add support for multi-gpu rendering

This commit adds speculative support for parallel rendering across
multiple GPUs. The parallelism is at the level of a session. Each
session is given access to a different GPU. When all GPUs are busy,
execution of the session will block until a GPU becomes available.

The code is untested at the current time, and is being posted for
comment.

.github/ISSUE_TEMPLATE/BUG_REPORT.yml

@@ -6,10 +6,6 @@ title: '[bug]: '
 
 labels: ['bug']
 
-# assignees:
-#   - moderator_bot
-#   - lstein
-
 body:
   - type: markdown
     attributes:
@@ -18,10 +14,9 @@ body:
 
   - type: checkboxes
     attributes:
-      label: Is there an existing issue for this?
+      label: Is there an existing issue for this problem?
       description: |
-        Please use the [search function](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
-        irst to see if an issue already exists for the bug you encountered.
+        Please [search](https://github.com/invoke-ai/InvokeAI/issues) first to see if an issue already exists for the problem.
       options:
         - label: I have searched the existing issues
           required: true
@@ -33,80 +28,119 @@ body:
   - type: dropdown
     id: os_dropdown
     attributes:
-      label: OS
-      description: Which operating System did you use when the bug occured
+      label: Operating system
+      description: Your computer's operating system.
       multiple: false
       options:
         - 'Linux'
         - 'Windows'
         - 'macOS'
+        - 'other'
     validations:
       required: true
 
   - type: dropdown
     id: gpu_dropdown
     attributes:
-      label: GPU
-      description: Which kind of Graphic-Adapter is your System using
+      label: GPU vendor
+      description: Your GPU's vendor.
       multiple: false
       options:
-        - 'cuda'
-        - 'amd'
-        - 'mps'
-        - 'cpu'
+        - 'Nvidia (CUDA)'
+        - 'AMD (ROCm)'
+        - 'Apple Silicon (MPS)'
+        - 'None (CPU)'
     validations:
       required: true
 
+  - type: input
+    id: gpu_model
+    attributes:
+      label: GPU model
+      description: Your GPU's model. If on Apple Silicon, this is your Mac's chip. Leave blank if on CPU.
+      placeholder: ex. RTX 2080 Ti, Mac M1 Pro
+    validations:
+      required: false
+
   - type: input
     id: vram
     attributes:
-      label: VRAM
-      description: Size of the VRAM if known
+      label: GPU VRAM
+      description: Your GPU's VRAM. If on Apple Silicon, this is your Mac's unified memory. Leave blank if on CPU.
       placeholder: 8GB
     validations:
       required: false
-      
+
   - type: input
     id: version-number
     attributes:
-      label: What version did you experience this issue on?
+      label: Version number
       description: |
-        Please share the version of Invoke AI that you experienced the issue on. If this is not the latest version, please update first to confirm the issue still exists. If you are testing main, please include the commit hash instead.
-      placeholder: X.X.X
+        The version of Invoke you have installed. If it is not the latest version, please update and try again to confirm the issue still exists. If you are testing main, please include the commit hash instead.
+      placeholder: ex. 3.6.1
     validations:
       required: true
 
+  - type: input
+    id: browser-version
+    attributes:
+      label: Browser
+      description: Your web browser and version.
+      placeholder: ex. Firefox 123.0b3
+    validations:
+      required: true
+
+  - type: textarea
+    id: python-deps
+    attributes:
+      label: Python dependencies
+      description: |
+        If the problem occurred during image generation, click the gear icon at the bottom left corner, click "About", click the copy button and then paste here.
+    validations:
+      required: false
+
   - type: textarea
     id: what-happened
     attributes:
-      label: What happened?
+      label: What happened
       description: |
-        Briefly describe what happened, what you expected to happen and how to reproduce this bug.
-      placeholder: When using the webinterface and right-clicking on button X instead of the popup-menu there error Y appears
+        Describe what happened. Include any relevant error messages, stack traces and screenshots here.
+      placeholder: I clicked button X and then Y happened.
     validations:
       required: true
 
   - type: textarea
+    id: what-you-expected
     attributes:
-      label: Screenshots
-      description: If applicable, add screenshots to help explain your problem
-      placeholder: this is what the result looked like <screenshot>
+      label: What you expected to happen
+      description: Describe what you expected to happen.
+      placeholder: I expected Z to happen.
+    validations:
+      required: true
+
+  - type: textarea
+    id: how-to-repro
+    attributes:
+      label: How to reproduce the problem
+      description: List steps to reproduce the problem.
+      placeholder: Start the app, generate an image with these settings, then click button X.
     validations:
       required: false
 
   - type: textarea
+    id: additional-context
     attributes:
       label: Additional context
-      description: Add any other context about the problem here
+      description: Any other context that might help us to understand the problem.
       placeholder: Only happens when there is full moon and Friday the 13th on Christmas Eve 🎅🏻
     validations:
       required: false
 
   - type: input
-    id: contact
+    id: discord-username
     attributes:
-      label: Contact Details
-      description: __OPTIONAL__ How can we get in touch with you if we need more info (besides this issue)?
-      placeholder: ex. email@example.com, discordname, twitter, ...
+      label: Discord username
+      description: If you are on the Invoke discord and would prefer to be contacted there, please provide your username.
+      placeholder: supercoolusername123
     validations:
       required: false

.github/pr_labels.yml

@@ -0,0 +1,59 @@
+Root:
+- changed-files:
+  - any-glob-to-any-file: '*'
+
+PythonDeps:
+- changed-files:
+  - any-glob-to-any-file: 'pyproject.toml'
+
+Python:
+- changed-files:
+  - all-globs-to-any-file: 
+    - 'invokeai/**'
+    - '!invokeai/frontend/web/**'
+
+PythonTests:
+- changed-files:
+  - any-glob-to-any-file: 'tests/**'
+
+CICD:
+- changed-files:
+  - any-glob-to-any-file: .github/**
+
+Docker:
+- changed-files:
+  - any-glob-to-any-file: docker/**
+
+Installer:
+- changed-files:
+  - any-glob-to-any-file: installer/**
+
+Documentation:
+- changed-files:
+  - any-glob-to-any-file: docs/**
+
+Invocations:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/app/invocations/**'
+
+Backend:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/backend/**'
+
+Api:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/app/api/**'
+
+Services:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/app/services/**'
+
+FrontendDeps:
+- changed-files:
+  - any-glob-to-any-file:
+    - '**/*/package.json'
+    - '**/*/pnpm-lock.yaml'
+
+Frontend:
+- changed-files:
+  - any-glob-to-any-file: 'invokeai/frontend/web/**'

.github/workflows/change-monitor.yml

@@ -1,29 +0,0 @@
-name: Trigger Target Workflow
-
-on:
-  push:
-    branches:
-      - main
-  workflow_dispatch:
-
-jobs:
-  trigger:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Trigger Workflow in Another Repository
-        run: |
-          # Set the required variables
-          repo_owner="invoke-ai" 
-          repo_name="Invoke"  
-          event_type="invokeai-pr-merge" 
-          service=${{ github.event.inputs.target_service }}"
-          version="${{ github.event.inputs.target_version }}"
-  
-          curl -L \
-            -X POST \
-            -H "Accept: application/vnd.github+json" \
-            -H "Authorization: Bearer ${{ secrets.PAT }}" \
-            -H "X-GitHub-Api-Version: 2022-11-28" \
-            https://api.github.com/repos/$repo_owner/$repo_name/dispatches \
-            -d "{\"event_type\": \"$event_type\", \"client_payload\": {\"service\": \"$service\", \"version\": \"$version\", \"unit\": false, \"integration\": true}}"

.github/workflows/label-pr.yml

@@ -0,0 +1,16 @@
+name: "Pull Request Labeler"
+on:
+- pull_request_target
+
+jobs:
+  labeler:
+    permissions:
+      contents: read
+      pull-requests: write
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - uses: actions/labeler@v5
+        with:
+          configuration-path: .github/pr_labels.yml

README.md

@@ -169,7 +169,7 @@ the command `npm install -g pnpm` if needed)
     _For Linux with an AMD GPU:_
 
     ```sh
-    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
     ```
 
     _For non-GPU systems:_

docker/Dockerfile

@@ -18,8 +18,8 @@ ENV INVOKEAI_SRC=/opt/invokeai
 ENV VIRTUAL_ENV=/opt/venv/invokeai
 
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-ARG TORCH_VERSION=2.1.0
-ARG TORCHVISION_VERSION=0.16
+ARG TORCH_VERSION=2.1.2
+ARG TORCHVISION_VERSION=0.16.2
 ARG GPU_DRIVER=cuda
 ARG TARGETPLATFORM="linux/amd64"
 # unused but available
@@ -35,7 +35,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ] || [ "$GPU_DRIVER" = "cpu" ]; then \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cpu"; \
     elif [ "$GPU_DRIVER" = "rocm" ]; then \
-        extra_index_url_arg="--index-url https://download.pytorch.org/whl/rocm5.6"; \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm5.6"; \
     else \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
     fi &&\
@@ -54,7 +54,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$GPU_DRIVER" = "cuda" ] && [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
         pip install -e ".[xformers]"; \
     else \
-        pip install -e "."; \
+        pip install $extra_index_url_arg -e "."; \
     fi
 
 # #### Build the Web UI ------------------------------------

docker/README.md

@@ -28,7 +28,7 @@ This is done via Docker Desktop preferences
 
 ### Configure Invoke environment
 
-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:
+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.
 1. Execute `run.sh`

docker/run.sh

@@ -21,7 +21,7 @@ run() {
     printf "%s\n" "$build_args"
   fi
 
-  docker compose build $build_args
+  docker compose build $build_args $service_name
   unset build_args
 
   printf "%s\n" "starting service $service_name"

docs/contributing/INVOCATIONS.md

@@ -9,11 +9,15 @@ complex functionality.
 
 ## Invocations Directory
 
-InvokeAI Nodes can be found in the `invokeai/app/invocations` directory. These can be used as examples to create your own nodes.
+InvokeAI Nodes can be found in the `invokeai/app/invocations` directory. These
+can be used as examples to create your own nodes.
 
-New nodes should be added to a subfolder in `nodes` direction found at the root level of the InvokeAI installation location. Nodes added to this folder will be able to be used upon application startup. 
+New nodes should be added to a subfolder in `nodes` direction found at the root
+level of the InvokeAI installation location. Nodes added to this folder will be
+able to be used upon application startup.
+
+Example `nodes` subfolder structure:
 
-Example `nodes`  subfolder structure:
 ```py
 ├── __init__.py # Invoke-managed custom node loader
 │
@@ -30,14 +34,14 @@ Example `nodes`  subfolder structure:
         └── fancy_node.py
 ```
 
-Each node folder must have an `__init__.py` file that imports its nodes. Only nodes imported in the `__init__.py` file are loaded.
- See the README in the nodes folder for more examples: 
+Each node folder must have an `__init__.py` file that imports its nodes. Only
+nodes imported in the `__init__.py` file are loaded. See the README in the nodes
+folder for more examples:
 
 ```py
 from .cool_node import CoolInvocation
 ```
 
-
 ## Creating A New Invocation
 
 In order to understand the process of creating a new Invocation, let us actually
@@ -131,7 +135,6 @@ from invokeai.app.invocations.primitives import ImageField
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -167,7 +170,6 @@ from invokeai.app.invocations.primitives import ImageField
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -197,7 +199,6 @@ from invokeai.app.invocations.image import ImageOutput
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -229,30 +230,17 @@ class ResizeInvocation(BaseInvocation):
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Load the image using InvokeAI's predefined Image Service. Returns the PIL image.
-        image = context.services.images.get_pil_image(self.image.image_name)
+        # Load the input image as a PIL image
+        image = context.images.get_pil(self.image.image_name)
 
-        # Resizing the image
+        # Resize the image
         resized_image = image.resize((self.width, self.height))
 
-        # Save the image using InvokeAI's predefined Image Service. Returns the prepared PIL image.
-        output_image = context.services.images.create(
-            image=resized_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,
-        )
+        # Save the image
+        image_dto = context.images.save(image=resized_image)
 
-        # Returning the Image
-        return ImageOutput(
-            image=ImageField(
-                image_name=output_image.image_name,
-            ),
-            width=output_image.width,
-            height=output_image.height,
-        )
+        # Return an ImageOutput
+        return ImageOutput.build(image_dto)
 ```
 
 **Note:** Do not be overwhelmed by the `ImageOutput` process. InvokeAI has a
@@ -343,27 +331,25 @@ class ImageColorStringOutput(BaseInvocationOutput):
 
 That's all there is to it.
 
-<!-- TODO: DANGER - we probably do not want people to create their own field types, because this requires a lot of work on the frontend to accomodate.
-
 ### Custom Input Fields
 
 Now that you know how to create your own Invocations, let us dive into slightly
 more advanced topics.
 
 While creating your own Invocations, you might run into a scenario where the
-existing input types in InvokeAI do not meet your requirements. In such cases,
-you can create your own input types.
+existing fields in InvokeAI do not meet your requirements. In such cases, you
+can create your own fields.
 
 Let us create one as an example. Let us say we want to create a color input
 field that represents a color code. But before we start on that here are some
 general good practices to keep in mind.
 
-**Good Practices**
+### Best Practices
 
 - There is no naming convention for input fields but we highly recommend that
   you name it something appropriate like `ColorField`.
 - It is not mandatory but it is heavily recommended to add a relevant
-  `docstring` to describe your input field.
+  `docstring` to describe your field.
 - Keep your field in the same file as the Invocation that it is made for or in
   another file where it is relevant.
 
@@ -378,10 +364,13 @@ class ColorField(BaseModel):
     pass
 ```
 
-Perfect. Now let us create our custom inputs for our field. This is exactly
-similar how you created input fields for your Invocation. All the same rules
-apply. Let us create four fields representing the _red(r)_, _blue(b)_,
-_green(g)_ and _alpha(a)_ channel of the color.
+Perfect. Now let us create the properties for our field. This is similar to how
+you created input fields for your Invocation. All the same rules apply. Let us
+create four fields representing the _red(r)_, _blue(b)_, _green(g)_ and
+_alpha(a)_ channel of the color.
+
+> Technically, the properties are _also_ called fields - but in this case, it
+> refers to a `pydantic` field.
 
 ```python
 class ColorField(BaseModel):
@@ -396,25 +385,11 @@ That's it. We now have a new input field type that we can use in our Invocations
 like this.
 
 ```python
-color: ColorField = Field(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
+color: ColorField = InputField(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
 ```
 
-### Custom Components For Frontend
+### Using the custom field
 
-Every backend input type should have a corresponding frontend component so the
-UI knows what to render when you use a particular field type.
+When you start the UI, your custom field will be automatically recognized.
 
-If you are using existing field types, we already have components for those. So
-you don't have to worry about creating anything new. But this might not always
-be the case. Sometimes you might want to create new field types and have the
-frontend UI deal with it in a different way.
-
-This is where we venture into the world of React and Javascript and create our
-own new components for our Invocations. Do not fear the world of JS. It's
-actually pretty straightforward.
-
-Let us create a new component for our custom color field we created above. When
-we use a color field, let us say we want the UI to display a color picker for
-the user to pick from rather than entering values. That is what we will build
-now.
--->
+Custom fields only support connection inputs in the Workflow Editor.

docs/contributing/MODEL_MANAGER.md

@@ -28,7 +28,7 @@ model. These are the:
   Hugging Face, as well as discriminating among model versions in
   Civitai, but can be used for arbitrary content.
   
-  * _ModelLoadServiceBase_ (**CURRENTLY UNDER DEVELOPMENT - NOT IMPLEMENTED**)
+  * _ModelLoadServiceBase_
   Responsible for loading a model from disk
   into RAM and VRAM and getting it ready for inference.
 
@@ -41,10 +41,10 @@ The four main services can be found in
 * `invokeai/app/services/model_records/`
 * `invokeai/app/services/model_install/`
 * `invokeai/app/services/downloads/`
-* `invokeai/app/services/model_loader/` (**under development**)
+* `invokeai/app/services/model_load/`
 
 Code related to the FastAPI web API can be found in
-`invokeai/app/api/routers/model_records.py`.
+`invokeai/app/api/routers/model_manager_v2.py`.
 
 ***
 
@@ -84,10 +84,10 @@ diffusers model. When this happens, `original_hash` is unchanged, but
 `ModelType`, `ModelFormat` and `BaseModelType` are string enums that
 are defined in `invokeai.backend.model_manager.config`. They are also
 imported by, and can be reexported from,
-`invokeai.app.services.model_record_service`:
+`invokeai.app.services.model_manager.model_records`:
 
 ```
-from invokeai.app.services.model_record_service import ModelType, ModelFormat, BaseModelType
+from invokeai.app.services.model_records import ModelType, ModelFormat, BaseModelType
 ```
 
 The `path` field can be absolute or relative. If relative, it is taken
@@ -123,7 +123,7 @@ taken to be the `models_dir` directory.
 
 `variant` is an enumerated string class with values `normal`,
 `inpaint` and `depth`. If needed, it can be imported if needed from
-either `invokeai.app.services.model_record_service` or
+either `invokeai.app.services.model_records` or
 `invokeai.backend.model_manager.config`.
 
 ### ONNXSD2Config
@@ -134,7 +134,7 @@ either `invokeai.app.services.model_record_service` or
 | `upcast_attention`  | bool | Model requires its attention module to be upcast |
 
 The `SchedulerPredictionType` enum can be imported from either
-`invokeai.app.services.model_record_service` or
+`invokeai.app.services.model_records` or
 `invokeai.backend.model_manager.config`.
 
 ### Other config classes
@@ -157,15 +157,6 @@ indicates that the model is compatible with any of the base
 models. This works OK for some models, such as the IP Adapter image
 encoders, but is an all-or-nothing proposition.
 
-Another issue is that the config class hierarchy is paralleled to some
-extent by a `ModelBase` class hierarchy defined in
-`invokeai.backend.model_manager.models.base` and its subclasses. These
-are classes representing the models after they are loaded into RAM and
-include runtime information such as load status and bytes used. Some
-of the fields, including `name`, `model_type` and `base_model`, are
-shared between `ModelConfigBase` and `ModelBase`, and this is a
-potential source of confusion.
-
 ## Reading and Writing Model Configuration Records
 
 The `ModelRecordService` provides the ability to retrieve model
@@ -177,11 +168,11 @@ initialization and can be retrieved within an invocation from the
 `InvocationContext` object:
 
 ```
-store = context.services.model_record_store
+store = context.services.model_manager.store
 ```
 
 or from elsewhere in the code by accessing
-`ApiDependencies.invoker.services.model_record_store`.
+`ApiDependencies.invoker.services.model_manager.store`.
 
 ### Creating a `ModelRecordService` 
 
@@ -190,7 +181,7 @@ you can directly create either a `ModelRecordServiceSQL` or a
 `ModelRecordServiceFile` object:
 
 ```
-from invokeai.app.services.model_record_service import ModelRecordServiceSQL, ModelRecordServiceFile
+from invokeai.app.services.model_records import ModelRecordServiceSQL, ModelRecordServiceFile
 
 store = ModelRecordServiceSQL.from_connection(connection, lock)
 store = ModelRecordServiceSQL.from_db_file('/path/to/sqlite_database.db')
@@ -252,7 +243,7 @@ So a typical startup pattern would be:
 ```
 import sqlite3
 from invokeai.app.services.thread import lock
-from invokeai.app.services.model_record_service import ModelRecordServiceBase
+from invokeai.app.services.model_records import ModelRecordServiceBase
 from invokeai.app.services.config import InvokeAIAppConfig
 
 config = InvokeAIAppConfig.get_config()
@@ -260,19 +251,6 @@ db_conn = sqlite3.connect(config.db_path.as_posix(), check_same_thread=False)
 store = ModelRecordServiceBase.open(config, db_conn, lock)
 ```
 
-_A note on simultaneous access to `invokeai.db`_: The current InvokeAI
-service architecture for the image and graph databases is careful to
-use a shared sqlite3 connection and a thread lock to ensure that two
-threads don't attempt to access the database simultaneously. However,
-the default `sqlite3` library used by Python reports using
-**Serialized** mode, which allows multiple threads to access the
-database simultaneously using multiple database connections (see
-https://www.sqlite.org/threadsafe.html and
-https://ricardoanderegg.com/posts/python-sqlite-thread-safety/). Therefore
-it should be safe to allow the record service to open its own SQLite
-database connection. Opening a model record service should then be as
-simple as `ModelRecordServiceBase.open(config)`.
-
 ### Fetching a Model's Configuration from `ModelRecordServiceBase`
 
 Configurations can be retrieved in several ways.
@@ -468,6 +446,44 @@ required parameters:
 
 Once initialized, the installer will provide the following methods:
 
+#### install_job = installer.heuristic_import(source, [config], [access_token])
+
+This is a simplified interface to the installer which takes a source
+string, an optional model configuration dictionary and an optional
+access token.
+
+The `source` is a string that can be any of these forms
+
+1. A path on the local filesystem (`C:\\users\\fred\\model.safetensors`)
+2. A Url pointing to a single downloadable model file (`https://civitai.com/models/58390/detail-tweaker-lora-lora`)
+3. A HuggingFace repo_id with any of the following formats:
+   - `model/name` -- entire model
+   - `model/name:fp32` -- entire model, using the fp32 variant
+   - `model/name:fp16:vae` -- vae submodel, using the fp16 variant
+   - `model/name::vae` -- vae submodel, using default precision
+   - `model/name:fp16:path/to/model.safetensors` -- an individual model file, fp16 variant
+   - `model/name::path/to/model.safetensors` -- an individual model file, default variant
+
+Note that by specifying a relative path to the top of the HuggingFace
+repo, you can download and install arbitrary models files. 
+
+The variant, if not provided, will be automatically filled in with
+`fp32` if the user has requested full precision, and `fp16`
+otherwise. If a variant that does not exist is requested, then the
+method will install whatever HuggingFace returns as its default
+revision.
+
+`config` is an optional dict of values that will override the
+autoprobed values for model type, base, scheduler prediction type, and
+so forth. See [Model configuration and
+probing](#Model-configuration-and-probing) for details.
+
+`access_token` is an optional access token for accessing resources
+that need authentication.
+
+The method will return a `ModelInstallJob`. This object is discussed
+at length in the following section.
+
 #### install_job = installer.import_model()
 
 The `import_model()` method is the core of the installer. The
@@ -486,9 +502,10 @@ source2 = LocalModelSource(path='/opt/models/sushi_diffusers')     # a local dif
 source3 = HFModelSource(repo_id='runwayml/stable-diffusion-v1-5')  # a repo_id
 source4 = HFModelSource(repo_id='runwayml/stable-diffusion-v1-5', subfolder='vae')  # a subfolder within a repo_id
 source5 = HFModelSource(repo_id='runwayml/stable-diffusion-v1-5', variant='fp16')   # a named variant of a HF model
+source6 = HFModelSource(repo_id='runwayml/stable-diffusion-v1-5', subfolder='OrangeMix/OrangeMix1.ckpt')   # path to an individual model file
 
-source6 = URLModelSource(url='https://civitai.com/api/download/models/63006')       # model located at a URL
-source7 = URLModelSource(url='https://civitai.com/api/download/models/63006', access_token='letmein') # with an access token
+source7 = URLModelSource(url='https://civitai.com/api/download/models/63006')       # model located at a URL
+source8 = URLModelSource(url='https://civitai.com/api/download/models/63006', access_token='letmein') # with an access token
 
 for source in [source1, source2, source3, source4, source5, source6, source7]:
    install_job = installer.install_model(source)
@@ -544,7 +561,6 @@ can be passed to `import_model()`.
 attributes returned by the model prober. See the section below for
 details.
 
-
 #### LocalModelSource
 
 This is used for a model that is located on a locally-accessible Posix
@@ -737,7 +753,7 @@ and `cancelled`, as well as `in_terminal_state`. The last will return
 True if the job is in the complete, errored or cancelled states.
 
 
-#### Model confguration and probing
+#### Model configuration and probing
 
 The install service uses the `invokeai.backend.model_manager.probe`
 module during import to determine the model's type, base type, and
@@ -776,6 +792,14 @@ returns a list of completed jobs. The optional `timeout` argument will
 return from the call if jobs aren't completed in the specified
 time. An argument of 0 (the default) will block indefinitely.
 
+#### jobs = installer.wait_for_job(job, [timeout])
+
+Like `wait_for_installs()`, but block until a specific job has
+completed or errored, and then return the job.  The optional `timeout`
+argument will return from the call if the job doesn't complete in the
+specified time. An argument of 0 (the default) will block
+indefinitely.
+
 #### jobs = installer.list_jobs()
 
 Return a list of all active and complete `ModelInstallJobs`.
@@ -838,6 +862,31 @@ This method is similar to `unregister()`, but also unconditionally
 deletes the corresponding model weights file(s), regardless of whether
 they are inside or outside the InvokeAI models hierarchy.
 
+
+#### path = installer.download_and_cache(remote_source, [access_token], [timeout])
+
+This utility routine will download the model file located at source,
+cache it, and return the path to the cached file. It does not attempt
+to determine the model type, probe its configuration values, or
+register it with the models database.
+
+You may provide an access token if the remote source requires
+authorization. The call will block indefinitely until the file is
+completely downloaded, cancelled or raises an error of some sort. If
+you provide a timeout (in seconds), the call will raise a
+`TimeoutError` exception if the download hasn't completed in the
+specified period.
+
+You may use this mechanism to request any type of file, not just a
+model. The file will be stored in a subdirectory of
+`INVOKEAI_ROOT/models/.cache`. If the requested file is found in the
+cache, its path will be returned without redownloading it.
+
+Be aware that the models cache is cleared of infrequently-used files
+and directories at regular intervals when the size of the cache
+exceeds the value specified in Invoke's `convert_cache` configuration
+variable.
+
 #### List[str]=installer.scan_directory(scan_dir: Path, install: bool)
 
 This method will recursively scan the directory indicated in
@@ -1128,7 +1177,7 @@ job = queue.create_download_job(
 		 event_handlers=[my_handler1, my_handler2], # if desired
 		 start=True,
 	)
- ```
+```
  
 The `filename` argument forces the downloader to use the specified
 name for the file rather than the name provided by the remote source,
@@ -1171,6 +1220,13 @@ queue or was not created by this queue.
 This method will block until all the active jobs in the queue have
 reached a terminal state (completed, errored or cancelled).
 
+#### queue.wait_for_job(job, [timeout])
+
+This method will block until the indicated job has reached a terminal
+state (completed, errored or cancelled). If the optional timeout is
+provided, the call will block for at most timeout seconds, and raise a
+TimeoutError otherwise.
+
 #### jobs = queue.list_jobs()
 
 This will return a list of all jobs, including ones that have not yet
@@ -1449,9 +1505,9 @@ set of keys to the corresponding model config objects.
 Find all model metadata records that have the given author and return
 a set of keys to the corresponding model config objects.
 
-# The remainder of this documentation is provisional, pending implementation of the Load service
+***
 
-## Let's get loaded, the lowdown on ModelLoadService
+## The Lowdown on the ModelLoadService
 
 The `ModelLoadService` is responsible for loading a named model into
 memory so that it can be used for inference. Despite the fact that it
@@ -1465,7 +1521,7 @@ create alternative instances if you wish.
 ### Creating a ModelLoadService object
 
 The class is defined in
-`invokeai.app.services.model_loader_service`. It is initialized with
+`invokeai.app.services.model_load`. It is initialized with
 an InvokeAIAppConfig object, from which it gets configuration
 information such as the user's desired GPU and precision, and with a
 previously-created `ModelRecordServiceBase` object, from which it
@@ -1475,26 +1531,29 @@ Here is a typical initialization pattern:
 
 ```
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.model_record_service import ModelRecordServiceBase
-from invokeai.app.services.model_loader_service import ModelLoadService
+from invokeai.app.services.model_load import ModelLoadService, ModelLoaderRegistry
 
 config = InvokeAIAppConfig.get_config()
-store = ModelRecordServiceBase.open(config)
-loader = ModelLoadService(config, store)
+ram_cache = ModelCache(
+	max_cache_size=config.ram_cache_size, max_vram_cache_size=config.vram_cache_size, logger=logger
+)
+convert_cache = ModelConvertCache(
+	cache_path=config.models_convert_cache_path, max_size=config.convert_cache_size
+)
+loader = ModelLoadService(
+	app_config=config,
+	ram_cache=ram_cache,
+	convert_cache=convert_cache,
+	registry=ModelLoaderRegistry
+)
 ```
 
-Note that we are relying on the contents of the application
-configuration to choose the implementation of
-`ModelRecordServiceBase`.
+### load_model(model_config, [submodel_type], [context]) -> LoadedModel
 
-### get_model(key, [submodel_type], [context]) -> ModelInfo:
-
-*** TO DO: change to get_model(key, context=None, **kwargs)
-
-The `get_model()` method, like its similarly-named cousin in
-`ModelRecordService`, receives the unique key that identifies the
+The `load_model()` method takes an `AnyModelConfig` returned by
+`ModelRecordService.get_model()` and returns the corresponding loaded
 model.  It loads the model into memory, gets the model ready for use,
-and returns a `ModelInfo` object. 
+and returns a `LoadedModel` object.
 
 The optional second argument, `subtype` is a `SubModelType` string
 enum, such as "vae". It is mandatory when used with a main model, and
@@ -1504,46 +1563,45 @@ The optional third argument, `context` can be provided by
 an invocation to trigger model load event reporting. See below for
 details.
 
-The returned `ModelInfo` object shares some fields in common with
-`ModelConfigBase`, but is otherwise a completely different beast:
+The returned `LoadedModel` object contains a copy of the configuration
+record returned by the model record `get_model()` method, as well as
+the in-memory loaded model:
 
-| **Field Name** | **Type**        |  **Description** |
+
+| **Attribute Name** | **Type**        |  **Description** |
 |----------------|-----------------|------------------|
-| `key`          | str                    | The model key derived from the ModelRecordService database |
-| `name`         | str                    | Name of this model |
-| `base_model`   | BaseModelType          | Base model for this model |
-| `type`         | ModelType or SubModelType   | Either the model type (non-main) or the submodel type (main models)|
-| `location`     | Path or str            | Location of the model on the filesystem |
-| `precision`    | torch.dtype            | The torch.precision to use for inference |
-| `context`      | ModelCache.ModelLocker | A context class used to lock the model in VRAM while in use |
+| `config`       | AnyModelConfig         | A copy of the model's configuration record for retrieving base type, etc. |
+| `model`        | AnyModel               | The instantiated model (details below) |
+| `locker`       | ModelLockerBase        | A context manager that mediates the movement of the model into VRAM |
 
-The types for `ModelInfo` and `SubModelType` can be imported from
-`invokeai.app.services.model_loader_service`.
+Because the loader can return multiple model types, it is typed to
+return `AnyModel`, a Union `ModelMixin`, `torch.nn.Module`,
+`IAIOnnxRuntimeModel`, `IPAdapter`, `IPAdapterPlus`, and
+`EmbeddingModelRaw`. `ModelMixin` is the base class of all diffusers
+models, `EmbeddingModelRaw` is used for LoRA and TextualInversion
+models. The others are obvious.
 
-To use the model, you use the `ModelInfo` as a context manager using
-the following pattern:
+
+`LoadedModel` acts as a context manager. The context loads the model
+into the execution device (e.g. VRAM on CUDA systems), locks the model
+in the execution device for the duration of the context, and returns
+the model. Use it like this:
 
 ```
-model_info = loader.get_model('f13dd932c0c35c22dcb8d6cda4203764', SubModelType('vae'))
+model_info = loader.get_model_by_key('f13dd932c0c35c22dcb8d6cda4203764', SubModelType('vae'))
 with model_info as vae:
 	image = vae.decode(latents)[0]
 ```
 
-The `vae` model will stay locked in the GPU during the period of time
-it is in the context manager's scope.
+`get_model_by_key()` may raise any of the following exceptions:
 
-`get_model()` may raise any of the following exceptions:
-
-- `UnknownModelException`  -- key not in database
-- `ModelNotFoundException` -- key in database but model not found at path
-- `InvalidModelException`  -- the model is guilty of a variety of sins
+- `UnknownModelException`   -- key not in database
+- `ModelNotFoundException`  -- key in database but model not found at path
+- `NotImplementedException` -- the loader doesn't know how to load this type of model
   
-** TO DO: ** Resolve discrepancy between ModelInfo.location and
-ModelConfig.path.
-
 ### Emitting model loading events
 
-When the `context` argument is passed to `get_model()`, it will
+When the `context` argument is passed to `load_model_*()`, it will
 retrieve the invocation event bus from the passed `InvocationContext`
 object to emit events on the invocation bus. The two events are
 "model_load_started" and "model_load_completed". Both carry the
@@ -1556,10 +1614,174 @@ payload=dict(
 	queue_batch_id=queue_batch_id,
 	graph_execution_state_id=graph_execution_state_id,
 	model_key=model_key,
-	submodel=submodel,
+	submodel_type=submodel,
 	hash=model_info.hash,
 	location=str(model_info.location),
 	precision=str(model_info.precision),
 )
 ```
 
+### Adding Model Loaders
+
+Model loaders are small classes that inherit from the `ModelLoader`
+base class. They typically implement one method `_load_model()` whose
+signature is:
+
+```
+def _load_model(
+    self,
+    model_path: Path,
+    model_variant: Optional[ModelRepoVariant] = None,
+    submodel_type: Optional[SubModelType] = None,
+) -> AnyModel:
+```
+
+`_load_model()` will be passed the path to the model on disk, an
+optional repository variant (used by the diffusers loaders to select,
+e.g.  the `fp16` variant, and an optional submodel_type for main and
+onnx models.
+
+To install a new loader, place it in
+`invokeai/backend/model_manager/load/model_loaders`. Inherit from
+`ModelLoader` and use the `@ModelLoaderRegistry.register()` decorator to
+indicate what type of models the loader can handle.
+
+Here is a complete example from `generic_diffusers.py`, which is able
+to load several different diffusers types:
+
+```
+from pathlib import Path
+from typing import Optional
+
+from invokeai.backend.model_manager import (
+    AnyModel,
+    BaseModelType,
+    ModelFormat,
+    ModelRepoVariant,
+    ModelType,
+    SubModelType,
+)
+from .. import ModelLoader, ModelLoaderRegistry
+
+
+@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.CLIPVision, format=ModelFormat.Diffusers)
+@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.T2IAdapter, format=ModelFormat.Diffusers)
+class GenericDiffusersLoader(ModelLoader):
+    """Class to load simple diffusers models."""
+
+    def _load_model(
+        self,
+        model_path: Path,
+        model_variant: Optional[ModelRepoVariant] = None,
+        submodel_type: Optional[SubModelType] = None,
+    ) -> AnyModel:
+        model_class = self._get_hf_load_class(model_path)
+        if submodel_type is not None:
+            raise Exception(f"There are no submodels in models of type {model_class}")
+        variant = model_variant.value if model_variant else None
+        result: AnyModel = model_class.from_pretrained(model_path, torch_dtype=self._torch_dtype, variant=variant)  # type: ignore
+        return result
+```
+
+Note that a loader can register itself to handle several different
+model types. An exception will be raised if more than one loader tries
+to register the same model type.
+
+#### Conversion
+
+Some models require conversion to diffusers format before they can be
+loaded. These loaders should override two additional methods:
+
+```
+_needs_conversion(self, config: AnyModelConfig, model_path: Path, dest_path: Path) -> bool
+_convert_model(self, config: AnyModelConfig, model_path: Path, output_path: Path) -> Path:
+```
+
+The first method accepts the model configuration, the path to where
+the unmodified model is currently installed, and a proposed
+destination for the converted model. This method returns True if the
+model needs to be converted. It typically does this by comparing the
+last modification time of the original model file to the modification
+time of the converted model. In some cases you will also want to check
+the modification date of the configuration record, in the event that
+the user has changed something like the scheduler prediction type that
+will require the model to be re-converted. See `controlnet.py` for an
+example of this logic.
+
+The second method accepts the model configuration, the path to the
+original model on disk, and the desired output path for the converted
+model. It does whatever it needs to do to get the model into diffusers
+format, and returns the Path of the resulting model. (The path should
+ordinarily be the same as `output_path`.)
+
+## The ModelManagerService object
+
+For convenience, the API provides a `ModelManagerService` object which
+gives a single point of access to the major model manager
+services. This object is created at initialization time and can be
+found in the global `ApiDependencies.invoker.services.model_manager`
+object, or in `context.services.model_manager` from within an
+invocation.
+
+In the examples below, we have retrieved the manager using:
+```
+mm = ApiDependencies.invoker.services.model_manager
+```
+
+The following properties and methods will be available:
+
+### mm.store
+
+This retrieves the `ModelRecordService` associated with the
+manager. Example:
+
+```
+configs = mm.store.get_model_by_attr(name='stable-diffusion-v1-5')
+```
+
+### mm.install
+
+This retrieves the `ModelInstallService` associated with the manager.
+Example:
+
+```
+job = mm.install.heuristic_import(`https://civitai.com/models/58390/detail-tweaker-lora-lora`)
+```
+
+### mm.load
+
+This retrieves the `ModelLoaderService` associated with the manager. Example:
+
+```
+configs = mm.store.get_model_by_attr(name='stable-diffusion-v1-5')
+assert len(configs) > 0
+
+loaded_model = mm.load.load_model(configs[0])
+```
+
+The model manager also offers a few convenience shortcuts for loading
+models:
+
+### mm.load_model_by_config(model_config, [submodel], [context]) -> LoadedModel
+
+Same as `mm.load.load_model()`.
+
+### mm.load_model_by_attr(model_name, base_model, model_type, [submodel], [context]) -> LoadedModel
+
+This accepts the combination of the model's name, type and base, which
+it passes to the model record config store for retrieval. If a unique
+model config is found, this method returns a `LoadedModel`. It can
+raise the following exceptions:
+
+```
+UnknownModelException -- model with these attributes not known
+NotImplementedException -- the loader doesn't know how to load this type of model
+ValueError -- more than one model matches this combination of base/type/name
+```
+
+### mm.load_model_by_key(key, [submodel], [context]) -> LoadedModel
+
+This method takes a model key, looks it up using the
+`ModelRecordServiceBase` object in `mm.store`, and passes the returned
+model configuration to `load_model_by_config()`.  It may raise a
+`NotImplementedException`.

docs/contributing/contribution_guides/contributingToFrontend.md

@@ -1,76 +0,0 @@
-# Contributing to the Frontend
-
-# InvokeAI Web UI
-
-- [InvokeAI Web UI](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#invokeai-web-ui)
-    - [Stack](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#stack)
-    - [Contributing](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#contributing)
-        - [Dev Environment](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#dev-environment)
-        - [Production builds](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#production-builds)
-
-The UI is a fairly straightforward Typescript React app, with the Unified Canvas being more complex.
-
-Code is located in `invokeai/frontend/web/` for review.
-
-## Stack
-
-State management is Redux via [Redux Toolkit](https://github.com/reduxjs/redux-toolkit). We lean heavily on RTK:
-
-- `createAsyncThunk` for HTTP requests
-- `createEntityAdapter` for fetching images and models
-- `createListenerMiddleware` for workflows
-
-The API client and associated types are generated from the OpenAPI schema. See API_CLIENT.md.
-
-Communication with server is a mix of HTTP and [socket.io](https://github.com/socketio/socket.io-client) (with a simple socket.io redux middleware to help).
-
-[Chakra-UI](https://github.com/chakra-ui/chakra-ui) & [Mantine](https://github.com/mantinedev/mantine) for components and styling.
-
-[Konva](https://github.com/konvajs/react-konva) for the canvas, but we are pushing the limits of what is feasible with it (and HTML canvas in general). We plan to rebuild it with [PixiJS](https://github.com/pixijs/pixijs) to take advantage of WebGL's improved raster handling.
-
-[Vite](https://vitejs.dev/) for bundling.
-
-Localisation is via [i18next](https://github.com/i18next/react-i18next), but translation happens on our [Weblate](https://hosted.weblate.org/engage/invokeai/) project. Only the English source strings should be changed on this repo.
-
-## Contributing
-
-Thanks for your interest in contributing to the InvokeAI Web UI!
-
-We encourage you to ping @psychedelicious and @blessedcoolant on [Discord](https://discord.gg/ZmtBAhwWhy) if you want to contribute, just to touch base and ensure your work doesn't conflict with anything else going on. The project is very active.
-
-### Dev Environment
-
-**Setup** 
-
-1. Install [node](https://nodejs.org/en/download/). You can confirm node is installed with:
-```bash
-node --version
-```
-
-2. Install [pnpm](https://pnpm.io/) and confirm it is installed by running this:
-```bash
-npm install --global pnpm
-pnpm --version
-```
-
-From `invokeai/frontend/web/` run `pnpm install` to get everything set up.
-
-Start everything in dev mode:
-1. Ensure your virtual environment is running
-2. Start the dev server: `pnpm dev`
-3. Start the InvokeAI Nodes backend: `python scripts/invokeai-web.py # run from the repo root`
-4. Point your browser to the dev server address e.g. [http://localhost:5173/](http://localhost:5173/)
-
-### VSCode Remote Dev
-
-We've noticed an intermittent issue with the VSCode Remote Dev port forwarding. If you use this feature of VSCode, you may intermittently click the Invoke button and then get nothing until the request times out. Suggest disabling the IDE's port forwarding feature and doing it manually via SSH:
-
-`ssh -L 9090:localhost:9090 -L 5173:localhost:5173 user@host`
-
-### Production builds
-
-For a number of technical and logistical reasons, we need to commit UI build artefacts to the repo.
-
-If you submit a PR, there is a good chance we will ask you to include a separate commit with a build of the app.
-
-To build for production, run `pnpm build`.

docs/contributing/contribution_guides/development.md

@@ -12,7 +12,7 @@ To get started, take a look at our [new contributors checklist](newContributorCh
 Once you're setup, for more information, you can review the documentation specific to your area of interest:
 
 * #### [InvokeAI Architecure](../ARCHITECTURE.md)
-* #### [Frontend Documentation](./contributingToFrontend.md)
+* #### [Frontend Documentation](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web)
 * #### [Node Documentation](../INVOCATIONS.md)
 * #### [Local Development](../LOCAL_DEVELOPMENT.md)
 

docs/features/CONTROLNET.md

@@ -94,6 +94,8 @@ A model that helps generate creative QR codes that still scan. Can also be used
 **Openpose**: 
 The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
 
+*Note:* The DWPose Processor has replaced the OpenPose processor in Invoke. Workflows and generations that relied on the OpenPose Processor will need to be updated to use the DWPose Processor instead.
+
 **Mediapipe Face**:
 
 The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.

docs/index.md

@@ -117,6 +117,11 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 
 ## :octicons-gift-24: InvokeAI Features
 
+### Installation
+  - [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
+  - [Manual Installation](installation/020_INSTALL_MANUAL.md)
+  - [Docker Installation](installation/040_INSTALL_DOCKER.md)
+
 ### The InvokeAI Web Interface
 - [WebUI overview](features/WEB.md)
 - [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)

docs/installation/010_INSTALL_AUTOMATED.md

@@ -477,7 +477,7 @@ Then type the following commands:
 
 === "AMD System"
     ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.6
     ```
 
 ### Corrupted configuration file

docs/installation/020_INSTALL_MANUAL.md

@@ -154,7 +154,7 @@ manager, please follow these steps:
     === "ROCm (AMD)"
 
         ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -230,13 +230,13 @@ manager, please follow these steps:
         === "local Webserver"
 
             ```bash
-            invokeai --web
+            invokeai-web
             ```
 
         === "Public Webserver"
 
             ```bash
-            invokeai --web --host 0.0.0.0
+            invokeai-web --host 0.0.0.0
             ```
 
         === "CLI"
@@ -313,7 +313,7 @@ code for InvokeAI. For this to work, you will need to install the
 on your system, please see the [Git Installation
 Guide](https://github.com/git-guides/install-git)
 
-You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md).
+You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md).
 
 If you have a "normal" installation, you should create a totally separate virtual environment for the git-based installation, else the two may interfere.
 
@@ -345,7 +345,7 @@ installation protocol (important!)
 
     === "ROCm (AMD)"
         ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -361,7 +361,7 @@ installation protocol (important!)
     Be sure to pass `-e` (for an editable install) and don't forget the
     dot ("."). It is part of the command.
 
-5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md) and do a production build of the UI as described.
+5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md) and do a production build of the UI as described.
 
 6.  You can now run `invokeai` and its related commands. The code will be
     read from the repository, so that you can edit the .py source files
@@ -402,4 +402,4 @@ environment variable INVOKEAI_ROOT to point to the installation directory.
 Note that if you run into problems with the Conda installation, the InvokeAI
 staff will **not** be able to help you out. Caveat Emptor!
 
-[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939
+[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -134,7 +134,7 @@ recipes are available
 
 When installing torch and torchvision manually with `pip`, remember to provide
 the argument `--extra-index-url
-https://download.pytorch.org/whl/rocm5.4.2` as described in the [Manual
+https://download.pytorch.org/whl/rocm5.6` as described in the [Manual
 Installation Guide](020_INSTALL_MANUAL.md).
 
 This will be done automatically for you if you use the installer

docs/installation/040_INSTALL_DOCKER.md

@@ -69,7 +69,7 @@ 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 up your environmnent variables. In the `docker` directory, make a copy of `.env.sample` and name it `.env`. Make changes as necessary.
 
 Any environment variables supported by InvokeAI can be set here - please see the [CONFIGURATION](../features/CONFIGURATION.md) for further detail.
 

docs/installation/INSTALLATION.md

@@ -18,13 +18,18 @@ either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
 driver).
 
 
-## **[Automated Installer](010_INSTALL_AUTOMATED.md)**
-✅ This is the recommended installation method for first-time users. 
+## **[Automated Installer (Recommended)](010_INSTALL_AUTOMATED.md)**
+ ✅ This is the recommended installation method for first-time users. 
 
   This is a script that will install all of InvokeAI's essential
-  third party libraries and InvokeAI itself. It includes access to a
-  "developer console" which will help us debug problems with you and
-  give you to access experimental features.
+  third party libraries and InvokeAI itself.
+
+🖥️ **Download the latest installer .zip file here** : https://github.com/invoke-ai/InvokeAI/releases/latest
+  
+- *Look for the file labelled "InvokeAI-installer-v3.X.X.zip" at the bottom of the page*
+- If you experience issues, read through the full [installation instructions](010_INSTALL_AUTOMATED.md) to make sure you have met all of the installation requirements. If you need more help, join the [Discord](discord.gg/invoke-ai) or create an issue on [Github](https://github.com/invoke-ai/InvokeAI).
+
+
 
 ## **[Manual Installation](020_INSTALL_MANUAL.md)**
 This method is recommended for experienced users and developers.

docs/nodes/communityNodes.md

@@ -14,6 +14,7 @@ To use a community workflow, download the the `.json` node graph file and load i
 
 - Community Nodes
     + [Adapters-Linked](#adapters-linked-nodes)
+    + [Autostereogram](#autostereogram-nodes)
     + [Average Images](#average-images)
     + [Clean Image Artifacts After Cut](#clean-image-artifacts-after-cut)
     + [Close Color Mask](#close-color-mask) 
@@ -25,7 +26,7 @@ To use a community workflow, download the the `.json` node graph file and load i
     + [GPT2RandomPromptMaker](#gpt2randompromptmaker)
     + [Grid to Gif](#grid-to-gif)
     + [Halftone](#halftone)
-    + [Ideal Size](#ideal-size)
+    + [Hand Refiner with MeshGraphormer](#hand-refiner-with-meshgraphormer)
     + [Image and Mask Composition Pack](#image-and-mask-composition-pack)
     + [Image Dominant Color](#image-dominant-color)
     + [Image to Character Art Image Nodes](#image-to-character-art-image-nodes)
@@ -41,6 +42,7 @@ To use a community workflow, download the the `.json` node graph file and load i
     + [Oobabooga](#oobabooga)
     + [Prompt Tools](#prompt-tools)
     + [Remote Image](#remote-image)
+    + [BriaAI Background Remove](#briaai-remove-background)
     + [Remove Background](#remove-background)    
     + [Retroize](#retroize)
     + [Size Stepper Nodes](#size-stepper-nodes)
@@ -67,6 +69,17 @@ Note: These are inherited from the core nodes so any update to the core nodes sh
 
 **Node Link:** https://github.com/skunkworxdark/adapters-linked-nodes
 
+--------------------------------
+### Autostereogram Nodes
+
+**Description:** Generate autostereogram images from a depth map. This is not a very practically useful node but more a 90s nostalgic indulgence as I used to love these images as a kid.
+
+**Node Link:** https://github.com/skunkworxdark/autostereogram_nodes
+
+**Example Usage:**
+</br>
+<img src="https://github.com/skunkworxdark/autostereogram_nodes/blob/main/images/spider.png" width="200" /> -> <img src="https://github.com/skunkworxdark/autostereogram_nodes/blob/main/images/spider-depth.png" width="200" /> -> <img src="https://github.com/skunkworxdark/autostereogram_nodes/raw/main/images/spider-dots.png" width="200" /> <img src="https://github.com/skunkworxdark/autostereogram_nodes/raw/main/images/spider-pattern.png" width="200" />
+
 --------------------------------
 ### Average Images
 
@@ -197,13 +210,18 @@ CMYK Halftone Output:
 <img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c59c578f-db8e-4d66-8c66-2851752d75ea" width="300" />
 
 --------------------------------
-### Ideal Size
 
-**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
+### Hand Refiner with MeshGraphormer
 
-**Node Link:** https://github.com/JPPhoto/ideal-size-node
+**Description**: Hand Refiner takes in your image and automatically generates a fixed depth map for the hands along with a mask of the hands region that will conveniently allow you to use them along with ControlNet to fix the wonky hands generated by Stable Diffusion
+
+**Node Link:** https://github.com/blessedcoolant/invoke_meshgraphormer
+
+**View**
+<img src="https://raw.githubusercontent.com/blessedcoolant/invoke_meshgraphormer/main/assets/preview.jpg" />
 
 --------------------------------
+
 ### Image and Mask Composition Pack
 
 **Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
@@ -417,6 +435,17 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 **Node Link:** https://github.com/fieldOfView/InvokeAI-remote_image
 
+--------------------------------
+
+### BriaAI Remove Background
+
+**Description**: Implements one click background removal with BriaAI's new version 1.4 model which seems to be be producing better results than any other previous background removal tool.
+
+**Node Link:** https://github.com/blessedcoolant/invoke_bria_rmbg
+
+**View**
+<img src="https://raw.githubusercontent.com/blessedcoolant/invoke_bria_rmbg/main/assets/preview.jpg" />
+
 --------------------------------
 ### Remove Background
 

docs/nodes/defaultNodes.md

@@ -36,6 +36,7 @@ their descriptions.
 | Integer Math                                                  | Perform basic math operations on two integers                                                                                                        |
 | Convert Image Mode                                            | Converts an image to a different mode.                                                                                                               |
 | Crop Image                                                    | Crops an image to a specified box. The box can be outside of the image.                                                                              |
+| Ideal Size                                                    | Calculates an ideal image size for latents for a first pass of a multi-pass upscaling to avoid duplication and other artifacts                       |
 | Image Hue Adjustment                                          | Adjusts the Hue of an image.                                                                                                                         |
 | Inverse Lerp Image                                            | Inverse linear interpolation of all pixels of an image                                                                                               |
 | Image Primitive                                               | An image primitive value                                                                                                                             |
@@ -80,7 +81,7 @@ their descriptions.
 | ONNX Text to Latents                                          | Generates latents from conditionings.                                                                                                                |
 | ONNX Model Loader                                             | Loads a main model, outputting its submodels.                                                                                                        |
 | OpenCV Inpaint                                                | Simple inpaint using opencv.                                                                                                                         |
-| Openpose Processor                                            | Applies Openpose processing to image                                                                                                                 |
+| DW Openpose Processor                                            | Applies Openpose processing to image                                                                                                                 |
 | PIDI Processor                                                | Applies PIDI processing to image                                                                                                                     |
 | Prompts from File                                             | Loads prompts from a text file                                                                                                                       |
 | Random Integer                                                | Outputs a single random integer.                                                                                                                     |

docs/other/CONTRIBUTORS.md

@@ -13,46 +13,69 @@ We thank them for all of their time and hard work.
 
 - [Lincoln D. Stein](mailto:lincoln.stein@gmail.com)
 
-## **Current core team**
+## **Current Core Team**
 
 * @lstein (Lincoln Stein) - Co-maintainer
 * @blessedcoolant - Co-maintainer
 * @hipsterusername (Kent Keirsey) - Co-maintainer, CEO, Positive Vibes
 * @psychedelicious (Spencer Mabrito) - Web Team Leader
-* @Kyle0654 (Kyle Schouviller) - Node Architect and General Backend Wizard
-* @damian0815 - Attention Systems and Compel Maintainer
-* @ebr (Eugene Brodsky) - Cloud/DevOps/Sofware engineer; your friendly neighbourhood cluster-autoscaler
-* @genomancer (Gregg Helt) - Controlnet support
-* @StAlKeR7779 (Sergey Borisov) - Torch stack, ONNX, model management, optimization
+* @chainchompa (Jennifer Player) - Web Development & Chain-Chomping
+* @josh is toast (Josh Corbett) - Web Development
 * @cheerio (Mary Rogers) - Lead Engineer & Web App Development
+* @ebr (Eugene Brodsky) - Cloud/DevOps/Sofware engineer; your friendly neighbourhood cluster-autoscaler
+* @sunija - Standalone version
+* @genomancer (Gregg Helt) - Controlnet support
 * @brandon (Brandon Rising) - Platform, Infrastructure, Backend Systems
 * @ryanjdick (Ryan Dick) - Machine Learning & Training
-* @millu (Millun Atluri) - Community Manager, Documentation, Node-wrangler
-* @chainchompa (Jennifer Player) - Web Development & Chain-Chomping
+* @JPPhoto - Core image generation nodes
+* @dunkeroni - Image generation backend
+* @SkunkWorxDark - Image generation backend
 * @keturn (Kevin Turner) - Diffusers
+* @millu (Millun Atluri) - Community Wizard, Documentation, Node-wrangler, 
+* @glimmerleaf (Devon Hopkins) - Community Wizard
 * @gogurt enjoyer - Discord moderator and end user support
 * @whosawhatsis - Discord moderator and end user support
 * @dwinrger - Discord moderator and end user support
 * @526christian - Discord moderator and end user support
+* @harvester62 -  Discord moderator and end user support
+
+
+## **Honored Team Alumni**
+
+* @StAlKeR7779 (Sergey Borisov) - Torch stack, ONNX, model management, optimization
+* @damian0815 - Attention Systems and Compel Maintainer
+* @netsvetaev (Artur) - Localization support
+* @Kyle0654 (Kyle Schouviller) - Node Architect and General Backend Wizard
+* @tildebyte - Installation and configuration
+* @mauwii (Matthias Wilde) - Installation, release, continuous integration
+
 
 ## **Full List of Contributors by Commit Name**
 
+- 이승석
 - AbdBarho
 - ablattmann
 - AdamOStark
 - Adam Rice
 - Airton Silva
+- Aldo Hoeben
 - Alexander Eichhorn
 - Alexandre D. Roberge
+- Alexandre Macabies
+- Alfie John
 - Andreas Rozek
 - Andre LaBranche
 - Andy Bearman
 - Andy Luhrs
 - Andy Pilate
+- Anonymous
+- Anthony Monthe
 - Any-Winter-4079
 - apolinario
+- Ar7ific1al
 - ArDiouscuros
 - Armando C. Santisbon
+- Arnold Cordewiner
 - Arthur Holstvoogd
 - artmen1516
 - Artur
@@ -64,13 +87,16 @@ We thank them for all of their time and hard work.
 - blhook
 - BlueAmulet
 - Bouncyknighter
+- Brandon
 - Brandon Rising
 - Brent Ozar
 - Brian Racer
 - bsilvereagle
 - c67e708d
+- camenduru
 - CapableWeb
 - Carson Katri
+- chainchompa
 - Chloe
 - Chris Dawson
 - Chris Hayes
@@ -86,30 +112,45 @@ We thank them for all of their time and hard work.
 - cpacker
 - Cragin Godley
 - creachec
+- CrypticWit
+- d8ahazard
+- damian
+- damian0815
+- Damian at mba
 - Damian Stewart
 - Daniel Manzke
 - Danny Beer
 - Dan Sully
+- Darren Ringer
 - David Burnett
 - David Ford
 - David Regla
+- David Sisco
 - David Wager
 - Daya Adianto
 - db3000
+- DekitaRPG
 - Denis Olshin
 - Dennis
+- dependabot[bot]
+- Dmitry Parnas
+- Dobrynia100
 - Dominic Letz
 - DrGunnarMallon
+- Drun555
+- dunkeroni
 - Edward Johan
 - elliotsayes
 - Elrik
 - ElrikUnderlake
 - Eric Khun
 - Eric Wolf
+- Eugene
 - Eugene Brodsky
 - ExperimentalCyborg
 - Fabian Bahl
 - Fabio 'MrWHO' Torchetti
+- Fattire
 - fattire
 - Felipe Nogueira
 - Félix Sanz
@@ -118,8 +159,12 @@ We thank them for all of their time and hard work.
 - gabrielrotbart
 - gallegonovato
 - Gérald LONLAS
+- Gille
 - GitHub Actions Bot
+- glibesyck
 - gogurtenjoyer
+- Gohsuke Shimada
+- greatwolf
 - greentext2
 - Gregg Helt
 - H4rk
@@ -131,6 +176,7 @@ We thank them for all of their time and hard work.
 - Hosted Weblate
 - Iman Karim
 - ismail ihsan bülbül
+- ItzAttila
 - Ivan Efimov
 - jakehl
 - Jakub Kolčář
@@ -141,6 +187,7 @@ We thank them for all of their time and hard work.
 - Jason Toffaletti
 - Jaulustus
 - Jeff Mahoney
+- Jennifer Player
 - jeremy
 - Jeremy Clark
 - JigenD
@@ -148,19 +195,26 @@ We thank them for all of their time and hard work.
 - Johan Roxendal
 - Johnathon Selstad
 - Jonathan
+- Jordan Hewitt
 - Joseph Dries III
+- Josh Corbett
 - JPPhoto
 - jspraul
+- junzi
 - Justin Wong
 - Juuso V
 - Kaspar Emanuel
 - Katsuyuki-Karasawa
+- Keerigan45
 - Kent Keirsey
+- Kevin Brack
 - Kevin Coakley
 - Kevin Gibbons
 - Kevin Schaul
 - Kevin Turner
+- Kieran Klaassen
 - krummrey
+- Kyle
 - Kyle Lacy
 - Kyle Schouviller
 - Lawrence Norton
@@ -171,10 +225,15 @@ We thank them for all of their time and hard work.
 - Lynne Whitehorn
 - majick
 - Marco Labarile
+- Marta Nahorniuk
 - Martin Kristiansen
+- Mary Hipp
+- maryhipp
 - Mary Hipp Rogers
+- mastercaster
 - mastercaster9000
 - Matthias Wild
+- mauwii
 - michaelk71
 - mickr777
 - Mihai
@@ -182,11 +241,15 @@ We thank them for all of their time and hard work.
 - Mikhail Tishin
 - Millun Atluri
 - Minjune Song
+- Mitchell Allain
 - mitien
 - mofuzz
 - Muhammad Usama
 - Name
 - _nderscore
+- Neil Wang
+- nekowaiz
+- nemuruibai
 - Netzer R
 - Nicholas Koh
 - Nicholas Körfer
@@ -197,9 +260,11 @@ We thank them for all of their time and hard work.
 - ofirkris
 - Olivier Louvignes
 - owenvincent
+- pand4z31
 - Patrick Esser
 - Patrick Tien
 - Patrick von Platen
+- Paul Curry
 - Paul Sajna
 - pejotr
 - Peter Baylies
@@ -207,6 +272,7 @@ We thank them for all of their time and hard work.
 - plucked
 - prixt
 - psychedelicious
+- psychedelicious@windows
 - Rainer Bernhardt
 - Riccardo Giovanetti
 - Rich Jones
@@ -215,17 +281,22 @@ We thank them for all of their time and hard work.
 - Robert Bolender
 - Robin Rombach
 - Rohan Barar
-- rohinish404
+- Rohinish
 - rpagliuca
 - rromb
 - Rupesh Sreeraman
+- Ryan
 - Ryan Cao
+- Ryan Dick
 - Saifeddine
 - Saifeddine ALOUI
+- Sam
 - SammCheese
+- Sam McLeod
 - Sammy
 - sammyf
 - Samuel Husso
+- Saurav Maheshkar
 - Scott Lahteine
 - Sean McLellan
 - Sebastian Aigner
@@ -233,16 +304,21 @@ We thank them for all of their time and hard work.
 - Sergey Krashevich
 - Shapor Naghibzadeh
 - Shawn Zhong
+- Simona Liliac
 - Simon Vans-Colina
 - skunkworxdark
 - slashtechno
+- SoheilRezaei
+- Song, Pengcheng
 - spezialspezial
 - ssantos
 - StAlKeR7779
+- Stefan Tobler
 - Stephan Koglin-Fischer
 - SteveCaruso
 - Steve Martinelli
 - Steven Frank
+- Surisen
 - System X - Files
 - Taylor Kems
 - techicode
@@ -261,26 +337,34 @@ We thank them for all of their time and hard work.
 - tyler
 - unknown
 - user1
+- vedant-3010
 - Vedant Madane
 - veprogames
 - wa.code
 - wfng92
+- whjms
 - whosawhatsis
 - Will
 - William Becher
 - William Chong
+- Wilson E. Alvarez
+- woweenie
+- Wubbbi
 - xra
 - Yeung Yiu Hung
 - ymgenesis
 - Yorzaren
 - Yosuke Shinya
 - yun saki
+- ZachNagengast
 - Zadagu
 - zeptofine
+- Zerdoumi
+- Васянатор
 - 冯不游
 - 唐澤 克幸
 
-## **Original CompVis Authors**
+## **Original CompVis (Stable Diffusion) Authors**
 
 - [Robin Rombach](https://github.com/rromb)
 - [Patrick von Platen](https://github.com/patrickvonplaten)

installer/create_installer.sh

@@ -14,11 +14,19 @@ function is_bin_in_path {
 }
 
 function git_show {
-    git show -s --format='%h %s' $1
+    git show -s --format=oneline --abbrev-commit "$1" | cat
 }
 
+if [[ -v "VIRTUAL_ENV" ]]; then
+    # we can't just call 'deactivate' because this function is not exported
+    # to the environment of this script from the bash process that runs the script
+    echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
+    exit -1
+fi
+
 cd "$(dirname "$0")"
 
+echo
 echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
 echo "The current working directory is $(pwd)"
 read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
@@ -32,13 +40,6 @@ if ! is_bin_in_path python && is_bin_in_path python3; then
     }
 fi
 
-if [[ -v "VIRTUAL_ENV" ]]; then
-    # we can't just call 'deactivate' because this function is not exported
-    # to the environment of this script from the bash process that runs the script
-    echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
-    exit -1
-fi
-
 VERSION=$(
     cd ..
     python -c "from invokeai.version import __version__ as version; print(version)"
@@ -47,38 +48,9 @@ PATCH=""
 VERSION="v${VERSION}${PATCH}"
 
 echo -e "${BGREEN}HEAD${RESET}:"
-git_show
+git_show HEAD
 echo
 
-# ---------------------- FRONTEND ----------------------
-
-pushd ../invokeai/frontend/web >/dev/null
-echo
-echo "Installing frontend dependencies..."
-echo
-pnpm i --frozen-lockfile
-echo
-echo "Building frontend..."
-echo
-pnpm build
-popd
-
-# ---------------------- BACKEND ----------------------
-
-echo
-echo "Building wheel..."
-echo
-
-# install the 'build' package in the user site packages, if needed
-# could be improved by using a temporary venv, but it's tiny and harmless
-if [[ $(python -c 'from importlib.util import find_spec; print(find_spec("build") is None)') == "True" ]]; then
-    pip install --user build
-fi
-
-rm -rf ../build
-
-python -m build --wheel --outdir dist/ ../.
-
 # ----------------------
 
 echo
@@ -97,16 +69,13 @@ done
 mkdir InvokeAI-Installer/lib
 cp lib/*.py InvokeAI-Installer/lib
 
-# Move the wheel
-mv dist/*.whl InvokeAI-Installer/lib/
-
 # Install scripts
 # Mac/Linux
 cp install.sh.in InvokeAI-Installer/install.sh
 chmod a+x InvokeAI-Installer/install.sh
 
 # Windows
-perl -p -e "s/^set INVOKEAI_VERSION=.*/set INVOKEAI_VERSION=$VERSION/" install.bat.in >InvokeAI-Installer/install.bat
+cp install.bat.in InvokeAI-Installer/install.bat
 cp WinLongPathsEnabled.reg InvokeAI-Installer/
 
 # Zip everything up

installer/install.bat.in

@@ -15,7 +15,6 @@ if "%1" == "use-cache" (
 @rem Config
 @rem The version in the next line is replaced by an up to date release number
 @rem when create_installer.sh is run. Change the release number there.
-set 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/

installer/lib/installer.py

@@ -11,7 +11,7 @@ import sys
 import venv
 from pathlib import Path
 from tempfile import TemporaryDirectory
-from typing import Union
+from typing import Optional, Tuple
 
 SUPPORTED_PYTHON = ">=3.10.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
@@ -21,40 +21,20 @@ OS = platform.uname().system
 ARCH = platform.uname().machine
 VERSION = "latest"
 
-### Feature flags
-# Install the virtualenv into the runtime dir
-FF_VENV_IN_RUNTIME = True
-
-# Install the wheel packaged with the installer
-FF_USE_LOCAL_WHEEL = True
-
 
 class Installer:
     """
     Deploys an InvokeAI installation into a given path
     """
 
+    reqs: list[str] = INSTALLER_REQS
+
     def __init__(self) -> None:
-        self.reqs = INSTALLER_REQS
-        self.preflight()
         if os.getenv("VIRTUAL_ENV") is not None:
             print("A virtual environment is already activated. Please 'deactivate' before installation.")
             sys.exit(-1)
         self.bootstrap()
-
-    def preflight(self) -> None:
-        """
-        Preflight checks
-        """
-
-        # TODO
-        # verify python version
-        # on macOS verify XCode tools are present
-        # verify libmesa, libglx on linux
-        # check that the system arch is not i386 (?)
-        # check that the system has a GPU, and the type of GPU
-
-        pass
+        self.available_releases = get_github_releases()
 
     def mktemp_venv(self) -> TemporaryDirectory:
         """
@@ -78,12 +58,9 @@ class Installer:
 
         return venv_dir
 
-    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory:
+    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory | None:
         """
         Bootstrap the installer venv with packages required at install time
-
-        :return: path to the virtual environment directory that was bootstrapped
-        :rtype: TemporaryDirectory
         """
 
         print("Initializing the installer. This may take a minute - please wait...")
@@ -95,39 +72,27 @@ class Installer:
         cmd.extend(self.reqs)
 
         try:
-            res = subprocess.check_output(cmd).decode()
+            # upgrade pip to the latest version to avoid a confusing message
+            res = upgrade_pip(Path(venv_dir.name))
             if verbose:
                 print(res)
+
+            # run the install prerequisites installation
+            res = subprocess.check_output(cmd).decode()
+
+            if verbose:
+                print(res)
+
             return venv_dir
         except subprocess.CalledProcessError as e:
             print(e)
 
-    def app_venv(self, path: str = None):
+    def app_venv(self, venv_parent) -> Path:
         """
         Create a virtualenv for the InvokeAI installation
         """
 
-        # explicit venv location
-        # currently unused in normal operation
-        # useful for testing or special cases
-        if path is not None:
-            venv_dir = Path(path)
-
-        # experimental / testing
-        elif not FF_VENV_IN_RUNTIME:
-            if OS == "Windows":
-                venv_dir_parent = os.getenv("APPDATA", "~/AppData/Roaming")
-            elif OS == "Darwin":
-                # there is no environment variable on macOS to find this
-                # TODO: confirm this is working as expected
-                venv_dir_parent = "~/Library/Application Support"
-            elif OS == "Linux":
-                venv_dir_parent = os.getenv("XDG_DATA_DIR", "~/.local/share")
-            venv_dir = Path(venv_dir_parent).expanduser().resolve() / f"InvokeAI/{VERSION}/venv"
-
-        # stable / current
-        else:
-            venv_dir = self.dest / ".venv"
+        venv_dir = venv_parent / ".venv"
 
         # Prefer to copy python executables
         # so that updates to system python don't break InvokeAI
@@ -141,7 +106,7 @@ class Installer:
         return venv_dir
 
     def install(
-        self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None
+        self, version=None, root: str = "~/invokeai", yes_to_all=False, find_links: Optional[Path] = None
     ) -> None:
         """
         Install the InvokeAI application into the given runtime path
@@ -158,15 +123,20 @@ class Installer:
 
         import messages
 
-        messages.welcome()
+        messages.welcome(self.available_releases)
 
-        default_path = os.environ.get("INVOKEAI_ROOT") or Path(root).expanduser().resolve()
-        self.dest = default_path if yes_to_all else messages.dest_path(root)
+        version = messages.choose_version(self.available_releases)
+
+        auto_dest = Path(os.environ.get("INVOKEAI_ROOT", root)).expanduser().resolve()
+        destination = auto_dest if yes_to_all else messages.dest_path(root)
+        if destination is None:
+            print("Could not find or create the destination directory. Installation cancelled.")
+            sys.exit(0)
 
         # create the venv for the app
-        self.venv = self.app_venv()
+        self.venv = self.app_venv(venv_parent=destination)
 
-        self.instance = InvokeAiInstance(runtime=self.dest, venv=self.venv, version=version)
+        self.instance = InvokeAiInstance(runtime=destination, venv=self.venv, version=version)
 
         # install dependencies and the InvokeAI application
         (extra_index_url, optional_modules) = get_torch_source() if not yes_to_all else (None, None)
@@ -190,7 +160,7 @@ class InvokeAiInstance:
     A single runtime directory *may* be shared by multiple virtual environments, though this isn't currently tested or supported.
     """
 
-    def __init__(self, runtime: Path, venv: Path, version: str) -> None:
+    def __init__(self, runtime: Path, venv: Path, version: str = "stable") -> None:
         self.runtime = runtime
         self.venv = venv
         self.pip = get_pip_from_venv(venv)
@@ -199,6 +169,7 @@ class InvokeAiInstance:
         set_sys_path(venv)
         os.environ["INVOKEAI_ROOT"] = str(self.runtime.expanduser().resolve())
         os.environ["VIRTUAL_ENV"] = str(self.venv.expanduser().resolve())
+        upgrade_pip(venv)
 
     def get(self) -> tuple[Path, Path]:
         """
@@ -212,54 +183,7 @@ class InvokeAiInstance:
 
     def install(self, extra_index_url=None, optional_modules=None, find_links=None):
         """
-        Install this instance, including dependencies and the app itself
-
-        :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
-        :type extra_index_url: str
-        """
-
-        import messages
-
-        # install torch first to ensure the correct version gets installed.
-        # works with either source or wheel install with negligible impact on installation times.
-        messages.simple_banner("Installing PyTorch :fire:")
-        self.install_torch(extra_index_url, find_links)
-
-        messages.simple_banner("Installing the InvokeAI Application :art:")
-        self.install_app(extra_index_url, optional_modules, find_links)
-
-    def install_torch(self, extra_index_url=None, find_links=None):
-        """
-        Install PyTorch
-        """
-
-        from plumbum import FG, local
-
-        pip = local[self.pip]
-
-        (
-            pip[
-                "install",
-                "--require-virtualenv",
-                "numpy==1.26.3",  # choose versions that won't be uninstalled during phase 2
-                "urllib3~=1.26.0",
-                "requests~=2.28.0",
-                "torch==2.1.2",
-                "torchmetrics==0.11.4",
-                "torchvision==0.16.2",
-                "--force-reinstall",
-                "--find-links" if find_links is not None else None,
-                find_links,
-                "--extra-index-url" if extra_index_url is not None else None,
-                extra_index_url,
-            ]
-            & FG
-        )
-
-    def install_app(self, extra_index_url=None, optional_modules=None, find_links=None):
-        """
-        Install the application with pip.
-        Supports installation from PyPi or from a local source directory.
+        Install the package from PyPi.
 
         :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
         :type extra_index_url: str
@@ -271,53 +195,52 @@ class InvokeAiInstance:
         :type find_links: Path
         """
 
-        ## this only applies to pypi installs; TODO actually use this
-        if self.version == "pre":
+        import messages
+
+        # not currently used, but may be useful for "install most recent version" option
+        if self.version == "prerelease":
             version = None
-            pre = "--pre"
+            pre_flag = "--pre"
+        elif self.version == "stable":
+            version = None
+            pre_flag = None
         else:
             version = self.version
-            pre = None
+            pre_flag = None
 
-        ## TODO: only local wheel will be installed as of now; support for --version arg is TODO
-        if FF_USE_LOCAL_WHEEL:
-            # if no wheel, try to do a source install before giving up
-            try:
-                src = str(next(Path(__file__).parent.glob("InvokeAI-*.whl")))
-            except StopIteration:
-                try:
-                    src = Path(__file__).parents[1].expanduser().resolve()
-                    # if the above directory contains one of these files, we'll do a source install
-                    next(src.glob("pyproject.toml"))
-                    next(src.glob("invokeai"))
-                except StopIteration:
-                    print("Unable to find a wheel or perform a source install. Giving up.")
+        src = "invokeai"
+        if optional_modules:
+            src += optional_modules
+        if version:
+            src += f"=={version}"
 
-        elif version == "source":
-            # this makes an assumption about the location of the installer package in the source tree
-            src = Path(__file__).parents[1].expanduser().resolve()
-        else:
-            # will install from PyPi
-            src = f"invokeai=={version}" if version is not None else "invokeai"
+        messages.simple_banner("Installing the InvokeAI Application :art:")
 
-        from plumbum import FG, local
+        from plumbum import FG, ProcessExecutionError, local  # type: ignore
 
         pip = local[self.pip]
 
-        (
-            pip[
-                "install",
-                "--require-virtualenv",
-                "--use-pep517",
-                str(src) + (optional_modules if optional_modules else ""),
-                "--find-links" if find_links is not None else None,
-                find_links,
-                "--extra-index-url" if extra_index_url is not None else None,
-                extra_index_url,
-                pre,
-            ]
-            & FG
-        )
+        pipeline = pip[
+            "install",
+            "--require-virtualenv",
+            "--force-reinstall",
+            "--use-pep517",
+            str(src),
+            "--find-links" if find_links is not None else None,
+            find_links,
+            "--extra-index-url" if extra_index_url is not None else None,
+            extra_index_url,
+            pre_flag,
+        ]
+
+        try:
+            _ = pipeline & FG
+        except ProcessExecutionError as e:
+            print(f"Error: {e}")
+            print(
+                "Could not install InvokeAI. Please try downloading the latest version of the installer and install again."
+            )
+            sys.exit(1)
 
     def configure(self):
         """
@@ -373,7 +296,6 @@ class InvokeAiInstance:
 
         ext = "bat" if OS == "Windows" else "sh"
 
-        # scripts = ['invoke', 'update']
         scripts = ["invoke"]
 
         for script in scripts:
@@ -408,6 +330,23 @@ def get_pip_from_venv(venv_path: Path) -> str:
     return str(venv_path.expanduser().resolve() / pip)
 
 
+def upgrade_pip(venv_path: Path) -> str | None:
+    """
+    Upgrade the pip executable in the given virtual environment
+    """
+
+    python = "Scripts\\python.exe" if OS == "Windows" else "bin/python"
+    python = str(venv_path.expanduser().resolve() / python)
+
+    try:
+        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode()
+    except subprocess.CalledProcessError as e:
+        print(e)
+        result = None
+
+    return result
+
+
 def set_sys_path(venv_path: Path) -> None:
     """
     Given a path to a virtual environment, set the sys.path, in a cross-platform fashion,
@@ -431,7 +370,43 @@ def set_sys_path(venv_path: Path) -> None:
     sys.path.append(str(Path(venv_path, lib, "site-packages").expanduser().resolve()))
 
 
-def get_torch_source() -> (Union[str, None], str):
+def get_github_releases() -> tuple[list, list] | None:
+    """
+    Query Github for published (pre-)release versions.
+    Return a tuple where the first element is a list of stable releases and the second element is a list of pre-releases.
+    Return None if the query fails for any reason.
+    """
+
+    import requests
+
+    ## get latest releases using github api
+    url = "https://api.github.com/repos/invoke-ai/InvokeAI/releases"
+    releases, pre_releases = [], []
+    try:
+        res = requests.get(url)
+        res.raise_for_status()
+        tag_info = res.json()
+        for tag in tag_info:
+            if not tag["prerelease"]:
+                releases.append(tag["tag_name"].lstrip("v"))
+            else:
+                pre_releases.append(tag["tag_name"].lstrip("v"))
+    except requests.HTTPError as e:
+        print(f"Error: {e}")
+        print("Could not fetch version information from GitHub. Please check your network connection and try again.")
+        return
+    except Exception as e:
+        print(f"Error: {e}")
+        print("An unexpected error occurred while trying to fetch version information from GitHub. Please try again.")
+        return
+
+    releases.sort(reverse=True)
+    pre_releases.sort(reverse=True)
+
+    return releases, pre_releases
+
+
+def get_torch_source() -> Tuple[str | None, str | None]:
     """
     Determine the extra index URL for pip to use for torch installation.
     This depends on the OS and the graphics accelerator in use.
@@ -446,25 +421,26 @@ def get_torch_source() -> (Union[str, None], str):
     :rtype: list
     """
 
-    from messages import graphical_accelerator
+    from messages import select_gpu
 
-    # device can be one of: "cuda", "rocm", "cpu", "idk"
-    device = graphical_accelerator()
+    # device can be one of: "cuda", "rocm", "cpu", "cuda_and_dml, autodetect"
+    device = select_gpu()
 
     url = None
     optional_modules = "[onnx]"
     if OS == "Linux":
-        if device == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.4.2"
-        elif device == "cpu":
+        if device.value == "rocm":
+            url = "https://download.pytorch.org/whl/rocm5.6"
+        elif device.value == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 
-    if device == "cuda":
-        url = "https://download.pytorch.org/whl/cu121"
-        optional_modules = "[xformers,onnx-cuda]"
-    if device == "cuda_and_dml":
-        url = "https://download.pytorch.org/whl/cu121"
-        optional_modules = "[xformers,onnx-directml]"
+    elif OS == "Windows":
+        if device.value == "cuda":
+            url = "https://download.pytorch.org/whl/cu121"
+            optional_modules = "[xformers,onnx-cuda]"
+        if device.value == "cuda_and_dml":
+            url = "https://download.pytorch.org/whl/cu121"
+            optional_modules = "[xformers,onnx-directml]"
 
     # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
 

installer/lib/messages.py

@@ -5,10 +5,11 @@ Installer user interaction
 
 import os
 import platform
+from enum import Enum
 from pathlib import Path
 
 from prompt_toolkit import HTML, prompt
-from prompt_toolkit.completion import PathCompleter
+from prompt_toolkit.completion import FuzzyWordCompleter, PathCompleter
 from prompt_toolkit.validation import Validator
 from rich import box, print
 from rich.console import Console, Group, group
@@ -35,16 +36,26 @@ else:
     console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
 
-def welcome():
+def welcome(available_releases: tuple | None = None) -> None:
     @group()
     def text():
-        if (platform_specific := _platform_specific_help()) != "":
+        if (platform_specific := _platform_specific_help()) is not None:
             yield platform_specific
             yield ""
         yield Text.from_markup(
             "Some of the installation steps take a long time to run. Please be patient. If the script appears to hang for more than 10 minutes, please interrupt with [i]Control-C[/] and retry.",
             justify="center",
         )
+        if available_releases is not None:
+            latest_stable = available_releases[0][0]
+            last_pre = available_releases[1][0]
+            yield ""
+            yield Text.from_markup(
+                f"[red3]🠶[/] Latest stable release (recommended): [b bright_white]{latest_stable}", justify="center"
+            )
+            yield Text.from_markup(
+                f"[red3]🠶[/] Last published pre-release version: [b bright_white]{last_pre}", justify="center"
+            )
 
     console.rule()
     print(
@@ -61,19 +72,30 @@ def welcome():
     console.line()
 
 
-def confirm_install(dest: Path) -> bool:
-    if dest.exists():
-        print(f":exclamation: Directory {dest} already exists :exclamation:")
-        dest_confirmed = Confirm.ask(
-            ":stop_sign: (re)install in this location?",
-            default=False,
-        )
-    else:
-        print(f"InvokeAI will be installed in {dest}")
-        dest_confirmed = Confirm.ask("Use this location?", default=True)
+def choose_version(available_releases: tuple | None = None) -> str:
+    """
+    Prompt the user to choose an Invoke version to install
+    """
+
+    # short circuit if we couldn't get a version list
+    # still try to install the latest stable version
+    if available_releases is None:
+        return "stable"
+
+    console.print(":grey_question: [orange3]Please choose an Invoke version to install.")
+
+    choices = available_releases[0] + available_releases[1]
+
+    response = prompt(
+        message=f"   <Enter> to install the recommended release ({choices[0]}). <Tab> or type to pick a version: ",
+        complete_while_typing=True,
+        completer=FuzzyWordCompleter(choices),
+    )
+    console.print(f"   Version {choices[0] if response == '' else response} will be installed.")
+
     console.line()
 
-    return dest_confirmed
+    return "stable" if response == "" else response
 
 
 def user_wants_auto_configuration() -> bool:
@@ -109,7 +131,23 @@ def user_wants_auto_configuration() -> bool:
     return choice.lower().startswith("a")
 
 
-def dest_path(dest=None) -> Path:
+def confirm_install(dest: Path) -> bool:
+    if dest.exists():
+        print(f":stop_sign: Directory {dest} already exists!")
+        print("   Is this location correct?")
+        default = False
+    else:
+        print(f":file_folder: InvokeAI will be installed in {dest}")
+        default = True
+
+    dest_confirmed = Confirm.ask("   Please confirm:", default=default)
+
+    console.line()
+
+    return dest_confirmed
+
+
+def dest_path(dest=None) -> Path | None:
     """
     Prompt the user for the destination path and create the path
 
@@ -124,25 +162,21 @@ def dest_path(dest=None) -> Path:
     else:
         dest = Path.cwd().expanduser().resolve()
     prev_dest = init_path = dest
-
-    dest_confirmed = confirm_install(dest)
+    dest_confirmed = False
 
     while not dest_confirmed:
-        # if the given destination already exists, the starting point for browsing is its parent directory.
-        # the user may have made a typo, or otherwise wants to place the root dir next to an existing one.
-        # if the destination dir does NOT exist, then the user must have changed their mind about the selection.
-        # since we can't read their mind, start browsing at Path.cwd().
-        browse_start = (prev_dest.parent if prev_dest.exists() else Path.cwd()).expanduser().resolve()
+        browse_start = (dest or Path.cwd()).expanduser().resolve()
 
         path_completer = PathCompleter(
             only_directories=True,
             expanduser=True,
-            get_paths=lambda: [browse_start],  # noqa: B023
+            get_paths=lambda: [str(browse_start)],  # noqa: B023
             # get_paths=lambda: [".."].extend(list(browse_start.iterdir()))
         )
 
         console.line()
-        console.print(f"[orange3]Please select the destination directory for the installation:[/] \\[{browse_start}]: ")
+
+        console.print(f":grey_question: [orange3]Please select the install destination:[/] \\[{browse_start}]: ")
         selected = prompt(
             ">>> ",
             complete_in_thread=True,
@@ -155,6 +189,7 @@ def dest_path(dest=None) -> Path:
         )
         prev_dest = dest
         dest = Path(selected)
+
         console.line()
 
         dest_confirmed = confirm_install(dest.expanduser().resolve())
@@ -182,41 +217,45 @@ def dest_path(dest=None) -> Path:
         console.rule("Goodbye!")
 
 
-def graphical_accelerator():
+class GpuType(Enum):
+    CUDA = "cuda"
+    CUDA_AND_DML = "cuda_and_dml"
+    ROCM = "rocm"
+    CPU = "cpu"
+    AUTODETECT = "autodetect"
+
+
+def select_gpu() -> GpuType:
     """
-    Prompt the user to select the graphical accelerator in their system
-    This does not validate user's choices (yet), but only offers choices
-    valid for the platform.
-    CUDA is the fallback.
-    We may be able to detect the GPU driver by shelling out to `modprobe` or `lspci`,
-    but this is not yet supported or reliable. Also, some users may have exotic preferences.
+    Prompt the user to select the GPU driver
     """
 
     if ARCH == "arm64" and OS != "Darwin":
         print(f"Only CPU acceleration is available on {ARCH} architecture. Proceeding with that.")
-        return "cpu"
+        return GpuType.CPU
 
     nvidia = (
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
-        "cuda",
+        GpuType.CUDA,
     )
     nvidia_with_dml = (
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™, and DirectML™ for ONNX) -- ALPHA",
-        "cuda_and_dml",
+        GpuType.CUDA_AND_DML,
     )
     amd = (
         "an [gold1 b]AMD[/] GPU (using ROCm™)",
-        "rocm",
+        GpuType.ROCM,
     )
     cpu = (
-        "no compatible GPU, or specifically prefer to use the CPU",
-        "cpu",
+        "Do not install any GPU support, use CPU for generation (slow)",
+        GpuType.CPU,
     )
-    idk = (
+    autodetect = (
         "I'm not sure what to choose",
-        "idk",
+        GpuType.AUTODETECT,
     )
 
+    options = []
     if OS == "Windows":
         options = [nvidia, nvidia_with_dml, cpu]
     if OS == "Linux":
@@ -230,7 +269,7 @@ def graphical_accelerator():
         return options[0][1]
 
     # "I don't know" is always added the last option
-    options.append(idk)
+    options.append(autodetect)  # type: ignore
 
     options = {str(i): opt for i, opt in enumerate(options, 1)}
 
@@ -265,9 +304,9 @@ def graphical_accelerator():
         ),
     )
 
-    if options[choice][1] == "idk":
+    if options[choice][1] is GpuType.AUTODETECT:
         console.print(
-            "No problem. We will try to install a version that [i]should[/i] be compatible. :crossed_fingers:"
+            "No problem. We will install CUDA support first :crossed_fingers: If Invoke does not detect a GPU, please re-run the installer and select one of the other GPU types."
         )
 
     return options[choice][1]
@@ -291,7 +330,7 @@ def windows_long_paths_registry() -> None:
     """
 
     with open(str(Path(__file__).parent / "WinLongPathsEnabled.reg"), "r", encoding="utf-16le") as code:
-        syntax = Syntax(code.read(), line_numbers=True)
+        syntax = Syntax(code.read(), line_numbers=True, lexer="regedit")
 
     console.print(
         Panel(
@@ -301,7 +340,7 @@ def windows_long_paths_registry() -> None:
                         "We will now apply a registry fix to enable long paths on Windows. InvokeAI needs this to function correctly. We are asking your permission to modify the Windows Registry on your behalf.",
                         "",
                         "This is the change that will be applied:",
-                        syntax,
+                        str(syntax),
                     ]
                 )
             ),
@@ -340,7 +379,7 @@ def introduction() -> None:
     console.line(2)
 
 
-def _platform_specific_help() -> str:
+def _platform_specific_help() -> Text | None:
     if OS == "Darwin":
         text = Text.from_markup(
             """[b wheat1]macOS Users![/]\n\nPlease be sure you have the [b wheat1]Xcode command-line tools[/] installed before continuing.\nIf not, cancel with [i]Control-C[/] and follow the Xcode install instructions at [deep_sky_blue1]https://www.freecodecamp.org/news/install-xcode-command-line-tools/[/]."""
@@ -354,5 +393,5 @@ def _platform_specific_help() -> str:
      [deep_sky_blue1]https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170[/]"""
         )
     else:
-        text = ""
+        return
     return text

installer/templates/invoke.bat.in

@@ -15,7 +15,7 @@ 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 8. Update InvokeAI (DEPRECATED - please use the installer)
 echo 9. Run the InvokeAI image database maintenance script
 echo 10. Command-line help
 echo Q - Quit
@@ -52,8 +52,10 @@ IF /I "%choice%" == "1" (
     echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
     call cmd /k
 ) ELSE IF /I "%choice%" == "8" (
-   echo Running invokeai-update...
-   python -m invokeai.frontend.install.invokeai_update
+    echo UPDATING FROM WITHIN THE APP IS BEING DEPRECATED.
+    echo Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.
+    timeout 4
+    python -m invokeai.frontend.install.invokeai_update
 ) ELSE IF /I "%choice%" == "9" (
    echo Running the db maintenance script...
    python .venv\Scripts\invokeai-db-maintenance.exe
@@ -77,4 +79,3 @@ pause
 
 :ending
 exit /b
-

installer/templates/invoke.sh.in

@@ -90,7 +90,9 @@ do_choice() {
         ;;
     8)
         clear
-        printf "Update InvokeAI\n"
+        printf "UPDATING FROM WITHIN THE APP IS BEING DEPRECATED\n"
+        printf "Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.\n"
+        sleep 4
         python -m invokeai.frontend.install.invokeai_update
         ;;
     9)
@@ -122,7 +124,7 @@ do_dialog() {
         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"
+        8 "Update InvokeAI (DEPRECATED - please use the installer)"
 	9 "Run the InvokeAI image database maintenance script"
 	10 "Command-line help"
     )

installer/templates/update.bat.in

@@ -1,72 +0,0 @@
-@echo off
-setlocal EnableExtensions EnableDelayedExpansion
-
-PUSHD "%~dp0"
-
-set INVOKE_AI_VERSION=latest
-set arg=%1
-if "%arg%" neq "" (
-   if "%arg:~0,2%" equ "/?" (
-       echo Usage: update.bat ^<release name or branch^>
-       echo Updates InvokeAI to use the indicated version of the code base.
-       echo Find the version or branch for the release you want, and pass it as the argument.
-       echo For example '.\update.bat v2.2.5' for release 2.2.5.
-       echo             '.\update.bat main' for the latest development version
-       echo.
-       echo If no argument provided then will install the most recent release, equivalent to
-       echo '.\update.bat latest'
-       exit /b
-   ) else (
-       set INVOKE_AI_VERSION=%arg%
-   )
-)
-
-set INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive/!INVOKE_AI_VERSION!.zip"
-set INVOKE_AI_DEP=https://raw.githubusercontent.com/invoke-ai/InvokeAI/!INVOKE_AI_VERSION!/environments-and-requirements/requirements-base.txt
-set INVOKE_AI_MODELS=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/configs/INITIAL_MODELS.yaml
-
-call curl -I "%INVOKE_AI_DEP%" -fs >.tmp.out
-if %errorlevel% neq 0 (
-    echo '!INVOKE_AI_VERSION!' is not a known branch name or tag. Please check the version and try again.
-    echo "Press any key to continue"
-    pause
-    exit /b
-)
-del .tmp.out
-
-echo This script will update InvokeAI and all its dependencies to !INVOKE_AI_SRC!.
-echo If you do not want to do this, press control-C now!
-pause
-
-call curl -L "%INVOKE_AI_DEP%" > environments-and-requirements/requirements-base.txt
-call curl -L "%INVOKE_AI_MODELS%" > configs/INITIAL_MODELS.yaml
-
-
-call .venv\Scripts\activate.bat
-call .venv\Scripts\python -mpip install -r requirements.txt
-if %errorlevel% neq 0 (
-   echo Installation of requirements failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-   pause
-   exit /b
-)
-
-call .venv\Scripts\python -mpip install !INVOKE_AI_SRC!
-if %errorlevel% neq 0 (
-   echo Installation of InvokeAI failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-   pause
-   exit /b
-)
-
-@rem call .venv\Scripts\invokeai-configure --root=.
-
-@rem if %errorlevel% neq 0 (
-@rem    echo Configuration InvokeAI failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
-@rem    pause
-@rem    exit /b
-@rem )
-
-echo InvokeAI has been updated to '%INVOKE_AI_VERSION%'
-
-echo "Press any key to continue"
-pause
-endlocal

installer/templates/update.sh.in

@@ -1,58 +0,0 @@
-#!/usr/bin/env bash
-
-set -eu
-
-if [ $# -ge 1 ] && [ "${1:0:2}" == "-h" ]; then
-    echo "Usage: update.sh <release>"
-    echo "Updates InvokeAI to use the indicated version of the code base."
-    echo "Find the version or branch for the release you want, and pass it as the argument."
-    echo "For example: update.sh v2.2.5 for release 2.2.5."
-    echo "             update.sh main for the current development version."
-    echo ""
-    echo "If no argument provided then will install the version tagged with 'latest', equivalent to"
-    echo "update.sh latest"
-    exit -1
-fi
-
-INVOKE_AI_VERSION=${1:-latest}
-
-INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive/$INVOKE_AI_VERSION.zip"
-INVOKE_AI_DEP=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/environments-and-requirements/requirements-base.txt
-INVOKE_AI_MODELS=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/configs/INITIAL_MODELS.yaml
-
-# ensure we're in the correct folder in case user's CWD is somewhere else
-scriptdir=$(dirname "$0")
-cd "$scriptdir"
-
-function _err_exit {
-    if test "$1" -ne 0
-    then
-	echo "Something went wrong while installing InvokeAI and/or its requirements."
-	echo "Update cannot continue. Please report this error to https://github.com/invoke-ai/InvokeAI/issues"
-        echo -e "Error code $1; Error caught was '$2'"
-        read -p "Press any key to exit..."
-        exit
-    fi
-}
-
-if ! curl -I "$INVOKE_AI_DEP" -fs >/dev/null; then
-    echo \'$INVOKE_AI_VERSION\' is not a known branch name or tag. Please check the version and try again.
-    exit
-fi
-
-echo This script will update InvokeAI and all its dependencies to version \'$INVOKE_AI_VERSION\'.
-echo If you do not want to do this, press control-C now!
-read -p "Press any key to continue, or CTRL-C to exit..."
-
-curl -L "$INVOKE_AI_DEP" > environments-and-requirements/requirements-base.txt
-curl -L "$INVOKE_AI_MODELS" > configs/INITIAL_MODELS.yaml
-
-. .venv/bin/activate
-
-./.venv/bin/python -mpip install -r requirements.txt
-_err_exit $? "The pip program failed to install InvokeAI's requirements."
-
-./.venv/bin/python -mpip install $INVOKE_AI_SRC
-_err_exit $? "The pip program failed to install InvokeAI."
-
-echo InvokeAI updated to \'$INVOKE_AI_VERSION\'

invokeai/app/api/dependencies.py

@@ -2,8 +2,13 @@
 
 from logging import Logger
 
+import torch
+
+from invokeai.app.services.item_storage.item_storage_memory import ItemStorageMemory
+from invokeai.app.services.object_serializer.object_serializer_disk import ObjectSerializerDisk
+from invokeai.app.services.object_serializer.object_serializer_forward_cache import ObjectSerializerForwardCache
 from invokeai.app.services.shared.sqlite.sqlite_util import init_db
-from invokeai.backend.model_manager.metadata import ModelMetadataStore
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
 
@@ -22,11 +27,8 @@ from ..services.invocation_queue.invocation_queue_memory import MemoryInvocation
 from ..services.invocation_services import InvocationServices
 from ..services.invocation_stats.invocation_stats_default import InvocationStatsService
 from ..services.invoker import Invoker
-from ..services.item_storage.item_storage_sqlite import SqliteItemStorage
-from ..services.latents_storage.latents_storage_disk import DiskLatentsStorage
-from ..services.latents_storage.latents_storage_forward_cache import ForwardCacheLatentsStorage
-from ..services.model_install import ModelInstallService
 from ..services.model_manager.model_manager_default import ModelManagerService
+from ..services.model_metadata import ModelMetadataStoreSQL
 from ..services.model_records import ModelRecordServiceSQL
 from ..services.names.names_default import SimpleNameService
 from ..services.session_processor.session_processor_default import DefaultSessionProcessor
@@ -68,6 +70,9 @@ class ApiDependencies:
         logger.debug(f"Internet connectivity is {config.internet_available}")
 
         output_folder = config.output_path
+        if output_folder is None:
+            raise ValueError("Output folder is not set")
+
         image_files = DiskImageFileStorage(f"{output_folder}/images")
 
         db = init_db(config=config, logger=logger, image_files=image_files)
@@ -80,21 +85,23 @@ class ApiDependencies:
         board_records = SqliteBoardRecordStorage(db=db)
         boards = BoardService()
         events = FastAPIEventService(event_handler_id)
-        graph_execution_manager = SqliteItemStorage[GraphExecutionState](db=db, table_name="graph_executions")
+        graph_execution_manager = ItemStorageMemory[GraphExecutionState]()
         image_records = SqliteImageRecordStorage(db=db)
         images = ImageService()
         invocation_cache = MemoryInvocationCache(max_cache_size=config.node_cache_size)
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
-        model_manager = ModelManagerService(config, logger)
-        model_record_service = ModelRecordServiceSQL(db=db)
+        tensors = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[torch.Tensor](output_folder / "tensors", ephemeral=True)
+        )
+        conditioning = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[ConditioningFieldData](output_folder / "conditioning", ephemeral=True)
+        )
         download_queue_service = DownloadQueueService(event_bus=events)
-        metadata_store = ModelMetadataStore(db=db)
-        model_install_service = ModelInstallService(
-            app_config=config,
-            record_store=model_record_service,
+        model_metadata_service = ModelMetadataStoreSQL(db=db)
+        model_manager = ModelManagerService.build_model_manager(
+            app_config=configuration,
+            model_record_service=ModelRecordServiceSQL(db=db, metadata_store=model_metadata_service),
             download_queue=download_queue_service,
-            metadata_store=metadata_store,
-            event_bus=events,
+            events=events,
         )
         names = SimpleNameService()
         performance_statistics = InvocationStatsService()
@@ -117,12 +124,9 @@ class ApiDependencies:
             image_records=image_records,
             images=images,
             invocation_cache=invocation_cache,
-            latents=latents,
             logger=logger,
             model_manager=model_manager,
-            model_records=model_record_service,
             download_queue=download_queue_service,
-            model_install=model_install_service,
             names=names,
             performance_statistics=performance_statistics,
             processor=processor,
@@ -131,6 +135,8 @@ class ApiDependencies:
             session_queue=session_queue,
             urls=urls,
             workflow_records=workflow_records,
+            tensors=tensors,
+            conditioning=conditioning,
         )
 
         ApiDependencies.invoker = Invoker(services)

invokeai/app/api/routers/download_queue.py

@@ -36,7 +36,7 @@ async def list_downloads() -> List[DownloadJob]:
         400: {"description": "Bad request"},
     },
 )
-async def prune_downloads():
+async def prune_downloads() -> Response:
     """Prune completed and errored jobs."""
     queue = ApiDependencies.invoker.services.download_queue
     queue.prune_jobs()
@@ -55,7 +55,7 @@ async def download(
 ) -> DownloadJob:
     """Download the source URL to the file or directory indicted in dest."""
     queue = ApiDependencies.invoker.services.download_queue
-    return queue.download(source, dest, priority, access_token)
+    return queue.download(source, Path(dest), priority, access_token)
 
 
 @download_queue_router.get(
@@ -87,7 +87,7 @@ async def get_download_job(
 )
 async def cancel_download_job(
     id: int = Path(description="ID of the download job to cancel."),
-):
+) -> Response:
     """Cancel a download job using its ID."""
     try:
         queue = ApiDependencies.invoker.services.download_queue
@@ -105,7 +105,7 @@ async def cancel_download_job(
         204: {"description": "Download jobs have been cancelled"},
     },
 )
-async def cancel_all_download_jobs():
+async def cancel_all_download_jobs() -> Response:
     """Cancel all download jobs."""
     ApiDependencies.invoker.services.download_queue.cancel_all_jobs()
     return Response(status_code=204)

invokeai/app/api/routers/images.py

@@ -8,7 +8,7 @@ from fastapi.routing import APIRouter
 from PIL import Image
 from pydantic import BaseModel, Field, ValidationError
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator
+from invokeai.app.invocations.fields import MetadataField, MetadataFieldValidator
 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

invokeai/app/api/routers/model_manager.py

@@ -0,0 +1,759 @@
+# Copyright (c) 2023 Lincoln D. Stein
+"""FastAPI route for model configuration records."""
+
+import pathlib
+import shutil
+from hashlib import sha1
+from random import randbytes
+from typing import Any, Dict, List, Optional, Set
+
+from fastapi import Body, Path, Query, Response
+from fastapi.routing import APIRouter
+from pydantic import BaseModel, ConfigDict
+from starlette.exceptions import HTTPException
+from typing_extensions import Annotated
+
+from invokeai.app.services.model_install import ModelInstallJob, ModelSource
+from invokeai.app.services.model_records import (
+    DuplicateModelException,
+    InvalidModelException,
+    ModelRecordOrderBy,
+    ModelSummary,
+    UnknownModelException,
+)
+from invokeai.app.services.shared.pagination import PaginatedResults
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    MainCheckpointConfig,
+    ModelFormat,
+    ModelType,
+    SubModelType,
+)
+from invokeai.backend.model_manager.merge import MergeInterpolationMethod, ModelMerger
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
+
+from ..dependencies import ApiDependencies
+
+model_manager_router = APIRouter(prefix="/v2/models", tags=["model_manager"])
+
+
+class ModelsList(BaseModel):
+    """Return list of configs."""
+
+    models: List[AnyModelConfig]
+
+    model_config = ConfigDict(use_enum_values=True)
+
+
+class ModelTagSet(BaseModel):
+    """Return tags for a set of models."""
+
+    key: str
+    name: str
+    author: str
+    tags: Set[str]
+
+
+##############################################################################
+# These are example inputs and outputs that are used in places where Swagger
+# is unable to generate a correct example.
+##############################################################################
+example_model_config = {
+    "path": "string",
+    "name": "string",
+    "base": "sd-1",
+    "type": "main",
+    "format": "checkpoint",
+    "config": "string",
+    "key": "string",
+    "original_hash": "string",
+    "current_hash": "string",
+    "description": "string",
+    "source": "string",
+    "last_modified": 0,
+    "vae": "string",
+    "variant": "normal",
+    "prediction_type": "epsilon",
+    "repo_variant": "fp16",
+    "upcast_attention": False,
+    "ztsnr_training": False,
+}
+
+example_model_input = {
+    "path": "/path/to/model",
+    "name": "model_name",
+    "base": "sd-1",
+    "type": "main",
+    "format": "checkpoint",
+    "config": "configs/stable-diffusion/v1-inference.yaml",
+    "description": "Model description",
+    "vae": None,
+    "variant": "normal",
+}
+
+example_model_metadata = {
+    "name": "ip_adapter_sd_image_encoder",
+    "author": "InvokeAI",
+    "tags": [
+        "transformers",
+        "safetensors",
+        "clip_vision_model",
+        "endpoints_compatible",
+        "region:us",
+        "has_space",
+        "license:apache-2.0",
+    ],
+    "files": [
+        {
+            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/README.md",
+            "path": "ip_adapter_sd_image_encoder/README.md",
+            "size": 628,
+            "sha256": None,
+        },
+        {
+            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/config.json",
+            "path": "ip_adapter_sd_image_encoder/config.json",
+            "size": 560,
+            "sha256": None,
+        },
+        {
+            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/model.safetensors",
+            "path": "ip_adapter_sd_image_encoder/model.safetensors",
+            "size": 2528373448,
+            "sha256": "6ca9667da1ca9e0b0f75e46bb030f7e011f44f86cbfb8d5a36590fcd7507b030",
+        },
+    ],
+    "type": "huggingface",
+    "id": "InvokeAI/ip_adapter_sd_image_encoder",
+    "tag_dict": {"license": "apache-2.0"},
+    "last_modified": "2023-09-23T17:33:25Z",
+}
+
+##############################################################################
+# ROUTES
+##############################################################################
+
+
+@model_manager_router.get(
+    "/",
+    operation_id="list_model_records",
+)
+async def list_model_records(
+    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
+    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
+    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
+    model_format: Optional[ModelFormat] = Query(
+        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
+    ),
+) -> ModelsList:
+    """Get a list of models."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    found_models: list[AnyModelConfig] = []
+    if base_models:
+        for base_model in base_models:
+            found_models.extend(
+                record_store.search_by_attr(
+                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
+                )
+            )
+    else:
+        found_models.extend(
+            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
+        )
+    return ModelsList(models=found_models)
+
+
+@model_manager_router.get(
+    "/i/{key}",
+    operation_id="get_model_record",
+    responses={
+        200: {
+            "description": "The model configuration was retrieved successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+    },
+)
+async def get_model_record(
+    key: str = Path(description="Key of the model record to fetch."),
+) -> AnyModelConfig:
+    """Get a model record"""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    try:
+        config: AnyModelConfig = record_store.get_model(key)
+        return config
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.get("/summary", operation_id="list_model_summary")
+async def list_model_summary(
+    page: int = Query(default=0, description="The page to get"),
+    per_page: int = Query(default=10, description="The number of models per page"),
+    order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
+) -> PaginatedResults[ModelSummary]:
+    """Gets a page of model summary data."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    results: PaginatedResults[ModelSummary] = record_store.list_models(page=page, per_page=per_page, order_by=order_by)
+    return results
+
+
+@model_manager_router.get(
+    "/meta/i/{key}",
+    operation_id="get_model_metadata",
+    responses={
+        200: {
+            "description": "The model metadata was retrieved successfully",
+            "content": {"application/json": {"example": example_model_metadata}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "No metadata available"},
+    },
+)
+async def get_model_metadata(
+    key: str = Path(description="Key of the model repo metadata to fetch."),
+) -> Optional[AnyModelRepoMetadata]:
+    """Get a model metadata object."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    result: Optional[AnyModelRepoMetadata] = record_store.get_metadata(key)
+    if not result:
+        raise HTTPException(status_code=404, detail="No metadata for a model with this key")
+    return result
+
+
+@model_manager_router.get(
+    "/tags",
+    operation_id="list_tags",
+)
+async def list_tags() -> Set[str]:
+    """Get a unique set of all the model tags."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    result: Set[str] = record_store.list_tags()
+    return result
+
+
+@model_manager_router.get(
+    "/tags/search",
+    operation_id="search_by_metadata_tags",
+)
+async def search_by_metadata_tags(
+    tags: Set[str] = Query(default=None, description="Tags to search for"),
+) -> ModelsList:
+    """Get a list of models."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    results = record_store.search_by_metadata_tag(tags)
+    return ModelsList(models=results)
+
+
+@model_manager_router.patch(
+    "/i/{key}",
+    operation_id="update_model_record",
+    responses={
+        200: {
+            "description": "The model was updated successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+        409: {"description": "There is already a model corresponding to the new name"},
+    },
+    status_code=200,
+)
+async def update_model_record(
+    key: Annotated[str, Path(description="Unique key of model")],
+    info: Annotated[
+        AnyModelConfig, Body(description="Model config", discriminator="type", example=example_model_input)
+    ],
+) -> AnyModelConfig:
+    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
+    logger = ApiDependencies.invoker.services.logger
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    try:
+        model_response: AnyModelConfig = record_store.update_model(key, config=info)
+        logger.info(f"Updated model: {key}")
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return model_response
+
+
+@model_manager_router.delete(
+    "/i/{key}",
+    operation_id="del_model_record",
+    responses={
+        204: {"description": "Model deleted successfully"},
+        404: {"description": "Model not found"},
+    },
+    status_code=204,
+)
+async def del_model_record(
+    key: str = Path(description="Unique key of model to remove from model registry."),
+) -> Response:
+    """
+    Delete model record from database.
+
+    The configuration record will be removed. The corresponding weights files will be
+    deleted as well if they reside within the InvokeAI "models" directory.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        installer.delete(key)
+        logger.info(f"Deleted model: {key}")
+        return Response(status_code=204)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.post(
+    "/i/",
+    operation_id="add_model_record",
+    responses={
+        201: {
+            "description": "The model added successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+        415: {"description": "Unrecognized file/folder format"},
+    },
+    status_code=201,
+)
+async def add_model_record(
+    config: Annotated[
+        AnyModelConfig, Body(description="Model config", discriminator="type", example=example_model_input)
+    ],
+) -> AnyModelConfig:
+    """Add a model using the configuration information appropriate for its type."""
+    logger = ApiDependencies.invoker.services.logger
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    if config.key == "<NOKEY>":
+        config.key = sha1(randbytes(100)).hexdigest()
+        logger.info(f"Created model {config.key} for {config.name}")
+    try:
+        record_store.add_model(config.key, config)
+    except DuplicateModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+
+    # now fetch it out
+    result: AnyModelConfig = record_store.get_model(config.key)
+    return result
+
+
+@model_manager_router.post(
+    "/heuristic_import",
+    operation_id="heuristic_import_model",
+    responses={
+        201: {"description": "The model imported successfully"},
+        415: {"description": "Unrecognized file/folder format"},
+        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+    },
+    status_code=201,
+)
+async def heuristic_import(
+    source: str,
+    config: Optional[Dict[str, Any]] = Body(
+        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
+        default=None,
+        example={"name": "modelT", "description": "antique cars"},
+    ),
+    access_token: Optional[str] = None,
+) -> ModelInstallJob:
+    """Install a model using a string identifier.
+
+    `source` can be any of the following.
+
+    1. A path on the local filesystem ('C:\\users\\fred\\model.safetensors')
+    2. A Url pointing to a single downloadable model file
+    3. A HuggingFace repo_id with any of the following formats:
+       - model/name
+       - model/name:fp16:vae
+       - model/name::vae          -- use default precision
+       - model/name:fp16:path/to/model.safetensors
+       - model/name::path/to/model.safetensors
+
+    `config` is an optional dict containing model configuration values that will override
+    the ones that are probed automatically.
+
+    `access_token` is an optional access token for use with Urls that require
+    authentication.
+
+    Models will be downloaded, probed, configured and installed in a
+    series of background threads. The return object has `status` attribute
+    that can be used to monitor progress.
+
+    See the documentation for `import_model_record` for more information on
+    interpreting the job information returned by this route.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        result: ModelInstallJob = installer.heuristic_import(
+            source=source,
+            config=config,
+        )
+        logger.info(f"Started installation of {source}")
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return result
+
+
+@model_manager_router.post(
+    "/install",
+    operation_id="import_model",
+    responses={
+        201: {"description": "The model imported successfully"},
+        415: {"description": "Unrecognized file/folder format"},
+        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+    },
+    status_code=201,
+)
+async def import_model(
+    source: ModelSource,
+    config: Optional[Dict[str, Any]] = Body(
+        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
+        default=None,
+    ),
+) -> ModelInstallJob:
+    """Install a model using its local path, repo_id, or remote URL.
+
+    Models will be downloaded, probed, configured and installed in a
+    series of background threads. The return object has `status` attribute
+    that can be used to monitor progress.
+
+    The source object is a discriminated Union of LocalModelSource,
+    HFModelSource and URLModelSource. Set the "type" field to the
+    appropriate value:
+
+    * To install a local path using LocalModelSource, pass a source of form:
+      ```
+      {
+        "type": "local",
+        "path": "/path/to/model",
+        "inplace": false
+      }
+      ```
+      The "inplace" flag, if true, will register the model in place in its
+      current filesystem location. Otherwise, the model will be copied
+      into the InvokeAI models directory.
+
+    * To install a HuggingFace repo_id using HFModelSource, pass a source of form:
+      ```
+      {
+        "type": "hf",
+        "repo_id": "stabilityai/stable-diffusion-2.0",
+        "variant": "fp16",
+        "subfolder": "vae",
+        "access_token": "f5820a918aaf01"
+      }
+      ```
+      The `variant`, `subfolder` and `access_token` fields are optional.
+
+    * To install a remote model using an arbitrary URL, pass:
+      ```
+      {
+        "type": "url",
+        "url": "http://www.civitai.com/models/123456",
+        "access_token": "f5820a918aaf01"
+      }
+      ```
+      The `access_token` field is optonal
+
+    The model's configuration record will be probed and filled in
+    automatically.  To override the default guesses, pass "metadata"
+    with a Dict containing the attributes you wish to override.
+
+    Installation occurs in the background. Either use list_model_install_jobs()
+    to poll for completion, or listen on the event bus for the following events:
+
+      * "model_install_running"
+      * "model_install_completed"
+      * "model_install_error"
+
+    On successful completion, the event's payload will contain the field "key"
+    containing the installed ID of the model. On an error, the event's payload
+    will contain the fields "error_type" and "error" describing the nature of the
+    error and its traceback, respectively.
+
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        result: ModelInstallJob = installer.import_model(
+            source=source,
+            config=config,
+        )
+        logger.info(f"Started installation of {source}")
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return result
+
+
+@model_manager_router.get(
+    "/import",
+    operation_id="list_model_install_jobs",
+)
+async def list_model_install_jobs() -> List[ModelInstallJob]:
+    """Return the list of model install jobs.
+
+    Install jobs have a numeric `id`, a `status`, and other fields that provide information on
+    the nature of the job and its progress. The `status` is one of:
+
+    * "waiting" -- Job is waiting in the queue to run
+    * "downloading" -- Model file(s) are downloading
+    * "running" -- Model has downloaded and the model probing and registration process is running
+    * "completed" -- Installation completed successfully
+    * "error" -- An error occurred. Details will be in the "error_type" and "error" fields.
+    * "cancelled" -- Job was cancelled before completion.
+
+    Once completed, information about the model such as its size, base
+    model, type, and metadata can be retrieved from the `config_out`
+    field. For multi-file models such as diffusers, information on individual files
+    can be retrieved from `download_parts`.
+
+    See the example and schema below for more information.
+    """
+    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_manager.install.list_jobs()
+    return jobs
+
+
+@model_manager_router.get(
+    "/import/{id}",
+    operation_id="get_model_install_job",
+    responses={
+        200: {"description": "Success"},
+        404: {"description": "No such job"},
+    },
+)
+async def get_model_install_job(id: int = Path(description="Model install id")) -> ModelInstallJob:
+    """
+    Return model install job corresponding to the given source. See the documentation for 'List Model Install Jobs'
+    for information on the format of the return value.
+    """
+    try:
+        result: ModelInstallJob = ApiDependencies.invoker.services.model_manager.install.get_job_by_id(id)
+        return result
+    except ValueError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.delete(
+    "/import/{id}",
+    operation_id="cancel_model_install_job",
+    responses={
+        201: {"description": "The job was cancelled successfully"},
+        415: {"description": "No such job"},
+    },
+    status_code=201,
+)
+async def cancel_model_install_job(id: int = Path(description="Model install job ID")) -> None:
+    """Cancel the model install job(s) corresponding to the given job ID."""
+    installer = ApiDependencies.invoker.services.model_manager.install
+    try:
+        job = installer.get_job_by_id(id)
+    except ValueError as e:
+        raise HTTPException(status_code=415, detail=str(e))
+    installer.cancel_job(job)
+
+
+@model_manager_router.patch(
+    "/import",
+    operation_id="prune_model_install_jobs",
+    responses={
+        204: {"description": "All completed and errored jobs have been pruned"},
+        400: {"description": "Bad request"},
+    },
+)
+async def prune_model_install_jobs() -> Response:
+    """Prune all completed and errored jobs from the install job list."""
+    ApiDependencies.invoker.services.model_manager.install.prune_jobs()
+    return Response(status_code=204)
+
+
+@model_manager_router.patch(
+    "/sync",
+    operation_id="sync_models_to_config",
+    responses={
+        204: {"description": "Model config record database resynced with files on disk"},
+        400: {"description": "Bad request"},
+    },
+)
+async def sync_models_to_config() -> Response:
+    """
+    Traverse the models and autoimport directories.
+
+    Model files without a corresponding
+    record in the database are added. Orphan records without a models file are deleted.
+    """
+    ApiDependencies.invoker.services.model_manager.install.sync_to_config()
+    return Response(status_code=204)
+
+
+@model_manager_router.put(
+    "/convert/{key}",
+    operation_id="convert_model",
+    responses={
+        200: {
+            "description": "Model converted successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "Model not found"},
+        409: {"description": "There is already a model registered at this location"},
+    },
+)
+async def convert_model(
+    key: str = Path(description="Unique key of the safetensors main model to convert to diffusers format."),
+) -> AnyModelConfig:
+    """
+    Permanently convert a model into diffusers format, replacing the safetensors version.
+    Note that during the conversion process the key and model hash will change.
+    The return value is the model configuration for the converted model.
+    """
+    logger = ApiDependencies.invoker.services.logger
+    loader = ApiDependencies.invoker.services.model_manager.load
+    store = ApiDependencies.invoker.services.model_manager.store
+    installer = ApiDependencies.invoker.services.model_manager.install
+
+    try:
+        model_config = store.get_model(key)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+
+    if not isinstance(model_config, MainCheckpointConfig):
+        logger.error(f"The model with key {key} is not a main checkpoint model.")
+        raise HTTPException(400, f"The model with key {key} is not a main checkpoint model.")
+
+    # loading the model will convert it into a cached diffusers file
+    loader.load_model_by_config(model_config, submodel_type=SubModelType.Scheduler)
+
+    # Get the path of the converted model from the loader
+    cache_path = loader.convert_cache.cache_path(key)
+    assert cache_path.exists()
+
+    # temporarily rename the original safetensors file so that there is no naming conflict
+    original_name = model_config.name
+    model_config.name = f"{original_name}.DELETE"
+    store.update_model(key, config=model_config)
+
+    # install the diffusers
+    try:
+        new_key = installer.install_path(
+            cache_path,
+            config={
+                "name": original_name,
+                "description": model_config.description,
+                "original_hash": model_config.original_hash,
+                "source": model_config.source,
+            },
+        )
+    except DuplicateModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+
+    # get the original metadata
+    if orig_metadata := store.get_metadata(key):
+        store.metadata_store.add_metadata(new_key, orig_metadata)
+
+    # delete the original safetensors file
+    installer.delete(key)
+
+    # delete the cached version
+    shutil.rmtree(cache_path)
+
+    # return the config record for the new diffusers directory
+    new_config: AnyModelConfig = store.get_model(new_key)
+    return new_config
+
+
+@model_manager_router.put(
+    "/merge",
+    operation_id="merge",
+    responses={
+        200: {
+            "description": "Model converted successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "Model not found"},
+        409: {"description": "There is already a model registered at this location"},
+    },
+)
+async def merge(
+    keys: List[str] = Body(description="Keys for two to three models to merge", min_length=2, max_length=3),
+    merged_model_name: Optional[str] = Body(description="Name of destination model", default=None),
+    alpha: float = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
+    force: bool = Body(
+        description="Force merging of models created with different versions of diffusers",
+        default=False,
+    ),
+    interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method", default=None),
+    merge_dest_directory: Optional[str] = Body(
+        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
+        default=None,
+    ),
+) -> AnyModelConfig:
+    """
+    Merge diffusers models. The process is controlled by a set parameters provided in the body of the request.
+    ```
+    Argument                Description [default]
+    --------               ----------------------
+    keys                   List of 2-3 model keys to merge together. All models must use the same base type.
+    merged_model_name      Name for the merged model [Concat model names]
+    alpha                  Alpha value (0.0-1.0). Higher values give more weight to the second model [0.5]
+    force                  If true, force the merge even if the models were generated by different versions of the diffusers library [False]
+    interp                 Interpolation method. One of "weighted_sum", "sigmoid", "inv_sigmoid" or "add_difference" [weighted_sum]
+    merge_dest_directory   Specify a directory to store the merged model in [models directory]
+    ```
+    """
+    logger = ApiDependencies.invoker.services.logger
+    try:
+        logger.info(f"Merging models: {keys} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
+        dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
+        installer = ApiDependencies.invoker.services.model_manager.install
+        merger = ModelMerger(installer)
+        model_names = [installer.record_store.get_model(x).name for x in keys]
+        response = merger.merge_diffusion_models_and_save(
+            model_keys=keys,
+            merged_model_name=merged_model_name or "+".join(model_names),
+            alpha=alpha,
+            interp=interp,
+            force=force,
+            merge_dest_directory=dest,
+        )
+    except UnknownModelException:
+        raise HTTPException(
+            status_code=404,
+            detail=f"One or more of the models '{keys}' not found",
+        )
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    return response

invokeai/app/api/routers/model_records.py

@@ -1,417 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein
-"""FastAPI route for model configuration records."""
-
-
-from hashlib import sha1
-from random import randbytes
-from typing import Any, Dict, List, Optional, Set
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, ConfigDict
-from starlette.exceptions import HTTPException
-from typing_extensions import Annotated
-
-from invokeai.app.services.model_install import ModelInstallJob, ModelSource
-from invokeai.app.services.model_records import (
-    DuplicateModelException,
-    InvalidModelException,
-    ModelRecordOrderBy,
-    ModelSummary,
-    UnknownModelException,
-)
-from invokeai.app.services.shared.pagination import PaginatedResults
-from invokeai.backend.model_manager.config import (
-    AnyModelConfig,
-    BaseModelType,
-    ModelFormat,
-    ModelType,
-)
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-from ..dependencies import ApiDependencies
-
-model_records_router = APIRouter(prefix="/v1/model/record", tags=["model_manager_v2_unstable"])
-
-
-class ModelsList(BaseModel):
-    """Return list of configs."""
-
-    models: List[AnyModelConfig]
-
-    model_config = ConfigDict(use_enum_values=True)
-
-
-class ModelTagSet(BaseModel):
-    """Return tags for a set of models."""
-
-    key: str
-    name: str
-    author: str
-    tags: Set[str]
-
-
-@model_records_router.get(
-    "/",
-    operation_id="list_model_records",
-)
-async def list_model_records(
-    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
-    model_format: Optional[ModelFormat] = Query(
-        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
-    ),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_records
-    found_models: list[AnyModelConfig] = []
-    if base_models:
-        for base_model in base_models:
-            found_models.extend(
-                record_store.search_by_attr(
-                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
-                )
-            )
-    else:
-        found_models.extend(
-            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
-        )
-    return ModelsList(models=found_models)
-
-
-@model_records_router.get(
-    "/i/{key}",
-    operation_id="get_model_record",
-    responses={
-        200: {"description": "Success"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-    },
-)
-async def get_model_record(
-    key: str = Path(description="Key of the model record to fetch."),
-) -> AnyModelConfig:
-    """Get a model record"""
-    record_store = ApiDependencies.invoker.services.model_records
-    try:
-        return record_store.get_model(key)
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.get("/meta", operation_id="list_model_summary")
-async def list_model_summary(
-    page: int = Query(default=0, description="The page to get"),
-    per_page: int = Query(default=10, description="The number of models per page"),
-    order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
-) -> PaginatedResults[ModelSummary]:
-    """Gets a page of model summary data."""
-    return ApiDependencies.invoker.services.model_records.list_models(page=page, per_page=per_page, order_by=order_by)
-
-
-@model_records_router.get(
-    "/meta/i/{key}",
-    operation_id="get_model_metadata",
-    responses={
-        200: {"description": "Success"},
-        400: {"description": "Bad request"},
-        404: {"description": "No metadata available"},
-    },
-)
-async def get_model_metadata(
-    key: str = Path(description="Key of the model repo metadata to fetch."),
-) -> Optional[AnyModelRepoMetadata]:
-    """Get a model metadata object."""
-    record_store = ApiDependencies.invoker.services.model_records
-    result = record_store.get_metadata(key)
-    if not result:
-        raise HTTPException(status_code=404, detail="No metadata for a model with this key")
-    return result
-
-
-@model_records_router.get(
-    "/tags",
-    operation_id="list_tags",
-)
-async def list_tags() -> Set[str]:
-    """Get a unique set of all the model tags."""
-    record_store = ApiDependencies.invoker.services.model_records
-    return record_store.list_tags()
-
-
-@model_records_router.get(
-    "/tags/search",
-    operation_id="search_by_metadata_tags",
-)
-async def search_by_metadata_tags(
-    tags: Set[str] = Query(default=None, description="Tags to search for"),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_records
-    results = record_store.search_by_metadata_tag(tags)
-    return ModelsList(models=results)
-
-
-@model_records_router.patch(
-    "/i/{key}",
-    operation_id="update_model_record",
-    responses={
-        200: {"description": "The model was updated successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-        409: {"description": "There is already a model corresponding to the new name"},
-    },
-    status_code=200,
-    response_model=AnyModelConfig,
-)
-async def update_model_record(
-    key: Annotated[str, Path(description="Unique key of model")],
-    info: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
-) -> AnyModelConfig:
-    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_records
-    try:
-        model_response = record_store.update_model(key, config=info)
-        logger.info(f"Updated model: {key}")
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return model_response
-
-
-@model_records_router.delete(
-    "/i/{key}",
-    operation_id="del_model_record",
-    responses={
-        204: {"description": "Model deleted successfully"},
-        404: {"description": "Model not found"},
-    },
-    status_code=204,
-)
-async def del_model_record(
-    key: str = Path(description="Unique key of model to remove from model registry."),
-) -> Response:
-    """
-    Delete model record from database.
-
-    The configuration record will be removed. The corresponding weights files will be
-    deleted as well if they reside within the InvokeAI "models" directory.
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_install
-        installer.delete(key)
-        logger.info(f"Deleted model: {key}")
-        return Response(status_code=204)
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.post(
-    "/i/",
-    operation_id="add_model_record",
-    responses={
-        201: {"description": "The model added successfully"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-        415: {"description": "Unrecognized file/folder format"},
-    },
-    status_code=201,
-)
-async def add_model_record(
-    config: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
-) -> AnyModelConfig:
-    """Add a model using the configuration information appropriate for its type."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_records
-    if config.key == "<NOKEY>":
-        config.key = sha1(randbytes(100)).hexdigest()
-        logger.info(f"Created model {config.key} for {config.name}")
-    try:
-        record_store.add_model(config.key, config)
-    except DuplicateModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-
-    # now fetch it out
-    return record_store.get_model(config.key)
-
-
-@model_records_router.post(
-    "/import",
-    operation_id="import_model_record",
-    responses={
-        201: {"description": "The model imported successfully"},
-        415: {"description": "Unrecognized file/folder format"},
-        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-)
-async def import_model(
-    source: ModelSource,
-    config: Optional[Dict[str, Any]] = Body(
-        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
-        default=None,
-    ),
-) -> ModelInstallJob:
-    """Add a model using its local path, repo_id, or remote URL.
-
-    Models will be downloaded, probed, configured and installed in a
-    series of background threads. The return object has `status` attribute
-    that can be used to monitor progress.
-
-    The source object is a discriminated Union of LocalModelSource,
-    HFModelSource and URLModelSource. Set the "type" field to the
-    appropriate value:
-
-    * To install a local path using LocalModelSource, pass a source of form:
-      `{
-        "type": "local",
-        "path": "/path/to/model",
-        "inplace": false
-      }`
-       The "inplace" flag, if true, will register the model in place in its
-       current filesystem location. Otherwise, the model will be copied
-       into the InvokeAI models directory.
-
-    * To install a HuggingFace repo_id using HFModelSource, pass a source of form:
-      `{
-        "type": "hf",
-        "repo_id": "stabilityai/stable-diffusion-2.0",
-        "variant": "fp16",
-        "subfolder": "vae",
-        "access_token": "f5820a918aaf01"
-      }`
-     The `variant`, `subfolder` and `access_token` fields are optional.
-
-    * To install a remote model using an arbitrary URL, pass:
-      `{
-        "type": "url",
-        "url": "http://www.civitai.com/models/123456",
-        "access_token": "f5820a918aaf01"
-      }`
-    The `access_token` field is optonal
-
-    The model's configuration record will be probed and filled in
-    automatically.  To override the default guesses, pass "metadata"
-    with a Dict containing the attributes you wish to override.
-
-    Installation occurs in the background. Either use list_model_install_jobs()
-    to poll for completion, or listen on the event bus for the following events:
-
-      "model_install_running"
-      "model_install_completed"
-      "model_install_error"
-
-    On successful completion, the event's payload will contain the field "key"
-    containing the installed ID of the model. On an error, the event's payload
-    will contain the fields "error_type" and "error" describing the nature of the
-    error and its traceback, respectively.
-
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_install
-        result: ModelInstallJob = installer.import_model(
-            source=source,
-            config=config,
-        )
-        logger.info(f"Started installation of {source}")
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=424, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return result
-
-
-@model_records_router.get(
-    "/import",
-    operation_id="list_model_install_jobs",
-)
-async def list_model_install_jobs() -> List[ModelInstallJob]:
-    """Return list of model install jobs."""
-    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_install.list_jobs()
-    return jobs
-
-
-@model_records_router.get(
-    "/import/{id}",
-    operation_id="get_model_install_job",
-    responses={
-        200: {"description": "Success"},
-        404: {"description": "No such job"},
-    },
-)
-async def get_model_install_job(id: int = Path(description="Model install id")) -> ModelInstallJob:
-    """Return model install job corresponding to the given source."""
-    try:
-        return ApiDependencies.invoker.services.model_install.get_job_by_id(id)
-    except ValueError as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.delete(
-    "/import/{id}",
-    operation_id="cancel_model_install_job",
-    responses={
-        201: {"description": "The job was cancelled successfully"},
-        415: {"description": "No such job"},
-    },
-    status_code=201,
-)
-async def cancel_model_install_job(id: int = Path(description="Model install job ID")) -> None:
-    """Cancel the model install job(s) corresponding to the given job ID."""
-    installer = ApiDependencies.invoker.services.model_install
-    try:
-        job = installer.get_job_by_id(id)
-    except ValueError as e:
-        raise HTTPException(status_code=415, detail=str(e))
-    installer.cancel_job(job)
-
-
-@model_records_router.patch(
-    "/import",
-    operation_id="prune_model_install_jobs",
-    responses={
-        204: {"description": "All completed and errored jobs have been pruned"},
-        400: {"description": "Bad request"},
-    },
-)
-async def prune_model_install_jobs() -> Response:
-    """Prune all completed and errored jobs from the install job list."""
-    ApiDependencies.invoker.services.model_install.prune_jobs()
-    return Response(status_code=204)
-
-
-@model_records_router.patch(
-    "/sync",
-    operation_id="sync_models_to_config",
-    responses={
-        204: {"description": "Model config record database resynced with files on disk"},
-        400: {"description": "Bad request"},
-    },
-)
-async def sync_models_to_config() -> Response:
-    """
-    Traverse the models and autoimport directories.
-
-    Model files without a corresponding
-    record in the database are added. Orphan records without a models file are deleted.
-    """
-    ApiDependencies.invoker.services.model_install.sync_to_config()
-    return Response(status_code=204)

invokeai/app/api/routers/models.py

@@ -1,427 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654), 2023 Kent Keirsey (https://github.com/hipsterusername), 2023 Lincoln D. Stein
-
-import pathlib
-from typing import Annotated, List, Literal, Optional, Union
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, ConfigDict, Field, TypeAdapter
-from starlette.exceptions import HTTPException
-
-from invokeai.backend import BaseModelType, ModelType
-from invokeai.backend.model_management import MergeInterpolationMethod
-from invokeai.backend.model_management.models import (
-    OPENAPI_MODEL_CONFIGS,
-    InvalidModelException,
-    ModelNotFoundException,
-    SchedulerPredictionType,
-)
-
-from ..dependencies import ApiDependencies
-
-models_router = APIRouter(prefix="/v1/models", tags=["models"])
-
-UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-UpdateModelResponseValidator = TypeAdapter(UpdateModelResponse)
-
-ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelResponseValidator = TypeAdapter(ImportModelResponse)
-
-ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ConvertModelResponseValidator = TypeAdapter(ConvertModelResponse)
-
-MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-
-
-class ModelsList(BaseModel):
-    models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
-
-    model_config = ConfigDict(use_enum_values=True)
-
-
-ModelsListValidator = TypeAdapter(ModelsList)
-
-
-@models_router.get(
-    "/",
-    operation_id="list_models",
-    responses={200: {"model": ModelsList}},
-)
-async def list_models(
-    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-) -> ModelsList:
-    """Gets a list of models"""
-    if base_models and len(base_models) > 0:
-        models_raw = []
-        for base_model in base_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})
-    return models
-
-
-@models_router.patch(
-    "/{base_model}/{model_type}/{model_name}",
-    operation_id="update_model",
-    responses={
-        200: {"description": "The model was updated successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-        409: {"description": "There is already a model corresponding to the new name"},
-    },
-    status_code=200,
-    response_model=UpdateModelResponse,
-)
-async def update_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
-) -> UpdateModelResponse:
-    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        previous_info = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        )
-
-        # rename operation requested
-        if info.model_name != model_name or info.base_model != base_model:
-            ApiDependencies.invoker.services.model_manager.rename_model(
-                base_model=base_model,
-                model_type=model_type,
-                model_name=model_name,
-                new_name=info.model_name,
-                new_base=info.base_model,
-            )
-            logger.info(f"Successfully renamed {base_model.value}/{model_name}=>{info.base_model}/{info.model_name}")
-            # update information to support an update of attributes
-            model_name = info.model_name
-            base_model = info.base_model
-            new_info = ApiDependencies.invoker.services.model_manager.list_model(
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-            )
-            if new_info.get("path") != previous_info.get(
-                "path"
-            ):  # model manager moved model path during rename - don't overwrite it
-                info.path = new_info.get("path")
-
-        # replace empty string values with None/null to avoid phenomenon of vae: ''
-        info_dict = info.model_dump()
-        info_dict = {x: info_dict[x] if info_dict[x] else None for x in info_dict.keys()}
-
-        ApiDependencies.invoker.services.model_manager.update_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-            model_attributes=info_dict,
-        )
-
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        )
-        model_response = UpdateModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    except Exception as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=400, detail=str(e))
-
-    return model_response
-
-
-@models_router.post(
-    "/import",
-    operation_id="import_model",
-    responses={
-        201: {"description": "The model imported successfully"},
-        404: {"description": "The model could not be found"},
-        415: {"description": "Unrecognized file/folder format"},
-        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-    response_model=ImportModelResponse,
-)
-async def import_model(
-    location: str = Body(description="A model path, repo_id or URL to import"),
-    prediction_type: Optional[Literal["v_prediction", "epsilon", "sample"]] = Body(
-        description="Prediction type for SDv2 checkpoints and rare SDv1 checkpoints",
-        default=None,
-    ),
-) -> ImportModelResponse:
-    """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
-
-    location = location.strip("\"' ")
-    items_to_import = {location}
-    prediction_types = {x.value: x for x in SchedulerPredictionType}
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
-            items_to_import=items_to_import,
-            prediction_type_helper=lambda x: prediction_types.get(prediction_type),
-        )
-        info = installed_models.get(location)
-
-        if not info:
-            logger.error("Import failed")
-            raise HTTPException(status_code=415)
-
-        logger.info(f"Successfully imported {location}, got {info}")
-        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)
-
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-
-
-@models_router.post(
-    "/add",
-    operation_id="add_model",
-    responses={
-        201: {"description": "The model added successfully"},
-        404: {"description": "The model could not be found"},
-        424: {"description": "The model appeared to add successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-    response_model=ImportModelResponse,
-)
-async def add_model(
-    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
-) -> ImportModelResponse:
-    """Add a model using the configuration information appropriate for its type. Only local models can be added by path"""
-
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        ApiDependencies.invoker.services.model_manager.add_model(
-            info.model_name,
-            info.base_model,
-            info.model_type,
-            model_attributes=info.model_dump(),
-        )
-        logger.info(f"Successfully added {info.model_name}")
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=info.model_name,
-            base_model=info.base_model,
-            model_type=info.model_type,
-        )
-        return ImportModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-
-
-@models_router.delete(
-    "/{base_model}/{model_type}/{model_name}",
-    operation_id="del_model",
-    responses={
-        204: {"description": "Model deleted successfully"},
-        404: {"description": "Model not found"},
-    },
-    status_code=204,
-    response_model=None,
-)
-async def delete_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-) -> Response:
-    """Delete Model"""
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        ApiDependencies.invoker.services.model_manager.del_model(
-            model_name, base_model=base_model, model_type=model_type
-        )
-        logger.info(f"Deleted model: {model_name}")
-        return Response(status_code=204)
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@models_router.put(
-    "/convert/{base_model}/{model_type}/{model_name}",
-    operation_id="convert_model",
-    responses={
-        200: {"description": "Model converted successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "Model not found"},
-    },
-    status_code=200,
-    response_model=ConvertModelResponse,
-)
-async def convert_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-    convert_dest_directory: Optional[str] = Query(
-        default=None, description="Save the converted model to the designated directory"
-    ),
-) -> ConvertModelResponse:
-    """Convert a checkpoint model into a diffusers model, optionally saving to the indicated destination directory, or `models` if none."""
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(f"Converting model: {model_name}")
-        dest = pathlib.Path(convert_dest_directory) if convert_dest_directory else None
-        ApiDependencies.invoker.services.model_manager.convert_model(
-            model_name,
-            base_model=base_model,
-            model_type=model_type,
-            convert_dest_directory=dest,
-        )
-        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)
-    except ModelNotFoundException as e:
-        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found: {str(e)}")
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response
-
-
-@models_router.get(
-    "/search",
-    operation_id="search_for_models",
-    responses={
-        200: {"description": "Directory searched successfully"},
-        404: {"description": "Invalid directory path"},
-    },
-    status_code=200,
-    response_model=List[pathlib.Path],
-)
-async def search_for_models(
-    search_path: pathlib.Path = Query(description="Directory path to search for models"),
-) -> List[pathlib.Path]:
-    if not search_path.is_dir():
-        raise HTTPException(
-            status_code=404,
-            detail=f"The search path '{search_path}' does not exist or is not directory",
-        )
-    return ApiDependencies.invoker.services.model_manager.search_for_models(search_path)
-
-
-@models_router.get(
-    "/ckpt_confs",
-    operation_id="list_ckpt_configs",
-    responses={
-        200: {"description": "paths retrieved successfully"},
-    },
-    status_code=200,
-    response_model=List[pathlib.Path],
-)
-async def list_ckpt_configs() -> List[pathlib.Path]:
-    """Return a list of the legacy checkpoint configuration files stored in `ROOT/configs/stable-diffusion`, relative to ROOT."""
-    return ApiDependencies.invoker.services.model_manager.list_checkpoint_configs()
-
-
-@models_router.post(
-    "/sync",
-    operation_id="sync_to_config",
-    responses={
-        201: {"description": "synchronization successful"},
-    },
-    status_code=201,
-    response_model=bool,
-)
-async def sync_to_config() -> bool:
-    """Call after making changes to models.yaml, autoimport directories or models directory to synchronize
-    in-memory data structures with disk data structures."""
-    ApiDependencies.invoker.services.model_manager.sync_to_config()
-    return True
-
-
-# There's some weird pydantic-fastapi behaviour that requires this to be a separate class
-# TODO: After a few updates, see if it works inside the route operation handler?
-class MergeModelsBody(BaseModel):
-    model_names: List[str] = Field(description="model name", min_length=2, max_length=3)
-    merged_model_name: Optional[str] = Field(description="Name of destination model")
-    alpha: Optional[float] = Field(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5)
-    interp: Optional[MergeInterpolationMethod] = Field(description="Interpolation method")
-    force: Optional[bool] = Field(
-        description="Force merging of models created with different versions of diffusers",
-        default=False,
-    )
-
-    merge_dest_directory: Optional[str] = Field(
-        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
-        default=None,
-    )
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@models_router.put(
-    "/merge/{base_model}",
-    operation_id="merge_models",
-    responses={
-        200: {"description": "Model converted successfully"},
-        400: {"description": "Incompatible models"},
-        404: {"description": "One or more models not found"},
-    },
-    status_code=200,
-    response_model=MergeModelResponse,
-)
-async def merge_models(
-    body: Annotated[MergeModelsBody, Body(description="Model configuration", embed=True)],
-    base_model: BaseModelType = Path(description="Base model"),
-) -> MergeModelResponse:
-    """Convert a checkpoint model into a diffusers model"""
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(
-            f"Merging models: {body.model_names} into {body.merge_dest_directory or '<MODELS>'}/{body.merged_model_name}"
-        )
-        dest = pathlib.Path(body.merge_dest_directory) if body.merge_dest_directory else None
-        result = ApiDependencies.invoker.services.model_manager.merge_models(
-            model_names=body.model_names,
-            base_model=base_model,
-            merged_model_name=body.merged_model_name or "+".join(body.model_names),
-            alpha=body.alpha,
-            interp=body.interp,
-            force=body.force,
-            merge_dest_directory=dest,
-        )
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            result.name,
-            base_model=base_model,
-            model_type=ModelType.Main,
-        )
-        response = ConvertModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException:
-        raise HTTPException(
-            status_code=404,
-            detail=f"One or more of the models '{body.model_names}' not found",
-        )
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response

invokeai/app/api/sockets.py

@@ -14,7 +14,7 @@ class SocketIO:
 
     def __init__(self, app: FastAPI):
         self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
-        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="socket.io")
+        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="/ws/socket.io")
         app.mount("/ws", self.__app)
 
         self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)

invokeai/app/api_app.py

@@ -6,6 +6,7 @@ import sys
 from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
 from invokeai.version.invokeai_version import __version__
 
+from .invocations.fields import InputFieldJSONSchemaExtra, OutputFieldJSONSchemaExtra
 from .services.config import InvokeAIAppConfig
 
 app_config = InvokeAIAppConfig.get_config()
@@ -47,8 +48,7 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
         boards,
         download_queue,
         images,
-        model_records,
-        models,
+        model_manager,
         session_queue,
         sessions,
         utilities,
@@ -57,8 +57,6 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
     from .api.sockets import SocketIO
     from .invocations.baseinvocation import (
         BaseInvocation,
-        InputFieldJSONSchemaExtra,
-        OutputFieldJSONSchemaExtra,
         UIConfigBase,
     )
 
@@ -115,8 +113,7 @@ async def shutdown_event() -> None:
 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(model_records.model_records_router, prefix="/api")
+app.include_router(model_manager.model_manager_router, prefix="/api")
 app.include_router(download_queue.download_queue_router, prefix="/api")
 app.include_router(images.images_router, prefix="/api")
 app.include_router(boards.boards_router, prefix="/api")
@@ -178,21 +175,23 @@ def custom_openapi() -> dict[str, Any]:
         invoker_schema["class"] = "invocation"
         openapi_schema["components"]["schemas"][f"{output_type_title}"]["class"] = "output"
 
-    from invokeai.backend.model_management.models import get_model_config_enums
+    # This code no longer seems to be necessary?
+    # Leave it here just in case
+    #
+    # from invokeai.backend.model_manager import get_model_config_formats
+    # formats = get_model_config_formats()
+    # for model_config_name, enum_set in formats.items():
 
-    for model_config_format_enum in set(get_model_config_enums()):
-        name = model_config_format_enum.__qualname__
+    #     if model_config_name in openapi_schema["components"]["schemas"]:
+    #         # print(f"Config with name {name} already defined")
+    #         continue
 
-        if name in openapi_schema["components"]["schemas"]:
-            # print(f"Config with name {name} already defined")
-            continue
-
-        openapi_schema["components"]["schemas"][name] = {
-            "title": name,
-            "description": "An enumeration.",
-            "type": "string",
-            "enum": [v.value for v in model_config_format_enum],
-        }
+    #     openapi_schema["components"]["schemas"][model_config_name] = {
+    #         "title": model_config_name,
+    #         "description": "An enumeration.",
+    #         "type": "string",
+    #         "enum": [v.value for v in enum_set],
+    #     }
 
     app.openapi_schema = openapi_schema
     return app.openapi_schema

invokeai/app/invocations/baseinvocation.py

@@ -12,13 +12,16 @@ from types import UnionType
 from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union, cast
 
 import semver
-from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter, create_model
-from pydantic.fields import FieldInfo, _Unset
+from pydantic import BaseModel, ConfigDict, Field, create_model
+from pydantic.fields import FieldInfo
 from pydantic_core import PydanticUndefined
 
+from invokeai.app.invocations.fields import (
+    FieldKind,
+    Input,
+)
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.metaenum import MetaEnum
 from invokeai.app.util.misc import uuid_string
 from invokeai.backend.util.logging import InvokeAILogger
@@ -52,393 +55,6 @@ class Classification(str, Enum, metaclass=MetaEnum):
     Prototype = "prototype"
 
 
-class Input(str, Enum, metaclass=MetaEnum):
-    """
-    The type of input a field accepts.
-    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
-      are instantiated.
-    - `Input.Connection`: The field must have its value provided by a connection.
-    - `Input.Any`: The field may have its value provided either directly or by a connection.
-    """
-
-    Connection = "connection"
-    Direct = "direct"
-    Any = "any"
-
-
-class FieldKind(str, Enum, metaclass=MetaEnum):
-    """
-    The kind of field.
-    - `Input`: An input field on a node.
-    - `Output`: An output field on a node.
-    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
-    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
-    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
-    allowing "metadata" for that field.
-    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
-    but which are used to store information about the node. For example, the `id` and `type` fields are node
-    attributes.
-
-    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
-    startup, and when generating the OpenAPI schema for the workflow editor.
-    """
-
-    Input = "input"
-    Output = "output"
-    Internal = "internal"
-    NodeAttribute = "node_attribute"
-
-
-class UIType(str, Enum, metaclass=MetaEnum):
-    """
-    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
-
-    - Model Fields
-    The most common node-author-facing use will be for model fields. Internally, there is no difference
-    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
-    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
-    the field is an SDXL main model field.
-
-    - Any Field
-    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
-    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
-
-    - Scheduler Field
-    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
-
-    - Internal Fields
-    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
-    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
-    should not be used by node authors.
-
-    - DEPRECATED Fields
-    These types are deprecated and should not be used by node authors. A warning will be logged if one is
-    used, and the type will be ignored. They are included here for backwards compatibility.
-    """
-
-    # region Model Field Types
-    SDXLMainModel = "SDXLMainModelField"
-    SDXLRefinerModel = "SDXLRefinerModelField"
-    ONNXModel = "ONNXModelField"
-    VaeModel = "VAEModelField"
-    LoRAModel = "LoRAModelField"
-    ControlNetModel = "ControlNetModelField"
-    IPAdapterModel = "IPAdapterModelField"
-    # endregion
-
-    # region Misc Field Types
-    Scheduler = "SchedulerField"
-    Any = "AnyField"
-    # endregion
-
-    # region Internal Field Types
-    _Collection = "CollectionField"
-    _CollectionItem = "CollectionItemField"
-    # endregion
-
-    # region DEPRECATED
-    Boolean = "DEPRECATED_Boolean"
-    Color = "DEPRECATED_Color"
-    Conditioning = "DEPRECATED_Conditioning"
-    Control = "DEPRECATED_Control"
-    Float = "DEPRECATED_Float"
-    Image = "DEPRECATED_Image"
-    Integer = "DEPRECATED_Integer"
-    Latents = "DEPRECATED_Latents"
-    String = "DEPRECATED_String"
-    BooleanCollection = "DEPRECATED_BooleanCollection"
-    ColorCollection = "DEPRECATED_ColorCollection"
-    ConditioningCollection = "DEPRECATED_ConditioningCollection"
-    ControlCollection = "DEPRECATED_ControlCollection"
-    FloatCollection = "DEPRECATED_FloatCollection"
-    ImageCollection = "DEPRECATED_ImageCollection"
-    IntegerCollection = "DEPRECATED_IntegerCollection"
-    LatentsCollection = "DEPRECATED_LatentsCollection"
-    StringCollection = "DEPRECATED_StringCollection"
-    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
-    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
-    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
-    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
-    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
-    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
-    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
-    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
-    StringPolymorphic = "DEPRECATED_StringPolymorphic"
-    MainModel = "DEPRECATED_MainModel"
-    UNet = "DEPRECATED_UNet"
-    Vae = "DEPRECATED_Vae"
-    CLIP = "DEPRECATED_CLIP"
-    Collection = "DEPRECATED_Collection"
-    CollectionItem = "DEPRECATED_CollectionItem"
-    Enum = "DEPRECATED_Enum"
-    WorkflowField = "DEPRECATED_WorkflowField"
-    IsIntermediate = "DEPRECATED_IsIntermediate"
-    BoardField = "DEPRECATED_BoardField"
-    MetadataItem = "DEPRECATED_MetadataItem"
-    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
-    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
-    MetadataDict = "DEPRECATED_MetadataDict"
-    # endregion
-
-
-class UIComponent(str, Enum, metaclass=MetaEnum):
-    """
-    The type of UI component to use for a field, used to override the default components, which are
-    inferred from the field type.
-    """
-
-    None_ = "none"
-    Textarea = "textarea"
-    Slider = "slider"
-
-
-class InputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
-    and by the workflow editor during schema parsing and UI rendering.
-    """
-
-    input: Input
-    orig_required: bool
-    field_kind: FieldKind
-    default: Optional[Any] = None
-    orig_default: Optional[Any] = None
-    ui_hidden: bool = False
-    ui_type: Optional[UIType] = None
-    ui_component: Optional[UIComponent] = None
-    ui_order: Optional[int] = None
-    ui_choice_labels: Optional[dict[str, str]] = None
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-class OutputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
-    during schema parsing and UI rendering.
-    """
-
-    field_kind: FieldKind
-    ui_hidden: bool
-    ui_type: Optional[UIType]
-    ui_order: Optional[int]
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-def InputField(
-    # copied from pydantic's Field
-    # TODO: Can we support default_factory?
-    default: Any = _Unset,
-    default_factory: Callable[[], Any] | None = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    input: Input = Input.Any,
-    ui_type: Optional[UIType] = None,
-    ui_component: Optional[UIComponent] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-    ui_choice_labels: Optional[dict[str, str]] = None,
-) -> Any:
-    """
-    Creates an input field for an invocation.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param Input input: [Input.Any] The kind of input this field requires. \
-      `Input.Direct` means a value must be provided on instantiation. \
-      `Input.Connection` means the value must be provided by a connection. \
-      `Input.Any` means either will do.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
-      The UI will always render a suitable component, but sometimes you want something different than the default. \
-      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
-      For this case, you could provide `UIComponent.Textarea`.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
-
-    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
-    """
-
-    json_schema_extra_ = InputFieldJSONSchemaExtra(
-        input=input,
-        ui_type=ui_type,
-        ui_component=ui_component,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        ui_choice_labels=ui_choice_labels,
-        field_kind=FieldKind.Input,
-        orig_required=True,
-    )
-
-    """
-    There is a conflict between the typing of invocation definitions and the typing of an invocation's
-    `invoke()` function.
-
-    On instantiation of a node, the invocation definition is used to create the python class. At this time,
-    any number of fields may be optional, because they may be provided by connections.
-
-    On calling of `invoke()`, however, those fields may be required.
-
-    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
-
-    `image` is required during the call to `invoke()`, but when the python class is instantiated,
-    the field may not be present. This is fine, because that image field will be provided by a
-    connection from an ancestor node, which outputs an image.
-
-    This means we want to type the `image` field as optional for the node class definition, but required
-    for the `invoke()` function.
-
-    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
-    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
-    any static type analysis tools will complain.
-
-    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
-    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
-    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
-    """
-
-    if default_factory is not _Unset and default_factory is not None:
-        default = default_factory()
-        logger.warn('"default_factory" is not supported, calling it now to set "default"')
-
-    # These are the args we may wish pass to the pydantic `Field()` function
-    field_args = {
-        "default": default,
-        "title": title,
-        "description": description,
-        "pattern": pattern,
-        "strict": strict,
-        "gt": gt,
-        "ge": ge,
-        "lt": lt,
-        "le": le,
-        "multiple_of": multiple_of,
-        "allow_inf_nan": allow_inf_nan,
-        "max_digits": max_digits,
-        "decimal_places": decimal_places,
-        "min_length": min_length,
-        "max_length": max_length,
-    }
-
-    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
-    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
-
-    # Because we are manually making fields optional, we need to store the original required bool for reference later
-    json_schema_extra_.orig_required = default is PydanticUndefined
-
-    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
-    if input is Input.Any or input is Input.Connection:
-        default_ = None if default is PydanticUndefined else default
-        provided_args.update({"default": default_})
-        if default is not PydanticUndefined:
-            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
-            json_schema_extra_.default = default
-            json_schema_extra_.orig_default = default
-    elif default is not PydanticUndefined:
-        default_ = default
-        provided_args.update({"default": default_})
-        json_schema_extra_.orig_default = default_
-
-    return Field(
-        **provided_args,
-        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
-    )
-
-
-def OutputField(
-    # copied from pydantic's Field
-    default: Any = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    ui_type: Optional[UIType] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-) -> Any:
-    """
-    Creates an output field for an invocation output.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
-    """
-    return Field(
-        default=default,
-        title=title,
-        description=description,
-        pattern=pattern,
-        strict=strict,
-        gt=gt,
-        ge=ge,
-        lt=lt,
-        le=le,
-        multiple_of=multiple_of,
-        allow_inf_nan=allow_inf_nan,
-        max_digits=max_digits,
-        decimal_places=decimal_places,
-        min_length=min_length,
-        max_length=max_length,
-        json_schema_extra=OutputFieldJSONSchemaExtra(
-            ui_type=ui_type,
-            ui_hidden=ui_hidden,
-            ui_order=ui_order,
-            field_kind=FieldKind.Output,
-        ).model_dump(exclude_none=True),
-    )
-
-
 class UIConfigBase(BaseModel):
     """
     Provides additional node configuration to the UI.
@@ -460,33 +76,6 @@ class UIConfigBase(BaseModel):
     )
 
 
-class InvocationContext:
-    """Initialized and provided to on execution of invocations."""
-
-    services: InvocationServices
-    graph_execution_state_id: str
-    queue_id: str
-    queue_item_id: int
-    queue_batch_id: str
-    workflow: Optional[WorkflowWithoutID]
-
-    def __init__(
-        self,
-        services: InvocationServices,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        workflow: Optional[WorkflowWithoutID],
-    ):
-        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.workflow = workflow
-
-
 class BaseInvocationOutput(BaseModel):
     """
     Base class for all invocation outputs.
@@ -632,7 +221,7 @@ class BaseInvocation(ABC, BaseModel):
         """Invoke with provided context and return outputs."""
         pass
 
-    def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
+    def invoke_internal(self, context: InvocationContext, services: "InvocationServices") -> BaseInvocationOutput:
         """
         Internal invoke method, calls `invoke()` after some prep.
         Handles optional fields that are required to call `invoke()` and invocation cache.
@@ -657,23 +246,23 @@ class BaseInvocation(ABC, BaseModel):
                     raise MissingInputException(self.model_fields["type"].default, field_name)
 
         # skip node cache codepath if it's disabled
-        if context.services.configuration.node_cache_size == 0:
+        if services.configuration.node_cache_size == 0:
             return self.invoke(context)
 
         output: BaseInvocationOutput
         if self.use_cache:
-            key = context.services.invocation_cache.create_key(self)
-            cached_value = context.services.invocation_cache.get(key)
+            key = services.invocation_cache.create_key(self)
+            cached_value = 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}')
+                services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
                 output = self.invoke(context)
-                context.services.invocation_cache.save(key, output)
+                services.invocation_cache.save(key, output)
                 return output
             else:
-                context.services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
                 return cached_value
         else:
-            context.services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
+            services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
             return self.invoke(context)
 
     id: str = Field(
@@ -714,9 +303,7 @@ RESERVED_NODE_ATTRIBUTE_FIELD_NAMES = {
     "workflow",
 }
 
-RESERVED_INPUT_FIELD_NAMES = {
-    "metadata",
-}
+RESERVED_INPUT_FIELD_NAMES = {"metadata", "board"}
 
 RESERVED_OUTPUT_FIELD_NAMES = {"type"}
 
@@ -926,37 +513,3 @@ def invocation_output(
         return cls
 
     return wrapper
-
-
-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=InputFieldJSONSchemaExtra(
-            field_kind=FieldKind.Internal,
-            input=Input.Connection,
-            orig_required=False,
-        ).model_dump(exclude_none=True),
-    )
-
-
-class WithWorkflow:
-    workflow = None
-
-    def __init_subclass__(cls) -> None:
-        logger.warn(
-            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
-        )
-        super().__init_subclass__()

invokeai/app/invocations/collections.py

@@ -5,9 +5,11 @@ import numpy as np
 from pydantic import ValidationInfo, field_validator
 
 from invokeai.app.invocations.primitives import IntegerCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField
 
 
 @invocation(

invokeai/app/invocations/compel.py

@@ -1,40 +1,43 @@
-from dataclasses import dataclass
-from typing import List, Optional, Union
+from typing import Iterator, List, Optional, Tuple, Union
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
+from transformers import CLIPTokenizer
 
-from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput
-from invokeai.app.shared.fields import FieldDescriptions
+import invokeai.backend.util.logging as logger
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    Input,
+    InputField,
+    OutputField,
+    UIComponent,
+)
+from invokeai.app.invocations.primitives import ConditioningOutput
+from invokeai.app.services.model_records import UnknownModelException
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.ti_utils import extract_ti_triggers_from_prompt
+from invokeai.backend.lora import LoRAModelRaw
+from invokeai.backend.model_manager import ModelType
+from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
+    ConditioningFieldData,
     ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
+from invokeai.backend.textual_inversion import TextualInversionModelRaw
+from invokeai.backend.util.devices import torch_dtype
 
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import ModelNotFoundException, ModelType
-from ...backend.util.devices import torch_dtype
-from ..util.ti_utils import extract_ti_triggers_from_prompt
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
 from .model import ClipField
 
-
-@dataclass
-class ConditioningFieldData:
-    conditionings: List[BasicConditioningInfo]
-    # unconditioned: Optional[torch.Tensor]
+# unconditioned: Optional[torch.Tensor]
 
 
 # class ConditioningAlgo(str, Enum):
@@ -48,7 +51,7 @@ class ConditioningFieldData:
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -66,49 +69,34 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-            context=context,
-        )
+        tokenizer_info = context.models.load(**self.clip.tokenizer.model_dump())
+        text_encoder_info = context.models.load(**self.clip.text_encoder.model_dump())
 
-        def _lora_loader():
+        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in self.clip.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
-                yield (lora_info.context.model, lora.weight)
+                lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
+                assert isinstance(lora_info.model, LoRAModelRaw)
+                yield (lora_info.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.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
         ti_list = []
         for trigger in extract_ti_triggers_from_prompt(self.prompt):
             name = trigger[1:-1]
             try:
-                ti_list.append(
-                    (
-                        name,
-                        context.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=self.clip.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                            context=context,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
+                loaded_model = context.models.load(**self.clip.text_encoder.model_dump()).model
+                assert isinstance(loaded_model, TextualInversionModelRaw)
+                ti_list.append((name, loaded_model))
+            except UnknownModelException:
                 # print(e)
                 # import traceback
                 # print(traceback.format_exc())
                 print(f'Warn: trigger: "{trigger}" not found')
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_info.model, text_encoder_info.model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -116,7 +104,7 @@ class CompelInvocation(BaseInvocation):
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_info.model, self.clip.skipped_layers),
         ):
             compel = Compel(
                 tokenizer=tokenizer,
@@ -128,7 +116,7 @@ class CompelInvocation(BaseInvocation):
 
             conjunction = Compel.parse_prompt_string(self.prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
             c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
@@ -149,17 +137,14 @@ 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.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 class SDXLPromptInvocationBase:
+    """Prompt processor for SDXL models."""
+
     def run_clip_compel(
         self,
         context: InvocationContext,
@@ -168,26 +153,21 @@ class SDXLPromptInvocationBase:
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ):
-        tokenizer_info = context.services.model_manager.get_model(
-            **clip_field.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.model_dump(),
-            context=context,
-        )
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[ExtraConditioningInfo]]:
+        tokenizer_info = context.models.load(**clip_field.tokenizer.model_dump())
+        text_encoder_info = context.models.load(**clip_field.text_encoder.model_dump())
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
-            cpu_text_encoder = text_encoder_info.context.model
+            cpu_text_encoder = text_encoder_info.model
+            assert isinstance(cpu_text_encoder, torch.nn.Module)
             c = torch.zeros(
                 (
                     1,
                     cpu_text_encoder.config.max_position_embeddings,
                     cpu_text_encoder.config.hidden_size,
                 ),
-                dtype=text_encoder_info.context.cache.precision,
+                dtype=cpu_text_encoder.dtype,
             )
             if get_pooled:
                 c_pooled = torch.zeros(
@@ -198,40 +178,36 @@ class SDXLPromptInvocationBase:
                 c_pooled = None
             return c, c_pooled, None
 
-        def _lora_loader():
+        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in clip_field.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
-                yield (lora_info.context.model, lora.weight)
+                lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
+                lora_model = lora_info.model
+                assert isinstance(lora_model, LoRAModelRaw)
+                yield (lora_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.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
         ti_list = []
         for trigger in extract_ti_triggers_from_prompt(prompt):
             name = trigger[1:-1]
             try:
-                ti_list.append(
-                    (
-                        name,
-                        context.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=clip_field.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                            context=context,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
+                ti_model = context.models.load_by_attrs(
+                    model_name=name, base_model=text_encoder_info.config.base, model_type=ModelType.TextualInversion
+                ).model
+                assert isinstance(ti_model, TextualInversionModelRaw)
+                ti_list.append((name, ti_model))
+            except UnknownModelException:
                 # print(e)
                 # import traceback
                 # print(traceback.format_exc())
-                print(f'Warn: trigger: "{trigger}" not found')
+                logger.warning(f'trigger: "{trigger}" not found')
+            except ValueError:
+                logger.warning(f'trigger: "{trigger}" more than one similarly-named textual inversion models')
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_info.model, text_encoder_info.model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -239,7 +215,7 @@ class SDXLPromptInvocationBase:
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_info.model, clip_field.skipped_layers),
         ):
             compel = Compel(
                 tokenizer=tokenizer,
@@ -253,7 +229,7 @@ class SDXLPromptInvocationBase:
 
             conjunction = Compel.parse_prompt_string(prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 # TODO: better logging for and syntax
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
@@ -286,7 +262,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -357,6 +333,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 dim=1,
             )
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -368,14 +345,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation(
@@ -383,7 +355,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     title="SDXL Refiner Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -410,6 +382,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         add_time_ids = torch.tensor([original_size + crop_coords + (self.aesthetic_score,)])
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -421,14 +394,9 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation_output("clip_skip_output")
@@ -459,9 +427,9 @@ class ClipSkipInvocation(BaseInvocation):
 
 
 def get_max_token_count(
-    tokenizer,
+    tokenizer: CLIPTokenizer,
     prompt: Union[FlattenedPrompt, Blend, Conjunction],
-    truncate_if_too_long=False,
+    truncate_if_too_long: bool = False,
 ) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt
@@ -473,7 +441,9 @@ def get_max_token_count(
         return len(get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long))
 
 
-def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True) -> List[str]:
+def get_tokens_for_prompt_object(
+    tokenizer: CLIPTokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long: bool = True
+) -> List[str]:
     if type(parsed_prompt) is Blend:
         raise ValueError("Blend is not supported here - you need to get tokens for each of its .children")
 
@@ -486,24 +456,29 @@ def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, trun
         for x in parsed_prompt.children
     ]
     text = " ".join(text_fragments)
-    tokens = tokenizer.tokenize(text)
+    tokens: List[str] = tokenizer.tokenize(text)
     if truncate_if_too_long:
         max_tokens_length = tokenizer.model_max_length - 2  # typically 75
         tokens = tokens[0:max_tokens_length]
     return tokens
 
 
-def log_tokenization_for_conjunction(c: Conjunction, tokenizer, display_label_prefix=None):
+def log_tokenization_for_conjunction(
+    c: Conjunction, tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
+) -> None:
     display_label_prefix = display_label_prefix or ""
     for i, p in enumerate(c.prompts):
         if len(c.prompts) > 1:
             this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
         else:
+            assert display_label_prefix is not None
             this_display_label_prefix = display_label_prefix
         log_tokenization_for_prompt_object(p, tokenizer, display_label_prefix=this_display_label_prefix)
 
 
-def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None):
+def log_tokenization_for_prompt_object(
+    p: Union[Blend, FlattenedPrompt], tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
+) -> None:
     display_label_prefix = display_label_prefix or ""
     if type(p) is Blend:
         blend: Blend = p
@@ -543,7 +518,12 @@ def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokeniz
             log_tokenization_for_text(text, tokenizer, display_label=display_label_prefix)
 
 
-def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
+def log_tokenization_for_text(
+    text: str,
+    tokenizer: CLIPTokenizer,
+    display_label: Optional[str] = None,
+    truncate_if_too_long: Optional[bool] = False,
+) -> None:
     """shows how the prompt is tokenized
     # usually tokens have '</w>' to indicate end-of-word,
     # but for readability it has been replaced with ' '

invokeai/app/invocations/constants.py

@@ -0,0 +1,17 @@
+from typing import Literal
+
+from invokeai.backend.stable_diffusion.schedulers import SCHEDULER_MAP
+
+LATENT_SCALE_FACTOR = 8
+"""
+HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
+be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
+factor is hard-coded to a literal '8' rather than using this constant.
+The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
+"""
+
+SCHEDULER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
+"""A literal type representing the valid scheduler names."""
+
+IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
+"""A literal type for PIL image modes supported by Invoke"""

invokeai/app/invocations/controlnet_image_processors.py

@@ -17,32 +17,30 @@ from controlnet_aux import (
     MidasDetector,
     MLSDdetector,
     NormalBaeDetector,
-    OpenposeDetector,
     PidiNetDetector,
     SamDetector,
     ZoeDetector,
 )
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
-
-from ...backend.model_management import BaseModelType
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
     Input,
     InputField,
-    InvocationContext,
     OutputField,
+    WithBoard,
     WithMetadata,
-    invocation,
-    invocation_output,
 )
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
+from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
+
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 
 CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
 CONTROLNET_RESIZE_VALUES = Literal[
@@ -56,10 +54,7 @@ CONTROLNET_RESIZE_VALUES = Literal[
 class ControlNetModelField(BaseModel):
     """ControlNet model field"""
 
-    model_name: str = Field(description="Name of the ControlNet model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Model config record key for the ControlNet model")
 
 
 class ControlField(BaseModel):
@@ -139,7 +134,7 @@ class ControlNetInvocation(BaseInvocation):
 
 
 # This invocation exists for other invocations to subclass it - do not register with @invocation!
-class ImageProcessorInvocation(BaseInvocation, WithMetadata):
+class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Base class for invocations that preprocess images for ControlNet"""
 
     image: ImageField = InputField(description="The image to process")
@@ -148,23 +143,18 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
         # superclass just passes through image without processing
         return image
 
+    def load_image(self, context: InvocationContext) -> Image.Image:
+        # allows override for any special formatting specific to the preprocessor
+        return context.images.get_pil(self.image.image_name, "RGB")
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        raw_image = context.services.images.get_pil_image(self.image.image_name)
+        raw_image = self.load_image(context)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
         # currently can't see processed image in node UI without a showImage node,
         #    so for now setting image_type to RESULT instead of INTERMEDIATE so will get saved in gallery
-        image_dto = context.services.images.create(
-            image=processed_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.CONTROL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=processed_image)
 
         """Builds an ImageOutput and its ImageField"""
         processed_image_field = ImageField(image_name=image_dto.image_name)
@@ -183,7 +173,7 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
     title="Canny Processor",
     tags=["controlnet", "canny"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class CannyImageProcessorInvocation(ImageProcessorInvocation):
     """Canny edge detection for ControlNet"""
@@ -195,6 +185,10 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
         default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)"
     )
 
+    def load_image(self, context: InvocationContext) -> Image.Image:
+        # Keep alpha channel for Canny processing to detect edges of transparent areas
+        return context.images.get_pil(self.image.image_name, "RGBA")
+
     def run_processor(self, image):
         canny_processor = CannyDetector()
         processed_image = canny_processor(image, self.low_threshold, self.high_threshold)
@@ -206,7 +200,7 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
     title="HED (softedge) Processor",
     tags=["controlnet", "hed", "softedge"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class HedImageProcessorInvocation(ImageProcessorInvocation):
     """Applies HED edge detection to image"""
@@ -235,7 +229,7 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Processor",
     tags=["controlnet", "lineart"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LineartImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art processing to image"""
@@ -257,7 +251,7 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Anime Processor",
     tags=["controlnet", "lineart", "anime"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art anime processing to image"""
@@ -275,37 +269,12 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "openpose_image_processor",
-    title="Openpose Processor",
-    tags=["controlnet", "openpose", "pose"],
-    category="controlnet",
-    version="1.2.0",
-)
-class OpenposeImageProcessorInvocation(ImageProcessorInvocation):
-    """Applies Openpose processing to image"""
-
-    hand_and_face: bool = InputField(default=False, description="Whether to use hands and face mode")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-
-    def run_processor(self, image):
-        openpose_processor = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = openpose_processor(
-            image,
-            detect_resolution=self.detect_resolution,
-            image_resolution=self.image_resolution,
-            hand_and_face=self.hand_and_face,
-        )
-        return processed_image
-
-
 @invocation(
     "midas_depth_image_processor",
     title="Midas Depth Processor",
     tags=["controlnet", "midas"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Midas depth processing to image"""
@@ -332,7 +301,7 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Normal BAE Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies NormalBae processing to image"""
@@ -349,7 +318,7 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.0"
+    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.1"
 )
 class MlsdImageProcessorInvocation(ImageProcessorInvocation):
     """Applies MLSD processing to image"""
@@ -372,7 +341,7 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.0"
+    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.1"
 )
 class PidiImageProcessorInvocation(ImageProcessorInvocation):
     """Applies PIDI processing to image"""
@@ -399,7 +368,7 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
     title="Content Shuffle Processor",
     tags=["controlnet", "contentshuffle"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     """Applies content shuffle processing to image"""
@@ -429,7 +398,7 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     title="Zoe (Depth) Processor",
     tags=["controlnet", "zoe", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Zoe depth processing to image"""
@@ -445,7 +414,7 @@ class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Mediapipe Face Processor",
     tags=["controlnet", "mediapipe", "face"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     """Applies mediapipe face processing to image"""
@@ -454,10 +423,6 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     min_confidence: float = InputField(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
 
     def run_processor(self, image):
-        # MediaPipeFaceDetector throws an error if image has alpha channel
-        #     so convert to RGB if needed
-        if image.mode == "RGBA":
-            image = image.convert("RGB")
         mediapipe_face_processor = MediapipeFaceDetector()
         processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence)
         return processed_image
@@ -468,7 +433,7 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     title="Leres (Depth) Processor",
     tags=["controlnet", "leres", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LeresImageProcessorInvocation(ImageProcessorInvocation):
     """Applies leres processing to image"""
@@ -497,7 +462,7 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
     title="Tile Resample Processor",
     tags=["controlnet", "tile"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     """Tile resampler processor"""
@@ -537,7 +502,7 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     title="Segment Anything Processor",
     tags=["controlnet", "segmentanything"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     """Applies segment anything processing to image"""
@@ -579,7 +544,7 @@ class SamDetectorReproducibleColors(SamDetector):
     title="Color Map Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a color map from the provided image"""
@@ -587,7 +552,6 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     color_map_tile_size: int = InputField(default=64, ge=0, description=FieldDescriptions.tile_size)
 
     def run_processor(self, image: Image.Image):
-        image = image.convert("RGB")
         np_image = np.array(image, dtype=np.uint8)
         height, width = np_image.shape[:2]
 
@@ -602,3 +566,57 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
         color_map = cv2.resize(color_map, (width, height), interpolation=cv2.INTER_NEAREST)
         color_map = Image.fromarray(color_map)
         return color_map
+
+
+DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
+
+
+@invocation(
+    "depth_anything_image_processor",
+    title="Depth Anything Processor",
+    tags=["controlnet", "depth", "depth anything"],
+    category="controlnet",
+    version="1.0.0",
+)
+class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
+    """Generates a depth map based on the Depth Anything algorithm"""
+
+    model_size: DEPTH_ANYTHING_MODEL_SIZES = InputField(
+        default="small", description="The size of the depth model to use"
+    )
+    resolution: int = InputField(default=512, ge=64, multiple_of=64, description=FieldDescriptions.image_res)
+    offload: bool = InputField(default=False)
+
+    def run_processor(self, image: Image.Image):
+        depth_anything_detector = DepthAnythingDetector()
+        depth_anything_detector.load_model(model_size=self.model_size)
+
+        processed_image = depth_anything_detector(image=image, resolution=self.resolution, offload=self.offload)
+        return processed_image
+
+
+@invocation(
+    "dw_openpose_image_processor",
+    title="DW Openpose Image Processor",
+    tags=["controlnet", "dwpose", "openpose"],
+    category="controlnet",
+    version="1.0.0",
+)
+class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
+    """Generates an openpose pose from an image using DWPose"""
+
+    draw_body: bool = InputField(default=True)
+    draw_face: bool = InputField(default=False)
+    draw_hands: bool = InputField(default=False)
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+
+    def run_processor(self, image: Image.Image):
+        dw_openpose = DWOpenposeDetector()
+        processed_image = dw_openpose(
+            image,
+            draw_face=self.draw_face,
+            draw_hands=self.draw_hands,
+            draw_body=self.draw_body,
+            resolution=self.image_resolution,
+        )
+        return processed_image

invokeai/app/invocations/cv.py

@@ -5,22 +5,24 @@ import cv2 as cv
 import numpy
 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 invokeai.app.invocations.fields import ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 
 
-@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.0")
-class CvInpaintInvocation(BaseInvocation, WithMetadata):
+@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.1")
+class CvInpaintInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Simple inpaint using opencv."""
 
     image: ImageField = InputField(description="The image to inpaint")
     mask: ImageField = InputField(description="The mask to use when inpainting")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        mask = context.services.images.get_pil_image(self.mask.image_name)
+        image = context.images.get_pil(self.image.image_name)
+        mask = context.images.get_pil(self.mask.image_name)
 
         # Convert to cv image/mask
         # TODO: consider making these utility functions
@@ -34,18 +36,6 @@ class CvInpaintInvocation(BaseInvocation, WithMetadata):
         # TODO: consider making a utility function
         image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
 
-        image_dto = context.services.images.create(
-            image=image_inpainted,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=image_inpainted)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/facetools.py

@@ -13,15 +13,13 @@ from pydantic import field_validator
 import invokeai.assets.fonts as font_assets
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 
 @invocation_output("face_mask_output")
@@ -306,37 +304,37 @@ def extract_face(
 
     # Adjust the crop boundaries to stay within the original image's dimensions
     if x_min < 0:
-        context.services.logger.warning("FaceTools --> -X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -X-axis padding reached image edge.")
         x_max -= x_min
         x_min = 0
     elif x_max > mask.width:
-        context.services.logger.warning("FaceTools --> +X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +X-axis padding reached image edge.")
         x_min -= x_max - mask.width
         x_max = mask.width
 
     if y_min < 0:
-        context.services.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
         y_max -= y_min
         y_min = 0
     elif y_max > mask.height:
-        context.services.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
         y_min -= y_max - mask.height
         y_max = mask.height
 
     # Ensure the crop is square and adjust the boundaries if needed
     if x_max - x_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
         diff = crop_size - (x_max - x_min)
         x_min -= diff // 2
         x_max += diff - diff // 2
 
     if y_max - y_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
         diff = crop_size - (y_max - y_min)
         y_min -= diff // 2
         y_max += diff - diff // 2
 
-    context.services.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
+    context.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
 
     # Crop the output image to the specified size with the center of the face mesh as the center.
     mask = mask.crop((x_min, y_min, x_max, y_max))
@@ -368,7 +366,7 @@ def get_faces_list(
 
     # Generate the face box mask and get the center of the face.
     if not should_chunk:
-        context.services.logger.info("FaceTools --> Attempting full image face detection.")
+        context.logger.info("FaceTools --> Attempting full image face detection.")
         result = generate_face_box_mask(
             context=context,
             minimum_confidence=minimum_confidence,
@@ -380,7 +378,7 @@ def get_faces_list(
             draw_mesh=draw_mesh,
         )
     if should_chunk or len(result) == 0:
-        context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
+        context.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
         width, height = image.size
         image_chunks = []
         x_offsets = []
@@ -399,7 +397,7 @@ def get_faces_list(
                 x_offsets.append(x)
                 y_offsets.append(0)
                 fx += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
+                context.logger.info(f"FaceTools --> Chunk starting at x = {x}")
         elif height > width:
             # Portrait - slice the image vertically
             fy = 0.0
@@ -411,10 +409,10 @@ def get_faces_list(
                 x_offsets.append(0)
                 y_offsets.append(y)
                 fy += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
+                context.logger.info(f"FaceTools --> Chunk starting at y = {y}")
 
         for idx in range(len(image_chunks)):
-            context.services.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
+            context.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
             result = result + generate_face_box_mask(
                 context=context,
                 minimum_confidence=minimum_confidence,
@@ -428,7 +426,7 @@ def get_faces_list(
 
         if len(result) == 0:
             # Give up
-            context.services.logger.warning(
+            context.logger.warning(
                 "FaceTools --> No face detected in chunked input image. Passing through original image."
             )
 
@@ -437,7 +435,7 @@ def get_faces_list(
     return all_faces
 
 
-@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.1")
 class FaceOffInvocation(BaseInvocation, WithMetadata):
     """Bound, extract, and mask a face from an image using MediaPipe detection"""
 
@@ -470,11 +468,11 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         )
 
         if len(all_faces) == 0:
-            context.services.logger.warning("FaceOff --> No faces detected. Passing through original image.")
+            context.logger.warning("FaceOff --> No faces detected. Passing through original image.")
             return None
 
         if self.face_id > len(all_faces) - 1:
-            context.services.logger.warning(
+            context.logger.warning(
                 f"FaceOff --> Face ID {self.face_id} is outside of the number of faces detected ({len(all_faces)}). Passing through original image."
             )
             return None
@@ -486,7 +484,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return face_data
 
     def invoke(self, context: InvocationContext) -> FaceOffOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.faceoff(context=context, image=image)
 
         if result is None:
@@ -500,24 +498,9 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
             x = result["x_min"]
             y = result["y_min"]
 
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        mask_dto = context.services.images.create(
-            image=result_mask,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result_mask, image_category=ImageCategory.MASK)
 
         output = FaceOffOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -531,7 +514,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return output
 
 
-@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.1")
 class FaceMaskInvocation(BaseInvocation, WithMetadata):
     """Face mask creation using mediapipe face detection"""
 
@@ -580,7 +563,7 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
             if len(intersected_face_ids) == 0:
                 id_range_str = ",".join([str(id) for id in id_range])
-                context.services.logger.warning(
+                context.logger.warning(
                     f"Face IDs must be in range of detected faces - requested {self.face_ids}, detected {id_range_str}. Passing through original image."
                 )
                 return FaceMaskResult(
@@ -616,27 +599,12 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
         )
 
     def invoke(self, context: InvocationContext) -> FaceMaskOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.facemask(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result["image"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result["image"])
 
-        mask_dto = context.services.images.create(
-            image=result["mask"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result["mask"], image_category=ImageCategory.MASK)
 
         output = FaceMaskOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -649,9 +617,9 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
 
 @invocation(
-    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.0"
+    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.1"
 )
-class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
+class FaceIdentifierInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
 
     image: ImageField = InputField(description="Image to face detect")
@@ -705,21 +673,9 @@ class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
         return image
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result_image = self.faceidentifier(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/fields.py

@@ -0,0 +1,565 @@
+from enum import Enum
+from typing import Any, Callable, Optional, Tuple
+
+from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter
+from pydantic.fields import _Unset
+from pydantic_core import PydanticUndefined
+
+from invokeai.app.util.metaenum import MetaEnum
+from invokeai.backend.util.logging import InvokeAILogger
+
+logger = InvokeAILogger.get_logger()
+
+
+class UIType(str, Enum, metaclass=MetaEnum):
+    """
+    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
+
+    - Model Fields
+    The most common node-author-facing use will be for model fields. Internally, there is no difference
+    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
+    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
+    the field is an SDXL main model field.
+
+    - Any Field
+    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
+    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
+
+    - Scheduler Field
+    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
+
+    - Internal Fields
+    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
+    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
+    should not be used by node authors.
+
+    - DEPRECATED Fields
+    These types are deprecated and should not be used by node authors. A warning will be logged if one is
+    used, and the type will be ignored. They are included here for backwards compatibility.
+    """
+
+    # region Model Field Types
+    SDXLMainModel = "SDXLMainModelField"
+    SDXLRefinerModel = "SDXLRefinerModelField"
+    ONNXModel = "ONNXModelField"
+    VaeModel = "VAEModelField"
+    LoRAModel = "LoRAModelField"
+    ControlNetModel = "ControlNetModelField"
+    IPAdapterModel = "IPAdapterModelField"
+    # endregion
+
+    # region Misc Field Types
+    Scheduler = "SchedulerField"
+    Any = "AnyField"
+    # endregion
+
+    # region Internal Field Types
+    _Collection = "CollectionField"
+    _CollectionItem = "CollectionItemField"
+    # endregion
+
+    # region DEPRECATED
+    Boolean = "DEPRECATED_Boolean"
+    Color = "DEPRECATED_Color"
+    Conditioning = "DEPRECATED_Conditioning"
+    Control = "DEPRECATED_Control"
+    Float = "DEPRECATED_Float"
+    Image = "DEPRECATED_Image"
+    Integer = "DEPRECATED_Integer"
+    Latents = "DEPRECATED_Latents"
+    String = "DEPRECATED_String"
+    BooleanCollection = "DEPRECATED_BooleanCollection"
+    ColorCollection = "DEPRECATED_ColorCollection"
+    ConditioningCollection = "DEPRECATED_ConditioningCollection"
+    ControlCollection = "DEPRECATED_ControlCollection"
+    FloatCollection = "DEPRECATED_FloatCollection"
+    ImageCollection = "DEPRECATED_ImageCollection"
+    IntegerCollection = "DEPRECATED_IntegerCollection"
+    LatentsCollection = "DEPRECATED_LatentsCollection"
+    StringCollection = "DEPRECATED_StringCollection"
+    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
+    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
+    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
+    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
+    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
+    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
+    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
+    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
+    StringPolymorphic = "DEPRECATED_StringPolymorphic"
+    MainModel = "DEPRECATED_MainModel"
+    UNet = "DEPRECATED_UNet"
+    Vae = "DEPRECATED_Vae"
+    CLIP = "DEPRECATED_CLIP"
+    Collection = "DEPRECATED_Collection"
+    CollectionItem = "DEPRECATED_CollectionItem"
+    Enum = "DEPRECATED_Enum"
+    WorkflowField = "DEPRECATED_WorkflowField"
+    IsIntermediate = "DEPRECATED_IsIntermediate"
+    BoardField = "DEPRECATED_BoardField"
+    MetadataItem = "DEPRECATED_MetadataItem"
+    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
+    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
+    MetadataDict = "DEPRECATED_MetadataDict"
+
+
+class UIComponent(str, Enum, metaclass=MetaEnum):
+    """
+    The type of UI component to use for a field, used to override the default components, which are
+    inferred from the field type.
+    """
+
+    None_ = "none"
+    Textarea = "textarea"
+    Slider = "slider"
+
+
+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"
+    cfg_scale = "Classifier-Free Guidance scale"
+    cfg_rescale_multiplier = "Rescale multiplier for CFG guidance, used for models trained with zero-terminal SNR"
+    scheduler = "Scheduler to use during inference"
+    positive_cond = "Positive conditioning tensor"
+    negative_cond = "Negative conditioning tensor"
+    noise = "Noise tensor"
+    clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
+    unet = "UNet (scheduler, LoRAs)"
+    vae = "VAE"
+    cond = "Conditioning tensor"
+    controlnet_model = "ControlNet model to load"
+    vae_model = "VAE model to load"
+    lora_model = "LoRA model to load"
+    main_model = "Main model (UNet, VAE, CLIP) to load"
+    sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
+    sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
+    onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
+    lora_weight = "The weight at which the LoRA is applied to each model"
+    compel_prompt = "Prompt to be parsed by Compel to create a conditioning tensor"
+    raw_prompt = "Raw prompt text (no parsing)"
+    sdxl_aesthetic = "The aesthetic score to apply to the conditioning tensor"
+    skipped_layers = "Number of layers to skip in text encoder"
+    seed = "Seed for random number generation"
+    steps = "Number of steps to run"
+    width = "Width of output (px)"
+    height = "Height of output (px)"
+    control = "ControlNet(s) to apply"
+    ip_adapter = "IP-Adapter to apply"
+    t2i_adapter = "T2I-Adapter(s) to apply"
+    denoised_latents = "Denoised latents tensor"
+    latents = "Latents tensor"
+    strength = "Strength of denoising (proportional to steps)"
+    metadata = "Optional metadata to be saved with the image"
+    metadata_collection = "Collection of Metadata"
+    metadata_item_polymorphic = "A single metadata item or collection of metadata items"
+    metadata_item_label = "Label for this metadata item"
+    metadata_item_value = "The value for this metadata item (may be any type)"
+    workflow = "Optional workflow to be saved with the image"
+    interp_mode = "Interpolation mode"
+    torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
+    fp32 = "Whether or not to use full float32 precision"
+    precision = "Precision to use"
+    tiled = "Processing using overlapping tiles (reduce memory consumption)"
+    detect_res = "Pixel resolution for detection"
+    image_res = "Pixel resolution for output image"
+    safe_mode = "Whether or not to use safe mode"
+    scribble_mode = "Whether or not to use scribble mode"
+    scale_factor = "The factor by which to scale"
+    blend_alpha = (
+        "Blending factor. 0.0 = use input A only, 1.0 = use input B only, 0.5 = 50% mix of input A and input B."
+    )
+    num_1 = "The first number"
+    num_2 = "The second number"
+    mask = "The mask to use for the operation"
+    board = "The board to save the image to"
+    image = "The image to process"
+    tile_size = "Tile size"
+    inclusive_low = "The inclusive low value"
+    exclusive_high = "The exclusive high value"
+    decimal_places = "The number of decimal places to round to"
+    freeu_s1 = 'Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
+    freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."
+
+
+class ImageField(BaseModel):
+    """An image primitive field"""
+
+    image_name: str = Field(description="The name of the image")
+
+
+class BoardField(BaseModel):
+    """A board primitive field"""
+
+    board_id: str = Field(description="The id of the board")
+
+
+class DenoiseMaskField(BaseModel):
+    """An inpaint mask field"""
+
+    mask_name: str = Field(description="The name of the mask image")
+    masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
+
+
+class LatentsField(BaseModel):
+    """A latents tensor primitive field"""
+
+    latents_name: str = Field(description="The name of the latents")
+    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
+
+
+class ColorField(BaseModel):
+    """A color primitive field"""
+
+    r: int = Field(ge=0, le=255, description="The red component")
+    g: int = Field(ge=0, le=255, description="The green component")
+    b: int = Field(ge=0, le=255, description="The blue component")
+    a: int = Field(ge=0, le=255, description="The alpha component")
+
+    def tuple(self) -> Tuple[int, int, int, int]:
+        return (self.r, self.g, self.b, self.a)
+
+
+class ConditioningField(BaseModel):
+    """A conditioning tensor primitive value"""
+
+    conditioning_name: str = Field(description="The name of conditioning tensor")
+    # endregion
+
+
+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 Input(str, Enum, metaclass=MetaEnum):
+    """
+    The type of input a field accepts.
+    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
+      are instantiated.
+    - `Input.Connection`: The field must have its value provided by a connection.
+    - `Input.Any`: The field may have its value provided either directly or by a connection.
+    """
+
+    Connection = "connection"
+    Direct = "direct"
+    Any = "any"
+
+
+class FieldKind(str, Enum, metaclass=MetaEnum):
+    """
+    The kind of field.
+    - `Input`: An input field on a node.
+    - `Output`: An output field on a node.
+    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
+    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
+    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
+    allowing "metadata" for that field.
+    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
+    but which are used to store information about the node. For example, the `id` and `type` fields are node
+    attributes.
+
+    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
+    startup, and when generating the OpenAPI schema for the workflow editor.
+    """
+
+    Input = "input"
+    Output = "output"
+    Internal = "internal"
+    NodeAttribute = "node_attribute"
+
+
+class InputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
+    and by the workflow editor during schema parsing and UI rendering.
+    """
+
+    input: Input
+    orig_required: bool
+    field_kind: FieldKind
+    default: Optional[Any] = None
+    orig_default: Optional[Any] = None
+    ui_hidden: bool = False
+    ui_type: Optional[UIType] = None
+    ui_component: Optional[UIComponent] = None
+    ui_order: Optional[int] = None
+    ui_choice_labels: Optional[dict[str, str]] = None
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+class WithMetadata(BaseModel):
+    """
+    Inherit from this class if your node needs a metadata input field.
+    """
+
+    metadata: Optional[MetadataField] = Field(
+        default=None,
+        description=FieldDescriptions.metadata,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Connection,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class WithWorkflow:
+    workflow = None
+
+    def __init_subclass__(cls) -> None:
+        logger.warn(
+            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
+        )
+        super().__init_subclass__()
+
+
+class WithBoard(BaseModel):
+    """
+    Inherit from this class if your node needs a board input field.
+    """
+
+    board: Optional[BoardField] = Field(
+        default=None,
+        description=FieldDescriptions.board,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Direct,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class OutputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
+    during schema parsing and UI rendering.
+    """
+
+    field_kind: FieldKind
+    ui_hidden: bool
+    ui_type: Optional[UIType]
+    ui_order: Optional[int]
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+def InputField(
+    # copied from pydantic's Field
+    # TODO: Can we support default_factory?
+    default: Any = _Unset,
+    default_factory: Callable[[], Any] | None = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    input: Input = Input.Any,
+    ui_type: Optional[UIType] = None,
+    ui_component: Optional[UIComponent] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+    ui_choice_labels: Optional[dict[str, str]] = None,
+) -> Any:
+    """
+    Creates an input field for an invocation.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param Input input: [Input.Any] The kind of input this field requires. \
+      `Input.Direct` means a value must be provided on instantiation. \
+      `Input.Connection` means the value must be provided by a connection. \
+      `Input.Any` means either will do.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
+      The UI will always render a suitable component, but sometimes you want something different than the default. \
+      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
+      For this case, you could provide `UIComponent.Textarea`.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
+
+    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
+    """
+
+    json_schema_extra_ = InputFieldJSONSchemaExtra(
+        input=input,
+        ui_type=ui_type,
+        ui_component=ui_component,
+        ui_hidden=ui_hidden,
+        ui_order=ui_order,
+        ui_choice_labels=ui_choice_labels,
+        field_kind=FieldKind.Input,
+        orig_required=True,
+    )
+
+    """
+    There is a conflict between the typing of invocation definitions and the typing of an invocation's
+    `invoke()` function.
+
+    On instantiation of a node, the invocation definition is used to create the python class. At this time,
+    any number of fields may be optional, because they may be provided by connections.
+
+    On calling of `invoke()`, however, those fields may be required.
+
+    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
+
+    `image` is required during the call to `invoke()`, but when the python class is instantiated,
+    the field may not be present. This is fine, because that image field will be provided by a
+    connection from an ancestor node, which outputs an image.
+
+    This means we want to type the `image` field as optional for the node class definition, but required
+    for the `invoke()` function.
+
+    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
+    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
+    any static type analysis tools will complain.
+
+    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
+    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
+    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
+    """
+
+    if default_factory is not _Unset and default_factory is not None:
+        default = default_factory()
+        logger.warn('"default_factory" is not supported, calling it now to set "default"')
+
+    # These are the args we may wish pass to the pydantic `Field()` function
+    field_args = {
+        "default": default,
+        "title": title,
+        "description": description,
+        "pattern": pattern,
+        "strict": strict,
+        "gt": gt,
+        "ge": ge,
+        "lt": lt,
+        "le": le,
+        "multiple_of": multiple_of,
+        "allow_inf_nan": allow_inf_nan,
+        "max_digits": max_digits,
+        "decimal_places": decimal_places,
+        "min_length": min_length,
+        "max_length": max_length,
+    }
+
+    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
+    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
+
+    # Because we are manually making fields optional, we need to store the original required bool for reference later
+    json_schema_extra_.orig_required = default is PydanticUndefined
+
+    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
+    if input is Input.Any or input is Input.Connection:
+        default_ = None if default is PydanticUndefined else default
+        provided_args.update({"default": default_})
+        if default is not PydanticUndefined:
+            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
+            json_schema_extra_.default = default
+            json_schema_extra_.orig_default = default
+    elif default is not PydanticUndefined:
+        default_ = default
+        provided_args.update({"default": default_})
+        json_schema_extra_.orig_default = default_
+
+    return Field(
+        **provided_args,
+        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
+    )
+
+
+def OutputField(
+    # copied from pydantic's Field
+    default: Any = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    ui_type: Optional[UIType] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+) -> Any:
+    """
+    Creates an output field for an invocation output.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
+    """
+    return Field(
+        default=default,
+        title=title,
+        description=description,
+        pattern=pattern,
+        strict=strict,
+        gt=gt,
+        ge=ge,
+        lt=lt,
+        le=le,
+        multiple_of=multiple_of,
+        allow_inf_nan=allow_inf_nan,
+        max_digits=max_digits,
+        decimal_places=decimal_places,
+        min_length=min_length,
+        max_length=max_length,
+        json_schema_extra=OutputFieldJSONSchemaExtra(
+            ui_type=ui_type,
+            ui_hidden=ui_hidden,
+            ui_order=ui_order,
+            field_kind=FieldKind.Output,
+        ).model_dump(exclude_none=True),
+    )

invokeai/app/invocations/infill.py

@@ -6,14 +6,16 @@ from typing import Literal, Optional, get_args
 import numpy as np
 from PIL import Image, ImageOps
 
-from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ColorField, ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
 from invokeai.backend.image_util.lama import LaMA
 from invokeai.backend.image_util.patchmatch import PatchMatch
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
 
 
@@ -118,8 +120,8 @@ def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int]
     return si
 
 
-@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class InfillColorInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class InfillColorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image with a solid color"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -129,33 +131,20 @@ class InfillColorInvocation(BaseInvocation, WithMetadata):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         solid_bg = Image.new("RGBA", image.size, self.color.tuple())
         infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
 
         infilled.paste(image, (0, 0), image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
-class InfillTileInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
+class InfillTileInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image with tiles of the image"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -168,33 +157,20 @@ class InfillTileInvocation(BaseInvocation, WithMetadata):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = tile_fill_missing(image.copy(), seed=self.seed, tile_size=self.tile_size)
         infilled.paste(image, (0, 0), image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
 @invocation(
-    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0"
+    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1"
 )
-class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
+class InfillPatchMatchInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -202,7 +178,7 @@ class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name).convert("RGBA")
+        image = context.images.get_pil(self.image.image_name).convert("RGBA")
 
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
@@ -227,77 +203,38 @@ class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
         infilled.paste(image, (0, 0), mask=image.split()[-1])
         # image.paste(infilled, (0, 0), mask=image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class LaMaInfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class LaMaInfillInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using the LaMa model"""
 
     image: ImageField = InputField(description="The image to infill")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = infill_lama(image.copy())
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class CV2InfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class CV2InfillInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
     image: ImageField = InputField(description="The image to infill")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = infill_cv2(image.copy())
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/ip_adapter.py

@@ -1,38 +1,29 @@
-import os
 from builtins import float
 from typing import List, Union
 
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
+from typing_extensions import Self
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.model_management.models.base import BaseModelType, ModelType
-from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager.config import BaseModelType, ModelType
 
 
+# LS: Consider moving these two classes into model.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=())
+    key: str = Field(description="Key to the IP-Adapter model")
 
 
 class CLIPVisionModelField(BaseModel):
-    model_name: str = Field(description="Name of the CLIP Vision image encoder model")
-    base_model: BaseModelType = Field(description="Base model (usually 'Any')")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Key to the CLIP Vision image encoder model")
 
 
 class IPAdapterField(BaseModel):
@@ -49,12 +40,12 @@ class IPAdapterField(BaseModel):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v):
+    def validate_ip_adapter_weight(cls, v: float) -> float:
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self):
+    def validate_begin_end_step_percent(self) -> Self:
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
@@ -65,7 +56,7 @@ 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="1.1.1")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.2")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
@@ -87,33 +78,25 @@ class IPAdapterInvocation(BaseInvocation):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v):
+    def validate_ip_adapter_weight(cls, v: float) -> float:
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self):
+    def validate_begin_end_step_percent(self) -> Self:
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
     def invoke(self, context: InvocationContext) -> IPAdapterOutput:
         # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
-        ip_adapter_info = context.services.model_manager.model_info(
-            self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
-        )
-        # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
-        # directly, and 2) we are reading from disk every time this invocation is called without caching the result.
-        # A better solution would be to store the image encoder model reference in the IP-Adapter model info, but this
-        # is currently messy due to differences between how the model info is generated when installing a model from
-        # disk vs. downloading the model.
-        image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
-            os.path.join(context.services.configuration.get_config().models_path, ip_adapter_info["path"])
-        )
+        ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
+        image_encoder_model_id = ip_adapter_info.image_encoder_model_id
         image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
-        image_encoder_model = CLIPVisionModelField(
-            model_name=image_encoder_model_name,
-            base_model=BaseModelType.Any,
+        image_encoder_models = context.models.search_by_attrs(
+            model_name=image_encoder_model_name, base_model=BaseModelType.Any, model_type=ModelType.CLIPVision
         )
+        assert len(image_encoder_models) == 1
+        image_encoder_model = CLIPVisionModelField(key=image_encoder_models[0].key)
         return IPAdapterOutput(
             ip_adapter=IPAdapterField(
                 image=self.image,

invokeai/app/invocations/latent.py

@@ -1,14 +1,17 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
+import math
 from contextlib import ExitStack
 from functools import singledispatchmethod
-from typing import List, Literal, Optional, Union
+from typing import Any, Iterator, List, Literal, Optional, Tuple, Union
 
 import einops
 import numpy as np
+import numpy.typing as npt
 import torch
 import torchvision.transforms as T
 from diffusers import AutoencoderKL, AutoencoderTiny
+from diffusers.configuration_utils import ConfigMixin
 from diffusers.image_processor import VaeImageProcessor
 from diffusers.models.adapter import T2IAdapter
 from diffusers.models.attention_processor import (
@@ -17,34 +20,44 @@ from diffusers.models.attention_processor import (
     LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
+from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
 from diffusers.schedulers import DPMSolverSDEScheduler
 from diffusers.schedulers import SchedulerMixin as Scheduler
+from PIL import Image
 from pydantic import field_validator
 from torchvision.transforms.functional import resize as tv_resize
 
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR, SCHEDULER_NAME_VALUES
+from invokeai.app.invocations.fields import (
+    ConditioningField,
+    DenoiseMaskField,
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    LatentsField,
+    OutputField,
+    UIType,
+    WithBoard,
+    WithMetadata,
+)
 from invokeai.app.invocations.ip_adapter import IPAdapterField
 from invokeai.app.invocations.primitives import (
-    DenoiseMaskField,
     DenoiseMaskOutput,
-    ImageField,
     ImageOutput,
-    LatentsField,
     LatentsOutput,
-    build_latents_output,
 )
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
-from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
-from invokeai.backend.model_management.models import ModelType, SilenceWarnings
+from invokeai.backend.lora import LoRAModelRaw
+from invokeai.backend.model_manager import BaseModelType, LoadedModel
+from invokeai.backend.model_patcher import ModelPatcher
+from invokeai.backend.stable_diffusion import PipelineIntermediateState, set_seamless
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
+from invokeai.backend.util.silence_warnings import SilenceWarnings
 
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import BaseModelType
-from ...backend.model_management.seamless import set_seamless
-from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.stable_diffusion.diffusers_pipeline import (
     ControlNetData,
     IPAdapterData,
@@ -58,16 +71,9 @@ from ...backend.util.devices import choose_precision, choose_torch_device
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from .compel import ConditioningField
 from .controlnet_image_processors import ControlField
 from .model import ModelInfo, UNetField, VaeField
 
@@ -76,18 +82,10 @@ if choose_torch_device() == torch.device("mps"):
 
 DEFAULT_PRECISION = choose_precision(choose_torch_device())
 
-SAMPLER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
-
-# HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
-# be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
-# factor is hard-coded to a literal '8' rather than using this constant.
-# The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
-LATENT_SCALE_FACTOR = 8
-
 
 @invocation_output("scheduler_output")
 class SchedulerOutput(BaseInvocationOutput):
-    scheduler: SAMPLER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
+    scheduler: SCHEDULER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
 
 
 @invocation(
@@ -100,7 +98,7 @@ class SchedulerOutput(BaseInvocationOutput):
 class SchedulerInvocation(BaseInvocation):
     """Selects a scheduler."""
 
-    scheduler: SAMPLER_NAME_VALUES = InputField(
+    scheduler: SCHEDULER_NAME_VALUES = InputField(
         default="euler",
         description=FieldDescriptions.scheduler,
         ui_type=UIType.Scheduler,
@@ -115,7 +113,7 @@ class SchedulerInvocation(BaseInvocation):
     title="Create Denoise Mask",
     tags=["mask", "denoise"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class CreateDenoiseMaskInvocation(BaseInvocation):
     """Creates mask for denoising model run."""
@@ -130,10 +128,10 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
         ui_order=4,
     )
 
-    def prep_mask_tensor(self, mask_image):
+    def prep_mask_tensor(self, mask_image: Image) -> torch.Tensor:
         if mask_image.mode != "L":
             mask_image = mask_image.convert("L")
-        mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        mask_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
         if mask_tensor.dim() == 3:
             mask_tensor = mask_tensor.unsqueeze(0)
         # if shape is not None:
@@ -143,41 +141,34 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
         if self.image is not None:
-            image = context.services.images.get_pil_image(self.image.image_name)
-            image = image_resized_to_grid_as_tensor(image.convert("RGB"))
-            if image.dim() == 3:
-                image = image.unsqueeze(0)
+            image = context.images.get_pil(self.image.image_name)
+            image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+            if image_tensor.dim() == 3:
+                image_tensor = image_tensor.unsqueeze(0)
         else:
-            image = None
+            image_tensor = None
 
         mask = self.prep_mask_tensor(
-            context.services.images.get_pil_image(self.mask.image_name),
+            context.images.get_pil(self.mask.image_name),
         )
 
-        if image is not None:
-            vae_info = context.services.model_manager.get_model(
-                **self.vae.vae.model_dump(),
-                context=context,
-            )
+        if image_tensor is not None:
+            vae_info = context.models.load(**self.vae.vae.model_dump())
 
-            img_mask = tv_resize(mask, image.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
-            masked_image = image * torch.where(img_mask < 0.5, 0.0, 1.0)
+            img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
+            masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
             # TODO:
             masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
 
-            masked_latents_name = f"{context.graph_execution_state_id}__{self.id}_masked_latents"
-            context.services.latents.save(masked_latents_name, masked_latents)
+            masked_latents_name = context.tensors.save(tensor=masked_latents)
         else:
             masked_latents_name = None
 
-        mask_name = f"{context.graph_execution_state_id}__{self.id}_mask"
-        context.services.latents.save(mask_name, mask)
+        mask_name = context.tensors.save(tensor=mask)
 
-        return DenoiseMaskOutput(
-            denoise_mask=DenoiseMaskField(
-                mask_name=mask_name,
-                masked_latents_name=masked_latents_name,
-            ),
+        return DenoiseMaskOutput.build(
+            mask_name=mask_name,
+            masked_latents_name=masked_latents_name,
         )
 
 
@@ -188,10 +179,7 @@ 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(
-        **scheduler_info.model_dump(),
-        context=context,
-    )
+    orig_scheduler_info = context.models.load(**scheduler_info.model_dump())
     with orig_scheduler_info as orig_scheduler:
         scheduler_config = orig_scheduler.config
 
@@ -199,7 +187,7 @@ def get_scheduler(
         scheduler_config = scheduler_config["_backup"]
     scheduler_config = {
         **scheduler_config,
-        **scheduler_extra_config,
+        **scheduler_extra_config,  # FIXME
         "_backup": scheduler_config,
     }
 
@@ -212,6 +200,7 @@ def get_scheduler(
     # hack copied over from generate.py
     if not hasattr(scheduler, "uses_inpainting_model"):
         scheduler.uses_inpainting_model = lambda: False
+    assert isinstance(scheduler, Scheduler)
     return scheduler
 
 
@@ -220,7 +209,7 @@ def get_scheduler(
     title="Denoise Latents",
     tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
     category="latents",
-    version="1.5.1",
+    version="1.5.2",
 )
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
@@ -248,7 +237,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         description=FieldDescriptions.denoising_start,
     )
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
-    scheduler: SAMPLER_NAME_VALUES = InputField(
+    scheduler: SCHEDULER_NAME_VALUES = InputField(
         default="euler",
         description=FieldDescriptions.scheduler,
         ui_type=UIType.Scheduler,
@@ -295,7 +284,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     )
 
     @field_validator("cfg_scale")
-    def ge_one(cls, v):
+    def ge_one(cls, v: Union[List[float], float]) -> Union[List[float], float]:
         """validate that all cfg_scale values are >= 1"""
         if isinstance(v, list):
             for i in v:
@@ -306,34 +295,18 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 raise ValueError("cfg_scale must be greater than 1")
         return v
 
-    # TODO: pass this an emitter method or something? or a session for dispatching?
-    def dispatch_progress(
-        self,
-        context: InvocationContext,
-        source_node_id: str,
-        intermediate_state: PipelineIntermediateState,
-        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,
-        )
-
     def get_conditioning_data(
         self,
         context: InvocationContext,
-        scheduler,
-        unet,
-        seed,
+        scheduler: Scheduler,
+        unet: UNet2DConditionModel,
+        seed: int,
     ) -> ConditioningData:
-        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        positive_cond_data = context.conditioning.load(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.conditioning.load(self.negative_conditioning.conditioning_name)
         uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
 
         conditioning_data = ConditioningData(
@@ -350,7 +323,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             ),
         )
 
-        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(
+        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(  # FIXME
             scheduler,
             # for ddim scheduler
             eta=0.0,  # ddim_eta
@@ -362,8 +335,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     def create_pipeline(
         self,
-        unet,
-        scheduler,
+        unet: UNet2DConditionModel,
+        scheduler: Scheduler,
     ) -> StableDiffusionGeneratorPipeline:
         # TODO:
         # configure_model_padding(
@@ -374,10 +347,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         class FakeVae:
             class FakeVaeConfig:
-                def __init__(self):
+                def __init__(self) -> None:
                     self.block_out_channels = [0]
 
-            def __init__(self):
+            def __init__(self) -> None:
                 self.config = FakeVae.FakeVaeConfig()
 
         return StableDiffusionGeneratorPipeline(
@@ -394,11 +367,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def prep_control_data(
         self,
         context: InvocationContext,
-        control_input: Union[ControlField, List[ControlField]],
+        control_input: Optional[Union[ControlField, List[ControlField]]],
         latents_shape: List[int],
         exit_stack: ExitStack,
         do_classifier_free_guidance: bool = True,
-    ) -> List[ControlNetData]:
+    ) -> Optional[List[ControlNetData]]:
         # Assuming fixed dimensional scaling of LATENT_SCALE_FACTOR.
         control_height_resize = latents_shape[2] * LATENT_SCALE_FACTOR
         control_width_resize = latents_shape[3] * LATENT_SCALE_FACTOR
@@ -420,18 +393,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         #        and if weight is None, populate with default 1.0?
         controlnet_data = []
         for control_info in control_list:
-            control_model = exit_stack.enter_context(
-                context.services.model_manager.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_model = exit_stack.enter_context(context.models.load(key=control_info.control_model.key))
 
             # 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.images.get_pil(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?
@@ -489,27 +455,17 @@ 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(
-                    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,
-                )
+                context.models.load(key=single_ip_adapter.ip_adapter_model.key)
             )
 
-            image_encoder_model_info = context.services.model_manager.get_model(
-                model_name=single_ip_adapter.image_encoder_model.model_name,
-                model_type=ModelType.CLIPVision,
-                base_model=single_ip_adapter.image_encoder_model.base_model,
-                context=context,
-            )
+            image_encoder_model_info = context.models.load(key=single_ip_adapter.image_encoder_model.key)
 
             # `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_image_fields = single_ip_adapter.image
+            if not isinstance(single_ipa_image_fields, list):
+                single_ipa_image_fields = [single_ipa_image_fields]
 
-            single_ipa_images = [context.services.images.get_pil_image(image.image_name) for image in single_ipa_images]
+            single_ipa_images = [context.images.get_pil(image.image_name) for image in single_ipa_image_fields]
 
             # 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.
@@ -553,26 +509,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
-            t2i_adapter_model_info = context.services.model_manager.get_model(
-                model_name=t2i_adapter_field.t2i_adapter_model.model_name,
-                model_type=ModelType.T2IAdapter,
-                base_model=t2i_adapter_field.t2i_adapter_model.base_model,
-                context=context,
-            )
-            image = context.services.images.get_pil_image(t2i_adapter_field.image.image_name)
+            t2i_adapter_model_config = context.models.get_config(key=t2i_adapter_field.t2i_adapter_model.key)
+            t2i_adapter_loaded_model = context.models.load(key=t2i_adapter_field.t2i_adapter_model.key)
+            image = context.images.get_pil(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:
+            if t2i_adapter_model_config.base == BaseModelType.StableDiffusion1:
                 max_unet_downscale = 8
-            elif t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusionXL:
+            elif t2i_adapter_model_config.base == BaseModelType.StableDiffusionXL:
                 max_unet_downscale = 4
             else:
-                raise ValueError(
-                    f"Unexpected T2I-Adapter base model type: '{t2i_adapter_field.t2i_adapter_model.base_model}'."
-                )
+                raise ValueError(f"Unexpected T2I-Adapter base model type: '{t2i_adapter_model_config.base}'.")
 
             t2i_adapter_model: T2IAdapter
-            with t2i_adapter_model_info as t2i_adapter_model:
+            with t2i_adapter_loaded_model as t2i_adapter_model:
                 total_downscale_factor = t2i_adapter_model.total_downscale_factor
 
                 # Resize the T2I-Adapter input image.
@@ -592,7 +542,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     do_classifier_free_guidance=False,
                     width=t2i_input_width,
                     height=t2i_input_height,
-                    num_channels=t2i_adapter_model.config.in_channels,
+                    num_channels=t2i_adapter_model.config["in_channels"],  # mypy treats this as a FrozenDict
                     device=t2i_adapter_model.device,
                     dtype=t2i_adapter_model.dtype,
                     resize_mode=t2i_adapter_field.resize_mode,
@@ -617,7 +567,15 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     # original idea by https://github.com/AmericanPresidentJimmyCarter
     # TODO: research more for second order schedulers timesteps
-    def init_scheduler(self, scheduler, device, steps, denoising_start, denoising_end):
+    def init_scheduler(
+        self,
+        scheduler: Union[Scheduler, ConfigMixin],
+        device: torch.device,
+        steps: int,
+        denoising_start: float,
+        denoising_end: float,
+    ) -> Tuple[int, List[int], int]:
+        assert isinstance(scheduler, ConfigMixin)
         if scheduler.config.get("cpu_only", False):
             scheduler.set_timesteps(steps, device="cpu")
             timesteps = scheduler.timesteps.to(device=device)
@@ -629,11 +587,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         _timesteps = timesteps[:: scheduler.order]
 
         # get start timestep index
-        t_start_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_start)))
+        t_start_val = int(round(scheduler.config["num_train_timesteps"] * (1 - denoising_start)))
         t_start_idx = len(list(filter(lambda ts: ts >= t_start_val, _timesteps)))
 
         # get end timestep index
-        t_end_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_end)))
+        t_end_val = int(round(scheduler.config["num_train_timesteps"] * (1 - denoising_end)))
         t_end_idx = len(list(filter(lambda ts: ts >= t_end_val, _timesteps[t_start_idx:])))
 
         # apply order to indexes
@@ -646,14 +604,16 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         return num_inference_steps, timesteps, init_timestep
 
-    def prep_inpaint_mask(self, context, latents):
+    def prep_inpaint_mask(
+        self, context: InvocationContext, latents: torch.Tensor
+    ) -> Tuple[Optional[torch.Tensor], Optional[torch.Tensor]]:
         if self.denoise_mask is None:
             return None, None
 
-        mask = context.services.latents.get(self.denoise_mask.mask_name)
+        mask = context.tensors.load(self.denoise_mask.mask_name)
         mask = tv_resize(mask, latents.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
         if self.denoise_mask.masked_latents_name is not None:
-            masked_latents = context.services.latents.get(self.denoise_mask.masked_latents_name)
+            masked_latents = context.tensors.load(self.denoise_mask.masked_latents_name)
         else:
             masked_latents = None
 
@@ -665,11 +625,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
             seed = None
             noise = None
             if self.noise is not None:
-                noise = context.services.latents.get(self.noise.latents_name)
+                noise = context.tensors.load(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.tensors.load(self.latents.latents_name)
                 if seed is None:
                     seed = self.latents.seed
 
@@ -695,35 +655,30 @@ 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]
+            # get the unet's config so that we can pass the base to dispatch_progress()
+            unet_config = context.models.get_config(self.unet.unet.key)
 
-            def step_callback(state: PipelineIntermediateState):
-                self.dispatch_progress(context, source_node_id, state, self.unet.unet.base_model)
+            def step_callback(state: PipelineIntermediateState) -> None:
+                context.util.sd_step_callback(state, unet_config.base)
 
-            def _lora_loader():
+            def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
                 for lora in self.unet.loras:
-                    lora_info = context.services.model_manager.get_model(
-                        **lora.model_dump(exclude={"weight"}),
-                        context=context,
-                    )
-                    yield (lora_info.context.model, lora.weight)
+                    lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
+                    yield (lora_info.model, lora.weight)
                     del lora_info
                 return
 
-            unet_info = context.services.model_manager.get_model(
-                **self.unet.unet.model_dump(),
-                context=context,
-            )
+            unet_info = context.models.load(**self.unet.unet.model_dump())
+            assert isinstance(unet_info.model, UNet2DConditionModel)
             with (
                 ExitStack() as exit_stack,
-                ModelPatcher.apply_freeu(unet_info.context.model, self.unet.freeu_config),
-                set_seamless(unet_info.context.model, self.unet.seamless_axes),
+                ModelPatcher.apply_freeu(unet_info.model, self.unet.freeu_config),
+                set_seamless(unet_info.model, self.unet.seamless_axes),  # FIXME
                 unet_info as unet,
                 # Apply the LoRA after unet has been moved to its target device for faster patching.
                 ModelPatcher.apply_lora_unet(unet, _lora_loader()),
             ):
+                assert isinstance(unet, UNet2DConditionModel)
                 latents = latents.to(device=unet.device, dtype=unet.dtype)
                 if noise is not None:
                     noise = noise.to(device=unet.device, dtype=unet.dtype)
@@ -791,9 +746,8 @@ 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)
+            name = context.tensors.save(tensor=result_latents)
+        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=seed)
 
 
 @invocation(
@@ -801,9 +755,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
     title="Latents to Image",
     tags=["latents", "image", "vae", "l2i"],
     category="latents",
-    version="1.2.0",
+    version="1.2.1",
 )
-class LatentsToImageInvocation(BaseInvocation, WithMetadata):
+class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Generates an image from latents."""
 
     latents: LatentsField = InputField(
@@ -819,14 +773,12 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-            context=context,
-        )
+        vae_info = context.models.load(**self.vae.vae.model_dump())
 
-        with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
+        with set_seamless(vae_info.model, self.vae.seamless_axes), vae_info as vae:
+            assert isinstance(vae, torch.nn.Module)
             latents = latents.to(vae.device)
             if self.fp32:
                 vae.to(dtype=torch.float32)
@@ -853,7 +805,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
                 vae.to(dtype=torch.float16)
                 latents = latents.half()
 
-            if self.tiled or context.services.configuration.tiled_decode:
+            if self.tiled or context.config.get().tiled_decode:
                 vae.enable_tiling()
             else:
                 vae.disable_tiling()
@@ -877,22 +829,9 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
         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=context.workflow,
-        )
+        image_dto = context.images.save(image=image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
 LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
@@ -903,7 +842,7 @@ LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic",
     title="Resize Latents",
     tags=["latents", "resize"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ResizeLatentsInvocation(BaseInvocation):
     """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
@@ -926,7 +865,7 @@ class ResizeLatentsInvocation(BaseInvocation):
     antialias: bool = InputField(default=False, description=FieldDescriptions.torch_antialias)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         # TODO:
         device = choose_torch_device()
@@ -944,10 +883,8 @@ class ResizeLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, resized_latents)
-        return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
+        name = context.tensors.save(tensor=resized_latents)
+        return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
 @invocation(
@@ -955,7 +892,7 @@ class ResizeLatentsInvocation(BaseInvocation):
     title="Scale Latents",
     tags=["latents", "resize"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ScaleLatentsInvocation(BaseInvocation):
     """Scales latents by a given factor."""
@@ -969,7 +906,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     antialias: bool = InputField(default=False, description=FieldDescriptions.torch_antialias)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         # TODO:
         device = choose_torch_device()
@@ -988,10 +925,8 @@ class ScaleLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, resized_latents)
-        return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
+        name = context.tensors.save(tensor=resized_latents)
+        return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
 @invocation(
@@ -999,7 +934,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     title="Image to Latents",
     tags=["latents", "image", "vae", "i2l"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ImageToLatentsInvocation(BaseInvocation):
     """Encodes an image into latents."""
@@ -1015,8 +950,9 @@ class ImageToLatentsInvocation(BaseInvocation):
     fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
 
     @staticmethod
-    def vae_encode(vae_info, upcast, tiled, image_tensor):
+    def vae_encode(vae_info: LoadedModel, upcast: bool, tiled: bool, image_tensor: torch.Tensor) -> torch.Tensor:
         with vae_info as vae:
+            assert isinstance(vae, torch.nn.Module)
             orig_dtype = vae.dtype
             if upcast:
                 vae.to(dtype=torch.float32)
@@ -1060,12 +996,9 @@ class ImageToLatentsInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-            context=context,
-        )
+        vae_info = context.models.load(**self.vae.vae.model_dump())
 
         image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
         if image_tensor.dim() == 3:
@@ -1073,22 +1006,26 @@ class ImageToLatentsInvocation(BaseInvocation):
 
         latents = self.vae_encode(vae_info, self.fp32, self.tiled, image_tensor)
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
         latents = latents.to("cpu")
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=latents, seed=None)
+        name = context.tensors.save(tensor=latents)
+        return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
 
     @singledispatchmethod
     @staticmethod
     def _encode_to_tensor(vae: AutoencoderKL, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
+        assert isinstance(vae, torch.nn.Module)
         image_tensor_dist = vae.encode(image_tensor).latent_dist
-        latents = image_tensor_dist.sample().to(dtype=vae.dtype)  # FIXME: uses torch.randn. make reproducible!
+        latents: torch.Tensor = image_tensor_dist.sample().to(
+            dtype=vae.dtype
+        )  # FIXME: uses torch.randn. make reproducible!
         return latents
 
     @_encode_to_tensor.register
     @staticmethod
     def _(vae: AutoencoderTiny, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
-        return vae.encode(image_tensor).latents
+        assert isinstance(vae, torch.nn.Module)
+        latents: torch.FloatTensor = vae.encode(image_tensor).latents
+        return latents
 
 
 @invocation(
@@ -1096,7 +1033,7 @@ class ImageToLatentsInvocation(BaseInvocation):
     title="Blend Latents",
     tags=["latents", "blend"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class BlendLatentsInvocation(BaseInvocation):
     """Blend two latents using a given alpha. Latents must have same size."""
@@ -1112,8 +1049,8 @@ class BlendLatentsInvocation(BaseInvocation):
     alpha: float = InputField(default=0.5, description=FieldDescriptions.blend_alpha)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents_a = context.services.latents.get(self.latents_a.latents_name)
-        latents_b = context.services.latents.get(self.latents_b.latents_name)
+        latents_a = context.tensors.load(self.latents_a.latents_name)
+        latents_b = context.tensors.load(self.latents_b.latents_name)
 
         if latents_a.shape != latents_b.shape:
             raise Exception("Latents to blend must be the same size.")
@@ -1121,7 +1058,12 @@ class BlendLatentsInvocation(BaseInvocation):
         # TODO:
         device = choose_torch_device()
 
-        def slerp(t, v0, v1, DOT_THRESHOLD=0.9995):
+        def slerp(
+            t: Union[float, npt.NDArray[Any]],  # FIXME: maybe use np.float32 here?
+            v0: Union[torch.Tensor, npt.NDArray[Any]],
+            v1: Union[torch.Tensor, npt.NDArray[Any]],
+            DOT_THRESHOLD: float = 0.9995,
+        ) -> Union[torch.Tensor, npt.NDArray[Any]]:
             """
             Spherical linear interpolation
             Args:
@@ -1154,12 +1096,16 @@ class BlendLatentsInvocation(BaseInvocation):
                 v2 = s0 * v0 + s1 * v1
 
             if inputs_are_torch:
-                v2 = torch.from_numpy(v2).to(device)
-
-            return v2
+                v2_torch: torch.Tensor = torch.from_numpy(v2).to(device)
+                return v2_torch
+            else:
+                assert isinstance(v2, np.ndarray)
+                return v2
 
         # blend
-        blended_latents = slerp(self.alpha, latents_a, latents_b)
+        bl = slerp(self.alpha, latents_a, latents_b)
+        assert isinstance(bl, torch.Tensor)
+        blended_latents: torch.Tensor = bl  # for type checking convenience
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         blended_latents = blended_latents.to("cpu")
@@ -1167,10 +1113,8 @@ class BlendLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, blended_latents)
-        return build_latents_output(latents_name=name, latents=blended_latents)
+        name = context.tensors.save(tensor=blended_latents)
+        return LatentsOutput.build(latents_name=name, latents=blended_latents)
 
 
 # The Crop Latents node was copied from @skunkworxdark's implementation here:
@@ -1180,7 +1124,7 @@ class BlendLatentsInvocation(BaseInvocation):
     title="Crop Latents",
     tags=["latents", "crop"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 # TODO(ryand): Named `CropLatentsCoreInvocation` to prevent a conflict with custom node `CropLatentsInvocation`.
 # Currently, if the class names conflict then 'GET /openapi.json' fails.
@@ -1215,7 +1159,7 @@ class CropLatentsCoreInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         x1 = self.x // LATENT_SCALE_FACTOR
         y1 = self.y // LATENT_SCALE_FACTOR
@@ -1224,7 +1168,61 @@ class CropLatentsCoreInvocation(BaseInvocation):
 
         cropped_latents = latents[..., y1:y2, x1:x2]
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, cropped_latents)
+        name = context.tensors.save(tensor=cropped_latents)
 
-        return build_latents_output(latents_name=name, latents=cropped_latents)
+        return LatentsOutput.build(latents_name=name, latents=cropped_latents)
+
+
+@invocation_output("ideal_size_output")
+class IdealSizeOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    width: int = OutputField(description="The ideal width of the image (in pixels)")
+    height: int = OutputField(description="The ideal height of the image (in pixels)")
+
+
+@invocation(
+    "ideal_size",
+    title="Ideal Size",
+    tags=["latents", "math", "ideal_size"],
+    version="1.0.2",
+)
+class IdealSizeInvocation(BaseInvocation):
+    """Calculates the ideal size for generation to avoid duplication"""
+
+    width: int = InputField(default=1024, description="Final image width")
+    height: int = InputField(default=576, description="Final image height")
+    unet: UNetField = InputField(default=None, description=FieldDescriptions.unet)
+    multiplier: float = InputField(
+        default=1.0,
+        description="Amount to multiply the model's dimensions by when calculating the ideal size (may result in initial generation artifacts if too large)",
+    )
+
+    def trim_to_multiple_of(self, *args: int, multiple_of: int = LATENT_SCALE_FACTOR) -> Tuple[int, ...]:
+        return tuple((x - x % multiple_of) for x in args)
+
+    def invoke(self, context: InvocationContext) -> IdealSizeOutput:
+        unet_config = context.models.get_config(**self.unet.unet.model_dump())
+        aspect = self.width / self.height
+        dimension: float = 512
+        if unet_config.base == BaseModelType.StableDiffusion2:
+            dimension = 768
+        elif unet_config.base == BaseModelType.StableDiffusionXL:
+            dimension = 1024
+        dimension = dimension * self.multiplier
+        min_dimension = math.floor(dimension * 0.5)
+        model_area = dimension * dimension  # hardcoded for now since all models are trained on square images
+
+        if aspect > 1.0:
+            init_height = max(min_dimension, math.sqrt(model_area / aspect))
+            init_width = init_height * aspect
+        else:
+            init_width = max(min_dimension, math.sqrt(model_area * aspect))
+            init_height = init_width / aspect
+
+        scaled_width, scaled_height = self.trim_to_multiple_of(
+            math.floor(init_width),
+            math.floor(init_height),
+        )
+
+        return IdealSizeOutput(width=scaled_width, height=scaled_height)

invokeai/app/invocations/math.py

@@ -5,10 +5,11 @@ from typing import Literal
 import numpy as np
 from pydantic import ValidationInfo, field_validator
 
+from invokeai.app.invocations.fields import FieldDescriptions, InputField
 from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
 
 
 @invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.0")

invokeai/app/invocations/metadata.py

@@ -5,20 +5,22 @@ from pydantic import BaseModel, ConfigDict, Field
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    MetadataField,
-    OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import ControlField
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
+    InputField,
+    MetadataField,
+    OutputField,
+    UIType,
+)
 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.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from ...version import __version__
 

invokeai/app/invocations/model.py

@@ -1,31 +1,24 @@
 import copy
 from typing import List, Optional
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.shared.models import FreeUConfig
 
-from ...backend.model_management import BaseModelType, ModelType, SubModelType
+from ...backend.model_manager import SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
 
 
 class ModelInfo(BaseModel):
-    model_name: str = Field(description="Info to load submodel")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Info to load submodel")
-    submodel: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Key of model as returned by ModelRecordServiceBase.get_model()")
+    submodel_type: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
 
 
 class LoraInfo(ModelInfo):
@@ -55,7 +48,7 @@ class VaeField(BaseModel):
 
 @invocation_output("unet_output")
 class UNetOutput(BaseInvocationOutput):
-    """Base class for invocations that output a UNet field"""
+    """Base class for invocations that output a UNet field."""
 
     unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
 
@@ -84,20 +77,13 @@ class ModelLoaderOutput(UNetOutput, CLIPOutput, VAEOutput):
 class MainModelField(BaseModel):
     """Main model field"""
 
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Model Type")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Model key")
 
 
 class LoRAModelField(BaseModel):
     """LoRA model field"""
 
-    model_name: str = Field(description="Name of the LoRA model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="LoRA model key")
 
 
 @invocation(
@@ -105,7 +91,7 @@ class LoRAModelField(BaseModel):
     title="Main Model",
     tags=["model"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
@@ -114,85 +100,40 @@ class MainModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.Main
+        key = self.model.key
 
         # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
-
-        """
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.Tokenizer,
-        ):
-            raise Exception(
-                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.TextEncoder,
-        ):
-            raise Exception(
-                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.UNet,
-        ):
-            raise Exception(
-                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
-            )
-        """
+        if not context.models.exists(key):
+            raise Exception(f"Unknown model {key}")
 
         return ModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
+                    key=key,
+                    submodel_type=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
+                    key=key,
+                    submodel_type=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip=ClipField(
                 tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
+                    key=key,
+                    submodel_type=SubModelType.Tokenizer,
                 ),
                 text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
+                    key=key,
+                    submodel_type=SubModelType.TextEncoder,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Vae,
+                    key=key,
+                    submodel_type=SubModelType.Vae,
                 ),
             ),
         )
@@ -206,7 +147,7 @@ class LoraLoaderOutput(BaseInvocationOutput):
     clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
-@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.0")
+@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.1")
 class LoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
@@ -229,21 +170,16 @@ class LoraLoaderInvocation(BaseInvocation):
         if self.lora is None:
             raise Exception("No LoRA provided")
 
-        base_model = self.lora.base_model
-        lora_name = self.lora.model_name
+        lora_key = self.lora.key
 
-        if not context.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unkown lora name: {lora_name}!")
+        if not context.models.exists(lora_key):
+            raise Exception(f"Unkown lora: {lora_key}!")
 
-        if self.unet is not None and any(lora.model_name == lora_name for lora in self.unet.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to unet')
+        if self.unet is not None and any(lora.key == lora_key for lora in self.unet.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to unet')
 
-        if self.clip is not None and any(lora.model_name == lora_name for lora in self.clip.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip')
+        if self.clip is not None and any(lora.key == lora_key for lora in self.clip.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to clip')
 
         output = LoraLoaderOutput()
 
@@ -251,10 +187,8 @@ class LoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -263,10 +197,8 @@ class LoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -288,7 +220,7 @@ class SDXLLoraLoaderOutput(BaseInvocationOutput):
     title="SDXL LoRA",
     tags=["lora", "model"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLLoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
@@ -318,24 +250,19 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
         if self.lora is None:
             raise Exception("No LoRA provided")
 
-        base_model = self.lora.base_model
-        lora_name = self.lora.model_name
+        lora_key = self.lora.key
 
-        if not context.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unknown lora name: {lora_name}!")
+        if not context.models.exists(lora_key):
+            raise Exception(f"Unknown lora: {lora_key}!")
 
-        if self.unet is not None and any(lora.model_name == lora_name for lora in self.unet.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to unet')
+        if self.unet is not None and any(lora.key == lora_key for lora in self.unet.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to unet')
 
-        if self.clip is not None and any(lora.model_name == lora_name for lora in self.clip.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip')
+        if self.clip is not None and any(lora.key == lora_key for lora in self.clip.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to clip')
 
-        if self.clip2 is not None and any(lora.model_name == lora_name for lora in self.clip2.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip2')
+        if self.clip2 is not None and any(lora.key == lora_key for lora in self.clip2.loras):
+            raise Exception(f'Lora "{lora_key}" already applied to clip2')
 
         output = SDXLLoraLoaderOutput()
 
@@ -343,10 +270,8 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -355,10 +280,8 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -367,10 +290,8 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.clip2 = copy.deepcopy(self.clip2)
             output.clip2.loras.append(
                 LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                    key=lora_key,
+                    submodel_type=None,
                     weight=self.weight,
                 )
             )
@@ -381,13 +302,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
 class VAEModelField(BaseModel):
     """Vae model field"""
 
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Model's key")
 
 
-@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.0")
+@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.1")
 class VaeLoaderInvocation(BaseInvocation):
     """Loads a VAE model, outputting a VaeLoaderOutput"""
 
@@ -398,25 +316,12 @@ class VaeLoaderInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> VAEOutput:
-        base_model = self.vae_model.base_model
-        model_name = self.vae_model.model_name
-        model_type = ModelType.Vae
+        key = self.vae_model.key
 
-        if not context.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=model_name,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unkown vae name: {model_name}!")
-        return VAEOutput(
-            vae=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                )
-            )
-        )
+        if not context.models.exists(key):
+            raise Exception(f"Unkown vae: {key}!")
+
+        return VAEOutput(vae=VaeField(vae=ModelInfo(key=key)))
 
 
 @invocation_output("seamless_output")

invokeai/app/invocations/noise.py

@@ -4,17 +4,15 @@
 import torch
 from pydantic import field_validator
 
-from invokeai.app.invocations.latent import LatentsField
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import FieldDescriptions, InputField, LatentsField, OutputField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
 from ...backend.util.devices import choose_torch_device, torch_dtype
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
@@ -69,13 +67,13 @@ class NoiseOutput(BaseInvocationOutput):
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
-
-def build_noise_output(latents_name: str, latents: torch.Tensor, seed: int):
-    return NoiseOutput(
-        noise=LatentsField(latents_name=latents_name, seed=seed),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
+    @classmethod
+    def build(cls, latents_name: str, latents: torch.Tensor, seed: int) -> "NoiseOutput":
+        return cls(
+            noise=LatentsField(latents_name=latents_name, seed=seed),
+            width=latents.size()[3] * LATENT_SCALE_FACTOR,
+            height=latents.size()[2] * LATENT_SCALE_FACTOR,
+        )
 
 
 @invocation(
@@ -96,13 +94,13 @@ class NoiseInvocation(BaseInvocation):
     )
     width: int = InputField(
         default=512,
-        multiple_of=8,
+        multiple_of=LATENT_SCALE_FACTOR,
         gt=0,
         description=FieldDescriptions.width,
     )
     height: int = InputField(
         default=512,
-        multiple_of=8,
+        multiple_of=LATENT_SCALE_FACTOR,
         gt=0,
         description=FieldDescriptions.height,
     )
@@ -124,6 +122,5 @@ 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)
+        name = context.tensors.save(tensor=noise)
+        return NoiseOutput.build(latents_name=name, latents=noise, seed=self.seed)

invokeai/app/invocations/onnx.py

@@ -1,508 +0,0 @@
-# Copyright (c) 2023 Borisov Sergey (https://github.com/StAlKeR7779)
-
-import inspect
-
-# from contextlib import ExitStack
-from typing import List, Literal, Union
-
-import numpy as np
-import torch
-from diffusers.image_processor import VaeImageProcessor
-from pydantic import BaseModel, ConfigDict, Field, field_validator
-from tqdm import tqdm
-
-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.shared.fields import FieldDescriptions
-from invokeai.app.util.step_callback import stable_diffusion_step_callback
-from invokeai.backend import BaseModelType, ModelType, SubModelType
-
-from ...backend.model_management import ONNXModelPatcher
-from ...backend.stable_diffusion import PipelineIntermediateState
-from ...backend.util import choose_torch_device
-from ..util.ti_utils import extract_ti_triggers_from_prompt
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
-    UIType,
-    WithMetadata,
-    invocation,
-    invocation_output,
-)
-from .controlnet_image_processors import ControlField
-from .latent import SAMPLER_NAME_VALUES, LatentsField, LatentsOutput, build_latents_output, get_scheduler
-from .model import ClipField, ModelInfo, UNetField, VaeField
-
-ORT_TO_NP_TYPE = {
-    "tensor(bool)": np.bool_,
-    "tensor(int8)": np.int8,
-    "tensor(uint8)": np.uint8,
-    "tensor(int16)": np.int16,
-    "tensor(uint16)": np.uint16,
-    "tensor(int32)": np.int32,
-    "tensor(uint32)": np.uint32,
-    "tensor(int64)": np.int64,
-    "tensor(uint64)": np.uint64,
-    "tensor(float16)": np.float16,
-    "tensor(float)": np.float32,
-    "tensor(double)": np.float64,
-}
-
-PRECISION_VALUES = Literal[tuple(ORT_TO_NP_TYPE.keys())]
-
-
-@invocation("prompt_onnx", title="ONNX Prompt (Raw)", tags=["prompt", "onnx"], category="conditioning", version="1.0.0")
-class ONNXPromptInvocation(BaseInvocation):
-    prompt: str = InputField(default="", description=FieldDescriptions.raw_prompt, ui_component=UIComponent.Textarea)
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
-
-    def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-        )
-        with tokenizer_info as orig_tokenizer, text_encoder_info as text_encoder:  # , ExitStack() as stack:
-            loras = [
-                (
-                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
-                    lora.weight,
-                )
-                for lora in self.clip.loras
-            ]
-
-            ti_list = []
-            for trigger in extract_ti_triggers_from_prompt(self.prompt):
-                name = trigger[1:-1]
-                try:
-                    ti_list.append(
-                        (
-                            name,
-                            context.services.model_manager.get_model(
-                                model_name=name,
-                                base_model=self.clip.text_encoder.base_model,
-                                model_type=ModelType.TextualInversion,
-                            ).context.model,
-                        )
-                    )
-                except Exception:
-                    # print(e)
-                    # import traceback
-                    # print(traceback.format_exc())
-                    print(f'Warn: trigger: "{trigger}" not found')
-            if loras or ti_list:
-                text_encoder.release_session()
-            with (
-                ONNXModelPatcher.apply_lora_text_encoder(text_encoder, loras),
-                ONNXModelPatcher.apply_ti(orig_tokenizer, text_encoder, ti_list) as (tokenizer, ti_manager),
-            ):
-                text_encoder.create_session()
-
-                # copy from
-                # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L153
-                text_inputs = tokenizer(
-                    self.prompt,
-                    padding="max_length",
-                    max_length=tokenizer.model_max_length,
-                    truncation=True,
-                    return_tensors="np",
-                )
-                text_input_ids = text_inputs.input_ids
-                """
-                untruncated_ids = tokenizer(prompt, padding="max_length", return_tensors="np").input_ids
-
-                if not np.array_equal(text_input_ids, untruncated_ids):
-                    removed_text = self.tokenizer.batch_decode(
-                        untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
-                    )
-                    logger.warning(
-                        "The following part of your input was truncated because CLIP can only handle sequences up to"
-                        f" {self.tokenizer.model_max_length} tokens: {removed_text}"
-                    )
-                """
-
-                prompt_embeds = text_encoder(input_ids=text_input_ids.astype(np.int32))[0]
-
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-
-        # TODO: hacky but works ;D maybe rename latents somehow?
-        context.services.latents.save(conditioning_name, (prompt_embeds, None))
-
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
-
-
-# Text to image
-@invocation(
-    "t2l_onnx",
-    title="ONNX Text to Latents",
-    tags=["latents", "inference", "txt2img", "onnx"],
-    category="latents",
-    version="1.0.0",
-)
-class ONNXTextToLatentsInvocation(BaseInvocation):
-    """Generates latents from conditionings."""
-
-    positive_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.positive_cond,
-        input=Input.Connection,
-    )
-    negative_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.negative_cond,
-        input=Input.Connection,
-    )
-    noise: LatentsField = InputField(
-        description=FieldDescriptions.noise,
-        input=Input.Connection,
-    )
-    steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
-    cfg_scale: Union[float, List[float]] = InputField(
-        default=7.5,
-        ge=1,
-        description=FieldDescriptions.cfg_scale,
-    )
-    scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, input=Input.Direct, ui_type=UIType.Scheduler
-    )
-    precision: PRECISION_VALUES = InputField(default="tensor(float16)", description=FieldDescriptions.precision)
-    unet: UNetField = InputField(
-        description=FieldDescriptions.unet,
-        input=Input.Connection,
-    )
-    control: Union[ControlField, list[ControlField]] = InputField(
-        default=None,
-        description=FieldDescriptions.control,
-    )
-    # seamless:   bool = InputField(default=False, description="Whether or not to generate an image that can tile without seams", )
-    # seamless_axes: str = InputField(default="", description="The axes to tile the image on, 'x' and/or 'y'")
-
-    @field_validator("cfg_scale")
-    def ge_one(cls, v):
-        """validate that all cfg_scale values are >= 1"""
-        if isinstance(v, list):
-            for i in v:
-                if i < 1:
-                    raise ValueError("cfg_scale must be greater than 1")
-        else:
-            if v < 1:
-                raise ValueError("cfg_scale must be greater than 1")
-        return v
-
-    # based on
-    # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L375
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        c, _ = context.services.latents.get(self.positive_conditioning.conditioning_name)
-        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
-        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]
-        if isinstance(c, torch.Tensor):
-            c = c.cpu().numpy()
-        if isinstance(uc, torch.Tensor):
-            uc = uc.cpu().numpy()
-        device = torch.device(choose_torch_device())
-        prompt_embeds = np.concatenate([uc, c])
-
-        latents = context.services.latents.get(self.noise.latents_name)
-        if isinstance(latents, torch.Tensor):
-            latents = latents.cpu().numpy()
-
-        # TODO: better execution device handling
-        latents = latents.astype(ORT_TO_NP_TYPE[self.precision])
-
-        # get the initial random noise unless the user supplied it
-        do_classifier_free_guidance = True
-        # latents_dtype = prompt_embeds.dtype
-        # latents_shape = (batch_size * num_images_per_prompt, 4, height // 8, width // 8)
-        # if latents.shape != latents_shape:
-        #    raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {latents_shape}")
-
-        scheduler = get_scheduler(
-            context=context,
-            scheduler_info=self.unet.scheduler,
-            scheduler_name=self.scheduler,
-            seed=0,  # TODO: refactor this node
-        )
-
-        def torch2numpy(latent: torch.Tensor):
-            return latent.cpu().numpy()
-
-        def numpy2torch(latent, device):
-            return torch.from_numpy(latent).to(device)
-
-        def dispatch_progress(
-            self, context: InvocationContext, source_node_id: str, intermediate_state: PipelineIntermediateState
-        ) -> None:
-            stable_diffusion_step_callback(
-                context=context,
-                intermediate_state=intermediate_state,
-                node=self.model_dump(),
-                source_node_id=source_node_id,
-            )
-
-        scheduler.set_timesteps(self.steps)
-        latents = latents * np.float64(scheduler.init_noise_sigma)
-
-        extra_step_kwargs = {}
-        if "eta" in set(inspect.signature(scheduler.step).parameters.keys()):
-            extra_step_kwargs.update(
-                eta=0.0,
-            )
-
-        unet_info = context.services.model_manager.get_model(**self.unet.unet.model_dump())
-
-        with unet_info as unet:  # , ExitStack() as stack:
-            # loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
-            loras = [
-                (
-                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
-                    lora.weight,
-                )
-                for lora in self.unet.loras
-            ]
-
-            if loras:
-                unet.release_session()
-            with ONNXModelPatcher.apply_lora_unet(unet, loras):
-                # TODO:
-                _, _, h, w = latents.shape
-                unet.create_session(h, w)
-
-                timestep_dtype = next(
-                    (input.type for input in unet.session.get_inputs() if input.name == "timestep"), "tensor(float16)"
-                )
-                timestep_dtype = ORT_TO_NP_TYPE[timestep_dtype]
-                for i in tqdm(range(len(scheduler.timesteps))):
-                    t = scheduler.timesteps[i]
-                    # expand the latents if we are doing classifier free guidance
-                    latent_model_input = np.concatenate([latents] * 2) if do_classifier_free_guidance else latents
-                    latent_model_input = scheduler.scale_model_input(numpy2torch(latent_model_input, device), t)
-                    latent_model_input = latent_model_input.cpu().numpy()
-
-                    # predict the noise residual
-                    timestep = np.array([t], dtype=timestep_dtype)
-                    noise_pred = unet(sample=latent_model_input, timestep=timestep, encoder_hidden_states=prompt_embeds)
-                    noise_pred = noise_pred[0]
-
-                    # perform guidance
-                    if do_classifier_free_guidance:
-                        noise_pred_uncond, noise_pred_text = np.split(noise_pred, 2)
-                        noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
-
-                    # compute the previous noisy sample x_t -> x_t-1
-                    scheduler_output = scheduler.step(
-                        numpy2torch(noise_pred, device), t, numpy2torch(latents, device), **extra_step_kwargs
-                    )
-                    latents = torch2numpy(scheduler_output.prev_sample)
-
-                    state = PipelineIntermediateState(
-                        run_id="test", step=i, timestep=timestep, latents=scheduler_output.prev_sample
-                    )
-                    dispatch_progress(self, context=context, source_node_id=source_node_id, intermediate_state=state)
-
-                    # call the callback, if provided
-                    # if callback is not None and i % callback_steps == 0:
-                    #    callback(i, t, latents)
-
-        torch.cuda.empty_cache()
-
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=torch.from_numpy(latents))
-
-
-# Latent to image
-@invocation(
-    "l2i_onnx",
-    title="ONNX Latents to Image",
-    tags=["latents", "image", "vae", "onnx"],
-    category="image",
-    version="1.2.0",
-)
-class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata):
-    """Generates an image from latents."""
-
-    latents: LatentsField = InputField(
-        description=FieldDescriptions.denoised_latents,
-        input=Input.Connection,
-    )
-    vae: VaeField = InputField(
-        description=FieldDescriptions.vae,
-        input=Input.Connection,
-    )
-    # tiled: bool = InputField(default=False, description="Decode latents by overlaping tiles(less memory consumption)")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
-
-        if self.vae.vae.submodel != SubModelType.VaeDecoder:
-            raise Exception(f"Expected vae_decoder, found: {self.vae.vae.model_type}")
-
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-        )
-
-        # clear memory as vae decode can request a lot
-        torch.cuda.empty_cache()
-
-        with vae_info as vae:
-            vae.create_session()
-
-            # copied from
-            # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L427
-            latents = 1 / 0.18215 * latents
-            # image = self.vae_decoder(latent_sample=latents)[0]
-            # it seems likes there is a strange result for using half-precision vae decoder if batchsize>1
-            image = np.concatenate([vae(latent_sample=latents[i : i + 1])[0] for i in range(latents.shape[0])])
-
-            image = np.clip(image / 2 + 0.5, 0, 1)
-            image = image.transpose((0, 2, 3, 1))
-            image = VaeImageProcessor.numpy_to_pil(image)[0]
-
-        torch.cuda.empty_cache()
-
-        image_dto = context.services.images.create(
-            image=image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation_output("model_loader_output_onnx")
-class ONNXModelLoaderOutput(BaseInvocationOutput):
-    """Model loader output"""
-
-    unet: UNetField = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
-    vae_decoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Decoder")
-    vae_encoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Encoder")
-
-
-class OnnxModelField(BaseModel):
-    """Onnx model field"""
-
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Model Type")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@invocation("onnx_model_loader", title="ONNX Main Model", tags=["onnx", "model"], category="model", version="1.0.0")
-class OnnxModelLoaderInvocation(BaseInvocation):
-    """Loads a main model, outputting its submodels."""
-
-    model: OnnxModelField = InputField(
-        description=FieldDescriptions.onnx_main_model, input=Input.Direct, ui_type=UIType.ONNXModel
-    )
-
-    def invoke(self, context: InvocationContext) -> ONNXModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.ONNX
-
-        # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
-
-        """
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.Tokenizer,
-        ):
-            raise Exception(
-                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.TextEncoder,
-        ):
-            raise Exception(
-                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.UNet,
-        ):
-            raise Exception(
-                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
-            )
-        """
-
-        return ONNXModelLoaderOutput(
-            unet=UNetField(
-                unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
-                ),
-                scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
-                ),
-                loras=[],
-            ),
-            clip=ClipField(
-                tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
-                ),
-                text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
-                ),
-                loras=[],
-                skipped_layers=0,
-            ),
-            vae_decoder=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.VaeDecoder,
-                ),
-            ),
-            vae_encoder=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.VaeEncoder,
-                ),
-            ),
-        )

invokeai/app/invocations/param_easing.py

@@ -40,8 +40,10 @@ from easing_functions import (
 from matplotlib.ticker import MaxNLocator
 
 from invokeai.app.invocations.primitives import FloatCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField
 
 
 @invocation(
@@ -109,7 +111,7 @@ EASING_FUNCTION_KEYS = Literal[tuple(EASING_FUNCTIONS_MAP.keys())]
     title="Step Param Easing",
     tags=["step", "easing"],
     category="step",
-    version="1.0.0",
+    version="1.0.1",
 )
 class StepParamEasingInvocation(BaseInvocation):
     """Experimental per-step parameter easing for denoising steps"""
@@ -148,19 +150,19 @@ class StepParamEasingInvocation(BaseInvocation):
         postlist = list(num_poststeps * [self.post_end_value])
 
         if log_diagnostics:
-            context.services.logger.debug("start_step: " + str(start_step))
-            context.services.logger.debug("end_step: " + str(end_step))
-            context.services.logger.debug("num_easing_steps: " + str(num_easing_steps))
-            context.services.logger.debug("num_presteps: " + str(num_presteps))
-            context.services.logger.debug("num_poststeps: " + str(num_poststeps))
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
-            context.services.logger.debug("prelist: " + str(prelist))
-            context.services.logger.debug("postlist: " + str(postlist))
+            context.logger.debug("start_step: " + str(start_step))
+            context.logger.debug("end_step: " + str(end_step))
+            context.logger.debug("num_easing_steps: " + str(num_easing_steps))
+            context.logger.debug("num_presteps: " + str(num_presteps))
+            context.logger.debug("num_poststeps: " + str(num_poststeps))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist: " + str(prelist))
+            context.logger.debug("postlist: " + str(postlist))
 
         easing_class = EASING_FUNCTIONS_MAP[self.easing]
         if log_diagnostics:
-            context.services.logger.debug("easing class: " + str(easing_class))
+            context.logger.debug("easing class: " + str(easing_class))
         easing_list = []
         if self.mirror:  # "expected" mirroring
             # if number of steps is even, squeeze duration down to (number_of_steps)/2
@@ -171,7 +173,7 @@ class StepParamEasingInvocation(BaseInvocation):
 
             base_easing_duration = int(np.ceil(num_easing_steps / 2.0))
             if log_diagnostics:
-                context.services.logger.debug("base easing duration: " + str(base_easing_duration))
+                context.logger.debug("base easing duration: " + str(base_easing_duration))
             even_num_steps = num_easing_steps % 2 == 0  # even number of steps
             easing_function = easing_class(
                 start=self.start_value,
@@ -183,14 +185,14 @@ class StepParamEasingInvocation(BaseInvocation):
                 easing_val = easing_function.ease(step_index)
                 base_easing_vals.append(easing_val)
                 if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
             if even_num_steps:
                 mirror_easing_vals = list(reversed(base_easing_vals))
             else:
                 mirror_easing_vals = list(reversed(base_easing_vals[0:-1]))
             if log_diagnostics:
-                context.services.logger.debug("base easing vals: " + str(base_easing_vals))
-                context.services.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
+                context.logger.debug("base easing vals: " + str(base_easing_vals))
+                context.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
             easing_list = base_easing_vals + mirror_easing_vals
 
         # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
@@ -225,12 +227,12 @@ class StepParamEasingInvocation(BaseInvocation):
                 step_val = easing_function.ease(step_index)
                 easing_list.append(step_val)
                 if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
 
         if log_diagnostics:
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("easing_list size: " + str(len(easing_list)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("easing_list size: " + str(len(easing_list)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
 
         param_list = prelist + easing_list + postlist
 

invokeai/app/invocations/primitives.py

@@ -1,20 +1,28 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Optional, Tuple
+from typing import Optional
 
 import torch
-from pydantic import BaseModel, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import (
+    ColorField,
+    ConditioningField,
+    DenoiseMaskField,
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    LatentsField,
+    OutputField,
+    UIComponent,
+)
+from invokeai.app.services.images.images_common import ImageDTO
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
@@ -221,18 +229,6 @@ class StringCollectionInvocation(BaseInvocation):
 # region Image
 
 
-class ImageField(BaseModel):
-    """An image primitive field"""
-
-    image_name: str = Field(description="The name of the image")
-
-
-class BoardField(BaseModel):
-    """A board primitive field"""
-
-    board_id: str = Field(description="The id of the board")
-
-
 @invocation_output("image_output")
 class ImageOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
@@ -241,6 +237,14 @@ class ImageOutput(BaseInvocationOutput):
     width: int = OutputField(description="The width of the image in pixels")
     height: int = OutputField(description="The height of the image in pixels")
 
+    @classmethod
+    def build(cls, image_dto: ImageDTO) -> "ImageOutput":
+        return cls(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
 
 @invocation_output("image_collection_output")
 class ImageCollectionOutput(BaseInvocationOutput):
@@ -251,16 +255,14 @@ class ImageCollectionOutput(BaseInvocationOutput):
     )
 
 
-@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.0")
-class ImageInvocation(
-    BaseInvocation,
-):
+@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.1")
+class ImageInvocation(BaseInvocation):
     """An image primitive value"""
 
     image: ImageField = InputField(description="The image to load")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         return ImageOutput(
             image=ImageField(image_name=self.image.image_name),
@@ -290,42 +292,40 @@ class ImageCollectionInvocation(BaseInvocation):
 # region DenoiseMask
 
 
-class DenoiseMaskField(BaseModel):
-    """An inpaint mask field"""
-
-    mask_name: str = Field(description="The name of the mask image")
-    masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
-
-
 @invocation_output("denoise_mask_output")
 class DenoiseMaskOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
 
     denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
 
+    @classmethod
+    def build(cls, mask_name: str, masked_latents_name: Optional[str] = None) -> "DenoiseMaskOutput":
+        return cls(
+            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=masked_latents_name),
+        )
+
 
 # endregion
 
 # region Latents
 
 
-class LatentsField(BaseModel):
-    """A latents tensor primitive field"""
-
-    latents_name: str = Field(description="The name of the latents")
-    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
-
-
 @invocation_output("latents_output")
 class LatentsOutput(BaseInvocationOutput):
     """Base class for nodes that output a single latents tensor"""
 
-    latents: LatentsField = OutputField(
-        description=FieldDescriptions.latents,
-    )
+    latents: LatentsField = OutputField(description=FieldDescriptions.latents)
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
+    @classmethod
+    def build(cls, latents_name: str, latents: torch.Tensor, seed: Optional[int] = None) -> "LatentsOutput":
+        return cls(
+            latents=LatentsField(latents_name=latents_name, seed=seed),
+            width=latents.size()[3] * LATENT_SCALE_FACTOR,
+            height=latents.size()[2] * LATENT_SCALE_FACTOR,
+        )
+
 
 @invocation_output("latents_collection_output")
 class LatentsCollectionOutput(BaseInvocationOutput):
@@ -337,7 +337,7 @@ class LatentsCollectionOutput(BaseInvocationOutput):
 
 
 @invocation(
-    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.0"
+    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.1"
 )
 class LatentsInvocation(BaseInvocation):
     """A latents tensor primitive value"""
@@ -345,9 +345,9 @@ class LatentsInvocation(BaseInvocation):
     latents: LatentsField = InputField(description="The latents tensor", input=Input.Connection)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
-        return build_latents_output(self.latents.latents_name, latents)
+        return LatentsOutput.build(self.latents.latents_name, latents)
 
 
 @invocation(
@@ -368,31 +368,11 @@ class LatentsCollectionInvocation(BaseInvocation):
         return LatentsCollectionOutput(collection=self.collection)
 
 
-def build_latents_output(latents_name: str, latents: torch.Tensor, seed: Optional[int] = None):
-    return LatentsOutput(
-        latents=LatentsField(latents_name=latents_name, seed=seed),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
-
-
 # endregion
 
 # region Color
 
 
-class ColorField(BaseModel):
-    """A color primitive field"""
-
-    r: int = Field(ge=0, le=255, description="The red component")
-    g: int = Field(ge=0, le=255, description="The green component")
-    b: int = Field(ge=0, le=255, description="The blue component")
-    a: int = Field(ge=0, le=255, description="The alpha component")
-
-    def tuple(self) -> Tuple[int, int, int, int]:
-        return (self.r, self.g, self.b, self.a)
-
-
 @invocation_output("color_output")
 class ColorOutput(BaseInvocationOutput):
     """Base class for nodes that output a single color"""
@@ -424,18 +404,16 @@ class ColorInvocation(BaseInvocation):
 # region Conditioning
 
 
-class ConditioningField(BaseModel):
-    """A conditioning tensor primitive value"""
-
-    conditioning_name: str = Field(description="The name of conditioning tensor")
-
-
 @invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""
 
     conditioning: ConditioningField = OutputField(description=FieldDescriptions.cond)
 
+    @classmethod
+    def build(cls, conditioning_name: str) -> "ConditioningOutput":
+        return cls(conditioning=ConditioningField(conditioning_name=conditioning_name))
+
 
 @invocation_output("conditioning_collection_output")
 class ConditioningCollectionOutput(BaseInvocationOutput):

invokeai/app/invocations/prompt.py

@@ -6,8 +6,10 @@ from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPrompt
 from pydantic import field_validator
 
 from invokeai.app.invocations.primitives import StringCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, UIComponent, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, UIComponent
 
 
 @invocation(

invokeai/app/invocations/sdxl.py

@@ -1,14 +1,10 @@
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager import SubModelType
 
-from ...backend.model_management import ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
@@ -34,7 +30,7 @@ class SDXLRefinerModelLoaderOutput(BaseInvocationOutput):
     vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
-@invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.0")
+@invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.1")
 class SDXLModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl base model, outputting its submodels."""
 
@@ -44,72 +40,52 @@ class SDXLModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> SDXLModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.Main
+        model_key = self.model.key
 
         # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+        if not context.models.exists(model_key):
+            raise Exception(f"Unknown model: {model_key}")
 
         return SDXLModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
+                    key=model_key,
+                    submodel_type=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
+                    key=model_key,
+                    submodel_type=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip=ClipField(
                 tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
+                    key=model_key,
+                    submodel_type=SubModelType.Tokenizer,
                 ),
                 text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
+                    key=model_key,
+                    submodel_type=SubModelType.TextEncoder,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             clip2=ClipField(
                 tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer2,
+                    key=model_key,
+                    submodel_type=SubModelType.Tokenizer2,
                 ),
                 text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder2,
+                    key=model_key,
+                    submodel_type=SubModelType.TextEncoder2,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Vae,
+                    key=model_key,
+                    submodel_type=SubModelType.Vae,
                 ),
             ),
         )
@@ -120,7 +96,7 @@ class SDXLModelLoaderInvocation(BaseInvocation):
     title="SDXL Refiner Model",
     tags=["model", "sdxl", "refiner"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLRefinerModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl refiner model, outputting its submodels."""
@@ -133,56 +109,40 @@ class SDXLRefinerModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> SDXLRefinerModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.Main
+        model_key = self.model.key
 
         # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+        if not context.models.exists(model_key):
+            raise Exception(f"Unknown model: {model_key}")
 
         return SDXLRefinerModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
+                    key=model_key,
+                    submodel_type=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
+                    key=model_key,
+                    submodel_type=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip2=ClipField(
                 tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer2,
+                    key=model_key,
+                    submodel_type=SubModelType.Tokenizer2,
                 ),
                 text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder2,
+                    key=model_key,
+                    submodel_type=SubModelType.TextEncoder2,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Vae,
+                    key=model_key,
+                    submodel_type=SubModelType.Vae,
                 ),
             ),
         )

invokeai/app/invocations/strings.py

@@ -2,16 +2,15 @@
 
 import re
 
+from invokeai.app.services.shared.invocation_context import InvocationContext
+
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
+from .fields import InputField, OutputField, UIComponent
 from .primitives import StringOutput
 
 

invokeai/app/invocations/t2i_adapter.py

@@ -1,29 +1,21 @@
 from typing import Union
 
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESIZE_VALUES
-from invokeai.app.invocations.primitives import ImageField
+from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField, OutputField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.model_management.models.base import BaseModelType
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 
 class T2IAdapterModelField(BaseModel):
-    model_name: str = Field(description="Name of the T2I-Adapter model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
+    key: str = Field(description="Model record key for the T2I-Adapter model")
 
 
 class T2IAdapterField(BaseModel):

invokeai/app/invocations/tiles.py

@@ -8,16 +8,12 @@ from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
     Classification,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField, Input, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.tiles.tiles import (
     calc_tiles_even_split,
     calc_tiles_min_overlap,
@@ -236,7 +232,7 @@ BLEND_MODES = Literal["Linear", "Seam"]
     version="1.1.0",
     classification=Classification.Beta,
 )
-class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
+class MergeTilesToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Merge multiple tile images into a single image."""
 
     # Inputs
@@ -268,7 +264,7 @@ class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
         # existed in memory at an earlier point in the graph.
         tile_np_images: list[np.ndarray] = []
         for image in images:
-            pil_image = context.services.images.get_pil_image(image.image_name)
+            pil_image = context.images.get_pil(image.image_name)
             pil_image = pil_image.convert("RGB")
             tile_np_images.append(np.array(pil_image))
 
@@ -291,18 +287,5 @@ class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
         # Convert into a PIL image and save
         pil_image = Image.fromarray(np_image)
 
-        image_dto = context.services.images.create(
-            image=pil_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=context.workflow,
-        )
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        image_dto = context.images.save(image=pil_image)
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/upscale.py

@@ -5,16 +5,18 @@ from typing import Literal
 import cv2
 import numpy as np
 import torch
-from basicsr.archs.rrdbnet_arch import RRDBNet
 from PIL import Image
 from pydantic import ConfigDict
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.image_util.basicsr.rrdbnet_arch import RRDBNet
 from invokeai.backend.image_util.realesrgan.realesrgan import RealESRGAN
 from invokeai.backend.util.devices import choose_torch_device
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 
 # TODO: Populate this from disk?
 # TODO: Use model manager to load?
@@ -29,8 +31,8 @@ if choose_torch_device() == torch.device("mps"):
     from torch import mps
 
 
-@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.3.0")
-class ESRGANInvocation(BaseInvocation, WithMetadata):
+@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.3.1")
+class ESRGANInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Upscales an image using RealESRGAN."""
 
     image: ImageField = InputField(description="The input image")
@@ -42,8 +44,8 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
     model_config = ConfigDict(protected_namespaces=())
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        models_path = context.services.configuration.models_path
+        image = context.images.get_pil(self.image.image_name)
+        models_path = context.config.get().models_path
 
         rrdbnet_model = None
         netscale = None
@@ -87,7 +89,7 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
             netscale = 2
         else:
             msg = f"Invalid RealESRGAN model: {self.model_name}"
-            context.services.logger.error(msg)
+            context.logger.error(msg)
             raise ValueError(msg)
 
         esrgan_model_path = Path(f"core/upscaling/realesrgan/{self.model_name}")
@@ -110,19 +112,6 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
         if choose_torch_device() == torch.device("mps"):
             mps.empty_cache()
 
-        image_dto = context.services.images.create(
-            image=pil_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=context.workflow,
-        )
+        image_dto = context.images.save(image=pil_image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/services/config/config_base.py

@@ -27,11 +27,11 @@ class InvokeAISettings(BaseSettings):
     """Runtime configuration settings in which default values are read from an omegaconf .yaml file."""
 
     initconf: ClassVar[Optional[DictConfig]] = None
-    argparse_groups: ClassVar[Dict] = {}
+    argparse_groups: ClassVar[Dict[str, Any]] = {}
 
     model_config = SettingsConfigDict(env_file_encoding="utf-8", arbitrary_types_allowed=True, case_sensitive=True)
 
-    def parse_args(self, argv: Optional[list] = sys.argv[1:]):
+    def parse_args(self, argv: Optional[List[str]] = sys.argv[1:]) -> None:
         """Call to parse command-line arguments."""
         parser = self.get_parser()
         opt, unknown_opts = parser.parse_known_args(argv)
@@ -68,7 +68,7 @@ class InvokeAISettings(BaseSettings):
         return OmegaConf.to_yaml(conf)
 
     @classmethod
-    def add_parser_arguments(cls, parser):
+    def add_parser_arguments(cls, parser: ArgumentParser) -> None:
         """Dynamically create arguments for a settings parser."""
         if "type" in get_type_hints(cls):
             settings_stanza = get_args(get_type_hints(cls)["type"])[0]
@@ -117,7 +117,8 @@ class InvokeAISettings(BaseSettings):
         """Return the category of a setting."""
         hints = get_type_hints(cls)
         if command_field in hints:
-            return get_args(hints[command_field])[0]
+            result: str = get_args(hints[command_field])[0]
+            return result
         else:
             return "Uncategorized"
 
@@ -158,7 +159,7 @@ class InvokeAISettings(BaseSettings):
         ]
 
     @classmethod
-    def add_field_argument(cls, command_parser, name: str, field, default_override=None):
+    def add_field_argument(cls, command_parser, name: str, field, default_override=None) -> None:
         """Add the argparse arguments for a setting parser."""
         field_type = get_type_hints(cls).get(name)
         default = (

invokeai/app/services/config/config_common.py

@@ -21,7 +21,7 @@ class PagingArgumentParser(argparse.ArgumentParser):
     It also supports reading defaults from an init file.
     """
 
-    def print_help(self, file=None):
+    def print_help(self, file=None) -> None:
         text = self.format_help()
         pydoc.pager(text)
 

invokeai/app/services/config/config_default.py

@@ -173,10 +173,10 @@ from __future__ import annotations
 
 import os
 from pathlib import Path
-from typing import Any, ClassVar, Dict, List, Literal, Optional, Union, get_type_hints
+from typing import Any, ClassVar, Dict, List, Literal, Optional
 
 from omegaconf import DictConfig, OmegaConf
-from pydantic import Field, TypeAdapter
+from pydantic import Field
 from pydantic.config import JsonDict
 from pydantic_settings import SettingsConfigDict
 
@@ -185,7 +185,9 @@ from .config_base import InvokeAISettings
 INIT_FILE = Path("invokeai.yaml")
 DB_FILE = Path("invokeai.db")
 LEGACY_INIT_FILE = Path("invokeai.init")
-DEFAULT_MAX_VRAM = 0.5
+DEFAULT_RAM_CACHE = 10.0
+DEFAULT_VRAM_CACHE = 0.25
+DEFAULT_CONVERT_CACHE = 20.0
 
 
 class Categories(object):
@@ -237,6 +239,7 @@ class InvokeAIAppConfig(InvokeAISettings):
     autoimport_dir      : Path = Field(default=Path('autoimport'), description='Path to a directory of models files to be imported on startup.', json_schema_extra=Categories.Paths)
     conf_path           : Path = Field(default=Path('configs/models.yaml'), description='Path to models definition file', json_schema_extra=Categories.Paths)
     models_dir          : Path = Field(default=Path('models'), description='Path to the models directory', json_schema_extra=Categories.Paths)
+    convert_cache_dir   : Path = Field(default=Path('models/.cache'), description='Path to the converted models cache directory', json_schema_extra=Categories.Paths)
     legacy_conf_dir     : Path = Field(default=Path('configs/stable-diffusion'), description='Path to directory of legacy checkpoint config files', json_schema_extra=Categories.Paths)
     db_dir              : Path = Field(default=Path('databases'), description='Path to InvokeAI databases directory', json_schema_extra=Categories.Paths)
     outdir              : Path = Field(default=Path('outputs'), description='Default folder for output images', json_schema_extra=Categories.Paths)
@@ -251,13 +254,19 @@ class InvokeAIAppConfig(InvokeAISettings):
     log_level           : Literal["debug", "info", "warning", "error", "critical"] = Field(default="info", description="Emit logging messages at this level or  higher", json_schema_extra=Categories.Logging)
     log_sql             : bool = Field(default=False, description="Log SQL queries", json_schema_extra=Categories.Logging)
 
+    # Development
     dev_reload          : bool = Field(default=False, description="Automatically reload when Python sources are changed.", json_schema_extra=Categories.Development)
+    profile_graphs      : bool = Field(default=False, description="Enable graph profiling", json_schema_extra=Categories.Development)
+    profile_prefix      : Optional[str] = Field(default=None, description="An optional prefix for profile output files.", json_schema_extra=Categories.Development)
+    profiles_dir        : Path = Field(default=Path('profiles'), description="Directory for graph profiles", json_schema_extra=Categories.Development)
 
     version             : bool = Field(default=False, description="Show InvokeAI version and exit", json_schema_extra=Categories.Other)
 
     # CACHE
-    ram                 : float = Field(default=7.5, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
-    vram                : float = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
+    ram                 : float = Field(default=DEFAULT_RAM_CACHE, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
+    vram                : float = Field(default=DEFAULT_VRAM_CACHE, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
+    convert_cache       : float = Field(default=DEFAULT_CONVERT_CACHE, ge=0, description="Maximum size of on-disk converted models cache (GB)", json_schema_extra=Categories.ModelCache)
+
     lazy_offload        : bool = Field(default=True, description="Keep models in VRAM until their space is needed", json_schema_extra=Categories.ModelCache, )
     log_memory_usage    : bool = Field(default=False, description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.", json_schema_extra=Categories.ModelCache)
 
@@ -270,7 +279,7 @@ class InvokeAIAppConfig(InvokeAISettings):
     attention_type      : Literal["auto", "normal", "xformers", "sliced", "torch-sdp"] = Field(default="auto", description="Attention type", json_schema_extra=Categories.Generation)
     attention_slice_size: Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', json_schema_extra=Categories.Generation)
     force_tiled_decode  : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", json_schema_extra=Categories.Generation)
-    png_compress_level  : int = Field(default=6, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", json_schema_extra=Categories.Generation)
+    png_compress_level  : int = Field(default=1, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", json_schema_extra=Categories.Generation)
 
     # QUEUE
     max_queue_size      : int = Field(default=10000, gt=0, description="Maximum number of items in the session queue", json_schema_extra=Categories.Queue)
@@ -280,6 +289,9 @@ class InvokeAIAppConfig(InvokeAISettings):
     deny_nodes          : Optional[List[str]] = Field(default=None, description="List of nodes to deny. Omit to deny none.", json_schema_extra=Categories.Nodes)
     node_cache_size     : int = Field(default=512, description="How many cached nodes to keep in memory", json_schema_extra=Categories.Nodes)
 
+    # MODEL IMPORT
+    civitai_api_key       : Optional[str] = Field(default=os.environ.get("CIVITAI_API_KEY"), description="API key for CivitAI", json_schema_extra=Categories.Other)
+
     # DEPRECATED FIELDS - STILL HERE IN ORDER TO OBTAN VALUES FROM PRE-3.1 CONFIG FILES
     always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", json_schema_extra=Categories.MemoryPerformance)
     max_cache_size      : Optional[float] = Field(default=None, gt=0, description="Maximum memory amount used by model cache for rapid switching", json_schema_extra=Categories.MemoryPerformance)
@@ -289,6 +301,7 @@ class InvokeAIAppConfig(InvokeAISettings):
     lora_dir            : Optional[Path] = Field(default=None, description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', json_schema_extra=Categories.Paths)
     embedding_dir       : Optional[Path] = Field(default=None, description='Path to a directory of Textual Inversion embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
     controlnet_dir      : Optional[Path] = Field(default=None, description='Path to a directory of ControlNet embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
+
     # this is not referred to in the source code and can be removed entirely
     #free_gpu_mem        : Optional[bool] = Field(default=None, description="If true, purge model from GPU after each generation.", json_schema_extra=Categories.MemoryPerformance)
 
@@ -328,13 +341,9 @@ class InvokeAIAppConfig(InvokeAISettings):
         super().parse_args(argv)
 
         if self.singleton_init and not clobber:
-            hints = get_type_hints(self.__class__)
-            for k in self.singleton_init:
-                setattr(
-                    self,
-                    k,
-                    TypeAdapter(hints[k]).validate_python(self.singleton_init[k]),
-                )
+            # When setting values in this way, set validate_assignment to true if you want to validate the value.
+            for k, v in self.singleton_init.items():
+                setattr(self, k, v)
 
     @classmethod
     def get_config(cls, **kwargs: Any) -> InvokeAIAppConfig:
@@ -400,6 +409,11 @@ class InvokeAIAppConfig(InvokeAISettings):
         """Path to the models directory."""
         return self._resolve(self.models_dir)
 
+    @property
+    def models_convert_cache_path(self) -> Path:
+        """Path to the converted cache models directory."""
+        return self._resolve(self.convert_cache_dir)
+
     @property
     def custom_nodes_path(self) -> Path:
         """Path to the custom nodes directory."""
@@ -429,15 +443,20 @@ class InvokeAIAppConfig(InvokeAISettings):
         return True
 
     @property
-    def ram_cache_size(self) -> Union[Literal["auto"], float]:
-        """Return the ram cache size using the legacy or modern setting."""
+    def ram_cache_size(self) -> float:
+        """Return the ram cache size using the legacy or modern setting (GB)."""
         return self.max_cache_size or self.ram
 
     @property
-    def vram_cache_size(self) -> Union[Literal["auto"], float]:
-        """Return the vram cache size using the legacy or modern setting."""
+    def vram_cache_size(self) -> float:
+        """Return the vram cache size using the legacy or modern setting (GB)."""
         return self.max_vram_cache_size or self.vram
 
+    @property
+    def convert_cache_size(self) -> float:
+        """Return the convert cache size on disk (GB)."""
+        return self.convert_cache
+
     @property
     def use_cpu(self) -> bool:
         """Return true if the device is set to CPU or the always_use_cpu flag is set."""
@@ -449,6 +468,11 @@ class InvokeAIAppConfig(InvokeAISettings):
         disabled_in_config = not self.xformers_enabled
         return disabled_in_config and self.attention_type != "xformers"
 
+    @property
+    def profiles_path(self) -> Path:
+        """Path to the graph profiles directory."""
+        return self._resolve(self.profiles_dir)
+
     @staticmethod
     def find_root() -> Path:
         """Choose the runtime root directory when not specified on command line or init file."""

invokeai/app/services/download/download_base.py

@@ -260,3 +260,16 @@ class DownloadQueueServiceBase(ABC):
     def join(self) -> None:
         """Wait until all jobs are off the queue."""
         pass
+
+    @abstractmethod
+    def wait_for_job(self, job: DownloadJob, timeout: int = 0) -> DownloadJob:
+        """Wait until the indicated download job has reached a terminal state.
+
+        This will block until the indicated install job has completed,
+        been cancelled, or errored out.
+
+        :param job: The job to wait on.
+        :param timeout: Wait up to indicated number of seconds. Raise a TimeoutError if
+        the job hasn't completed within the indicated time.
+        """
+        pass

invokeai/app/services/download/download_default.py

@@ -4,10 +4,11 @@
 import os
 import re
 import threading
+import time
 import traceback
 from pathlib import Path
 from queue import Empty, PriorityQueue
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Set
 
 import requests
 from pydantic.networks import AnyHttpUrl
@@ -48,11 +49,12 @@ class DownloadQueueService(DownloadQueueServiceBase):
         :param max_parallel_dl: Number of simultaneous downloads allowed [5].
         :param requests_session: Optional requests.sessions.Session object, for unit tests.
         """
-        self._jobs = {}
+        self._jobs: Dict[int, DownloadJob] = {}
         self._next_job_id = 0
-        self._queue = PriorityQueue()
+        self._queue: PriorityQueue[DownloadJob] = PriorityQueue()
         self._stop_event = threading.Event()
-        self._worker_pool = set()
+        self._job_completed_event = threading.Event()
+        self._worker_pool: Set[threading.Thread] = set()
         self._lock = threading.Lock()
         self._logger = InvokeAILogger.get_logger("DownloadQueueService")
         self._event_bus = event_bus
@@ -188,6 +190,16 @@ class DownloadQueueService(DownloadQueueServiceBase):
             if not job.in_terminal_state:
                 self.cancel_job(job)
 
+    def wait_for_job(self, job: DownloadJob, timeout: int = 0) -> DownloadJob:
+        """Block until the indicated job has reached terminal state, or when timeout limit reached."""
+        start = time.time()
+        while not job.in_terminal_state:
+            if self._job_completed_event.wait(timeout=0.25):  # in case we miss an event
+                self._job_completed_event.clear()
+            if timeout > 0 and time.time() - start > timeout:
+                raise TimeoutError("Timeout exceeded")
+        return job
+
     def _start_workers(self, max_workers: int) -> None:
         """Start the requested number of worker threads."""
         self._stop_event.clear()
@@ -208,7 +220,6 @@ class DownloadQueueService(DownloadQueueServiceBase):
                 job = self._queue.get(timeout=1)
             except Empty:
                 continue
-
             try:
                 job.job_started = get_iso_timestamp()
                 self._do_download(job)
@@ -224,6 +235,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
 
             finally:
                 job.job_ended = get_iso_timestamp()
+                self._job_completed_event.set()  # signal a change to terminal state
                 self._queue.task_done()
         self._logger.debug(f"Download queue worker thread {threading.current_thread().name} exiting.")
 
@@ -408,11 +420,11 @@ class DownloadQueueService(DownloadQueueServiceBase):
 
 # Example on_progress event handler to display a TQDM status bar
 # Activate with:
-#   download_service.download('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().job_update
+#   download_service.download(DownloadJob('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().update))
 class TqdmProgress(object):
     """TQDM-based progress bar object to use in on_progress handlers."""
 
-    _bars: Dict[int, tqdm]  # the tqdm object
+    _bars: Dict[int, tqdm]  # type: ignore
     _last: Dict[int, int]  # last bytes downloaded
 
     def __init__(self) -> None:  # noqa D107

invokeai/app/services/events/events_base.py

@@ -11,8 +11,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     SessionQueueStatus,
 )
 from invokeai.app.util.misc import get_timestamp
-from invokeai.backend.model_management.model_manager import ModelInfo
-from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
+from invokeai.backend.model_manager import AnyModelConfig
 
 
 class EventServiceBase:
@@ -55,7 +54,7 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        node: dict,
+        node_id: str,
         source_node_id: str,
         progress_image: Optional[ProgressImage],
         step: int,
@@ -70,7 +69,7 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "node_id": node.get("id"),
+                "node_id": node_id,
                 "source_node_id": source_node_id,
                 "progress_image": progress_image.model_dump() if progress_image is not None else None,
                 "step": step,
@@ -171,10 +170,7 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: SubModelType,
+        model_config: AnyModelConfig,
     ) -> None:
         """Emitted when a model is requested"""
         self.__emit_queue_event(
@@ -184,10 +180,7 @@ class EventServiceBase:
                 "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_config": model_config.model_dump(),
             },
         )
 
@@ -197,11 +190,7 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: SubModelType,
-        model_info: ModelInfo,
+        model_config: AnyModelConfig,
     ) -> None:
         """Emitted when a model is correctly loaded (returns model info)"""
         self.__emit_queue_event(
@@ -211,13 +200,7 @@ class EventServiceBase:
                 "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,
-                "hash": model_info.hash,
-                "location": str(model_info.location),
-                "precision": str(model_info.precision),
+                "model_config": model_config.model_dump(),
             },
         )
 

invokeai/app/services/image_files/image_files_base.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 
 

invokeai/app/services/image_files/image_files_disk.py

@@ -7,7 +7,7 @@ from PIL import Image, PngImagePlugin
 from PIL.Image import Image as PILImageType
 from send2trash import send2trash
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail

invokeai/app/services/image_records/image_records_base.py

@@ -2,7 +2,7 @@ from abc import ABC, abstractmethod
 from datetime import datetime
 from typing import Optional
 
-from invokeai.app.invocations.metadata import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 
 from .image_records_common import ImageCategory, ImageRecord, ImageRecordChanges, ResourceOrigin

invokeai/app/services/image_records/image_records_sqlite.py

@@ -3,7 +3,7 @@ import threading
 from datetime import datetime
 from typing import Optional, Union, cast
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator
+from invokeai.app.invocations.fields import MetadataField, MetadataFieldValidator
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
 

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
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.image_records.image_records_common import (
     ImageCategory,
     ImageRecord,

invokeai/app/services/images/images_default.py

@@ -2,7 +2,7 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
@@ -154,7 +154,7 @@ class ImageService(ImageServiceABC):
             self.__invoker.services.logger.error("Image record not found")
             raise
         except Exception as e:
-            self.__invoker.services.logger.error("Problem getting image DTO")
+            self.__invoker.services.logger.error("Problem getting image metadata")
             raise e
 
     def get_workflow(self, image_name: str) -> Optional[WorkflowWithoutID]:

invokeai/app/services/invocation_cache/invocation_cache_memory.py

@@ -37,7 +37,8 @@ class MemoryInvocationCache(InvocationCacheBase):
         if self._max_cache_size == 0:
             return
         self._invoker.services.images.on_deleted(self._delete_by_match)
-        self._invoker.services.latents.on_deleted(self._delete_by_match)
+        self._invoker.services.tensors.on_deleted(self._delete_by_match)
+        self._invoker.services.conditioning.on_deleted(self._delete_by_match)
 
     def get(self, key: Union[int, str]) -> Optional[BaseInvocationOutput]:
         with self._lock:

invokeai/app/services/invocation_processor/invocation_processor_default.py

@@ -1,11 +1,16 @@
 import time
 import traceback
+from contextlib import suppress
 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.services.invocation_queue.invocation_queue_common import InvocationQueueItem
+from invokeai.app.services.invocation_stats.invocation_stats_common import (
+    GESStatsNotFoundError,
+)
+from invokeai.app.services.shared.invocation_context import InvocationContextData, build_invocation_context
+from invokeai.app.util.profiler import Profiler
 
 from ..invoker import Invoker
 from .invocation_processor_base import InvocationProcessorABC
@@ -18,9 +23,11 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
     __invoker: Invoker
     __threadLimit: BoundedSemaphore
 
-    def start(self, invoker) -> None:
-        # if we do want multithreading at some point, we could make this configurable
-        self.__threadLimit = BoundedSemaphore(1)
+    def start(self, invoker: Invoker) -> None:
+        # LS - this will probably break
+        # but the idea is to enable multithreading up to the number of available
+        # GPUs. Nodes will block on model loading if no GPU is free.
+        self.__threadLimit = BoundedSemaphore(invoker.services.model_manager.gpu_count)
         self.__invoker = invoker
         self.__stop_event = Event()
         self.__invoker_thread = Thread(
@@ -39,6 +46,27 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
             self.__threadLimit.acquire()
             queue_item: Optional[InvocationQueueItem] = None
 
+            profiler = (
+                Profiler(
+                    logger=self.__invoker.services.logger,
+                    output_dir=self.__invoker.services.configuration.profiles_path,
+                    prefix=self.__invoker.services.configuration.profile_prefix,
+                )
+                if self.__invoker.services.configuration.profile_graphs
+                else None
+            )
+
+            def stats_cleanup(graph_execution_state_id: str) -> None:
+                if profiler:
+                    profile_path = profiler.stop()
+                    stats_path = profile_path.with_suffix(".json")
+                    self.__invoker.services.performance_statistics.dump_stats(
+                        graph_execution_state_id=graph_execution_state_id, output_path=stats_path
+                    )
+                with suppress(GESStatsNotFoundError):
+                    self.__invoker.services.performance_statistics.log_stats(graph_execution_state_id)
+                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state_id)
+
             while not stop_event.is_set():
                 try:
                     queue_item = self.__invoker.services.queue.get()
@@ -49,6 +77,10 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     # do not hammer the queue
                     time.sleep(0.5)
                     continue
+
+                if profiler and profiler.profile_id != queue_item.graph_execution_state_id:
+                    profiler.start(profile_id=queue_item.graph_execution_state_id)
+
                 try:
                     graph_execution_state = self.__invoker.services.graph_execution_manager.get(
                         queue_item.graph_execution_state_id
@@ -101,16 +133,20 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                         # 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(
-                                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,
-                                workflow=queue_item.workflow,
-                            )
+                        context_data = InvocationContextData(
+                            invocation=invocation,
+                            session_id=graph_id,
+                            workflow=queue_item.workflow,
+                            source_node_id=source_node_id,
+                            queue_id=queue_item.session_queue_id,
+                            queue_item_id=queue_item.session_queue_item_id,
+                            batch_id=queue_item.session_queue_batch_id,
                         )
+                        context = build_invocation_context(
+                            services=self.__invoker.services,
+                            context_data=context_data,
+                        )
+                        outputs = invocation.invoke_internal(context=context, services=self.__invoker.services)
 
                         # Check queue to see if this is canceled, and skip if so
                         if self.__invoker.services.queue.is_canceled(graph_execution_state.id):
@@ -137,7 +173,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     pass
 
                 except CanceledException:
-                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state.id)
+                    stats_cleanup(graph_execution_state.id)
                     pass
 
                 except Exception as e:
@@ -162,7 +198,6 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                         error_type=e.__class__.__name__,
                         error=error,
                     )
-                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state.id)
                     pass
 
                 # Check queue to see if this is canceled, and skip if so
@@ -194,13 +229,13 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                             error=traceback.format_exc(),
                         )
                 elif is_complete:
-                    self.__invoker.services.performance_statistics.log_stats(graph_execution_state.id)
                     self.__invoker.services.events.emit_graph_execution_complete(
                         queue_batch_id=queue_item.session_queue_batch_id,
                         queue_item_id=queue_item.session_queue_item_id,
                         queue_id=queue_item.session_queue_id,
                         graph_execution_state_id=graph_execution_state.id,
                     )
+                    stats_cleanup(graph_execution_state.id)
 
         except KeyboardInterrupt:
             pass  # Log something? KeyboardInterrupt is probably not going to be seen by the processor

invokeai/app/services/invocation_services.py

@@ -3,9 +3,15 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING
 
+from invokeai.app.services.object_serializer.object_serializer_base import ObjectSerializerBase
+
 if TYPE_CHECKING:
     from logging import Logger
 
+    import torch
+
+    from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
+
     from .board_image_records.board_image_records_base import BoardImageRecordStorageBase
     from .board_images.board_images_base import BoardImagesServiceABC
     from .board_records.board_records_base import BoardRecordStorageBase
@@ -21,10 +27,7 @@ if TYPE_CHECKING:
     from .invocation_queue.invocation_queue_base import InvocationQueueABC
     from .invocation_stats.invocation_stats_base import InvocationStatsServiceBase
     from .item_storage.item_storage_base import ItemStorageABC
-    from .latents_storage.latents_storage_base import LatentsStorageBase
-    from .model_install import ModelInstallServiceBase
     from .model_manager.model_manager_base import ModelManagerServiceBase
-    from .model_records import ModelRecordServiceBase
     from .names.names_base import NameServiceBase
     from .session_processor.session_processor_base import SessionProcessorBase
     from .session_queue.session_queue_base import SessionQueueBase
@@ -36,33 +39,6 @@ if TYPE_CHECKING:
 class InvocationServices:
     """Services that can be used by invocations"""
 
-    # TODO: Just forward-declared everything due to circular dependencies. Fix structure.
-    board_images: "BoardImagesServiceABC"
-    board_image_record_storage: "BoardImageRecordStorageBase"
-    boards: "BoardServiceABC"
-    board_records: "BoardRecordStorageBase"
-    configuration: "InvokeAIAppConfig"
-    events: "EventServiceBase"
-    graph_execution_manager: "ItemStorageABC[GraphExecutionState]"
-    images: "ImageServiceABC"
-    image_records: "ImageRecordStorageBase"
-    image_files: "ImageFileStorageBase"
-    latents: "LatentsStorageBase"
-    logger: "Logger"
-    model_manager: "ModelManagerServiceBase"
-    model_records: "ModelRecordServiceBase"
-    download_queue: "DownloadQueueServiceBase"
-    model_install: "ModelInstallServiceBase"
-    processor: "InvocationProcessorABC"
-    performance_statistics: "InvocationStatsServiceBase"
-    queue: "InvocationQueueABC"
-    session_queue: "SessionQueueBase"
-    session_processor: "SessionProcessorBase"
-    invocation_cache: "InvocationCacheBase"
-    names: "NameServiceBase"
-    urls: "UrlServiceBase"
-    workflow_records: "WorkflowRecordsStorageBase"
-
     def __init__(
         self,
         board_images: "BoardImagesServiceABC",
@@ -75,12 +51,9 @@ class InvocationServices:
         images: "ImageServiceABC",
         image_files: "ImageFileStorageBase",
         image_records: "ImageRecordStorageBase",
-        latents: "LatentsStorageBase",
         logger: "Logger",
         model_manager: "ModelManagerServiceBase",
-        model_records: "ModelRecordServiceBase",
         download_queue: "DownloadQueueServiceBase",
-        model_install: "ModelInstallServiceBase",
         processor: "InvocationProcessorABC",
         performance_statistics: "InvocationStatsServiceBase",
         queue: "InvocationQueueABC",
@@ -90,6 +63,8 @@ class InvocationServices:
         names: "NameServiceBase",
         urls: "UrlServiceBase",
         workflow_records: "WorkflowRecordsStorageBase",
+        tensors: "ObjectSerializerBase[torch.Tensor]",
+        conditioning: "ObjectSerializerBase[ConditioningFieldData]",
     ):
         self.board_images = board_images
         self.board_image_records = board_image_records
@@ -101,12 +76,9 @@ class InvocationServices:
         self.images = images
         self.image_files = image_files
         self.image_records = image_records
-        self.latents = latents
         self.logger = logger
         self.model_manager = model_manager
-        self.model_records = model_records
         self.download_queue = download_queue
-        self.model_install = model_install
         self.processor = processor
         self.performance_statistics = performance_statistics
         self.queue = queue
@@ -116,3 +88,5 @@ class InvocationServices:
         self.names = names
         self.urls = urls
         self.workflow_records = workflow_records
+        self.tensors = tensors
+        self.conditioning = conditioning

invokeai/app/services/invocation_stats/invocation_stats_base.py

@@ -29,27 +29,28 @@ writes to the system log is stored in InvocationServices.performance_statistics.
 """
 
 from abc import ABC, abstractmethod
-from contextlib import AbstractContextManager
+from pathlib import Path
+from typing import Iterator
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation
+from invokeai.app.services.invocation_stats.invocation_stats_common import InvocationStatsSummary
 
 
 class InvocationStatsServiceBase(ABC):
     "Abstract base class for recording node memory/time performance statistics"
 
     @abstractmethod
-    def __init__(self):
+    def __init__(self) -> None:
         """
         Initialize the InvocationStatsService and reset counters to zero
         """
-        pass
 
     @abstractmethod
     def collect_stats(
         self,
         invocation: BaseInvocation,
         graph_execution_state_id: str,
-    ) -> AbstractContextManager:
+    ) -> Iterator[None]:
         """
         Return a context object that will capture the statistics on the execution
         of invocaation. Use with: to place around the part of the code that executes the invocation.
@@ -59,16 +60,38 @@ class InvocationStatsServiceBase(ABC):
         pass
 
     @abstractmethod
-    def reset_stats(self, graph_execution_state_id: str):
+    def reset_stats(self, graph_execution_state_id: str) -> None:
         """
-        Reset all statistics for the indicated graph
-        :param graph_execution_state_id
+        Reset all statistics for the indicated graph.
+        :param graph_execution_state_id: The id of the session whose stats to reset.
+        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
         """
         pass
 
     @abstractmethod
-    def log_stats(self, graph_execution_state_id: str):
+    def log_stats(self, graph_execution_state_id: str) -> None:
         """
         Write out the accumulated statistics to the log or somewhere else.
+        :param graph_execution_state_id: The id of the session whose stats to log.
+        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
+        """
+        pass
+
+    @abstractmethod
+    def get_stats(self, graph_execution_state_id: str) -> InvocationStatsSummary:
+        """
+        Gets the accumulated statistics for the indicated graph.
+        :param graph_execution_state_id: The id of the session whose stats to get.
+        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
+        """
+        pass
+
+    @abstractmethod
+    def dump_stats(self, graph_execution_state_id: str, output_path: Path) -> None:
+        """
+        Write out the accumulated statistics to the indicated path as JSON.
+        :param graph_execution_state_id: The id of the session whose stats to dump.
+        :param output_path: The file to write the stats to.
+        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
         """
         pass

invokeai/app/services/invocation_stats/invocation_stats_common.py

@@ -1,5 +1,91 @@
 from collections import defaultdict
-from dataclasses import dataclass
+from dataclasses import asdict, dataclass
+from typing import Any, Optional
+
+
+class GESStatsNotFoundError(Exception):
+    """Raised when execution stats are not found for a given Graph Execution State."""
+
+
+@dataclass
+class NodeExecutionStatsSummary:
+    """The stats for a specific type of node."""
+
+    node_type: str
+    num_calls: int
+    time_used_seconds: float
+    peak_vram_gb: float
+
+
+@dataclass
+class ModelCacheStatsSummary:
+    """The stats for the model cache."""
+
+    high_water_mark_gb: float
+    cache_size_gb: float
+    total_usage_gb: float
+    cache_hits: int
+    cache_misses: int
+    models_cached: int
+    models_cleared: int
+
+
+@dataclass
+class GraphExecutionStatsSummary:
+    """The stats for the graph execution state."""
+
+    graph_execution_state_id: str
+    execution_time_seconds: float
+    # `wall_time_seconds`, `ram_usage_gb` and `ram_change_gb` are derived from the node execution stats.
+    # In some situations, there are no node stats, so these values are optional.
+    wall_time_seconds: Optional[float]
+    ram_usage_gb: Optional[float]
+    ram_change_gb: Optional[float]
+
+
+@dataclass
+class InvocationStatsSummary:
+    """
+    The accumulated stats for a graph execution.
+    Its `__str__` method returns a human-readable stats summary.
+    """
+
+    vram_usage_gb: Optional[float]
+    graph_stats: GraphExecutionStatsSummary
+    model_cache_stats: ModelCacheStatsSummary
+    node_stats: list[NodeExecutionStatsSummary]
+
+    def __str__(self) -> str:
+        _str = ""
+        _str = f"Graph stats: {self.graph_stats.graph_execution_state_id}\n"
+        _str += f"{'Node':>30} {'Calls':>7} {'Seconds':>9} {'VRAM Used':>10}\n"
+
+        for summary in self.node_stats:
+            _str += f"{summary.node_type:>30} {summary.num_calls:>7} {summary.time_used_seconds:>8.3f}s {summary.peak_vram_gb:>9.3f}G\n"
+
+        _str += f"TOTAL GRAPH EXECUTION TIME: {self.graph_stats.execution_time_seconds:7.3f}s\n"
+
+        if self.graph_stats.wall_time_seconds is not None:
+            _str += f"TOTAL GRAPH WALL TIME: {self.graph_stats.wall_time_seconds:7.3f}s\n"
+
+        if self.graph_stats.ram_usage_gb is not None and self.graph_stats.ram_change_gb is not None:
+            _str += f"RAM used by InvokeAI process: {self.graph_stats.ram_usage_gb:4.2f}G ({self.graph_stats.ram_change_gb:+5.3f}G)\n"
+
+        _str += f"RAM used to load models: {self.model_cache_stats.total_usage_gb:4.2f}G\n"
+        if self.vram_usage_gb:
+            _str += f"VRAM in use: {self.vram_usage_gb:4.3f}G\n"
+        _str += "RAM cache statistics:\n"
+        _str += f"   Model cache hits: {self.model_cache_stats.cache_hits}\n"
+        _str += f"   Model cache misses: {self.model_cache_stats.cache_misses}\n"
+        _str += f"   Models cached: {self.model_cache_stats.models_cached}\n"
+        _str += f"   Models cleared from cache: {self.model_cache_stats.models_cleared}\n"
+        _str += f"   Cache high water mark: {self.model_cache_stats.high_water_mark_gb:4.2f}/{self.model_cache_stats.cache_size_gb:4.2f}G\n"
+
+        return _str
+
+    def as_dict(self) -> dict[str, Any]:
+        """Returns the stats as a dictionary."""
+        return asdict(self)
 
 
 @dataclass
@@ -55,12 +141,33 @@ class GraphExecutionStats:
 
         return last_node
 
-    def get_pretty_log(self, graph_execution_state_id: str) -> str:
-        log = f"Graph stats: {graph_execution_state_id}\n"
-        log += f"{'Node':>30} {'Calls':>7}{'Seconds':>9} {'VRAM Used':>10}\n"
+    def get_graph_stats_summary(self, graph_execution_state_id: str) -> GraphExecutionStatsSummary:
+        """Get a summary of the graph stats."""
+        first_node = self.get_first_node_stats()
+        last_node = self.get_last_node_stats()
 
-        # Log stats aggregated by node type.
+        wall_time_seconds: Optional[float] = None
+        ram_usage_gb: Optional[float] = None
+        ram_change_gb: Optional[float] = None
+
+        if last_node and first_node:
+            wall_time_seconds = last_node.end_time - first_node.start_time
+            ram_usage_gb = last_node.end_ram_gb
+            ram_change_gb = last_node.end_ram_gb - first_node.start_ram_gb
+
+        return GraphExecutionStatsSummary(
+            graph_execution_state_id=graph_execution_state_id,
+            execution_time_seconds=self.get_total_run_time(),
+            wall_time_seconds=wall_time_seconds,
+            ram_usage_gb=ram_usage_gb,
+            ram_change_gb=ram_change_gb,
+        )
+
+    def get_node_stats_summaries(self) -> list[NodeExecutionStatsSummary]:
+        """Get a summary of the node stats."""
+        summaries: list[NodeExecutionStatsSummary] = []
         node_stats_by_type: dict[str, list[NodeExecutionStats]] = defaultdict(list)
+
         for node_stats in self._node_stats_list:
             node_stats_by_type[node_stats.invocation_type].append(node_stats)
 
@@ -68,17 +175,9 @@ class GraphExecutionStats:
             num_calls = len(node_type_stats_list)
             time_used = sum([n.total_time() for n in node_type_stats_list])
             peak_vram = max([n.peak_vram_gb for n in node_type_stats_list])
-            log += f"{node_type:>30}  {num_calls:>4}   {time_used:7.3f}s     {peak_vram:4.3f}G\n"
+            summary = NodeExecutionStatsSummary(
+                node_type=node_type, num_calls=num_calls, time_used_seconds=time_used, peak_vram_gb=peak_vram
+            )
+            summaries.append(summary)
 
-        # Log stats for the entire graph.
-        log += f"TOTAL GRAPH EXECUTION TIME: {self.get_total_run_time():7.3f}s\n"
-
-        first_node = self.get_first_node_stats()
-        last_node = self.get_last_node_stats()
-        if first_node is not None and last_node is not None:
-            total_wall_time = last_node.end_time - first_node.start_time
-            ram_change = last_node.end_ram_gb - first_node.start_ram_gb
-            log += f"TOTAL GRAPH WALL TIME: {total_wall_time:7.3f}s\n"
-            log += f"RAM used by InvokeAI process: {last_node.end_ram_gb:4.2f}G ({ram_change:+5.3f}G)\n"
-
-        return log
+        return summaries

invokeai/app/services/invocation_stats/invocation_stats_default.py

@@ -1,5 +1,8 @@
+import json
 import time
 from contextlib import contextmanager
+from pathlib import Path
+from typing import Iterator
 
 import psutil
 import torch
@@ -7,10 +10,19 @@ import torch
 import invokeai.backend.util.logging as logger
 from invokeai.app.invocations.baseinvocation import BaseInvocation
 from invokeai.app.services.invoker import Invoker
-from invokeai.backend.model_management.model_cache import CacheStats
+from invokeai.app.services.item_storage.item_storage_common import ItemNotFoundError
+from invokeai.backend.model_manager.load.model_cache import CacheStats
 
 from .invocation_stats_base import InvocationStatsServiceBase
-from .invocation_stats_common import GraphExecutionStats, NodeExecutionStats
+from .invocation_stats_common import (
+    GESStatsNotFoundError,
+    GraphExecutionStats,
+    GraphExecutionStatsSummary,
+    InvocationStatsSummary,
+    ModelCacheStatsSummary,
+    NodeExecutionStats,
+    NodeExecutionStatsSummary,
+)
 
 # Size of 1GB in bytes.
 GB = 2**30
@@ -30,7 +42,10 @@ class InvocationStatsService(InvocationStatsServiceBase):
         self._invoker = invoker
 
     @contextmanager
-    def collect_stats(self, invocation: BaseInvocation, graph_execution_state_id: str):
+    def collect_stats(self, invocation: BaseInvocation, graph_execution_state_id: str) -> Iterator[None]:
+        # This is to handle case of the model manager not being initialized, which happens
+        # during some tests.
+        services = self._invoker.services
         if not self._stats.get(graph_execution_state_id):
             # First time we're seeing this graph_execution_state_id.
             self._stats[graph_execution_state_id] = GraphExecutionStats()
@@ -44,8 +59,9 @@ class InvocationStatsService(InvocationStatsServiceBase):
         start_ram = psutil.Process().memory_info().rss
         if torch.cuda.is_available():
             torch.cuda.reset_peak_memory_stats()
-        if self._invoker.services.model_manager:
-            self._invoker.services.model_manager.collect_cache_stats(self._cache_stats[graph_execution_state_id])
+
+        assert services.model_manager.load is not None
+        services.model_manager.load.ram_cache.stats = self._cache_stats[graph_execution_state_id]
 
         try:
             # Let the invocation run.
@@ -53,7 +69,7 @@ class InvocationStatsService(InvocationStatsServiceBase):
         finally:
             # Record state after the invocation.
             node_stats = NodeExecutionStats(
-                invocation_type=invocation.type,
+                invocation_type=invocation.get_type(),
                 start_time=start_time,
                 end_time=time.time(),
                 start_ram_gb=start_ram / GB,
@@ -62,17 +78,17 @@ class InvocationStatsService(InvocationStatsServiceBase):
             )
             self._stats[graph_execution_state_id].add_node_execution_stats(node_stats)
 
-    def _prune_stale_stats(self):
+    def _prune_stale_stats(self) -> None:
         """Check all graphs being tracked and prune any that have completed/errored.
 
         This shouldn't be necessary, but we don't have totally robust upstream handling of graph completions/errors, so
         for now we call this function periodically to prevent them from accumulating.
         """
-        to_prune = []
+        to_prune: list[str] = []
         for graph_execution_state_id in self._stats:
             try:
                 graph_execution_state = self._invoker.services.graph_execution_manager.get(graph_execution_state_id)
-            except Exception:
+            except ItemNotFoundError:
                 # TODO(ryand): What would cause this? Should this exception just be allowed to propagate?
                 logger.warning(f"Failed to get graph state for {graph_execution_state_id}.")
                 continue
@@ -95,31 +111,66 @@ class InvocationStatsService(InvocationStatsServiceBase):
             del self._stats[graph_execution_state_id]
             del self._cache_stats[graph_execution_state_id]
         except KeyError as e:
-            logger.warning(f"Attempted to clear statistics for unknown graph {graph_execution_state_id}: {e}.")
+            raise GESStatsNotFoundError(
+                f"Attempted to clear statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
 
-    def log_stats(self, graph_execution_state_id: str):
+    def get_stats(self, graph_execution_state_id: str) -> InvocationStatsSummary:
+        graph_stats_summary = self._get_graph_summary(graph_execution_state_id)
+        node_stats_summaries = self._get_node_summaries(graph_execution_state_id)
+        model_cache_stats_summary = self._get_model_cache_summary(graph_execution_state_id)
+        vram_usage_gb = torch.cuda.memory_allocated() / GB if torch.cuda.is_available() else None
+
+        return InvocationStatsSummary(
+            graph_stats=graph_stats_summary,
+            model_cache_stats=model_cache_stats_summary,
+            node_stats=node_stats_summaries,
+            vram_usage_gb=vram_usage_gb,
+        )
+
+    def log_stats(self, graph_execution_state_id: str) -> None:
+        stats = self.get_stats(graph_execution_state_id)
+        logger.info(str(stats))
+
+    def dump_stats(self, graph_execution_state_id: str, output_path: Path) -> None:
+        stats = self.get_stats(graph_execution_state_id)
+        with open(output_path, "w") as f:
+            f.write(json.dumps(stats.as_dict(), indent=2))
+
+    def _get_model_cache_summary(self, graph_execution_state_id: str) -> ModelCacheStatsSummary:
         try:
-            graph_stats = self._stats[graph_execution_state_id]
             cache_stats = self._cache_stats[graph_execution_state_id]
         except KeyError as e:
-            logger.warning(f"Attempted to log statistics for unknown graph {graph_execution_state_id}: {e}.")
-            return
+            raise GESStatsNotFoundError(
+                f"Attempted to get model cache statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
 
-        log = graph_stats.get_pretty_log(graph_execution_state_id)
+        return ModelCacheStatsSummary(
+            cache_hits=cache_stats.hits,
+            cache_misses=cache_stats.misses,
+            high_water_mark_gb=cache_stats.high_watermark / GB,
+            cache_size_gb=cache_stats.cache_size / GB,
+            total_usage_gb=sum(list(cache_stats.loaded_model_sizes.values())) / GB,
+            models_cached=cache_stats.in_cache,
+            models_cleared=cache_stats.cleared,
+        )
 
-        hwm = cache_stats.high_watermark / GB
-        tot = cache_stats.cache_size / GB
-        loaded = sum(list(cache_stats.loaded_model_sizes.values())) / GB
-        log += f"RAM used to load models: {loaded:4.2f}G\n"
-        if torch.cuda.is_available():
-            log += f"VRAM in use: {(torch.cuda.memory_allocated() / GB):4.3f}G\n"
-        log += "RAM cache statistics:\n"
-        log += f"   Model cache hits: {cache_stats.hits}\n"
-        log += f"   Model cache misses: {cache_stats.misses}\n"
-        log += f"   Models cached: {cache_stats.in_cache}\n"
-        log += f"   Models cleared from cache: {cache_stats.cleared}\n"
-        log += f"   Cache high water mark: {hwm:4.2f}/{tot:4.2f}G\n"
-        logger.info(log)
+    def _get_graph_summary(self, graph_execution_state_id: str) -> GraphExecutionStatsSummary:
+        try:
+            graph_stats = self._stats[graph_execution_state_id]
+        except KeyError as e:
+            raise GESStatsNotFoundError(
+                f"Attempted to get graph statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
 
-        del self._stats[graph_execution_state_id]
-        del self._cache_stats[graph_execution_state_id]
+        return graph_stats.get_graph_stats_summary(graph_execution_state_id)
+
+    def _get_node_summaries(self, graph_execution_state_id: str) -> list[NodeExecutionStatsSummary]:
+        try:
+            graph_stats = self._stats[graph_execution_state_id]
+        except KeyError as e:
+            raise GESStatsNotFoundError(
+                f"Attempted to get node statistics for unknown graph {graph_execution_state_id}: {e}."
+            ) from e
+
+        return graph_stats.get_node_stats_summaries()

invokeai/app/services/item_storage/item_storage_base.py

@@ -1,10 +1,8 @@
 from abc import ABC, abstractmethod
-from typing import Callable, Generic, Optional, TypeVar
+from typing import Callable, Generic, TypeVar
 
 from pydantic import BaseModel
 
-from invokeai.app.services.shared.pagination import PaginatedResults
-
 T = TypeVar("T", bound=BaseModel)
 
 
@@ -22,26 +20,26 @@ class ItemStorageABC(ABC, Generic[T]):
 
     @abstractmethod
     def get(self, item_id: str) -> T:
-        """Gets the item, parsing it into a Pydantic model"""
-        pass
-
-    @abstractmethod
-    def get_raw(self, item_id: str) -> Optional[str]:
-        """Gets the raw item as a string, skipping Pydantic parsing"""
+        """
+        Gets the item.
+        :param item_id: the id of the item to get
+        :raises ItemNotFoundError: if the item is not found
+        """
         pass
 
     @abstractmethod
     def set(self, item: T) -> None:
-        """Sets the item"""
+        """
+        Sets the item.
+        :param item: the item to set
+        """
         pass
 
     @abstractmethod
-    def list(self, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
-        """Gets a paginated list of items"""
-        pass
-
-    @abstractmethod
-    def search(self, query: str, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
+    def delete(self, item_id: str) -> None:
+        """
+        Deletes the item, if it exists.
+        """
         pass
 
     def on_changed(self, on_changed: Callable[[T], None]) -> None:

invokeai/app/services/item_storage/item_storage_common.py

@@ -0,0 +1,5 @@
+class ItemNotFoundError(KeyError):
+    """Raised when an item is not found in storage"""
+
+    def __init__(self, item_id: str) -> None:
+        super().__init__(f"Item with id {item_id} not found")

invokeai/app/services/item_storage/item_storage_memory.py

@@ -0,0 +1,52 @@
+from collections import OrderedDict
+from contextlib import suppress
+from typing import Generic, TypeVar
+
+from pydantic import BaseModel
+
+from invokeai.app.services.item_storage.item_storage_base import ItemStorageABC
+from invokeai.app.services.item_storage.item_storage_common import ItemNotFoundError
+
+T = TypeVar("T", bound=BaseModel)
+
+
+class ItemStorageMemory(ItemStorageABC[T], Generic[T]):
+    """
+    Provides a simple in-memory storage for items, with a maximum number of items to store.
+    The storage uses the LRU strategy to evict items from storage when the max has been reached.
+    """
+
+    def __init__(self, id_field: str = "id", max_items: int = 10) -> None:
+        super().__init__()
+        if max_items < 1:
+            raise ValueError("max_items must be at least 1")
+        if not id_field:
+            raise ValueError("id_field must not be empty")
+        self._id_field = id_field
+        self._items: OrderedDict[str, T] = OrderedDict()
+        self._max_items = max_items
+
+    def get(self, item_id: str) -> T:
+        # If the item exists, move it to the end of the OrderedDict.
+        item = self._items.pop(item_id, None)
+        if item is None:
+            raise ItemNotFoundError(item_id)
+        self._items[item_id] = item
+        return item
+
+    def set(self, item: T) -> None:
+        item_id = getattr(item, self._id_field)
+        if item_id in self._items:
+            # If item already exists, remove it and add it to the end
+            self._items.pop(item_id)
+        elif len(self._items) >= self._max_items:
+            # If cache is full, evict the least recently used item
+            self._items.popitem(last=False)
+        self._items[item_id] = item
+        self._on_changed(item)
+
+    def delete(self, item_id: str) -> None:
+        # This is a no-op if the item doesn't exist.
+        with suppress(KeyError):
+            del self._items[item_id]
+            self._on_deleted(item_id)

invokeai/app/services/item_storage/item_storage_sqlite.py

@@ -1,147 +0,0 @@
-import sqlite3
-import threading
-from typing import Generic, Optional, TypeVar, get_args
-
-from pydantic import BaseModel, TypeAdapter
-
-from invokeai.app.services.shared.pagination import PaginatedResults
-from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
-
-from .item_storage_base import ItemStorageABC
-
-T = TypeVar("T", bound=BaseModel)
-
-
-class SqliteItemStorage(ItemStorageABC, Generic[T]):
-    _table_name: str
-    _conn: sqlite3.Connection
-    _cursor: sqlite3.Cursor
-    _id_field: str
-    _lock: threading.RLock
-    _validator: Optional[TypeAdapter[T]]
-
-    def __init__(self, db: SqliteDatabase, table_name: str, id_field: str = "id"):
-        super().__init__()
-
-        self._lock = db.lock
-        self._conn = db.conn
-        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._create_table()
-
-    def _create_table(self):
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                f"""CREATE TABLE IF NOT EXISTS {self._table_name} (
-                item TEXT,
-                id TEXT GENERATED ALWAYS AS (json_extract(item, '$.{self._id_field}')) VIRTUAL NOT NULL);"""
-            )
-            self._cursor.execute(
-                f"""CREATE UNIQUE INDEX IF NOT EXISTS {self._table_name}_id ON {self._table_name}(id);"""
-            )
-        finally:
-            self._lock.release()
-
-    def _parse_item(self, item: str) -> T:
-        if self._validator 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)
-
-    def set(self, item: T):
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                f"""INSERT OR REPLACE INTO {self._table_name} (item) VALUES (?);""",
-                (item.model_dump_json(warnings=False, exclude_none=True),),
-            )
-            self._conn.commit()
-        finally:
-            self._lock.release()
-        self._on_changed(item)
-
-    def get(self, id: str) -> Optional[T]:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(f"""SELECT item FROM {self._table_name} WHERE id = ?;""", (str(id),))
-            result = self._cursor.fetchone()
-        finally:
-            self._lock.release()
-
-        if not result:
-            return None
-
-        return self._parse_item(result[0])
-
-    def get_raw(self, id: str) -> Optional[str]:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(f"""SELECT item FROM {self._table_name} WHERE id = ?;""", (str(id),))
-            result = self._cursor.fetchone()
-        finally:
-            self._lock.release()
-
-        if not result:
-            return None
-
-        return result[0]
-
-    def delete(self, id: str):
-        try:
-            self._lock.acquire()
-            self._cursor.execute(f"""DELETE FROM {self._table_name} WHERE id = ?;""", (str(id),))
-            self._conn.commit()
-        finally:
-            self._lock.release()
-        self._on_deleted(id)
-
-    def list(self, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                f"""SELECT item FROM {self._table_name} LIMIT ? OFFSET ?;""",
-                (per_page, page * per_page),
-            )
-            result = self._cursor.fetchall()
-
-            items = [self._parse_item(r[0]) for r in result]
-
-            self._cursor.execute(f"""SELECT count(*) FROM {self._table_name};""")
-            count = self._cursor.fetchone()[0]
-        finally:
-            self._lock.release()
-
-        pageCount = int(count / per_page) + 1
-
-        return PaginatedResults[T](items=items, page=page, pages=pageCount, per_page=per_page, total=count)
-
-    def search(self, query: str, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
-        try:
-            self._lock.acquire()
-            self._cursor.execute(
-                f"""SELECT item FROM {self._table_name} WHERE item LIKE ? LIMIT ? OFFSET ?;""",
-                (f"%{query}%", per_page, page * per_page),
-            )
-            result = self._cursor.fetchall()
-
-            items = [self._parse_item(r[0]) for r in result]
-
-            self._cursor.execute(
-                f"""SELECT count(*) FROM {self._table_name} WHERE item LIKE ?;""",
-                (f"%{query}%",),
-            )
-            count = self._cursor.fetchone()[0]
-        finally:
-            self._lock.release()
-
-        pageCount = int(count / per_page) + 1
-
-        return PaginatedResults[T](items=items, page=page, pages=pageCount, per_page=per_page, total=count)

invokeai/app/services/latents_storage/latents_storage_base.py

@@ -1,45 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from abc import ABC, abstractmethod
-from typing import Callable
-
-import torch
-
-
-class LatentsStorageBase(ABC):
-    """Responsible for storing and retrieving latents."""
-
-    _on_changed_callbacks: list[Callable[[torch.Tensor], None]]
-    _on_deleted_callbacks: list[Callable[[str], None]]
-
-    def __init__(self) -> None:
-        self._on_changed_callbacks = []
-        self._on_deleted_callbacks = []
-
-    @abstractmethod
-    def get(self, name: str) -> torch.Tensor:
-        pass
-
-    @abstractmethod
-    def save(self, name: str, data: torch.Tensor) -> None:
-        pass
-
-    @abstractmethod
-    def delete(self, name: str) -> None:
-        pass
-
-    def on_changed(self, on_changed: Callable[[torch.Tensor], None]) -> None:
-        """Register a callback for when an item is changed"""
-        self._on_changed_callbacks.append(on_changed)
-
-    def on_deleted(self, on_deleted: Callable[[str], None]) -> None:
-        """Register a callback for when an item is deleted"""
-        self._on_deleted_callbacks.append(on_deleted)
-
-    def _on_changed(self, item: torch.Tensor) -> None:
-        for callback in self._on_changed_callbacks:
-            callback(item)
-
-    def _on_deleted(self, item_id: str) -> None:
-        for callback in self._on_deleted_callbacks:
-            callback(item_id)

invokeai/app/services/latents_storage/latents_storage_disk.py

@@ -1,58 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from pathlib import Path
-from typing import Union
-
-import torch
-
-from invokeai.app.services.invoker import Invoker
-
-from .latents_storage_base import LatentsStorageBase
-
-
-class DiskLatentsStorage(LatentsStorageBase):
-    """Stores latents in a folder on disk without caching"""
-
-    __output_folder: Path
-
-    def __init__(self, output_folder: Union[str, Path]):
-        self.__output_folder = output_folder if isinstance(output_folder, Path) else Path(output_folder)
-        self.__output_folder.mkdir(parents=True, exist_ok=True)
-
-    def start(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-        self._delete_all_latents()
-
-    def get(self, name: str) -> torch.Tensor:
-        latent_path = self.get_path(name)
-        return torch.load(latent_path)
-
-    def save(self, name: str, data: torch.Tensor) -> None:
-        self.__output_folder.mkdir(parents=True, exist_ok=True)
-        latent_path = self.get_path(name)
-        torch.save(data, latent_path)
-
-    def delete(self, name: str) -> None:
-        latent_path = self.get_path(name)
-        latent_path.unlink()
-
-    def get_path(self, name: str) -> Path:
-        return self.__output_folder / name
-
-    def _delete_all_latents(self) -> None:
-        """
-        Deletes all latents from disk.
-        Must be called after we have access to `self._invoker` (e.g. in `start()`).
-        """
-        deleted_latents_count = 0
-        freed_space = 0
-        for latents_file in Path(self.__output_folder).glob("*"):
-            if latents_file.is_file():
-                freed_space += latents_file.stat().st_size
-                deleted_latents_count += 1
-                latents_file.unlink()
-        if deleted_latents_count > 0:
-            freed_space_in_mb = round(freed_space / 1024 / 1024, 2)
-            self._invoker.services.logger.info(
-                f"Deleted {deleted_latents_count} latents files (freed {freed_space_in_mb}MB)"
-            )

invokeai/app/services/latents_storage/latents_storage_forward_cache.py

@@ -1,68 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from queue import Queue
-from typing import Dict, Optional
-
-import torch
-
-from invokeai.app.services.invoker import Invoker
-
-from .latents_storage_base import LatentsStorageBase
-
-
-class ForwardCacheLatentsStorage(LatentsStorageBase):
-    """Caches the latest N latents in memory, writing-thorugh to and reading from underlying storage"""
-
-    __cache: Dict[str, torch.Tensor]
-    __cache_ids: Queue
-    __max_cache_size: int
-    __underlying_storage: LatentsStorageBase
-
-    def __init__(self, underlying_storage: LatentsStorageBase, max_cache_size: int = 20):
-        super().__init__()
-        self.__underlying_storage = underlying_storage
-        self.__cache = {}
-        self.__cache_ids = Queue()
-        self.__max_cache_size = max_cache_size
-
-    def start(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-        start_op = getattr(self.__underlying_storage, "start", None)
-        if callable(start_op):
-            start_op(invoker)
-
-    def stop(self, invoker: Invoker) -> None:
-        self._invoker = invoker
-        stop_op = getattr(self.__underlying_storage, "stop", None)
-        if callable(stop_op):
-            stop_op(invoker)
-
-    def get(self, name: str) -> torch.Tensor:
-        cache_item = self.__get_cache(name)
-        if cache_item is not None:
-            return cache_item
-
-        latent = self.__underlying_storage.get(name)
-        self.__set_cache(name, latent)
-        return latent
-
-    def save(self, name: str, data: torch.Tensor) -> None:
-        self.__underlying_storage.save(name, data)
-        self.__set_cache(name, data)
-        self._on_changed(data)
-
-    def delete(self, name: str) -> None:
-        self.__underlying_storage.delete(name)
-        if name in self.__cache:
-            del self.__cache[name]
-        self._on_deleted(name)
-
-    def __get_cache(self, name: str) -> Optional[torch.Tensor]:
-        return None if name not in self.__cache else self.__cache[name]
-
-    def __set_cache(self, name: str, data: torch.Tensor):
-        if name not in self.__cache:
-            self.__cache[name] = data
-            self.__cache_ids.put(name)
-            if self.__cache_ids.qsize() > self.__max_cache_size:
-                self.__cache.pop(self.__cache_ids.get())

invokeai/app/services/model_install/model_install_base.py

@@ -14,11 +14,13 @@ from typing_extensions import Annotated
 
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase
-from invokeai.app.services.events import EventServiceBase
+from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.model_records import ModelRecordServiceBase
 from invokeai.backend.model_manager import AnyModelConfig, ModelRepoVariant
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, ModelMetadataStore
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
+
+from ..model_metadata import ModelMetadataStoreBase
 
 
 class InstallStatus(str, Enum):
@@ -127,8 +129,8 @@ class HFModelSource(StringLikeSource):
     def __str__(self) -> str:
         """Return string version of repoid when string rep needed."""
         base: str = self.repo_id
+        base += f":{self.variant or ''}"
         base += f":{self.subfolder}" if self.subfolder else ""
-        base += f" ({self.variant})" if self.variant else ""
         return base
 
 
@@ -165,8 +167,8 @@ class ModelInstallJob(BaseModel):
     )
     source: ModelSource = Field(description="Source (URL, repo_id, or local path) of model")
     local_path: Path = Field(description="Path to locally-downloaded model; may be the same as the source")
-    bytes: Optional[int] = Field(
-        default=None, description="For a remote model, the number of bytes downloaded so far (may not be available)"
+    bytes: int = Field(
+        default=0, description="For a remote model, the number of bytes downloaded so far (may not be available)"
     )
     total_bytes: int = Field(default=0, description="Total size of the model to be installed")
     source_metadata: Optional[AnyModelRepoMetadata] = Field(
@@ -243,7 +245,7 @@ class ModelInstallServiceBase(ABC):
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
         download_queue: DownloadQueueServiceBase,
-        metadata_store: ModelMetadataStore,
+        metadata_store: ModelMetadataStoreBase,
         event_bus: Optional["EventServiceBase"] = None,
     ):
         """
@@ -324,6 +326,43 @@ class ModelInstallServiceBase(ABC):
         :returns id: The string ID of the registered model.
         """
 
+    @abstractmethod
+    def heuristic_import(
+        self,
+        source: str,
+        config: Optional[Dict[str, Any]] = None,
+        access_token: Optional[str] = None,
+    ) -> ModelInstallJob:
+        r"""Install the indicated model using heuristics to interpret user intentions.
+
+        :param source: String source
+        :param config: Optional dict. Any fields in this dict
+         will override corresponding autoassigned probe fields in the
+         model's config record as described in `import_model()`.
+        :param access_token: Optional access token for remote sources.
+
+        The source can be:
+        1. A local file path in posix() format (`/foo/bar` or `C:\foo\bar`)
+        2. An http or https URL (`https://foo.bar/foo`)
+        3. A HuggingFace repo_id (`foo/bar`, `foo/bar:fp16`, `foo/bar:fp16:vae`)
+
+        We extend the HuggingFace repo_id syntax to include the variant and the
+        subfolder or path. The following are acceptable alternatives:
+            stabilityai/stable-diffusion-v4
+            stabilityai/stable-diffusion-v4:fp16
+            stabilityai/stable-diffusion-v4:fp16:vae
+            stabilityai/stable-diffusion-v4::/checkpoints/sd4.safetensors
+            stabilityai/stable-diffusion-v4:onnx:vae
+
+        Because a local file path can look like a huggingface repo_id, the logic
+        first checks whether the path exists on disk, and if not, it is treated as
+        a parseable huggingface repo.
+
+        The previous support for recursing into a local folder and loading all model-like files
+        has been removed.
+        """
+        pass
+
     @abstractmethod
     def import_model(
         self,
@@ -385,6 +424,18 @@ class ModelInstallServiceBase(ABC):
     def cancel_job(self, job: ModelInstallJob) -> None:
         """Cancel the indicated job."""
 
+    @abstractmethod
+    def wait_for_job(self, job: ModelInstallJob, timeout: int = 0) -> ModelInstallJob:
+        """Wait for the indicated job to reach a terminal state.
+
+        This will block until the indicated install job has completed,
+        been cancelled, or errored out.
+
+        :param job: The job to wait on.
+        :param timeout: Wait up to indicated number of seconds. Raise a TimeoutError if
+        the job hasn't completed within the indicated time.
+        """
+
     @abstractmethod
     def wait_for_installs(self, timeout: int = 0) -> List[ModelInstallJob]:
         """
@@ -394,7 +445,8 @@ class ModelInstallServiceBase(ABC):
         completed, been cancelled, or errored out.
 
         :param timeout: Wait up to indicated number of seconds. Raise an Exception('timeout') if
-        installs do not complete within the indicated time.
+        installs do not complete within the indicated time. A timeout of zero (the default)
+        will block indefinitely until the installs complete.
         """
 
     @abstractmethod
@@ -410,3 +462,22 @@ class ModelInstallServiceBase(ABC):
     @abstractmethod
     def sync_to_config(self) -> None:
         """Synchronize models on disk to those in the model record database."""
+
+    @abstractmethod
+    def download_and_cache(self, source: Union[str, AnyHttpUrl], access_token: Optional[str] = None) -> Path:
+        """
+        Download the model file located at source to the models cache and return its Path.
+
+        :param source: A Url or a string that can be converted into one.
+        :param access_token: Optional access token to access restricted resources.
+
+        The model file will be downloaded into the system-wide model cache
+        (`models/.cache`) if it isn't already there. Note that the model cache
+        is periodically cleared of infrequently-used entries when the model
+        converter runs.
+
+        Note that this doesn't automaticallly install or register the model, but is
+        intended for use by nodes that need access to models that aren't directly
+        supported by InvokeAI. The downloading process takes advantage of the download queue
+        to avoid interrupting other operations.
+        """

invokeai/app/services/model_install/model_install_default.py

@@ -17,10 +17,10 @@ from pydantic.networks import AnyHttpUrl
 from requests import Session
 
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase
+from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase, TqdmProgress
 from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase, ModelRecordServiceSQL
+from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
@@ -33,7 +33,6 @@ from invokeai.backend.model_manager.metadata import (
     AnyModelRepoMetadata,
     CivitaiMetadataFetch,
     HuggingFaceMetadataFetch,
-    ModelMetadataStore,
     ModelMetadataWithFiles,
     RemoteModelFile,
 )
@@ -50,6 +49,7 @@ from .model_install_base import (
     ModelInstallJob,
     ModelInstallServiceBase,
     ModelSource,
+    StringLikeSource,
     URLModelSource,
 )
 
@@ -64,7 +64,6 @@ class ModelInstallService(ModelInstallServiceBase):
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
         download_queue: DownloadQueueServiceBase,
-        metadata_store: Optional[ModelMetadataStore] = None,
         event_bus: Optional[EventServiceBase] = None,
         session: Optional[Session] = None,
     ):
@@ -86,19 +85,13 @@ class ModelInstallService(ModelInstallServiceBase):
         self._lock = threading.Lock()
         self._stop_event = threading.Event()
         self._downloads_changed_event = threading.Event()
+        self._install_completed_event = threading.Event()
         self._download_queue = download_queue
         self._download_cache: Dict[AnyHttpUrl, ModelInstallJob] = {}
         self._running = False
         self._session = session
         self._next_job_id = 0
-        # There may not necessarily be a metadata store initialized
-        # so we create one and initialize it with the same sql database
-        # used by the record store service.
-        if metadata_store:
-            self._metadata_store = metadata_store
-        else:
-            assert isinstance(record_store, ModelRecordServiceSQL)
-            self._metadata_store = ModelMetadataStore(record_store.db)
+        self._metadata_store = record_store.metadata_store  # for convenience
 
     @property
     def app_config(self) -> InvokeAIAppConfig:  # noqa D102
@@ -145,7 +138,7 @@ class ModelInstallService(ModelInstallServiceBase):
     ) -> str:  # noqa D102
         model_path = Path(model_path)
         config = config or {}
-        if config.get("source") is None:
+        if not config.get("source"):
             config["source"] = model_path.resolve().as_posix()
         return self._register(model_path, config)
 
@@ -156,12 +149,14 @@ class ModelInstallService(ModelInstallServiceBase):
     ) -> str:  # noqa D102
         model_path = Path(model_path)
         config = config or {}
-        if config.get("source") is None:
+        if not config.get("source"):
             config["source"] = model_path.resolve().as_posix()
 
         info: AnyModelConfig = self._probe_model(Path(model_path), config)
-        old_hash = info.original_hash
-        dest_path = self.app_config.models_path / info.base.value / info.type.value / model_path.name
+        old_hash = info.current_hash
+        dest_path = (
+            self.app_config.models_path / info.base.value / info.type.value / (config.get("name") or model_path.name)
+        )
         try:
             new_path = self._copy_model(model_path, dest_path)
         except FileExistsError as excp:
@@ -177,7 +172,40 @@ class ModelInstallService(ModelInstallServiceBase):
             info,
         )
 
+    def heuristic_import(
+        self,
+        source: str,
+        config: Optional[Dict[str, Any]] = None,
+        access_token: Optional[str] = None,
+    ) -> ModelInstallJob:
+        variants = "|".join(ModelRepoVariant.__members__.values())
+        hf_repoid_re = f"^([^/:]+/[^/:]+)(?::({variants})?(?::/?([^:]+))?)?$"
+        source_obj: Optional[StringLikeSource] = None
+
+        if Path(source).exists():  # A local file or directory
+            source_obj = LocalModelSource(path=Path(source))
+        elif match := re.match(hf_repoid_re, source):
+            source_obj = HFModelSource(
+                repo_id=match.group(1),
+                variant=match.group(2) if match.group(2) else None,  # pass None rather than ''
+                subfolder=Path(match.group(3)) if match.group(3) else None,
+                access_token=access_token,
+            )
+        elif re.match(r"^https?://[^/]+", source):
+            source_obj = URLModelSource(
+                url=AnyHttpUrl(source),
+                access_token=access_token,
+            )
+        else:
+            raise ValueError(f"Unsupported model source: '{source}'")
+        return self.import_model(source_obj, config)
+
     def import_model(self, source: ModelSource, config: Optional[Dict[str, Any]] = None) -> ModelInstallJob:  # noqa D102
+        similar_jobs = [x for x in self.list_jobs() if x.source == source and not x.in_terminal_state]
+        if similar_jobs:
+            self._logger.warning(f"There is already an active install job for {source}. Not enqueuing.")
+            return similar_jobs[0]
+
         if isinstance(source, LocalModelSource):
             install_job = self._import_local_model(source, config)
             self._install_queue.put(install_job)  # synchronously install
@@ -207,14 +235,25 @@ class ModelInstallService(ModelInstallServiceBase):
         assert isinstance(jobs[0], ModelInstallJob)
         return jobs[0]
 
+    def wait_for_job(self, job: ModelInstallJob, timeout: int = 0) -> ModelInstallJob:
+        """Block until the indicated job has reached terminal state, or when timeout limit reached."""
+        start = time.time()
+        while not job.in_terminal_state:
+            if self._install_completed_event.wait(timeout=5):  # in case we miss an event
+                self._install_completed_event.clear()
+            if timeout > 0 and time.time() - start > timeout:
+                raise TimeoutError("Timeout exceeded")
+        return job
+
+    # TODO: Better name? Maybe wait_for_jobs()? Maybe too easily confused with above
     def wait_for_installs(self, timeout: int = 0) -> List[ModelInstallJob]:  # noqa D102
         """Block until all installation jobs are done."""
         start = time.time()
         while len(self._download_cache) > 0:
-            if self._downloads_changed_event.wait(timeout=5):  # in case we miss an event
+            if self._downloads_changed_event.wait(timeout=0.25):  # in case we miss an event
                 self._downloads_changed_event.clear()
             if timeout > 0 and time.time() - start > timeout:
-                raise Exception("Timeout exceeded")
+                raise TimeoutError("Timeout exceeded")
         self._install_queue.join()
         return self._install_jobs
 
@@ -268,6 +307,38 @@ class ModelInstallService(ModelInstallServiceBase):
             path.unlink()
         self.unregister(key)
 
+    def download_and_cache(
+        self,
+        source: Union[str, AnyHttpUrl],
+        access_token: Optional[str] = None,
+        timeout: int = 0,
+    ) -> Path:
+        """Download the model file located at source to the models cache and return its Path."""
+        model_hash = sha256(str(source).encode("utf-8")).hexdigest()[0:32]
+        model_path = self._app_config.models_convert_cache_path / model_hash
+
+        # We expect the cache directory to contain one and only one downloaded file.
+        # We don't know the file's name in advance, as it is set by the download
+        # content-disposition header.
+        if model_path.exists():
+            contents = [x for x in model_path.iterdir() if x.is_file()]
+            if len(contents) > 0:
+                return contents[0]
+
+        model_path.mkdir(parents=True, exist_ok=True)
+        job = self._download_queue.download(
+            source=AnyHttpUrl(str(source)),
+            dest=model_path,
+            access_token=access_token,
+            on_progress=TqdmProgress().update,
+        )
+        self._download_queue.wait_for_job(job, timeout)
+        if job.complete:
+            assert job.download_path is not None
+            return job.download_path
+        else:
+            raise Exception(job.error)
+
     # --------------------------------------------------------------------------------------------
     # Internal functions that manage the installer threads
     # --------------------------------------------------------------------------------------------
@@ -300,6 +371,7 @@ class ModelInstallService(ModelInstallServiceBase):
                     job.total_bytes = self._stat_size(job.local_path)
                     job.bytes = job.total_bytes
                     self._signal_job_running(job)
+                    job.config_in["source"] = str(job.source)
                     if job.inplace:
                         key = self.register_path(job.local_path, job.config_in)
                     else:
@@ -330,6 +402,7 @@ class ModelInstallService(ModelInstallServiceBase):
                 # if this is an install of a remote file, then clean up the temporary directory
                 if job._install_tmpdir is not None:
                     rmtree(job._install_tmpdir)
+                self._install_completed_event.set()
                 self._install_queue.task_done()
 
         self._logger.info("Install thread exiting")
@@ -489,10 +562,10 @@ class ModelInstallService(ModelInstallServiceBase):
         return id
 
     @staticmethod
-    def _guess_variant() -> ModelRepoVariant:
+    def _guess_variant() -> Optional[ModelRepoVariant]:
         """Guess the best HuggingFace variant type to download."""
         precision = choose_precision(choose_torch_device())
-        return ModelRepoVariant.FP16 if precision == "float16" else ModelRepoVariant.DEFAULT
+        return ModelRepoVariant.FP16 if precision == "float16" else None
 
     def _import_local_model(self, source: LocalModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
         return ModelInstallJob(
@@ -517,7 +590,7 @@ class ModelInstallService(ModelInstallServiceBase):
         if not source.access_token:
             self._logger.info("No HuggingFace access token present; some models may not be downloadable.")
 
-        metadata = HuggingFaceMetadataFetch(self._session).from_id(source.repo_id)
+        metadata = HuggingFaceMetadataFetch(self._session).from_id(source.repo_id, source.variant)
         assert isinstance(metadata, ModelMetadataWithFiles)
         remote_files = metadata.download_urls(
             variant=source.variant or self._guess_variant(),
@@ -535,19 +608,19 @@ class ModelInstallService(ModelInstallServiceBase):
     def _import_from_url(self, source: URLModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
         # URLs from Civitai or HuggingFace will be handled specially
         url_patterns = {
-            r"https?://civitai.com/": CivitaiMetadataFetch,
-            r"https?://huggingface.co/": HuggingFaceMetadataFetch,
+            r"^https?://civitai.com/": CivitaiMetadataFetch,
+            r"^https?://huggingface.co/[^/]+/[^/]+$": HuggingFaceMetadataFetch,
         }
         metadata = None
         for pattern, fetcher in url_patterns.items():
             if re.match(pattern, str(source.url), re.IGNORECASE):
                 metadata = fetcher(self._session).from_url(source.url)
                 break
+        self._logger.debug(f"metadata={metadata}")
         if metadata and isinstance(metadata, ModelMetadataWithFiles):
             remote_files = metadata.download_urls(session=self._session)
         else:
             remote_files = [RemoteModelFile(url=source.url, path=Path("."), size=0)]
-
         return self._import_remote_model(
             source=source,
             config=config,
@@ -565,6 +638,8 @@ class ModelInstallService(ModelInstallServiceBase):
         # TODO: Replace with tempfile.tmpdir() when multithreading is cleaned up.
         # Currently the tmpdir isn't automatically removed at exit because it is
         # being held in a daemon thread.
+        if len(remote_files) == 0:
+            raise ValueError(f"{source}: No downloadable files found")
         tmpdir = Path(
             mkdtemp(
                 dir=self._app_config.models_path,
@@ -580,15 +655,26 @@ class ModelInstallService(ModelInstallServiceBase):
             bytes=0,
             total_bytes=0,
         )
+        # In the event that there is a subfolder specified in the source,
+        # we need to remove it from the destination path in order to avoid
+        # creating unwanted subfolders
+        if hasattr(source, "subfolder") and source.subfolder:
+            root = Path(remote_files[0].path.parts[0])
+            subfolder = root / source.subfolder
+        else:
+            root = Path(".")
+            subfolder = Path(".")
+
         # we remember the path up to the top of the tmpdir so that it may be
         # removed safely at the end of the install process.
         install_job._install_tmpdir = tmpdir
         assert install_job.total_bytes is not None  # to avoid type checking complaints in the loop below
 
         self._logger.info(f"Queuing {source} for downloading")
+        self._logger.debug(f"remote_files={remote_files}")
         for model_file in remote_files:
             url = model_file.url
-            path = model_file.path
+            path = root / model_file.path.relative_to(subfolder)
             self._logger.info(f"Downloading {url} => {path}")
             install_job.total_bytes += model_file.size
             assert hasattr(source, "access_token")

invokeai/app/services/model_load/__init__.py

@@ -0,0 +1,6 @@
+"""Initialization file for model load service module."""
+
+from .model_load_base import ModelLoadServiceBase
+from .model_load_default import ModelLoadService
+
+__all__ = ["ModelLoadServiceBase", "ModelLoadService"]

invokeai/app/services/model_load/model_load_base.py

@@ -0,0 +1,45 @@
+# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Team
+"""Base class for model loader."""
+
+from abc import ABC, abstractmethod
+from typing import Optional
+
+from invokeai.app.services.shared.invocation_context import InvocationContextData
+from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
+from invokeai.backend.model_manager.load import LoadedModel
+from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
+
+
+class ModelLoadServiceBase(ABC):
+    """Wrapper around AnyModelLoader."""
+
+    @abstractmethod
+    def load_model(
+        self,
+        model_config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
+        """
+        Given a model's configuration, load it and return the LoadedModel object.
+
+        :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
+        :param submodel: For main (pipeline models), the submodel to fetch.
+        :param context_data: Invocation context data used for event reporting
+        """
+
+    @property
+    @abstractmethod
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
+        """Return the RAM cache used by this loader."""
+
+    @property
+    @abstractmethod
+    def convert_cache(self) -> ModelConvertCacheBase:
+        """Return the checkpoint convert cache used by this loader."""
+
+    @property
+    @abstractmethod
+    def gpu_count(self) -> int:
+        """Return the number of GPUs we are configured to use."""

invokeai/app/services/model_load/model_load_default.py

@@ -0,0 +1,122 @@
+# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Team
+"""Implementation of model loader service."""
+
+from typing import Optional, Type
+
+from invokeai.app.services.config import InvokeAIAppConfig
+from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.shared.invocation_context import InvocationContextData
+from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
+from invokeai.backend.model_manager.load import (
+    LoadedModel,
+    ModelLoaderRegistry,
+    ModelLoaderRegistryBase,
+)
+from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
+from invokeai.backend.util.logging import InvokeAILogger
+
+from .model_load_base import ModelLoadServiceBase
+
+
+class ModelLoadService(ModelLoadServiceBase):
+    """Wrapper around ModelLoaderRegistry."""
+
+    def __init__(
+        self,
+        app_config: InvokeAIAppConfig,
+        ram_cache: ModelCacheBase[AnyModel],
+        convert_cache: ModelConvertCacheBase,
+        registry: Optional[Type[ModelLoaderRegistryBase]] = ModelLoaderRegistry,
+    ):
+        """Initialize the model load service."""
+        logger = InvokeAILogger.get_logger(self.__class__.__name__)
+        logger.setLevel(app_config.log_level.upper())
+        self._logger = logger
+        self._app_config = app_config
+        self._ram_cache = ram_cache
+        self._convert_cache = convert_cache
+        self._registry = registry
+
+    def start(self, invoker: Invoker) -> None:
+        """Start the service."""
+        self._invoker = invoker
+
+    @property
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
+        """Return the RAM cache used by this loader."""
+        return self._ram_cache
+
+    @property
+    def gpu_count(self) -> int:
+        """Return the number of GPUs available for our uses."""
+        return len(self._ram_cache.execution_devices)
+
+    @property
+    def convert_cache(self) -> ModelConvertCacheBase:
+        """Return the checkpoint convert cache used by this loader."""
+        return self._convert_cache
+
+    def load_model(
+        self,
+        model_config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
+        """
+        Given a model's configuration, load it and return the LoadedModel object.
+
+        :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
+        :param submodel: For main (pipeline models), the submodel to fetch.
+        :param context: Invocation context used for event reporting
+        """
+        if context_data:
+            self._emit_load_event(
+                context_data=context_data,
+                model_config=model_config,
+            )
+
+        implementation, model_config, submodel_type = self._registry.get_implementation(model_config, submodel_type)  # type: ignore
+        loaded_model: LoadedModel = implementation(
+            app_config=self._app_config,
+            logger=self._logger,
+            ram_cache=self._ram_cache,
+            convert_cache=self._convert_cache,
+        ).load_model(model_config, submodel_type)
+
+        if context_data:
+            self._emit_load_event(
+                context_data=context_data,
+                model_config=model_config,
+                loaded=True,
+            )
+        return loaded_model
+
+    def _emit_load_event(
+        self,
+        context_data: InvocationContextData,
+        model_config: AnyModelConfig,
+        loaded: Optional[bool] = False,
+    ) -> None:
+        if not self._invoker:
+            return
+        if self._invoker.services.queue.is_canceled(context_data.session_id):
+            raise CanceledException()
+
+        if not loaded:
+            self._invoker.services.events.emit_model_load_started(
+                queue_id=context_data.queue_id,
+                queue_item_id=context_data.queue_item_id,
+                queue_batch_id=context_data.batch_id,
+                graph_execution_state_id=context_data.session_id,
+                model_config=model_config,
+            )
+        else:
+            self._invoker.services.events.emit_model_load_completed(
+                queue_id=context_data.queue_id,
+                queue_item_id=context_data.queue_item_id,
+                queue_batch_id=context_data.batch_id,
+                graph_execution_state_id=context_data.session_id,
+                model_config=model_config,
+            )

invokeai/app/services/model_manager/__init__.py

@@ -1 +1,17 @@
-from .model_manager_default import ModelManagerService  # noqa F401
+"""Initialization file for model manager service."""
+
+from invokeai.backend.model_manager import AnyModel, AnyModelConfig, BaseModelType, ModelType, SubModelType
+from invokeai.backend.model_manager.load import LoadedModel
+
+from .model_manager_default import ModelManagerService, ModelManagerServiceBase
+
+__all__ = [
+    "ModelManagerServiceBase",
+    "ModelManagerService",
+    "AnyModel",
+    "AnyModelConfig",
+    "BaseModelType",
+    "ModelType",
+    "SubModelType",
+    "LoadedModel",
+]

invokeai/app/services/model_manager/model_manager_base.py

@@ -1,286 +1,105 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
 
-from __future__ import annotations
-
 from abc import ABC, abstractmethod
-from logging import Logger
-from pathlib import Path
-from typing import TYPE_CHECKING, Callable, List, Literal, Optional, Tuple, Union
+from typing import Optional
 
-from pydantic import Field
+from typing_extensions import Self
 
-from invokeai.app.services.config.config_default import InvokeAIAppConfig
-from invokeai.backend.model_management import (
-    AddModelResult,
-    BaseModelType,
-    MergeInterpolationMethod,
-    ModelInfo,
-    ModelType,
-    SchedulerPredictionType,
-    SubModelType,
-)
-from invokeai.backend.model_management.model_cache import CacheStats
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.shared.invocation_context import InvocationContextData
+from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, ModelType, SubModelType
+from invokeai.backend.model_manager.load.load_base import LoadedModel
 
-if TYPE_CHECKING:
-    from invokeai.app.invocations.baseinvocation import BaseInvocation, InvocationContext
+from ..config import InvokeAIAppConfig
+from ..download import DownloadQueueServiceBase
+from ..events.events_base import EventServiceBase
+from ..model_install import ModelInstallServiceBase
+from ..model_load import ModelLoadServiceBase
+from ..model_records import ModelRecordServiceBase
+from ..shared.sqlite.sqlite_database import SqliteDatabase
 
 
 class ModelManagerServiceBase(ABC):
-    """Responsible for managing models on disk and in memory"""
+    """Abstract base class for the model manager service."""
 
+    # attributes:
+    # store: ModelRecordServiceBase = Field(description="An instance of the model record configuration service.")
+    # install: ModelInstallServiceBase = Field(description="An instance of the model install service.")
+    # load: ModelLoadServiceBase = Field(description="An instance of the model load service.")
+
+    @classmethod
     @abstractmethod
-    def __init__(
-        self,
-        config: InvokeAIAppConfig,
-        logger: Logger,
-    ):
+    def build_model_manager(
+        cls,
+        app_config: InvokeAIAppConfig,
+        db: SqliteDatabase,
+        download_queue: DownloadQueueServiceBase,
+        events: EventServiceBase,
+    ) -> Self:
         """
-        Initialize with the path to the models.yaml config file.
-        Optional parameters are the torch device type, precision, max_models,
-        and sequential_offload boolean. Note that the default device
-        type and precision are set up for a CUDA system running at half precision.
+        Construct the model manager service instance.
+
+        Use it rather than the __init__ constructor. This class
+        method simplifies the construction considerably.
         """
         pass
 
+    @property
     @abstractmethod
-    def get_model(
+    def store(self) -> ModelRecordServiceBase:
+        """Return the ModelRecordServiceBase used to store and retrieve configuration records."""
+        pass
+
+    @property
+    @abstractmethod
+    def load(self) -> ModelLoadServiceBase:
+        """Return the ModelLoadServiceBase used to load models from their configuration records."""
+        pass
+
+    @property
+    @abstractmethod
+    def install(self) -> ModelInstallServiceBase:
+        """Return the ModelInstallServiceBase used to download and manipulate model files."""
+        pass
+
+    @abstractmethod
+    def start(self, invoker: Invoker) -> None:
+        pass
+
+    @abstractmethod
+    def stop(self, invoker: Invoker) -> None:
+        pass
+
+    @abstractmethod
+    def load_model_by_config(
+        self,
+        model_config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
+        pass
+
+    @abstractmethod
+    def load_model_by_key(
+        self,
+        key: str,
+        submodel_type: Optional[SubModelType] = None,
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
+        pass
+
+    @abstractmethod
+    def load_model_by_attr(
         self,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
         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)
-        of a diffusers pipeline."""
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
         pass
 
     @property
     @abstractmethod
-    def logger(self):
-        pass
-
-    @abstractmethod
-    def model_exists(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-    ) -> bool:
-        pass
-
-    @abstractmethod
-    def model_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
-        """
-        Given a model name returns a dict-like (OmegaConf) object describing it.
-        Uses the exact format as the omegaconf stanza.
-        """
-        pass
-
-    @abstractmethod
-    def list_models(self, base_model: Optional[BaseModelType] = None, model_type: Optional[ModelType] = None) -> dict:
-        """
-        Return a dict of models in the format:
-        { model_type1:
-          { model_name1: {'status': 'active'|'cached'|'not loaded',
-                         'model_name' : name,
-                         'model_type' : SDModelType,
-                         'description': description,
-                         'format': 'folder'|'safetensors'|'ckpt'
-                         },
-            model_name2: { etc }
-          },
-          model_type2:
-            { model_name_n: etc
-        }
-        """
-        pass
-
-    @abstractmethod
-    def list_model(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
-        """
-        Return information about the model using the same format as list_models()
-        """
-        pass
-
-    @abstractmethod
-    def model_names(self) -> List[Tuple[str, BaseModelType, ModelType]]:
-        """
-        Returns a list of all the model names known.
-        """
-        pass
-
-    @abstractmethod
-    def add_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        model_attributes: dict,
-        clobber: bool = False,
-    ) -> AddModelResult:
-        """
-        Update the named model with a dictionary of attributes. Will fail with an
-        assertion error if the name already exists. Pass clobber=True to overwrite.
-        On a successful update, the config will be changed in memory. Will fail
-        with an assertion error if provided attributes are incorrect or
-        the model name is missing. Call commit() to write changes to disk.
-        """
-        pass
-
-    @abstractmethod
-    def update_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        model_attributes: dict,
-    ) -> AddModelResult:
-        """
-        Update the named model with a dictionary of attributes. Will fail with a
-        ModelNotFoundException if the name does not already exist.
-
-        On a successful update, the config will be changed in memory. Will fail
-        with an assertion error if provided attributes are incorrect or
-        the model name is missing. Call commit() to write changes to disk.
-        """
-        pass
-
-    @abstractmethod
-    def del_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-    ):
-        """
-        Delete the named model from configuration. If delete_files is true,
-        then the underlying weight file or diffusers directory will be deleted
-        as well. Call commit() to write to disk.
-        """
-        pass
-
-    @abstractmethod
-    def rename_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        new_name: str,
-    ):
-        """
-        Rename the indicated model.
-        """
-        pass
-
-    @abstractmethod
-    def list_checkpoint_configs(self) -> List[Path]:
-        """
-        List the checkpoint config paths from ROOT/configs/stable-diffusion.
-        """
-        pass
-
-    @abstractmethod
-    def convert_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: Literal[ModelType.Main, ModelType.Vae],
-    ) -> AddModelResult:
-        """
-        Convert a checkpoint file into a diffusers folder, deleting the cached
-        version and deleting the original checkpoint file if it is in the models
-        directory.
-        :param model_name: Name of the model to convert
-        :param base_model: Base model type
-        :param model_type: Type of model ['vae' or 'main']
-
-        This will raise a ValueError unless the model is not a checkpoint. It will
-        also raise a ValueError in the event that there is a similarly-named diffusers
-        directory already in place.
-        """
-        pass
-
-    @abstractmethod
-    def heuristic_import(
-        self,
-        items_to_import: set[str],
-        prediction_type_helper: Optional[Callable[[Path], SchedulerPredictionType]] = None,
-    ) -> dict[str, AddModelResult]:
-        """Import a list of paths, repo_ids or URLs. Returns the set of
-        successfully imported items.
-        :param items_to_import: Set of strings corresponding to models to be imported.
-        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
-
-        The prediction type helper is necessary to distinguish between
-        models based on Stable Diffusion 2 Base (requiring
-        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
-        (requiring SchedulerPredictionType.VPrediction). It is
-        generally impossible to do this programmatically, so the
-        prediction_type_helper usually asks the user to choose.
-
-        The result is a set of successfully installed models. Each element
-        of the set is a dict corresponding to the newly-created OmegaConf stanza for
-        that model.
-        """
-        pass
-
-    @abstractmethod
-    def merge_models(
-        self,
-        model_names: List[str] = Field(
-            default=None, min_length=2, max_length=3, description="List of model names to merge"
-        ),
-        base_model: Union[BaseModelType, str] = Field(
-            default=None, description="Base model shared by all models to be merged"
-        ),
-        merged_model_name: str = Field(default=None, description="Name of destination model after merging"),
-        alpha: Optional[float] = 0.5,
-        interp: Optional[MergeInterpolationMethod] = None,
-        force: Optional[bool] = False,
-        merge_dest_directory: Optional[Path] = None,
-    ) -> AddModelResult:
-        """
-        Merge two to three diffusrs pipeline models and save as a new model.
-        :param model_names: List of 2-3 models to merge
-        :param base_model: Base model to use for all models
-        :param merged_model_name: Name of destination merged model
-        :param alpha: Alpha strength to apply to 2d and 3d model
-        :param interp: Interpolation method. None (default)
-        :param merge_dest_directory: Save the merged model to the designated directory (with 'merged_model_name' appended)
-        """
-        pass
-
-    @abstractmethod
-    def search_for_models(self, directory: Path) -> List[Path]:
-        """
-        Return list of all models found in the designated directory.
-        """
-        pass
-
-    @abstractmethod
-    def sync_to_config(self):
-        """
-        Re-read models.yaml, rescan the models directory, and reimport models
-        in the autoimport directories. Call after making changes outside the
-        model manager API.
-        """
-        pass
-
-    @abstractmethod
-    def collect_cache_stats(self, cache_stats: CacheStats):
-        """
-        Reset model cache statistics for graph with graph_id.
-        """
-        pass
-
-    @abstractmethod
-    def commit(self, conf_file: Optional[Path] = None) -> None:
-        """
-        Write current configuration out to the indicated file.
-        If no conf_file is provided, then replaces the
-        original file/database used to initialize the object.
-        """
-        pass
+    def gpu_count(self) -> int:
+        """Return the number of GPUs we are configured to use."""

invokeai/app/services/model_manager/model_manager_default.py

@@ -1,413 +1,154 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
+"""Implementation of ModelManagerServiceBase."""
 
-from __future__ import annotations
+from typing import Optional
 
-from logging import Logger
-from pathlib import Path
-from typing import TYPE_CHECKING, Callable, List, Literal, Optional, Tuple, Union
+from typing_extensions import Self
 
-import torch
-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.backend.model_management import (
-    AddModelResult,
-    BaseModelType,
-    MergeInterpolationMethod,
-    ModelInfo,
-    ModelManager,
-    ModelMerger,
-    ModelNotFoundException,
-    ModelType,
-    SchedulerPredictionType,
-    SubModelType,
-)
-from invokeai.backend.model_management.model_cache import CacheStats
-from invokeai.backend.model_management.model_search import FindModels
-from invokeai.backend.util import choose_precision, choose_torch_device
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.shared.invocation_context import InvocationContextData
+from invokeai.backend.model_manager import AnyModelConfig, BaseModelType, LoadedModel, ModelType, SubModelType
+from invokeai.backend.model_manager.load import ModelCache, ModelConvertCache, ModelLoaderRegistry
+from invokeai.backend.util.logging import InvokeAILogger
 
+from ..config import InvokeAIAppConfig
+from ..download import DownloadQueueServiceBase
+from ..events.events_base import EventServiceBase
+from ..model_install import ModelInstallService, ModelInstallServiceBase
+from ..model_load import ModelLoadService, ModelLoadServiceBase
+from ..model_records import ModelRecordServiceBase, UnknownModelException
 from .model_manager_base import ModelManagerServiceBase
 
-if TYPE_CHECKING:
-    from invokeai.app.invocations.baseinvocation import InvocationContext
 
-
-# simple implementation
 class ModelManagerService(ModelManagerServiceBase):
-    """Responsible for managing models on disk and in memory"""
+    """
+    The ModelManagerService handles various aspects of model installation, maintenance and loading.
+
+    It bundles three distinct services:
+    model_manager.store   -- Routines to manage the database of model configuration records.
+    model_manager.install -- Routines to install, move and delete models.
+    model_manager.load    -- Routines to load models into memory.
+    """
 
     def __init__(
         self,
-        config: InvokeAIAppConfig,
-        logger: Logger,
+        store: ModelRecordServiceBase,
+        install: ModelInstallServiceBase,
+        load: ModelLoadServiceBase,
     ):
-        """
-        Initialize with the path to the models.yaml config file.
-        Optional parameters are the torch device type, precision, max_models,
-        and sequential_offload boolean. Note that the default device
-        type and precision are set up for a CUDA system running at half precision.
-        """
-        if config.model_conf_path and config.model_conf_path.exists():
-            config_file = config.model_conf_path
-        else:
-            config_file = config.root_dir / "configs/models.yaml"
-
-        logger.debug(f"Config file={config_file}")
-
-        device = torch.device(choose_torch_device())
-        device_name = torch.cuda.get_device_name() if device == torch.device("cuda") else ""
-        logger.info(f"GPU device = {device} {device_name}")
-
-        precision = config.precision
-        if precision == "auto":
-            precision = choose_precision(device)
-        dtype = torch.float32 if precision == "float32" else torch.float16
-
-        # this is transitional backward compatibility
-        # support for the deprecated `max_loaded_models`
-        # configuration value. If present, then the
-        # cache size is set to 2.5 GB times
-        # the number of max_loaded_models. Otherwise
-        # use new `ram_cache_size` config setting
-        max_cache_size = config.ram_cache_size
-
-        logger.debug(f"Maximum RAM cache size: {max_cache_size} GiB")
-
-        sequential_offload = config.sequential_guidance
-
-        self.mgr = ModelManager(
-            config=config_file,
-            device_type=device,
-            precision=dtype,
-            max_cache_size=max_cache_size,
-            sequential_offload=sequential_offload,
-            logger=logger,
-        )
-        logger.info("Model manager service initialized")
-
-    def get_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        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,
-            )
-
-        model_info = self.mgr.get_model(
-            model_name,
-            base_model,
-            model_type,
-            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,
-            )
-
-        return model_info
-
-    def model_exists(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-    ) -> bool:
-        """
-        Given a model name, returns True if it is a valid
-        identifier.
-        """
-        return self.mgr.model_exists(
-            model_name,
-            base_model,
-            model_type,
-        )
-
-    def model_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> Union[dict, None]:
-        """
-        Given a model name returns a dict-like (OmegaConf) object describing it.
-        """
-        return self.mgr.model_info(model_name, base_model, model_type)
-
-    def model_names(self) -> List[Tuple[str, BaseModelType, ModelType]]:
-        """
-        Returns a list of all the model names known.
-        """
-        return self.mgr.model_names()
-
-    def list_models(
-        self, base_model: Optional[BaseModelType] = None, model_type: Optional[ModelType] = None
-    ) -> list[dict]:
-        """
-        Return a list of models.
-        """
-        return self.mgr.list_models(base_model, model_type)
-
-    def list_model(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> Union[dict, None]:
-        """
-        Return information about the model using the same format as list_models()
-        """
-        return self.mgr.list_model(model_name=model_name, base_model=base_model, model_type=model_type)
-
-    def add_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        model_attributes: dict,
-        clobber: bool = False,
-    ) -> AddModelResult:
-        """
-        Update the named model with a dictionary of attributes. Will fail with an
-        assertion error if the name already exists. Pass clobber=True to overwrite.
-        On a successful update, the config will be changed in memory. Will fail
-        with an assertion error if provided attributes are incorrect or
-        the model name is missing. Call commit() to write changes to disk.
-        """
-        self.logger.debug(f"add/update model {model_name}")
-        return self.mgr.add_model(model_name, base_model, model_type, model_attributes, clobber)
-
-    def update_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        model_attributes: dict,
-    ) -> AddModelResult:
-        """
-        Update the named model with a dictionary of attributes. Will fail with a
-        ModelNotFoundException exception if the name does not already exist.
-        On a successful update, the config will be changed in memory. Will fail
-        with an assertion error if provided attributes are incorrect or
-        the model name is missing. Call commit() to write changes to disk.
-        """
-        self.logger.debug(f"update model {model_name}")
-        if not self.model_exists(model_name, base_model, model_type):
-            raise ModelNotFoundException(f"Unknown model {model_name}")
-        return self.add_model(model_name, base_model, model_type, model_attributes, clobber=True)
-
-    def del_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-    ):
-        """
-        Delete the named model from configuration. If delete_files is true,
-        then the underlying weight file or diffusers directory will be deleted
-        as well.
-        """
-        self.logger.debug(f"delete model {model_name}")
-        self.mgr.del_model(model_name, base_model, model_type)
-        self.mgr.commit()
-
-    def convert_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: Literal[ModelType.Main, ModelType.Vae],
-        convert_dest_directory: Optional[Path] = Field(
-            default=None, description="Optional directory location for merged model"
-        ),
-    ) -> AddModelResult:
-        """
-        Convert a checkpoint file into a diffusers folder, deleting the cached
-        version and deleting the original checkpoint file if it is in the models
-        directory.
-        :param model_name: Name of the model to convert
-        :param base_model: Base model type
-        :param model_type: Type of model ['vae' or 'main']
-        :param convert_dest_directory: Save the converted model to the designated directory (`models/etc/etc` by default)
-
-        This will raise a ValueError unless the model is not a checkpoint. It will
-        also raise a ValueError in the event that there is a similarly-named diffusers
-        directory already in place.
-        """
-        self.logger.debug(f"convert model {model_name}")
-        return self.mgr.convert_model(model_name, base_model, model_type, convert_dest_directory)
-
-    def collect_cache_stats(self, cache_stats: CacheStats):
-        """
-        Reset model cache statistics for graph with graph_id.
-        """
-        self.mgr.cache.stats = cache_stats
-
-    def commit(self, conf_file: Optional[Path] = None):
-        """
-        Write current configuration out to the indicated file.
-        If no conf_file is provided, then replaces the
-        original file/database used to initialize the object.
-        """
-        return self.mgr.commit(conf_file)
-
-    def _emit_load_event(
-        self,
-        context: InvocationContext,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: Optional[SubModelType] = None,
-        model_info: Optional[ModelInfo] = None,
-    ):
-        if context.services.queue.is_canceled(context.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,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-                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,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-            )
+        self._store = store
+        self._install = install
+        self._load = load
 
     @property
-    def logger(self):
-        return self.mgr.logger
+    def store(self) -> ModelRecordServiceBase:
+        return self._store
 
-    def heuristic_import(
+    @property
+    def install(self) -> ModelInstallServiceBase:
+        return self._install
+
+    @property
+    def load(self) -> ModelLoadServiceBase:
+        return self._load
+
+    def start(self, invoker: Invoker) -> None:
+        for service in [self._store, self._install, self._load]:
+            if hasattr(service, "start"):
+                service.start(invoker)
+
+    def stop(self, invoker: Invoker) -> None:
+        for service in [self._store, self._install, self._load]:
+            if hasattr(service, "stop"):
+                service.stop(invoker)
+
+    def load_model_by_config(
         self,
-        items_to_import: set[str],
-        prediction_type_helper: Optional[Callable[[Path], SchedulerPredictionType]] = None,
-    ) -> dict[str, AddModelResult]:
-        """Import a list of paths, repo_ids or URLs. Returns the set of
-        successfully imported items.
-        :param items_to_import: Set of strings corresponding to models to be imported.
-        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
+        model_config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
+        return self.load.load_model(model_config, submodel_type, context_data)
 
-        The prediction type helper is necessary to distinguish between
-        models based on Stable Diffusion 2 Base (requiring
-        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
-        (requiring SchedulerPredictionType.VPrediction). It is
-        generally impossible to do this programmatically, so the
-        prediction_type_helper usually asks the user to choose.
-
-        The result is a set of successfully installed models. Each element
-        of the set is a dict corresponding to the newly-created OmegaConf stanza for
-        that model.
-        """
-        return self.mgr.heuristic_import(items_to_import, prediction_type_helper)
-
-    def merge_models(
+    def load_model_by_key(
         self,
-        model_names: List[str] = Field(
-            default=None, min_length=2, max_length=3, description="List of model names to merge"
-        ),
-        base_model: Union[BaseModelType, str] = Field(
-            default=None, description="Base model shared by all models to be merged"
-        ),
-        merged_model_name: str = Field(default=None, description="Name of destination model after merging"),
-        alpha: float = 0.5,
-        interp: Optional[MergeInterpolationMethod] = None,
-        force: bool = False,
-        merge_dest_directory: Optional[Path] = Field(
-            default=None, description="Optional directory location for merged model"
-        ),
-    ) -> AddModelResult:
-        """
-        Merge two to three diffusrs pipeline models and save as a new model.
-        :param model_names: List of 2-3 models to merge
-        :param base_model: Base model to use for all models
-        :param merged_model_name: Name of destination merged model
-        :param alpha: Alpha strength to apply to 2d and 3d model
-        :param interp: Interpolation method. None (default)
-        :param merge_dest_directory: Save the merged model to the designated directory (with 'merged_model_name' appended)
-        """
-        merger = ModelMerger(self.mgr)
-        try:
-            result = merger.merge_diffusion_models_and_save(
-                model_names=model_names,
-                base_model=base_model,
-                merged_model_name=merged_model_name,
-                alpha=alpha,
-                interp=interp,
-                force=force,
-                merge_dest_directory=merge_dest_directory,
-            )
-        except AssertionError as e:
-            raise ValueError(e)
-        return result
+        key: str,
+        submodel_type: Optional[SubModelType] = None,
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
+        config = self.store.get_model(key)
+        return self.load.load_model(config, submodel_type, context_data)
 
-    def search_for_models(self, directory: Path) -> List[Path]:
-        """
-        Return list of all models found in the designated directory.
-        """
-        search = FindModels([directory], self.logger)
-        return search.list_models()
-
-    def sync_to_config(self):
-        """
-        Re-read models.yaml, rescan the models directory, and reimport models
-        in the autoimport directories. Call after making changes outside the
-        model manager API.
-        """
-        return self.mgr.sync_to_config()
-
-    def list_checkpoint_configs(self) -> List[Path]:
-        """
-        List the checkpoint config paths from ROOT/configs/stable-diffusion.
-        """
-        config = self.mgr.app_config
-        conf_path = config.legacy_conf_path
-        root_path = config.root_path
-        return [(conf_path / x).relative_to(root_path) for x in conf_path.glob("**/*.yaml")]
-
-    def rename_model(
+    def load_model_by_attr(
         self,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
-        new_name: Optional[str] = None,
-        new_base: Optional[BaseModelType] = None,
-    ):
+        submodel: Optional[SubModelType] = None,
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
         """
-        Rename the indicated model. Can provide a new name and/or a new base.
-        :param model_name: Current name of the model
-        :param base_model: Current base of the model
-        :param model_type: Model type (can't be changed)
-        :param new_name: New name for the model
-        :param new_base: New base for the model
+        Given a model's attributes, search the database for it, and if found, load and return the LoadedModel object.
+
+        This is provided for API compatability with the get_model() method
+        in the original model manager. However, note that LoadedModel is
+        not the same as the original ModelInfo that ws returned.
+
+        :param model_name: Name of to be fetched.
+        :param base_model: Base model
+        :param model_type: Type of the model
+        :param submodel: For main (pipeline models), the submodel to fetch
+        :param context: The invocation context.
+
+        Exceptions: UnknownModelException -- model with this key not known
+                    NotImplementedException -- a model loader was not provided at initialization time
+                    ValueError -- more than one model matches this combination
         """
-        self.mgr.rename_model(
-            base_model=base_model,
-            model_type=model_type,
-            model_name=model_name,
-            new_name=new_name,
-            new_base=new_base,
+        configs = self.store.search_by_attr(model_name, base_model, model_type)
+        if len(configs) == 0:
+            raise UnknownModelException(f"{base_model}/{model_type}/{model_name}: Unknown model")
+        elif len(configs) > 1:
+            raise ValueError(f"{base_model}/{model_type}/{model_name}: More than one model matches.")
+        else:
+            return self.load.load_model(configs[0], submodel, context_data)
+
+    @property
+    def gpu_count(self) -> int:
+        """Return the number of GPUs we are using."""
+        return self.load.gpu_count
+
+    @classmethod
+    def build_model_manager(
+        cls,
+        app_config: InvokeAIAppConfig,
+        model_record_service: ModelRecordServiceBase,
+        download_queue: DownloadQueueServiceBase,
+        events: EventServiceBase,
+    ) -> Self:
+        """
+        Construct the model manager service instance.
+
+        For simplicity, use this class method rather than the __init__ constructor.
+        """
+        logger = InvokeAILogger.get_logger(cls.__name__)
+        logger.setLevel(app_config.log_level.upper())
+
+        ram_cache = ModelCache(
+            max_cache_size=app_config.ram_cache_size, max_vram_cache_size=app_config.vram_cache_size, logger=logger
         )
+        convert_cache = ModelConvertCache(
+            cache_path=app_config.models_convert_cache_path, max_size=app_config.convert_cache_size
+        )
+        loader = ModelLoadService(
+            app_config=app_config,
+            ram_cache=ram_cache,
+            convert_cache=convert_cache,
+            registry=ModelLoaderRegistry,
+        )
+        installer = ModelInstallService(
+            app_config=app_config,
+            record_store=model_record_service,
+            download_queue=download_queue,
+            event_bus=events,
+        )
+        return cls(store=model_record_service, install=installer, load=loader)

invokeai/app/services/model_metadata/__init__.py

@@ -0,0 +1,9 @@
+"""Init file for ModelMetadataStoreService module."""
+
+from .metadata_store_base import ModelMetadataStoreBase
+from .metadata_store_sql import ModelMetadataStoreSQL
+
+__all__ = [
+    "ModelMetadataStoreBase",
+    "ModelMetadataStoreSQL",
+]