+            return json.loads(result[0])
         except sqlite3.Error as e:
             self._conn.rollback()
             raise ImageRecordNotFoundException from e
@@ -301,8 +297,11 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
             images_query += query_conditions + query_pagination + ";"
             # Add all the parameters
             images_params = query_params.copy()
-            # Add the pagination parameters
-            images_params.extend([limit, offset])
+
+            if limit is not None:
+                images_params.append(limit)
+            if offset is not None:
+                images_params.append(offset)
 
             # Build the list of images, deserializing each row
             self._cursor.execute(images_query, images_params)
@@ -358,24 +357,6 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
         finally:
             self._lock.release()
 
-    def get_intermediates_count(self) -> int:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                SELECT COUNT(*) FROM images
-                WHERE is_intermediate = TRUE;
-                """
-            )
-            count = cast(int, self._cursor.fetchone()[0])
-            self._conn.commit()
-            return count
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise ImageRecordDeleteException from e
-        finally:
-            self._lock.release()
-
     def delete_intermediates(self) -> list[str]:
         try:
             self._lock.acquire()
@@ -412,10 +393,10 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
         starred: Optional[bool] = False,
         session_id: Optional[str] = None,
         node_id: Optional[str] = None,
-        metadata: Optional[MetadataField] = None,
+        metadata: Optional[dict] = None,
     ) -> datetime:
         try:
-            metadata_json = metadata.model_dump_json() if metadata is not None else None
+            metadata_json = None if metadata is None else json.dumps(metadata)
             self._lock.acquire()
             self._cursor.execute(
                 """--sql

invokeai/app/services/images/images_base.py

@@ -3,7 +3,7 @@ from typing import Callable, Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField, WorkflowField
+from invokeai.app.invocations.metadata import ImageMetadata
 from invokeai.app.services.image_records.image_records_common import (
     ImageCategory,
     ImageRecord,
@@ -50,8 +50,8 @@ class ImageServiceABC(ABC):
         session_id: Optional[str] = None,
         board_id: Optional[str] = None,
         is_intermediate: Optional[bool] = False,
-        metadata: Optional[MetadataField] = None,
-        workflow: Optional[WorkflowField] = None,
+        metadata: Optional[dict] = None,
+        workflow: Optional[str] = None,
     ) -> ImageDTO:
         """Creates an image, storing the file and its metadata."""
         pass
@@ -81,7 +81,7 @@ class ImageServiceABC(ABC):
         pass
 
     @abstractmethod
-    def get_metadata(self, image_name: str) -> Optional[MetadataField]:
+    def get_metadata(self, image_name: str) -> ImageMetadata:
         """Gets an image's metadata."""
         pass
 
@@ -123,11 +123,6 @@ class ImageServiceABC(ABC):
         """Deletes all intermediate images."""
         pass
 
-    @abstractmethod
-    def get_intermediates_count(self) -> int:
-        """Gets the number of intermediate images."""
-        pass
-
     @abstractmethod
     def delete_images_on_board(self, board_id: str):
         """Deletes all images on a board."""

invokeai/app/services/images/images_common.py

@@ -24,11 +24,8 @@ class ImageDTO(ImageRecord, ImageUrlsDTO):
         default=None, description="The id of the board the image belongs to, if one exists."
     )
     """The id of the board the image belongs to, if one exists."""
-    workflow_id: Optional[str] = Field(
-        default=None,
-        description="The workflow that generated this image.",
-    )
-    """The workflow that generated this image."""
+
+    pass
 
 
 def image_record_to_dto(
@@ -36,7 +33,6 @@ def image_record_to_dto(
     image_url: str,
     thumbnail_url: str,
     board_id: Optional[str],
-    workflow_id: Optional[str],
 ) -> ImageDTO:
     """Converts an image record to an image DTO."""
     return ImageDTO(
@@ -44,5 +40,4 @@ def image_record_to_dto(
         image_url=image_url,
         thumbnail_url=thumbnail_url,
         board_id=board_id,
-        workflow_id=workflow_id,
     )

invokeai/app/services/images/images_default.py

@@ -2,9 +2,10 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField, WorkflowField
+from invokeai.app.invocations.metadata import ImageMetadata
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+from invokeai.app.util.metadata import get_metadata_graph_from_raw_session
 
 from ..image_files.image_files_common import (
     ImageFileDeleteException,
@@ -41,8 +42,8 @@ class ImageService(ImageServiceABC):
         session_id: Optional[str] = None,
         board_id: Optional[str] = None,
         is_intermediate: Optional[bool] = False,
-        metadata: Optional[MetadataField] = None,
-        workflow: Optional[WorkflowField] = None,
+        metadata: Optional[dict] = None,
+        workflow: Optional[str] = None,
     ) -> ImageDTO:
         if image_origin not in ResourceOrigin:
             raise InvalidOriginException
@@ -55,12 +56,6 @@ class ImageService(ImageServiceABC):
         (width, height) = image.size
 
         try:
-            if workflow is not None:
-                created_workflow = self.__invoker.services.workflow_records.create(workflow)
-                workflow_id = created_workflow.model_dump()["id"]
-            else:
-                workflow_id = None
-
             # TODO: Consider using a transaction here to ensure consistency between storage and database
             self.__invoker.services.image_records.save(
                 # Non-nullable fields
@@ -78,8 +73,6 @@ class ImageService(ImageServiceABC):
             )
             if board_id is not None:
                 self.__invoker.services.board_image_records.add_image_to_board(board_id=board_id, image_name=image_name)
-            if workflow_id is not None:
-                self.__invoker.services.workflow_image_records.create(workflow_id=workflow_id, image_name=image_name)
             self.__invoker.services.image_files.save(
                 image_name=image_name, image=image, metadata=metadata, workflow=workflow
             )
@@ -139,11 +132,10 @@ class ImageService(ImageServiceABC):
             image_record = self.__invoker.services.image_records.get(image_name)
 
             image_dto = image_record_to_dto(
-                image_record=image_record,
-                image_url=self.__invoker.services.urls.get_image_url(image_name),
-                thumbnail_url=self.__invoker.services.urls.get_image_url(image_name, True),
-                board_id=self.__invoker.services.board_image_records.get_board_for_image(image_name),
-                workflow_id=self.__invoker.services.workflow_image_records.get_workflow_for_image(image_name),
+                image_record,
+                self.__invoker.services.urls.get_image_url(image_name),
+                self.__invoker.services.urls.get_image_url(image_name, True),
+                self.__invoker.services.board_image_records.get_board_for_image(image_name),
             )
 
             return image_dto
@@ -154,22 +146,25 @@ class ImageService(ImageServiceABC):
             self.__invoker.services.logger.error("Problem getting image DTO")
             raise e
 
-    def get_metadata(self, image_name: str) -> Optional[MetadataField]:
+    def get_metadata(self, image_name: str) -> ImageMetadata:
         try:
-            return self.__invoker.services.image_records.get_metadata(image_name)
-        except ImageRecordNotFoundException:
-            self.__invoker.services.logger.error("Image record not found")
-            raise
-        except Exception as e:
-            self.__invoker.services.logger.error("Problem getting image DTO")
-            raise e
+            image_record = self.__invoker.services.image_records.get(image_name)
+            metadata = self.__invoker.services.image_records.get_metadata(image_name)
 
-    def get_workflow(self, image_name: str) -> Optional[WorkflowField]:
-        try:
-            workflow_id = self.__invoker.services.workflow_image_records.get_workflow_for_image(image_name)
-            if workflow_id is None:
-                return None
-            return self.__invoker.services.workflow_records.get(workflow_id)
+            if not image_record.session_id:
+                return ImageMetadata(metadata=metadata)
+
+            session_raw = self.__invoker.services.graph_execution_manager.get_raw(image_record.session_id)
+            graph = None
+
+            if session_raw:
+                try:
+                    graph = get_metadata_graph_from_raw_session(session_raw)
+                except Exception as e:
+                    self.__invoker.services.logger.warn(f"Failed to parse session graph: {e}")
+                    graph = None
+
+            return ImageMetadata(graph=graph, metadata=metadata)
         except ImageRecordNotFoundException:
             self.__invoker.services.logger.error("Image record not found")
             raise
@@ -220,11 +215,10 @@ class ImageService(ImageServiceABC):
             image_dtos = list(
                 map(
                     lambda r: image_record_to_dto(
-                        image_record=r,
-                        image_url=self.__invoker.services.urls.get_image_url(r.image_name),
-                        thumbnail_url=self.__invoker.services.urls.get_image_url(r.image_name, True),
-                        board_id=self.__invoker.services.board_image_records.get_board_for_image(r.image_name),
-                        workflow_id=self.__invoker.services.workflow_image_records.get_workflow_for_image(r.image_name),
+                        r,
+                        self.__invoker.services.urls.get_image_url(r.image_name),
+                        self.__invoker.services.urls.get_image_url(r.image_name, True),
+                        self.__invoker.services.board_image_records.get_board_for_image(r.image_name),
                     ),
                     results.items,
                 )
@@ -290,10 +284,3 @@ class ImageService(ImageServiceABC):
         except Exception as e:
             self.__invoker.services.logger.error("Problem deleting image records and files")
             raise e
-
-    def get_intermediates_count(self) -> int:
-        try:
-            return self.__invoker.services.image_records.get_intermediates_count()
-        except Exception as e:
-            self.__invoker.services.logger.error("Problem getting intermediates count")
-            raise e

invokeai/app/services/invocation_processor/invocation_processor_default.py

@@ -4,7 +4,7 @@ from threading import BoundedSemaphore, Event, Thread
 from typing import Optional
 
 import invokeai.backend.util.logging as logger
-from invokeai.app.invocations.baseinvocation import InvocationContext
+from invokeai.app.invocations.baseinvocation import AppInvocationContext
 from invokeai.app.services.invocation_queue.invocation_queue_common import InvocationQueueItem
 
 from ..invoker import Invoker
@@ -96,18 +96,21 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 # Invoke
                 try:
                     graph_id = graph_execution_state.id
+                    source_node_id = graph_execution_state.prepared_source_mapping[invocation.id]
+
                     with self.__invoker.services.performance_statistics.collect_stats(invocation, graph_id):
                         # use the internal invoke_internal(), which wraps the node's invoke() method,
                         # which handles a few things:
                         # - nodes that require a value, but get it only from a connection
                         # - referencing the invocation cache instead of executing the node
                         outputs = invocation.invoke_internal(
-                            InvocationContext(
+                            AppInvocationContext(
                                 services=self.__invoker.services,
                                 graph_execution_state_id=graph_execution_state.id,
                                 queue_item_id=queue_item.session_queue_item_id,
                                 queue_id=queue_item.session_queue_id,
                                 queue_batch_id=queue_item.session_queue_batch_id,
+                                source_node_id=source_node_id,
                             )
                         )
 

invokeai/app/services/invocation_services.py

@@ -27,8 +27,6 @@ if TYPE_CHECKING:
     from .session_queue.session_queue_base import SessionQueueBase
     from .shared.graph import GraphExecutionState, LibraryGraph
     from .urls.urls_base import UrlServiceBase
-    from .workflow_image_records.workflow_image_records_base import WorkflowImageRecordsStorageBase
-    from .workflow_records.workflow_records_base import WorkflowRecordsStorageBase
 
 
 class InvocationServices:
@@ -57,8 +55,6 @@ class InvocationServices:
     invocation_cache: "InvocationCacheBase"
     names: "NameServiceBase"
     urls: "UrlServiceBase"
-    workflow_image_records: "WorkflowImageRecordsStorageBase"
-    workflow_records: "WorkflowRecordsStorageBase"
 
     def __init__(
         self,
@@ -84,8 +80,6 @@ class InvocationServices:
         invocation_cache: "InvocationCacheBase",
         names: "NameServiceBase",
         urls: "UrlServiceBase",
-        workflow_image_records: "WorkflowImageRecordsStorageBase",
-        workflow_records: "WorkflowRecordsStorageBase",
     ):
         self.board_images = board_images
         self.board_image_records = board_image_records
@@ -109,5 +103,3 @@ class InvocationServices:
         self.invocation_cache = invocation_cache
         self.names = names
         self.urls = urls
-        self.workflow_image_records = workflow_image_records
-        self.workflow_records = workflow_records

invokeai/app/services/item_storage/item_storage_sqlite.py

@@ -18,7 +18,7 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
     _cursor: sqlite3.Cursor
     _id_field: str
     _lock: threading.RLock
-    _validator: Optional[TypeAdapter[T]]
+    _adapter: Optional[TypeAdapter[T]]
 
     def __init__(self, db: SqliteDatabase, table_name: str, id_field: str = "id"):
         super().__init__()
@@ -28,7 +28,7 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
         self._table_name = table_name
         self._id_field = id_field  # TODO: validate that T has this field
         self._cursor = self._conn.cursor()
-        self._validator: Optional[TypeAdapter[T]] = None
+        self._adapter: Optional[TypeAdapter[T]] = None
 
         self._create_table()
 
@@ -47,14 +47,14 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
             self._lock.release()
 
     def _parse_item(self, item: str) -> T:
-        if self._validator is None:
+        if self._adapter is None:
             """
             We don't get access to `__orig_class__` in `__init__()`, and we need this before start(), so
             we can create it when it is first needed instead.
             __orig_class__ is technically an implementation detail of the typing module, not a supported API
             """
-            self._validator = TypeAdapter(get_args(self.__orig_class__)[0])  # type: ignore [attr-defined]
-        return self._validator.validate_json(item)
+            self._adapter = TypeAdapter(get_args(self.__orig_class__)[0])  # type: ignore [attr-defined]
+        return self._adapter.validate_json(item)
 
     def set(self, item: T):
         try:

invokeai/app/services/model_manager/__init__.py

@@ -1 +0,0 @@
-from .model_manager_default import ModelManagerService  # noqa F401

invokeai/app/services/model_manager/model_manager_base.py

@@ -48,9 +48,12 @@ class ModelManagerServiceBase(ABC):
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
         submodel: Optional[SubModelType] = None,
         node: Optional[BaseInvocation] = None,
-        context: Optional[InvocationContext] = None,
     ) -> ModelInfo:
         """Retrieve the indicated model with name and type.
         submodel can be used to get a part (such as the vae)

invokeai/app/services/model_manager/model_manager_default.py

@@ -11,6 +11,7 @@ from pydantic import Field
 
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
 from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException
+from invokeai.app.services.invoker import Invoker
 from invokeai.backend.model_management import (
     AddModelResult,
     BaseModelType,
@@ -86,28 +87,35 @@ class ModelManagerService(ModelManagerServiceBase):
         )
         logger.info("Model manager service initialized")
 
+    def start(self, invoker: Invoker) -> None:
+        self._invoker = invoker
+
     def get_model(
         self,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
         submodel: Optional[SubModelType] = None,
-        context: Optional[InvocationContext] = None,
     ) -> ModelInfo:
         """
         Retrieve the indicated model. submodel can be used to get a
         part (such as the vae) of a diffusers mode.
         """
 
-        # we can emit model loading events if we are executing with access to the invocation context
-        if context:
-            self._emit_load_event(
-                context=context,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-            )
+        self._emit_load_event(
+            queue_id=queue_id,
+            queue_item_id=queue_item_id,
+            queue_batch_id=queue_batch_id,
+            graph_execution_state_id=graph_execution_state_id,
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+            submodel=submodel,
+        )
 
         model_info = self.mgr.get_model(
             model_name,
@@ -116,15 +124,17 @@ class ModelManagerService(ModelManagerServiceBase):
             submodel,
         )
 
-        if context:
-            self._emit_load_event(
-                context=context,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-                model_info=model_info,
-            )
+        self._emit_load_event(
+            queue_id=queue_id,
+            queue_item_id=queue_item_id,
+            queue_batch_id=queue_batch_id,
+            graph_execution_state_id=graph_execution_state_id,
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+            submodel=submodel,
+            model_info=model_info,
+        )
 
         return model_info
 
@@ -263,22 +273,25 @@ class ModelManagerService(ModelManagerServiceBase):
 
     def _emit_load_event(
         self,
-        context: InvocationContext,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
+        queue_id: str,
+        queue_item_id: int,
+        queue_batch_id: str,
+        graph_execution_state_id: str,
         submodel: Optional[SubModelType] = None,
         model_info: Optional[ModelInfo] = None,
     ):
-        if context.services.queue.is_canceled(context.graph_execution_state_id):
+        if self._invoker.services.queue.is_canceled(graph_execution_state_id):
             raise CanceledException()
 
         if model_info:
-            context.services.events.emit_model_load_completed(
-                queue_id=context.queue_id,
-                queue_item_id=context.queue_item_id,
-                queue_batch_id=context.queue_batch_id,
-                graph_execution_state_id=context.graph_execution_state_id,
+            self._invoker.services.events.emit_model_load_completed(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
+                graph_execution_state_id=graph_execution_state_id,
                 model_name=model_name,
                 base_model=base_model,
                 model_type=model_type,
@@ -286,11 +299,11 @@ class ModelManagerService(ModelManagerServiceBase):
                 model_info=model_info,
             )
         else:
-            context.services.events.emit_model_load_started(
-                queue_id=context.queue_id,
-                queue_item_id=context.queue_item_id,
-                queue_batch_id=context.queue_batch_id,
-                graph_execution_state_id=context.graph_execution_state_id,
+            self._invoker.services.events.emit_model_load_started(
+                queue_id=queue_id,
+                queue_item_id=queue_item_id,
+                queue_batch_id=queue_batch_id,
+                graph_execution_state_id=graph_execution_state_id,
                 model_name=model_name,
                 base_model=base_model,
                 model_type=model_type,

invokeai/app/services/session_queue/session_queue_base.py

@@ -9,6 +9,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     CancelByQueueIDResult,
     ClearResult,
     EnqueueBatchResult,
+    EnqueueGraphResult,
     IsEmptyResult,
     IsFullResult,
     PruneResult,
@@ -16,6 +17,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     SessionQueueItemDTO,
     SessionQueueStatus,
 )
+from invokeai.app.services.shared.graph import Graph
 from invokeai.app.services.shared.pagination import CursorPaginatedResults
 
 
@@ -27,6 +29,11 @@ class SessionQueueBase(ABC):
         """Dequeues the next session queue item."""
         pass
 
+    @abstractmethod
+    def enqueue_graph(self, queue_id: str, graph: Graph, prepend: bool) -> EnqueueGraphResult:
+        """Enqueues a single graph for execution."""
+        pass
+
     @abstractmethod
     def enqueue_batch(self, queue_id: str, batch: Batch, prepend: bool) -> EnqueueBatchResult:
         """Enqueues all permutations of a batch for execution."""

invokeai/app/services/session_queue/session_queue_common.py

@@ -147,20 +147,20 @@ DEFAULT_QUEUE_ID = "default"
 
 QUEUE_ITEM_STATUS = Literal["pending", "in_progress", "completed", "failed", "canceled"]
 
-NodeFieldValueValidator = TypeAdapter(list[NodeFieldValue])
+adapter_NodeFieldValue = TypeAdapter(list[NodeFieldValue])
 
 
 def get_field_values(queue_item_dict: dict) -> Optional[list[NodeFieldValue]]:
     field_values_raw = queue_item_dict.get("field_values", None)
-    return NodeFieldValueValidator.validate_json(field_values_raw) if field_values_raw is not None else None
+    return adapter_NodeFieldValue.validate_json(field_values_raw) if field_values_raw is not None else None
 
 
-GraphExecutionStateValidator = TypeAdapter(GraphExecutionState)
+adapter_GraphExecutionState = TypeAdapter(GraphExecutionState)
 
 
 def get_session(queue_item_dict: dict) -> GraphExecutionState:
     session_raw = queue_item_dict.get("session", "{}")
-    session = GraphExecutionStateValidator.validate_json(session_raw, strict=False)
+    session = adapter_GraphExecutionState.validate_json(session_raw, strict=False)
     return session
 
 
@@ -276,6 +276,14 @@ class EnqueueBatchResult(BaseModel):
     priority: int = Field(description="The priority of the enqueued batch")
 
 
+class EnqueueGraphResult(BaseModel):
+    enqueued: int = Field(description="The total number of queue items enqueued")
+    requested: int = Field(description="The total number of queue items requested to be enqueued")
+    batch: Batch = Field(description="The batch that was enqueued")
+    priority: int = Field(description="The priority of the enqueued batch")
+    queue_item: SessionQueueItemDTO = Field(description="The queue item that was enqueued")
+
+
 class ClearResult(BaseModel):
     """Result of clearing the session queue"""
 

invokeai/app/services/session_queue/session_queue_sqlite.py

@@ -17,6 +17,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     CancelByQueueIDResult,
     ClearResult,
     EnqueueBatchResult,
+    EnqueueGraphResult,
     IsEmptyResult,
     IsFullResult,
     PruneResult,
@@ -27,6 +28,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     calc_session_count,
     prepare_values_to_insert,
 )
+from invokeai.app.services.shared.graph import Graph
 from invokeai.app.services.shared.pagination import CursorPaginatedResults
 from invokeai.app.services.shared.sqlite import SqliteDatabase
 
@@ -253,6 +255,32 @@ class SqliteSessionQueue(SessionQueueBase):
         )
         return cast(Union[int, None], self.__cursor.fetchone()[0]) or 0
 
+    def enqueue_graph(self, queue_id: str, graph: Graph, prepend: bool) -> EnqueueGraphResult:
+        enqueue_result = self.enqueue_batch(queue_id=queue_id, batch=Batch(graph=graph), prepend=prepend)
+        try:
+            self.__lock.acquire()
+            self.__cursor.execute(
+                """--sql
+                SELECT *
+                FROM session_queue
+                WHERE queue_id = ?
+                AND batch_id = ?
+                """,
+                (queue_id, enqueue_result.batch.batch_id),
+            )
+            result = cast(Union[sqlite3.Row, None], self.__cursor.fetchone())
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        if result is None:
+            raise SessionQueueItemNotFoundError(f"No queue item with batch id {enqueue_result.batch.batch_id}")
+        return EnqueueGraphResult(
+            **enqueue_result.model_dump(),
+            queue_item=SessionQueueItemDTO.queue_item_dto_from_dict(dict(result)),
+        )
+
     def enqueue_batch(self, queue_id: str, batch: Batch, prepend: bool) -> EnqueueBatchResult:
         try:
             self.__lock.acquire()

invokeai/app/services/shared/graph.py

@@ -193,7 +193,7 @@ class GraphInvocation(BaseInvocation):
     """Execute a graph"""
 
     # TODO: figure out how to create a default here
-    graph: "Graph" = InputField(description="The graph to run", default=None)
+    graph: "Graph" = Field(description="The graph to run", default=None)
 
     def invoke(self, context: InvocationContext) -> GraphInvocationOutput:
         """Invoke with provided services and return outputs."""
@@ -439,14 +439,6 @@ class Graph(BaseModel):
         except Exception as e:
             raise UnknownGraphValidationError(f"Problem validating graph {e}") from e
 
-    def _is_destination_field_Any(self, edge: Edge) -> bool:
-        """Checks if the destination field for an edge is of type typing.Any"""
-        return get_input_field(self.get_node(edge.destination.node_id), edge.destination.field) == Any
-
-    def _is_destination_field_list_of_Any(self, edge: Edge) -> bool:
-        """Checks if the destination field for an edge is of type typing.Any"""
-        return get_input_field(self.get_node(edge.destination.node_id), edge.destination.field) == list[Any]
-
     def _validate_edge(self, edge: Edge):
         """Validates that a new edge doesn't create a cycle in the graph"""
 
@@ -499,19 +491,8 @@ class Graph(BaseModel):
                     f"Collector output type does not match collector input type: {edge.source.node_id}.{edge.source.field} to {edge.destination.node_id}.{edge.destination.field}"
                 )
 
-        # Validate that we are not connecting collector to iterator (currently unsupported)
-        if isinstance(from_node, CollectInvocation) and isinstance(to_node, IterateInvocation):
-            raise InvalidEdgeError(
-                f"Cannot connect collector to iterator: {edge.source.node_id}.{edge.source.field} to {edge.destination.node_id}.{edge.destination.field}"
-            )
-
-        # Validate if collector output type matches input type (if this edge results in both being set) - skip if the destination field is not Any or list[Any]
-        if (
-            isinstance(from_node, CollectInvocation)
-            and edge.source.field == "collection"
-            and not self._is_destination_field_list_of_Any(edge)
-            and not self._is_destination_field_Any(edge)
-        ):
+        # Validate if collector output type matches input type (if this edge results in both being set)
+        if isinstance(from_node, CollectInvocation) and edge.source.field == "collection":
             if not self._is_collector_connection_valid(edge.source.node_id, new_output=edge.destination):
                 raise InvalidEdgeError(
                     f"Collector input type does not match collector output type: {edge.source.node_id}.{edge.source.field} to {edge.destination.node_id}.{edge.destination.field}"
@@ -744,15 +725,16 @@ class Graph(BaseModel):
         # Get the input root type
         input_root_type = next(t[0] for t in type_degrees if t[1] == 0)  # type: ignore
 
+        # Verify that all outputs are lists
+        # if not all((get_origin(f) == list for f in output_fields)):
+        #     return False
+
         # Verify that all outputs are lists
         if not all(is_list_or_contains_list(f) for f in output_fields):
             return False
 
         # Verify that all outputs match the input type (are a base class or the same class)
-        if not all(
-            is_union_subtype(input_root_type, get_args(f)[0]) or issubclass(input_root_type, get_args(f)[0])
-            for f in output_fields
-        ):
+        if not all((issubclass(input_root_type, get_args(f)[0]) for f in output_fields)):
             return False
 
         return True

invokeai/app/services/workflow_image_records/workflow_image_records_base.py

@@ -1,23 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import Optional
-
-
-class WorkflowImageRecordsStorageBase(ABC):
-    """Abstract base class for the one-to-many workflow-image relationship record storage."""
-
-    @abstractmethod
-    def create(
-        self,
-        workflow_id: str,
-        image_name: str,
-    ) -> None:
-        """Creates a workflow-image record."""
-        pass
-
-    @abstractmethod
-    def get_workflow_for_image(
-        self,
-        image_name: str,
-    ) -> Optional[str]:
-        """Gets an image's workflow id, if it has one."""
-        pass

invokeai/app/services/workflow_image_records/workflow_image_records_sqlite.py

@@ -1,122 +0,0 @@
-import sqlite3
-import threading
-from typing import Optional, cast
-
-from invokeai.app.services.shared.sqlite import SqliteDatabase
-from invokeai.app.services.workflow_image_records.workflow_image_records_base import WorkflowImageRecordsStorageBase
-
-
-class SqliteWorkflowImageRecordsStorage(WorkflowImageRecordsStorageBase):
-    """SQLite implementation of WorkflowImageRecordsStorageBase."""
-
-    _conn: sqlite3.Connection
-    _cursor: sqlite3.Cursor
-    _lock: threading.RLock
-
-    def __init__(self, db: SqliteDatabase) -> None:
-        super().__init__()
-        self._lock = db.lock
-        self._conn = db.conn
-        self._cursor = self._conn.cursor()
-
-        try:
-            self._lock.acquire()
-            self._create_tables()
-            self._conn.commit()
-        finally:
-            self._lock.release()
-
-    def _create_tables(self) -> None:
-        # Create the `workflow_images` junction table.
-        self._cursor.execute(
-            """--sql
-            CREATE TABLE IF NOT EXISTS workflow_images (
-                workflow_id TEXT NOT NULL,
-                image_name TEXT NOT NULL,
-                created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                -- updated via trigger
-                updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                -- Soft delete, currently unused
-                deleted_at DATETIME,
-                -- enforce one-to-many relationship between workflows and images using PK
-                -- (we can extend this to many-to-many later)
-                PRIMARY KEY (image_name),
-                FOREIGN KEY (workflow_id) REFERENCES workflows (workflow_id) ON DELETE CASCADE,
-                FOREIGN KEY (image_name) REFERENCES images (image_name) ON DELETE CASCADE
-            );
-            """
-        )
-
-        # Add index for workflow id
-        self._cursor.execute(
-            """--sql
-            CREATE INDEX IF NOT EXISTS idx_workflow_images_workflow_id ON workflow_images (workflow_id);
-            """
-        )
-
-        # Add index for workflow id, sorted by created_at
-        self._cursor.execute(
-            """--sql
-            CREATE INDEX IF NOT EXISTS idx_workflow_images_workflow_id_created_at ON workflow_images (workflow_id, created_at);
-            """
-        )
-
-        # Add trigger for `updated_at`.
-        self._cursor.execute(
-            """--sql
-            CREATE TRIGGER IF NOT EXISTS tg_workflow_images_updated_at
-            AFTER UPDATE
-            ON workflow_images FOR EACH ROW
-            BEGIN
-                UPDATE workflow_images SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
-                    WHERE workflow_id = old.workflow_id AND image_name = old.image_name;
-            END;
-            """
-        )
-
-    def create(
-        self,
-        workflow_id: str,
-        image_name: str,
-    ) -> None:
-        """Creates a workflow-image record."""
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                INSERT INTO workflow_images (workflow_id, image_name)
-                VALUES (?, ?);
-                """,
-                (workflow_id, image_name),
-            )
-            self._conn.commit()
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()
-
-    def get_workflow_for_image(
-        self,
-        image_name: str,
-    ) -> Optional[str]:
-        """Gets an image's workflow id, if it has one."""
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                SELECT workflow_id
-                FROM workflow_images
-                WHERE image_name = ?;
-                """,
-                (image_name,),
-            )
-            result = self._cursor.fetchone()
-            if result is None:
-                return None
-            return cast(str, result[0])
-        except sqlite3.Error as e:
-            self._conn.rollback()
-            raise e
-        finally:
-            self._lock.release()

invokeai/app/services/workflow_records/workflow_records_base.py

@@ -1,17 +0,0 @@
-from abc import ABC, abstractmethod
-
-from invokeai.app.invocations.baseinvocation import WorkflowField
-
-
-class WorkflowRecordsStorageBase(ABC):
-    """Base class for workflow storage services."""
-
-    @abstractmethod
-    def get(self, workflow_id: str) -> WorkflowField:
-        """Get workflow by id."""
-        pass
-
-    @abstractmethod
-    def create(self, workflow: WorkflowField) -> WorkflowField:
-        """Creates a workflow."""
-        pass

invokeai/app/services/workflow_records/workflow_records_common.py

@@ -1,2 +0,0 @@
-class WorkflowNotFoundError(Exception):
-    """Raised when a workflow is not found"""

invokeai/app/services/workflow_records/workflow_records_sqlite.py

@@ -1,102 +0,0 @@
-import sqlite3
-import threading
-
-from invokeai.app.invocations.baseinvocation import WorkflowField, WorkflowFieldValidator
-from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.shared.sqlite import SqliteDatabase
-from invokeai.app.services.workflow_records.workflow_records_base import WorkflowRecordsStorageBase
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowNotFoundError
-from invokeai.app.util.misc import uuid_string
-
-
-class SqliteWorkflowRecordsStorage(WorkflowRecordsStorageBase):
-    _invoker: Invoker
-    _conn: sqlite3.Connection
-    _cursor: sqlite3.Cursor
-    _lock: threading.RLock
-
-    def __init__(self, db: SqliteDatabase) -> None:
-        super().__init__()
-        self._lock = db.lock
-        self._conn = db.conn
-        self._cursor = self._conn.cursor()
-        self._create_tables()
-
-    def start(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-
-    def get(self, workflow_id: str) -> WorkflowField:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                SELECT workflow
-                FROM workflows
-                WHERE workflow_id = ?;
-                """,
-                (workflow_id,),
-            )
-            row = self._cursor.fetchone()
-            if row is None:
-                raise WorkflowNotFoundError(f"Workflow with id {workflow_id} not found")
-            return WorkflowFieldValidator.validate_json(row[0])
-        except Exception:
-            self._conn.rollback()
-            raise
-        finally:
-            self._lock.release()
-
-    def create(self, workflow: WorkflowField) -> WorkflowField:
-        try:
-            # workflows do not have ids until they are saved
-            workflow_id = uuid_string()
-            workflow.root["id"] = workflow_id
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                INSERT INTO workflows(workflow)
-                VALUES (?);
-                """,
-                (workflow.json(),),
-            )
-            self._conn.commit()
-        except Exception:
-            self._conn.rollback()
-            raise
-        finally:
-            self._lock.release()
-        return self.get(workflow_id)
-
-    def _create_tables(self) -> None:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                """--sql
-                CREATE TABLE IF NOT EXISTS workflows (
-                    workflow TEXT NOT NULL,
-                    workflow_id TEXT GENERATED ALWAYS AS (json_extract(workflow, '$.id')) VIRTUAL NOT NULL UNIQUE, -- gets implicit index
-                    created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
-                    updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')) -- updated via trigger
-                );
-                """
-            )
-
-            self._cursor.execute(
-                """--sql
-                CREATE TRIGGER IF NOT EXISTS tg_workflows_updated_at
-                AFTER UPDATE
-                ON workflows FOR EACH ROW
-                BEGIN
-                    UPDATE workflows
-                    SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
-                    WHERE workflow_id = old.workflow_id;
-                END;
-                """
-            )
-
-            self._conn.commit()
-        except Exception:
-            self._conn.rollback()
-            raise
-        finally:
-            self._lock.release()

invokeai/app/util/step_callback.py

@@ -27,11 +27,9 @@ def sample_to_lowres_estimated_image(samples, latent_rgb_factors, smooth_matrix=
 def stable_diffusion_step_callback(
     context: InvocationContext,
     intermediate_state: PipelineIntermediateState,
-    node: dict,
-    source_node_id: str,
     base_model: BaseModelType,
 ):
-    if context.services.queue.is_canceled(context.graph_execution_state_id):
+    if context.is_canceled():
         raise CanceledException
 
     # Some schedulers report not only the noisy latents at the current timestep,
@@ -108,13 +106,7 @@ def stable_diffusion_step_callback(
 
     dataURL = image_to_dataURL(image, image_format="JPEG")
 
-    context.services.events.emit_generator_progress(
-        queue_id=context.queue_id,
-        queue_item_id=context.queue_item_id,
-        queue_batch_id=context.queue_batch_id,
-        graph_execution_state_id=context.graph_execution_state_id,
-        node=node,
-        source_node_id=source_node_id,
+    context.emit_denoising_progress(
         progress_image=ProgressImage(width=width, height=height, dataURL=dataURL),
         step=intermediate_state.step,
         order=intermediate_state.order,

invokeai/backend/image_util/invisible_watermark.py

@@ -20,12 +20,12 @@ class InvisibleWatermark:
     """
 
     @classmethod
-    def invisible_watermark_available(cls) -> bool:
+    def invisible_watermark_available(self) -> bool:
         return config.invisible_watermark
 
     @classmethod
-    def add_watermark(cls, image: Image.Image, watermark_text: str) -> Image.Image:
-        if not cls.invisible_watermark_available():
+    def add_watermark(self, image: Image, watermark_text: str) -> Image:
+        if not self.invisible_watermark_available():
             return image
         logger.debug(f'Applying invisible watermark "{watermark_text}"')
         bgr = cv2.cvtColor(np.array(image.convert("RGB")), cv2.COLOR_RGB2BGR)

invokeai/backend/image_util/safety_checker.py

@@ -26,8 +26,8 @@ class SafetyChecker:
     tried_load: bool = False
 
     @classmethod
-    def _load_safety_checker(cls):
-        if cls.tried_load:
+    def _load_safety_checker(self):
+        if self.tried_load:
             return
 
         if config.nsfw_checker:
@@ -35,31 +35,31 @@ class SafetyChecker:
                 from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
                 from transformers import AutoFeatureExtractor
 
-                cls.safety_checker = StableDiffusionSafetyChecker.from_pretrained(config.models_path / CHECKER_PATH)
-                cls.feature_extractor = AutoFeatureExtractor.from_pretrained(config.models_path / CHECKER_PATH)
+                self.safety_checker = StableDiffusionSafetyChecker.from_pretrained(config.models_path / CHECKER_PATH)
+                self.feature_extractor = AutoFeatureExtractor.from_pretrained(config.models_path / CHECKER_PATH)
                 logger.info("NSFW checker initialized")
             except Exception as e:
                 logger.warning(f"Could not load NSFW checker: {str(e)}")
         else:
             logger.info("NSFW checker loading disabled")
-        cls.tried_load = True
+        self.tried_load = True
 
     @classmethod
-    def safety_checker_available(cls) -> bool:
-        cls._load_safety_checker()
-        return cls.safety_checker is not None
+    def safety_checker_available(self) -> bool:
+        self._load_safety_checker()
+        return self.safety_checker is not None
 
     @classmethod
-    def has_nsfw_concept(cls, image: Image.Image) -> bool:
-        if not cls.safety_checker_available():
+    def has_nsfw_concept(self, image: Image) -> bool:
+        if not self.safety_checker_available():
             return False
 
         device = choose_torch_device()
-        features = cls.feature_extractor([image], return_tensors="pt")
+        features = self.feature_extractor([image], return_tensors="pt")
         features.to(device)
-        cls.safety_checker.to(device)
+        self.safety_checker.to(device)
         x_image = np.array(image).astype(np.float32) / 255.0
         x_image = x_image[None].transpose(0, 3, 1, 2)
         with SilenceWarnings():
-            checked_image, has_nsfw_concept = cls.safety_checker(images=x_image, clip_input=features.pixel_values)
+            checked_image, has_nsfw_concept = self.safety_checker(images=x_image, clip_input=features.pixel_values)
         return has_nsfw_concept[0]

invokeai/backend/install/model_install_backend.py

@@ -460,12 +460,6 @@ class ModelInstall(object):
             possible_conf = path.with_suffix(".yaml")
             if possible_conf.exists():
                 legacy_conf = str(self.relative_to_root(possible_conf))
-            else:
-                legacy_conf = Path(
-                    self.config.root_path,
-                    "configs/controlnet",
-                    ("cldm_v15.yaml" if info.base_type == BaseModelType("sd-1") else "cldm_v21.yaml"),
-                )
 
         if legacy_conf:
             attributes.update(dict(config=str(legacy_conf)))

invokeai/backend/ip_adapter/attention_processor.py

@@ -67,12 +67,6 @@ class IPAttnProcessor2_0(torch.nn.Module):
         temb=None,
         ip_adapter_image_prompt_embeds=None,
     ):
-        """Apply IP-Adapter attention.
-
-        Args:
-            ip_adapter_image_prompt_embeds (torch.Tensor): The image prompt embeddings.
-                Shape: (batch_size, num_ip_images, seq_len, ip_embedding_len).
-        """
         residual = hidden_states
 
         if attn.spatial_norm is not None:
@@ -133,35 +127,26 @@ class IPAttnProcessor2_0(torch.nn.Module):
             for ipa_embed, ipa_weights, scale in zip(ip_adapter_image_prompt_embeds, self._weights, self._scales):
                 # The batch dimensions should match.
                 assert ipa_embed.shape[0] == encoder_hidden_states.shape[0]
-                # The token_len dimensions should match.
-                assert ipa_embed.shape[-1] == encoder_hidden_states.shape[-1]
+                # The channel dimensions should match.
+                assert ipa_embed.shape[2] == encoder_hidden_states.shape[2]
 
                 ip_hidden_states = ipa_embed
 
-                # Expected ip_hidden_state shape: (batch_size, num_ip_images, ip_seq_len, ip_image_embedding)
-
                 ip_key = ipa_weights.to_k_ip(ip_hidden_states)
                 ip_value = ipa_weights.to_v_ip(ip_hidden_states)
 
-                # Expected ip_key and ip_value shape: (batch_size, num_ip_images, ip_seq_len, head_dim * num_heads)
-
                 ip_key = ip_key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
                 ip_value = ip_value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
 
-                # Expected ip_key and ip_value shape: (batch_size, num_heads, num_ip_images * ip_seq_len, head_dim)
-
+                # The output of sdpa has shape: (batch, num_heads, seq_len, head_dim)
                 # TODO: add support for attn.scale when we move to Torch 2.1
                 ip_hidden_states = F.scaled_dot_product_attention(
                     query, ip_key, ip_value, attn_mask=None, dropout_p=0.0, is_causal=False
                 )
 
-                # Expected ip_hidden_states shape: (batch_size, num_heads, query_seq_len, head_dim)
-
                 ip_hidden_states = ip_hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
                 ip_hidden_states = ip_hidden_states.to(query.dtype)
 
-                # Expected ip_hidden_states shape: (batch_size, query_seq_len, num_heads * head_dim)
-
                 hidden_states = hidden_states + scale * ip_hidden_states
 
         # linear proj

invokeai/backend/model_management/model_manager.py

@@ -1011,8 +1011,6 @@ class ModelManager(object):
                                 self.logger.warning(f"Not a valid model: {model_path}. {e}")
                             except NotImplementedError as e:
                                 self.logger.warning(e)
-                            except Exception as e:
-                                self.logger.warning(f"Error loading model {model_path}. {e}")
 
         imported_models = self.scan_autoimport_directory()
         if (new_models_found or imported_models) and self.config_path:

invokeai/backend/model_management/models/controlnet.py

@@ -132,14 +132,13 @@ def _convert_controlnet_ckpt_and_cache(
     model_path: str,
     output_path: str,
     base_model: BaseModelType,
-    model_config: str,
+    model_config: ControlNetModel.CheckpointConfig,
 ) -> str:
     """
     Convert the controlnet from checkpoint format to diffusers format,
     cache it to disk, and return Path to converted
     file. If already on disk then just returns Path.
     """
-    print(f"DEBUG: controlnet config = {model_config}")
     app_config = InvokeAIAppConfig.get_config()
     weights = app_config.root_path / model_path
     output_path = Path(output_path)

invokeai/backend/stable_diffusion/diffusion/conditioning_data.py

@@ -55,11 +55,11 @@ class PostprocessingSettings:
 class IPAdapterConditioningInfo:
     cond_image_prompt_embeds: torch.Tensor
     """IP-Adapter image encoder conditioning embeddings.
-    Shape: (num_images, num_tokens, encoding_dim).
+    Shape: (batch_size, num_tokens, encoding_dim).
     """
     uncond_image_prompt_embeds: torch.Tensor
     """IP-Adapter image encoding embeddings to use for unconditional generation.
-    Shape: (num_images, num_tokens, encoding_dim).
+    Shape: (batch_size, num_tokens, encoding_dim).
     """