chore(ui): lint

Canvas dev build.

.github/workflows/python-checks.yml

@@ -62,7 +62,7 @@ jobs:
 
       - name: install ruff
         if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
-        run: pip install ruff
+        run: pip install ruff==0.6.0
         shell: bash
 
       - name: ruff check

docker/Dockerfile

@@ -55,6 +55,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
 FROM node:20-slim AS web-builder
 ENV PNPM_HOME="/pnpm"
 ENV PATH="$PNPM_HOME:$PATH"
+RUN corepack use pnpm@8.x
 RUN corepack enable
 
 WORKDIR /build

docker/README.md

@@ -1,20 +1,22 @@
 # Invoke in Docker
 
-- Ensure that Docker can use the GPU on your system
-- This documentation assumes Linux, but should work similarly under Windows with WSL2
+First things first:
+
+- Ensure that Docker can use your [NVIDIA][nvidia docker docs] or [AMD][amd docker docs] GPU.
+- This document assumes a Linux system, but should work similarly under Windows with WSL2.
 - We don't recommend running Invoke in Docker on macOS at this time. It works, but very slowly.
 
-## Quickstart :lightning:
+## Quickstart
 
-No `docker compose`, no persistence, just a simple one-liner using the official images:
+No `docker compose`, no persistence, single command, using the official images:
 
-**CUDA:**
+**CUDA (NVIDIA GPU):**
 
 ```bash
 docker run --runtime=nvidia --gpus=all --publish 9090:9090 ghcr.io/invoke-ai/invokeai
 ```
 
-**ROCm:**
+**ROCm (AMD GPU):**
 
 ```bash
 docker run --device /dev/kfd --device /dev/dri --publish 9090:9090 ghcr.io/invoke-ai/invokeai:main-rocm
@@ -22,12 +24,20 @@ docker run --device /dev/kfd --device /dev/dri --publish 9090:9090 ghcr.io/invok
 
 Open `http://localhost:9090` in your browser once the container finishes booting, install some models, and generate away!
 
-> [!TIP]
-> To persist your data (including downloaded models) outside of the container, add a `--volume/-v` flag to the above command, e.g.: `docker run --volume /some/local/path:/invokeai <...the rest of the command>`
+### Data persistence
+
+To persist your generated images and downloaded models outside of the container, add a `--volume/-v` flag to the above command, e.g.:
+
+```bash
+docker run --volume /some/local/path:/invokeai {...etc...}
+```
+
+`/some/local/path/invokeai` will contain all your data.
+It can *usually* be reused between different installs of Invoke. Tread with caution and read the release notes!
 
 ## Customize the container
 
-We ship the `run.sh` script, which is a convenient wrapper around `docker compose` for cases where custom image build args are needed. Alternatively, the familiar `docker compose` commands work just as well.
+The included `run.sh` script is a convenience wrapper around `docker compose`. It can be helpful for passing additional build arguments to `docker compose`. Alternatively, the familiar `docker compose` commands work just as well.
 
 ```bash
 cd docker
@@ -38,11 +48,14 @@ cp .env.sample .env
 
 It will take a few minutes to build the image the first time. Once the application starts up, open `http://localhost:9090` in your browser to invoke!
 
+>[!TIP]
+>When using the `run.sh` script, the container will continue running after Ctrl+C. To shut it down, use the `docker compose down` command.
+
 ## Docker setup in detail
 
 #### Linux
 
-1. Ensure builkit is enabled in the Docker daemon settings (`/etc/docker/daemon.json`)
+1. Ensure buildkit is enabled in the Docker daemon settings (`/etc/docker/daemon.json`)
 2. Install the `docker compose` plugin using your package manager, or follow a [tutorial](https://docs.docker.com/compose/install/linux/#install-using-the-repository).
     - The deprecated `docker-compose` (hyphenated) CLI probably won't work. Update to a recent version.
 3. Ensure docker daemon is able to access the GPU.
@@ -98,25 +111,7 @@ GPU_DRIVER=cuda
 
 Any environment variables supported by InvokeAI can be set here. See the [Configuration docs](https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/) for further detail.
 
-## Even More Customizing!
+---
 
-See the `docker-compose.yml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
-
-### Reconfigure the runtime directory
-
-Can be used to download additional models from the supported model list
-
-In conjunction with `INVOKEAI_ROOT` can be also used to initialize a runtime directory
-
-```yaml
-command:
-  - invokeai-configure
-  - --yes
-```
-
-Or install models:
-
-```yaml
-command:
-  - invokeai-model-install
-```
+[nvidia docker docs]: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
+[amd docker docs]: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html

docs/contributing/MODEL_MANAGER.md

@@ -408,7 +408,7 @@ config = get_config()
 
 logger = InvokeAILogger.get_logger(config=config)
 db = SqliteDatabase(config.db_path, logger)
-record_store = ModelRecordServiceSQL(db)
+record_store = ModelRecordServiceSQL(db, logger)
 queue = DownloadQueueService()
 queue.start()
 

installer/templates/invoke.sh.in

@@ -17,7 +17,7 @@
 set -eu
 
 # Ensure we're in the correct folder in case user's CWD is somewhere else
-scriptdir=$(dirname "$0")
+scriptdir=$(dirname $(readlink -f "$0"))
 cd "$scriptdir"
 
 . .venv/bin/activate

invokeai/app/api/dependencies.py

@@ -1,5 +1,6 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+import asyncio
 from logging import Logger
 
 import torch
@@ -31,6 +32,8 @@ from invokeai.app.services.session_processor.session_processor_default import (
 )
 from invokeai.app.services.session_queue.session_queue_sqlite import SqliteSessionQueue
 from invokeai.app.services.shared.sqlite.sqlite_util import init_db
+from invokeai.app.services.style_preset_images.style_preset_images_disk import StylePresetImageFileStorageDisk
+from invokeai.app.services.style_preset_records.style_preset_records_sqlite import SqliteStylePresetRecordsStorage
 from invokeai.app.services.urls.urls_default import LocalUrlService
 from invokeai.app.services.workflow_records.workflow_records_sqlite import SqliteWorkflowRecordsStorage
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
@@ -63,7 +66,12 @@ class ApiDependencies:
     invoker: Invoker
 
     @staticmethod
-    def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger) -> None:
+    def initialize(
+        config: InvokeAIAppConfig,
+        event_handler_id: int,
+        loop: asyncio.AbstractEventLoop,
+        logger: Logger = logger,
+    ) -> None:
         logger.info(f"InvokeAI version {__version__}")
         logger.info(f"Root directory = {str(config.root_path)}")
 
@@ -74,6 +82,7 @@ class ApiDependencies:
         image_files = DiskImageFileStorage(f"{output_folder}/images")
 
         model_images_folder = config.models_path
+        style_presets_folder = config.style_presets_path
 
         db = init_db(config=config, logger=logger, image_files=image_files)
 
@@ -84,7 +93,7 @@ class ApiDependencies:
         board_images = BoardImagesService()
         board_records = SqliteBoardRecordStorage(db=db)
         boards = BoardService()
-        events = FastAPIEventService(event_handler_id)
+        events = FastAPIEventService(event_handler_id, loop=loop)
         bulk_download = BulkDownloadService()
         image_records = SqliteImageRecordStorage(db=db)
         images = ImageService()
@@ -99,7 +108,7 @@ class ApiDependencies:
         model_images_service = ModelImageFileStorageDisk(model_images_folder / "model_images")
         model_manager = ModelManagerService.build_model_manager(
             app_config=configuration,
-            model_record_service=ModelRecordServiceSQL(db=db),
+            model_record_service=ModelRecordServiceSQL(db=db, logger=logger),
             download_queue=download_queue_service,
             events=events,
         )
@@ -109,6 +118,8 @@ class ApiDependencies:
         session_queue = SqliteSessionQueue(db=db)
         urls = LocalUrlService()
         workflow_records = SqliteWorkflowRecordsStorage(db=db)
+        style_preset_records = SqliteStylePresetRecordsStorage(db=db)
+        style_preset_image_files = StylePresetImageFileStorageDisk(style_presets_folder / "images")
 
         services = InvocationServices(
             board_image_records=board_image_records,
@@ -134,6 +145,8 @@ class ApiDependencies:
             workflow_records=workflow_records,
             tensors=tensors,
             conditioning=conditioning,
+            style_preset_records=style_preset_records,
+            style_preset_image_files=style_preset_image_files,
         )
 
         ApiDependencies.invoker = Invoker(services)

invokeai/app/api/routers/images.py

@@ -218,9 +218,8 @@ async def get_image_workflow(
         raise HTTPException(status_code=404)
 
 
-@images_router.api_route(
+@images_router.get(
     "/i/{image_name}/full",
-    methods=["GET", "HEAD"],
     operation_id="get_image_full",
     response_class=Response,
     responses={
@@ -231,24 +230,30 @@ async def get_image_workflow(
         404: {"description": "Image not found"},
     },
 )
+@images_router.head(
+    "/i/{image_name}/full",
+    operation_id="get_image_full_head",
+    response_class=Response,
+    responses={
+        200: {
+            "description": "Return the full-resolution image",
+            "content": {"image/png": {}},
+        },
+        404: {"description": "Image not found"},
+    },
+)
 async def get_image_full(
     image_name: str = Path(description="The name of full-resolution image file to get"),
-) -> FileResponse:
+) -> Response:
     """Gets a full-resolution image file"""
 
     try:
         path = ApiDependencies.invoker.services.images.get_path(image_name)
-
-        if not ApiDependencies.invoker.services.images.validate_path(path):
-            raise HTTPException(status_code=404)
-
-        response = FileResponse(
-            path,
-            media_type="image/png",
-            filename=image_name,
-            content_disposition_type="inline",
-        )
+        with open(path, "rb") as f:
+            content = f.read()
+        response = Response(content, media_type="image/png")
         response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
+        response.headers["Content-Disposition"] = f'inline; filename="{image_name}"'
         return response
     except Exception:
         raise HTTPException(status_code=404)
@@ -268,15 +273,14 @@ async def get_image_full(
 )
 async def get_image_thumbnail(
     image_name: str = Path(description="The name of thumbnail image file to get"),
-) -> FileResponse:
+) -> Response:
     """Gets a thumbnail image file"""
 
     try:
         path = ApiDependencies.invoker.services.images.get_path(image_name, thumbnail=True)
-        if not ApiDependencies.invoker.services.images.validate_path(path):
-            raise HTTPException(status_code=404)
-
-        response = FileResponse(path, media_type="image/webp", content_disposition_type="inline")
+        with open(path, "rb") as f:
+            content = f.read()
+        response = Response(content, media_type="image/webp")
         response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
         return response
     except Exception:

invokeai/app/api/routers/model_manager.py

@@ -6,7 +6,7 @@ import pathlib
 import traceback
 from copy import deepcopy
 from tempfile import TemporaryDirectory
-from typing import Any, Dict, List, Optional, Type
+from typing import List, Optional, Type
 
 from fastapi import Body, Path, Query, Response, UploadFile
 from fastapi.responses import FileResponse, HTMLResponse
@@ -430,13 +430,11 @@ async def delete_model_image(
 async def install_model(
     source: str = Query(description="Model source to install, can be a local path, repo_id, or remote URL"),
     inplace: Optional[bool] = Query(description="Whether or not to install a local model in place", default=False),
-    # TODO(MM2): Can we type this?
-    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,
+    access_token: Optional[str] = Query(description="access token for the remote resource", default=None),
+    config: ModelRecordChanges = Body(
+        description="Object containing fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
         example={"name": "string", "description": "string"},
     ),
-    access_token: Optional[str] = None,
 ) -> ModelInstallJob:
     """Install a model using a string identifier.
 
@@ -451,8 +449,9 @@ async def install_model(
        - 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.
+    `config` is a ModelRecordChanges object. Fields in this object will override
+    the ones that are probed automatically. Pass an empty object to accept
+    all the defaults.
 
     `access_token` is an optional access token for use with Urls that require
     authentication.
@@ -737,7 +736,7 @@ async def convert_model(
         # write the converted file to the convert path
         raw_model = converted_model.model
         assert hasattr(raw_model, "save_pretrained")
-        raw_model.save_pretrained(convert_path)
+        raw_model.save_pretrained(convert_path)  # type: ignore
         assert convert_path.exists()
 
         # temporarily rename the original safetensors file so that there is no naming conflict
@@ -750,12 +749,12 @@ async def convert_model(
         try:
             new_key = installer.install_path(
                 convert_path,
-                config={
-                    "name": original_name,
-                    "description": model_config.description,
-                    "hash": model_config.hash,
-                    "source": model_config.source,
-                },
+                config=ModelRecordChanges(
+                    name=original_name,
+                    description=model_config.description,
+                    hash=model_config.hash,
+                    source=model_config.source,
+                ),
             )
         except Exception as e:
             logger.error(str(e))

invokeai/app/api/routers/session_queue.py

@@ -11,6 +11,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     Batch,
     BatchStatus,
     CancelByBatchIDsResult,
+    CancelByOriginResult,
     ClearResult,
     EnqueueBatchResult,
     PruneResult,
@@ -105,6 +106,19 @@ async def cancel_by_batch_ids(
     return ApiDependencies.invoker.services.session_queue.cancel_by_batch_ids(queue_id=queue_id, batch_ids=batch_ids)
 
 
+@session_queue_router.put(
+    "/{queue_id}/cancel_by_origin",
+    operation_id="cancel_by_origin",
+    responses={200: {"model": CancelByBatchIDsResult}},
+)
+async def cancel_by_origin(
+    queue_id: str = Path(description="The queue id to perform this operation on"),
+    origin: str = Query(description="The origin to cancel all queue items for"),
+) -> CancelByOriginResult:
+    """Immediately cancels all queue items with the given origin"""
+    return ApiDependencies.invoker.services.session_queue.cancel_by_origin(queue_id=queue_id, origin=origin)
+
+
 @session_queue_router.put(
     "/{queue_id}/clear",
     operation_id="clear",

invokeai/app/api/routers/style_presets.py

@@ -0,0 +1,274 @@
+import csv
+import io
+import json
+import traceback
+from typing import Optional
+
+import pydantic
+from fastapi import APIRouter, File, Form, HTTPException, Path, Response, UploadFile
+from fastapi.responses import FileResponse
+from PIL import Image
+from pydantic import BaseModel, Field
+
+from invokeai.app.api.dependencies import ApiDependencies
+from invokeai.app.api.routers.model_manager import IMAGE_MAX_AGE
+from invokeai.app.services.style_preset_images.style_preset_images_common import StylePresetImageFileNotFoundException
+from invokeai.app.services.style_preset_records.style_preset_records_common import (
+    InvalidPresetImportDataError,
+    PresetData,
+    PresetType,
+    StylePresetChanges,
+    StylePresetNotFoundError,
+    StylePresetRecordWithImage,
+    StylePresetWithoutId,
+    UnsupportedFileTypeError,
+    parse_presets_from_file,
+)
+
+
+class StylePresetFormData(BaseModel):
+    name: str = Field(description="Preset name")
+    positive_prompt: str = Field(description="Positive prompt")
+    negative_prompt: str = Field(description="Negative prompt")
+    type: PresetType = Field(description="Preset type")
+
+
+style_presets_router = APIRouter(prefix="/v1/style_presets", tags=["style_presets"])
+
+
+@style_presets_router.get(
+    "/i/{style_preset_id}",
+    operation_id="get_style_preset",
+    responses={
+        200: {"model": StylePresetRecordWithImage},
+    },
+)
+async def get_style_preset(
+    style_preset_id: str = Path(description="The style preset to get"),
+) -> StylePresetRecordWithImage:
+    """Gets a style preset"""
+    try:
+        image = ApiDependencies.invoker.services.style_preset_image_files.get_url(style_preset_id)
+        style_preset = ApiDependencies.invoker.services.style_preset_records.get(style_preset_id)
+        return StylePresetRecordWithImage(image=image, **style_preset.model_dump())
+    except StylePresetNotFoundError:
+        raise HTTPException(status_code=404, detail="Style preset not found")
+
+
+@style_presets_router.patch(
+    "/i/{style_preset_id}",
+    operation_id="update_style_preset",
+    responses={
+        200: {"model": StylePresetRecordWithImage},
+    },
+)
+async def update_style_preset(
+    image: Optional[UploadFile] = File(description="The image file to upload", default=None),
+    style_preset_id: str = Path(description="The id of the style preset to update"),
+    data: str = Form(description="The data of the style preset to update"),
+) -> StylePresetRecordWithImage:
+    """Updates a style preset"""
+    if image is not None:
+        if not image.content_type or not image.content_type.startswith("image"):
+            raise HTTPException(status_code=415, detail="Not an image")
+
+        contents = await image.read()
+        try:
+            pil_image = Image.open(io.BytesIO(contents))
+
+        except Exception:
+            ApiDependencies.invoker.services.logger.error(traceback.format_exc())
+            raise HTTPException(status_code=415, detail="Failed to read image")
+
+        try:
+            ApiDependencies.invoker.services.style_preset_image_files.save(style_preset_id, pil_image)
+        except ValueError as e:
+            raise HTTPException(status_code=409, detail=str(e))
+    else:
+        try:
+            ApiDependencies.invoker.services.style_preset_image_files.delete(style_preset_id)
+        except StylePresetImageFileNotFoundException:
+            pass
+
+    try:
+        parsed_data = json.loads(data)
+        validated_data = StylePresetFormData(**parsed_data)
+
+        name = validated_data.name
+        type = validated_data.type
+        positive_prompt = validated_data.positive_prompt
+        negative_prompt = validated_data.negative_prompt
+
+    except pydantic.ValidationError:
+        raise HTTPException(status_code=400, detail="Invalid preset data")
+
+    preset_data = PresetData(positive_prompt=positive_prompt, negative_prompt=negative_prompt)
+    changes = StylePresetChanges(name=name, preset_data=preset_data, type=type)
+
+    style_preset_image = ApiDependencies.invoker.services.style_preset_image_files.get_url(style_preset_id)
+    style_preset = ApiDependencies.invoker.services.style_preset_records.update(
+        style_preset_id=style_preset_id, changes=changes
+    )
+    return StylePresetRecordWithImage(image=style_preset_image, **style_preset.model_dump())
+
+
+@style_presets_router.delete(
+    "/i/{style_preset_id}",
+    operation_id="delete_style_preset",
+)
+async def delete_style_preset(
+    style_preset_id: str = Path(description="The style preset to delete"),
+) -> None:
+    """Deletes a style preset"""
+    try:
+        ApiDependencies.invoker.services.style_preset_image_files.delete(style_preset_id)
+    except StylePresetImageFileNotFoundException:
+        pass
+
+    ApiDependencies.invoker.services.style_preset_records.delete(style_preset_id)
+
+
+@style_presets_router.post(
+    "/",
+    operation_id="create_style_preset",
+    responses={
+        200: {"model": StylePresetRecordWithImage},
+    },
+)
+async def create_style_preset(
+    image: Optional[UploadFile] = File(description="The image file to upload", default=None),
+    data: str = Form(description="The data of the style preset to create"),
+) -> StylePresetRecordWithImage:
+    """Creates a style preset"""
+
+    try:
+        parsed_data = json.loads(data)
+        validated_data = StylePresetFormData(**parsed_data)
+
+        name = validated_data.name
+        type = validated_data.type
+        positive_prompt = validated_data.positive_prompt
+        negative_prompt = validated_data.negative_prompt
+
+    except pydantic.ValidationError:
+        raise HTTPException(status_code=400, detail="Invalid preset data")
+
+    preset_data = PresetData(positive_prompt=positive_prompt, negative_prompt=negative_prompt)
+    style_preset = StylePresetWithoutId(name=name, preset_data=preset_data, type=type)
+    new_style_preset = ApiDependencies.invoker.services.style_preset_records.create(style_preset=style_preset)
+
+    if image is not None:
+        if not image.content_type or not image.content_type.startswith("image"):
+            raise HTTPException(status_code=415, detail="Not an image")
+
+        contents = await image.read()
+        try:
+            pil_image = Image.open(io.BytesIO(contents))
+
+        except Exception:
+            ApiDependencies.invoker.services.logger.error(traceback.format_exc())
+            raise HTTPException(status_code=415, detail="Failed to read image")
+
+        try:
+            ApiDependencies.invoker.services.style_preset_image_files.save(new_style_preset.id, pil_image)
+        except ValueError as e:
+            raise HTTPException(status_code=409, detail=str(e))
+
+    preset_image = ApiDependencies.invoker.services.style_preset_image_files.get_url(new_style_preset.id)
+    return StylePresetRecordWithImage(image=preset_image, **new_style_preset.model_dump())
+
+
+@style_presets_router.get(
+    "/",
+    operation_id="list_style_presets",
+    responses={
+        200: {"model": list[StylePresetRecordWithImage]},
+    },
+)
+async def list_style_presets() -> list[StylePresetRecordWithImage]:
+    """Gets a page of style presets"""
+    style_presets_with_image: list[StylePresetRecordWithImage] = []
+    style_presets = ApiDependencies.invoker.services.style_preset_records.get_many()
+    for preset in style_presets:
+        image = ApiDependencies.invoker.services.style_preset_image_files.get_url(preset.id)
+        style_preset_with_image = StylePresetRecordWithImage(image=image, **preset.model_dump())
+        style_presets_with_image.append(style_preset_with_image)
+
+    return style_presets_with_image
+
+
+@style_presets_router.get(
+    "/i/{style_preset_id}/image",
+    operation_id="get_style_preset_image",
+    responses={
+        200: {
+            "description": "The style preset image was fetched successfully",
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The style preset image could not be found"},
+    },
+    status_code=200,
+)
+async def get_style_preset_image(
+    style_preset_id: str = Path(description="The id of the style preset image to get"),
+) -> FileResponse:
+    """Gets an image file that previews the model"""
+
+    try:
+        path = ApiDependencies.invoker.services.style_preset_image_files.get_path(style_preset_id)
+
+        response = FileResponse(
+            path,
+            media_type="image/png",
+            filename=style_preset_id + ".png",
+            content_disposition_type="inline",
+        )
+        response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
+        return response
+    except Exception:
+        raise HTTPException(status_code=404)
+
+
+@style_presets_router.get(
+    "/export",
+    operation_id="export_style_presets",
+    responses={200: {"content": {"text/csv": {}}, "description": "A CSV file with the requested data."}},
+    status_code=200,
+)
+async def export_style_presets():
+    # Create an in-memory stream to store the CSV data
+    output = io.StringIO()
+    writer = csv.writer(output)
+
+    # Write the header
+    writer.writerow(["name", "prompt", "negative_prompt"])
+
+    style_presets = ApiDependencies.invoker.services.style_preset_records.get_many(type=PresetType.User)
+
+    for preset in style_presets:
+        writer.writerow([preset.name, preset.preset_data.positive_prompt, preset.preset_data.negative_prompt])
+
+    csv_data = output.getvalue()
+    output.close()
+
+    return Response(
+        content=csv_data,
+        media_type="text/csv",
+        headers={"Content-Disposition": "attachment; filename=prompt_templates.csv"},
+    )
+
+
+@style_presets_router.post(
+    "/import",
+    operation_id="import_style_presets",
+)
+async def import_style_presets(file: UploadFile = File(description="The file to import")):
+    try:
+        style_presets = await parse_presets_from_file(file)
+        ApiDependencies.invoker.services.style_preset_records.create_many(style_presets)
+    except InvalidPresetImportDataError as e:
+        ApiDependencies.invoker.services.logger.error(traceback.format_exc())
+        raise HTTPException(status_code=400, detail=str(e))
+    except UnsupportedFileTypeError as e:
+        ApiDependencies.invoker.services.logger.error(traceback.format_exc())
+        raise HTTPException(status_code=415, detail=str(e))

invokeai/app/api_app.py

@@ -30,6 +30,7 @@ from invokeai.app.api.routers import (
     images,
     model_manager,
     session_queue,
+    style_presets,
     utilities,
     workflows,
 )
@@ -55,11 +56,13 @@ mimetypes.add_type("text/css", ".css")
 torch_device_name = TorchDevice.get_torch_device_name()
 logger.info(f"Using torch device: {torch_device_name}")
 
+loop = asyncio.new_event_loop()
+
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     # Add startup event to load dependencies
-    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
+    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, loop=loop, logger=logger)
     yield
     # Shut down threads
     ApiDependencies.shutdown()
@@ -106,6 +109,7 @@ app.include_router(board_images.board_images_router, prefix="/api")
 app.include_router(app_info.app_router, prefix="/api")
 app.include_router(session_queue.session_queue_router, prefix="/api")
 app.include_router(workflows.workflows_router, prefix="/api")
+app.include_router(style_presets.style_presets_router, prefix="/api")
 
 app.openapi = get_openapi_func(app)
 
@@ -161,6 +165,7 @@ def invoke_api() -> None:
         # Taken from https://waylonwalker.com/python-find-available-port/, thanks Waylon!
         # https://github.com/WaylonWalker
         with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
+            s.settimeout(1)
             if s.connect_ex(("localhost", port)) == 0:
                 return find_port(port=port + 1)
             else:
@@ -183,8 +188,6 @@ def invoke_api() -> None:
 
     check_cudnn(logger)
 
-    # Start our own event loop for eventing usage
-    loop = asyncio.new_event_loop()
     config = uvicorn.Config(
         app=app,
         host=app_config.host,

invokeai/app/invocations/compel.py

@@ -80,12 +80,12 @@ class CompelInvocation(BaseInvocation):
 
         with (
             # apply all patches while the model is on the target device
-            text_encoder_info.model_on_device() as (model_state_dict, text_encoder),
+            text_encoder_info.model_on_device() as (cached_weights, text_encoder),
             tokenizer_info as tokenizer,
             ModelPatcher.apply_lora_text_encoder(
                 text_encoder,
                 loras=_lora_loader(),
-                model_state_dict=model_state_dict,
+                cached_weights=cached_weights,
             ),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
             ModelPatcher.apply_clip_skip(text_encoder, self.clip.skipped_layers),
@@ -175,13 +175,13 @@ class SDXLPromptInvocationBase:
 
         with (
             # apply all patches while the model is on the target device
-            text_encoder_info.model_on_device() as (state_dict, text_encoder),
+            text_encoder_info.model_on_device() as (cached_weights, text_encoder),
             tokenizer_info as tokenizer,
             ModelPatcher.apply_lora(
                 text_encoder,
                 loras=_lora_loader(),
                 prefix=lora_prefix,
-                model_state_dict=state_dict,
+                cached_weights=cached_weights,
             ),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
             ModelPatcher.apply_clip_skip(text_encoder, clip_field.skipped_layers),

invokeai/app/invocations/controlnet_image_processors.py

@@ -21,6 +21,8 @@ from controlnet_aux import (
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
 from pydantic import BaseModel, Field, field_validator, model_validator
+from transformers import pipeline
+from transformers.pipelines import DepthEstimationPipeline
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -44,13 +46,12 @@ from invokeai.app.invocations.util import validate_begin_end_step, validate_weig
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES, heuristic_resize
 from invokeai.backend.image_util.canny import get_canny_edges
-from invokeai.backend.image_util.depth_anything import DEPTH_ANYTHING_MODELS, DepthAnythingDetector
+from invokeai.backend.image_util.depth_anything.depth_anything_pipeline import DepthAnythingPipeline
 from invokeai.backend.image_util.dw_openpose import DWPOSE_MODELS, DWOpenposeDetector
 from invokeai.backend.image_util.hed import HEDProcessor
 from invokeai.backend.image_util.lineart import LineartProcessor
 from invokeai.backend.image_util.lineart_anime import LineartAnimeProcessor
 from invokeai.backend.image_util.util import np_to_pil, pil_to_np
-from invokeai.backend.util.devices import TorchDevice
 
 
 class ControlField(BaseModel):
@@ -592,7 +593,14 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
         return color_map
 
 
-DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
+DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small", "small_v2"]
+# DepthAnything V2 Small model is licensed under Apache 2.0 but not the base and large models.
+DEPTH_ANYTHING_MODELS = {
+    "large": "LiheYoung/depth-anything-large-hf",
+    "base": "LiheYoung/depth-anything-base-hf",
+    "small": "LiheYoung/depth-anything-small-hf",
+    "small_v2": "depth-anything/Depth-Anything-V2-Small-hf",
+}
 
 
 @invocation(
@@ -600,28 +608,33 @@ DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
     title="Depth Anything Processor",
     tags=["controlnet", "depth", "depth anything"],
     category="controlnet",
-    version="1.1.2",
+    version="1.1.3",
 )
 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"
+        default="small_v2", description="The size of the depth model to use"
     )
     resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image: Image.Image) -> Image.Image:
-        def loader(model_path: Path):
-            return DepthAnythingDetector.load_model(
-                model_path, model_size=self.model_size, device=TorchDevice.choose_torch_device()
-            )
+        def load_depth_anything(model_path: Path):
+            depth_anything_pipeline = pipeline(model=str(model_path), task="depth-estimation", local_files_only=True)
+            assert isinstance(depth_anything_pipeline, DepthEstimationPipeline)
+            return DepthAnythingPipeline(depth_anything_pipeline)
 
         with self._context.models.load_remote_model(
-            source=DEPTH_ANYTHING_MODELS[self.model_size], loader=loader
-        ) as model:
-            depth_anything_detector = DepthAnythingDetector(model, TorchDevice.choose_torch_device())
-            processed_image = depth_anything_detector(image=image, resolution=self.resolution)
-            return processed_image
+            source=DEPTH_ANYTHING_MODELS[self.model_size], loader=load_depth_anything
+        ) as depth_anything_detector:
+            assert isinstance(depth_anything_detector, DepthAnythingPipeline)
+            depth_map = depth_anything_detector.generate_depth(image)
+
+            # Resizing to user target specified size
+            new_height = int(image.size[1] * (self.resolution / image.size[0]))
+            depth_map = depth_map.resize((self.resolution, new_height))
+
+            return depth_map
 
 
 @invocation(

invokeai/app/invocations/create_gradient_mask.py

@@ -39,7 +39,7 @@ class GradientMaskOutput(BaseInvocationOutput):
     title="Create Gradient Mask",
     tags=["mask", "denoise"],
     category="latents",
-    version="1.1.0",
+    version="1.2.0",
 )
 class CreateGradientMaskInvocation(BaseInvocation):
     """Creates mask for denoising model run."""
@@ -93,6 +93,7 @@ class CreateGradientMaskInvocation(BaseInvocation):
 
             # redistribute blur so that the original edges are 0 and blur outwards to 1
             blur_tensor = (blur_tensor - 0.5) * 2
+            blur_tensor[blur_tensor < 0] = 0.0
 
             threshold = 1 - self.minimum_denoise
 

invokeai/app/invocations/denoise_latents.py

@@ -1,5 +1,6 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 import inspect
+import os
 from contextlib import ExitStack
 from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
 
@@ -36,9 +37,10 @@ from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
 from invokeai.backend.lora import LoRAModelRaw
-from invokeai.backend.model_manager import BaseModelType
+from invokeai.backend.model_manager import BaseModelType, ModelVariantType
 from invokeai.backend.model_patcher import ModelPatcher
-from invokeai.backend.stable_diffusion import PipelineIntermediateState, set_seamless
+from invokeai.backend.stable_diffusion import PipelineIntermediateState
+from invokeai.backend.stable_diffusion.denoise_context import DenoiseContext, DenoiseInputs
 from invokeai.backend.stable_diffusion.diffusers_pipeline import (
     ControlNetData,
     StableDiffusionGeneratorPipeline,
@@ -53,6 +55,19 @@ from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     TextConditioningData,
     TextConditioningRegions,
 )
+from invokeai.backend.stable_diffusion.diffusion.custom_atttention import CustomAttnProcessor2_0
+from invokeai.backend.stable_diffusion.diffusion_backend import StableDiffusionBackend
+from invokeai.backend.stable_diffusion.extension_callback_type import ExtensionCallbackType
+from invokeai.backend.stable_diffusion.extensions.controlnet import ControlNetExt
+from invokeai.backend.stable_diffusion.extensions.freeu import FreeUExt
+from invokeai.backend.stable_diffusion.extensions.inpaint import InpaintExt
+from invokeai.backend.stable_diffusion.extensions.inpaint_model import InpaintModelExt
+from invokeai.backend.stable_diffusion.extensions.lora import LoRAExt
+from invokeai.backend.stable_diffusion.extensions.preview import PreviewExt
+from invokeai.backend.stable_diffusion.extensions.rescale_cfg import RescaleCFGExt
+from invokeai.backend.stable_diffusion.extensions.seamless import SeamlessExt
+from invokeai.backend.stable_diffusion.extensions.t2i_adapter import T2IAdapterExt
+from invokeai.backend.stable_diffusion.extensions_manager import ExtensionsManager
 from invokeai.backend.stable_diffusion.schedulers import SCHEDULER_MAP
 from invokeai.backend.stable_diffusion.schedulers.schedulers import SCHEDULER_NAME_VALUES
 from invokeai.backend.util.devices import TorchDevice
@@ -314,9 +329,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
         context: InvocationContext,
         positive_conditioning_field: Union[ConditioningField, list[ConditioningField]],
         negative_conditioning_field: Union[ConditioningField, list[ConditioningField]],
-        unet: UNet2DConditionModel,
         latent_height: int,
         latent_width: int,
+        device: torch.device,
+        dtype: torch.dtype,
         cfg_scale: float | list[float],
         steps: int,
         cfg_rescale_multiplier: float,
@@ -330,10 +346,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
             uncond_list = [uncond_list]
 
         cond_text_embeddings, cond_text_embedding_masks = DenoiseLatentsInvocation._get_text_embeddings_and_masks(
-            cond_list, context, unet.device, unet.dtype
+            cond_list, context, device, dtype
         )
         uncond_text_embeddings, uncond_text_embedding_masks = DenoiseLatentsInvocation._get_text_embeddings_and_masks(
-            uncond_list, context, unet.device, unet.dtype
+            uncond_list, context, device, dtype
         )
 
         cond_text_embedding, cond_regions = DenoiseLatentsInvocation._concat_regional_text_embeddings(
@@ -341,14 +357,14 @@ class DenoiseLatentsInvocation(BaseInvocation):
             masks=cond_text_embedding_masks,
             latent_height=latent_height,
             latent_width=latent_width,
-            dtype=unet.dtype,
+            dtype=dtype,
         )
         uncond_text_embedding, uncond_regions = DenoiseLatentsInvocation._concat_regional_text_embeddings(
             text_conditionings=uncond_text_embeddings,
             masks=uncond_text_embedding_masks,
             latent_height=latent_height,
             latent_width=latent_width,
-            dtype=unet.dtype,
+            dtype=dtype,
         )
 
         if isinstance(cfg_scale, list):
@@ -455,6 +471,65 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         return controlnet_data
 
+    @staticmethod
+    def parse_controlnet_field(
+        exit_stack: ExitStack,
+        context: InvocationContext,
+        control_input: ControlField | list[ControlField] | None,
+        ext_manager: ExtensionsManager,
+    ) -> None:
+        # Normalize control_input to a list.
+        control_list: list[ControlField]
+        if isinstance(control_input, ControlField):
+            control_list = [control_input]
+        elif isinstance(control_input, list):
+            control_list = control_input
+        elif control_input is None:
+            control_list = []
+        else:
+            raise ValueError(f"Unexpected control_input type: {type(control_input)}")
+
+        for control_info in control_list:
+            model = exit_stack.enter_context(context.models.load(control_info.control_model))
+            ext_manager.add_extension(
+                ControlNetExt(
+                    model=model,
+                    image=context.images.get_pil(control_info.image.image_name),
+                    weight=control_info.control_weight,
+                    begin_step_percent=control_info.begin_step_percent,
+                    end_step_percent=control_info.end_step_percent,
+                    control_mode=control_info.control_mode,
+                    resize_mode=control_info.resize_mode,
+                )
+            )
+
+    @staticmethod
+    def parse_t2i_adapter_field(
+        exit_stack: ExitStack,
+        context: InvocationContext,
+        t2i_adapters: Optional[Union[T2IAdapterField, list[T2IAdapterField]]],
+        ext_manager: ExtensionsManager,
+    ) -> None:
+        if t2i_adapters is None:
+            return
+
+        # Handle the possibility that t2i_adapters could be a list or a single T2IAdapterField.
+        if isinstance(t2i_adapters, T2IAdapterField):
+            t2i_adapters = [t2i_adapters]
+
+        for t2i_adapter_field in t2i_adapters:
+            ext_manager.add_extension(
+                T2IAdapterExt(
+                    node_context=context,
+                    model_id=t2i_adapter_field.t2i_adapter_model,
+                    image=context.images.get_pil(t2i_adapter_field.image.image_name),
+                    weight=t2i_adapter_field.weight,
+                    begin_step_percent=t2i_adapter_field.begin_step_percent,
+                    end_step_percent=t2i_adapter_field.end_step_percent,
+                    resize_mode=t2i_adapter_field.resize_mode,
+                )
+            )
+
     def prep_ip_adapter_image_prompts(
         self,
         context: InvocationContext,
@@ -664,7 +739,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         else:
             masked_latents = torch.where(mask < 0.5, 0.0, latents)
 
-        return 1 - mask, masked_latents, self.denoise_mask.gradient
+        return mask, masked_latents, self.denoise_mask.gradient
 
     @staticmethod
     def prepare_noise_and_latents(
@@ -707,12 +782,157 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         return seed, noise, latents
 
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        if os.environ.get("USE_MODULAR_DENOISE", False):
+            return self._new_invoke(context)
+        else:
+            return self._old_invoke(context)
+
     @torch.no_grad()
     @SilenceWarnings()  # This quenches the NSFW nag from diffusers.
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
+    def _new_invoke(self, context: InvocationContext) -> LatentsOutput:
+        ext_manager = ExtensionsManager(is_canceled=context.util.is_canceled)
+
+        device = TorchDevice.choose_torch_device()
+        dtype = TorchDevice.choose_torch_dtype()
+
+        seed, noise, latents = self.prepare_noise_and_latents(context, self.noise, self.latents)
+        _, _, latent_height, latent_width = latents.shape
+
+        conditioning_data = self.get_conditioning_data(
+            context=context,
+            positive_conditioning_field=self.positive_conditioning,
+            negative_conditioning_field=self.negative_conditioning,
+            cfg_scale=self.cfg_scale,
+            steps=self.steps,
+            latent_height=latent_height,
+            latent_width=latent_width,
+            device=device,
+            dtype=dtype,
+            # TODO: old backend, remove
+            cfg_rescale_multiplier=self.cfg_rescale_multiplier,
+        )
+
+        scheduler = get_scheduler(
+            context=context,
+            scheduler_info=self.unet.scheduler,
+            scheduler_name=self.scheduler,
+            seed=seed,
+        )
+
+        timesteps, init_timestep, scheduler_step_kwargs = self.init_scheduler(
+            scheduler,
+            seed=seed,
+            device=device,
+            steps=self.steps,
+            denoising_start=self.denoising_start,
+            denoising_end=self.denoising_end,
+        )
+
+        # get the unet's config so that we can pass the base to sd_step_callback()
+        unet_config = context.models.get_config(self.unet.unet.key)
+
+        ### preview
+        def step_callback(state: PipelineIntermediateState) -> None:
+            context.util.sd_step_callback(state, unet_config.base)
+
+        ext_manager.add_extension(PreviewExt(step_callback))
+
+        ### cfg rescale
+        if self.cfg_rescale_multiplier > 0:
+            ext_manager.add_extension(RescaleCFGExt(self.cfg_rescale_multiplier))
+
+        ### freeu
+        if self.unet.freeu_config:
+            ext_manager.add_extension(FreeUExt(self.unet.freeu_config))
+
+        ### lora
+        if self.unet.loras:
+            for lora_field in self.unet.loras:
+                ext_manager.add_extension(
+                    LoRAExt(
+                        node_context=context,
+                        model_id=lora_field.lora,
+                        weight=lora_field.weight,
+                    )
+                )
+        ### seamless
+        if self.unet.seamless_axes:
+            ext_manager.add_extension(SeamlessExt(self.unet.seamless_axes))
+
+        ### inpaint
+        mask, masked_latents, is_gradient_mask = self.prep_inpaint_mask(context, latents)
+        # NOTE: We used to identify inpainting models by inpecting the shape of the loaded UNet model weights. Now we
+        # use the ModelVariantType config. During testing, there was a report of a user with models that had an
+        # incorrect ModelVariantType value. Re-installing the model fixed the issue. If this issue turns out to be
+        # prevalent, we will have to revisit how we initialize the inpainting extensions.
+        if unet_config.variant == ModelVariantType.Inpaint:
+            ext_manager.add_extension(InpaintModelExt(mask, masked_latents, is_gradient_mask))
+        elif mask is not None:
+            ext_manager.add_extension(InpaintExt(mask, is_gradient_mask))
+
+        # Initialize context for modular denoise
+        latents = latents.to(device=device, dtype=dtype)
+        if noise is not None:
+            noise = noise.to(device=device, dtype=dtype)
+        denoise_ctx = DenoiseContext(
+            inputs=DenoiseInputs(
+                orig_latents=latents,
+                timesteps=timesteps,
+                init_timestep=init_timestep,
+                noise=noise,
+                seed=seed,
+                scheduler_step_kwargs=scheduler_step_kwargs,
+                conditioning_data=conditioning_data,
+                attention_processor_cls=CustomAttnProcessor2_0,
+            ),
+            unet=None,
+            scheduler=scheduler,
+        )
+
+        # context for loading additional models
+        with ExitStack() as exit_stack:
+            # later should be smth like:
+            # for extension_field in self.extensions:
+            #    ext = extension_field.to_extension(exit_stack, context, ext_manager)
+            #    ext_manager.add_extension(ext)
+            self.parse_controlnet_field(exit_stack, context, self.control, ext_manager)
+            self.parse_t2i_adapter_field(exit_stack, context, self.t2i_adapter, ext_manager)
+
+            # ext: t2i/ip adapter
+            ext_manager.run_callback(ExtensionCallbackType.SETUP, denoise_ctx)
+
+            unet_info = context.models.load(self.unet.unet)
+            assert isinstance(unet_info.model, UNet2DConditionModel)
+            with (
+                unet_info.model_on_device() as (cached_weights, unet),
+                ModelPatcher.patch_unet_attention_processor(unet, denoise_ctx.inputs.attention_processor_cls),
+                # ext: controlnet
+                ext_manager.patch_extensions(denoise_ctx),
+                # ext: freeu, seamless, ip adapter, lora
+                ext_manager.patch_unet(unet, cached_weights),
+            ):
+                sd_backend = StableDiffusionBackend(unet, scheduler)
+                denoise_ctx.unet = unet
+                result_latents = sd_backend.latents_from_embeddings(denoise_ctx, ext_manager)
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        result_latents = result_latents.detach().to("cpu")
+        TorchDevice.empty_cache()
+
+        name = context.tensors.save(tensor=result_latents)
+        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=None)
+
+    @torch.no_grad()
+    @SilenceWarnings()  # This quenches the NSFW nag from diffusers.
+    def _old_invoke(self, context: InvocationContext) -> LatentsOutput:
         seed, noise, latents = self.prepare_noise_and_latents(context, self.noise, self.latents)
 
         mask, masked_latents, gradient_mask = self.prep_inpaint_mask(context, latents)
+        # At this point, the mask ranges from 0 (leave unchanged) to 1 (inpaint).
+        # We invert the mask here for compatibility with the old backend implementation.
+        if mask is not None:
+            mask = 1 - mask
 
         # TODO(ryand): I have hard-coded `do_classifier_free_guidance=True` to mirror the behaviour of ControlNets,
         # below. Investigate whether this is appropriate.
@@ -755,14 +975,14 @@ class DenoiseLatentsInvocation(BaseInvocation):
         assert isinstance(unet_info.model, UNet2DConditionModel)
         with (
             ExitStack() as exit_stack,
-            unet_info.model_on_device() as (model_state_dict, unet),
+            unet_info.model_on_device() as (cached_weights, unet),
             ModelPatcher.apply_freeu(unet, self.unet.freeu_config),
-            set_seamless(unet, self.unet.seamless_axes),  # FIXME
+            SeamlessExt.static_patch_model(unet, self.unet.seamless_axes),  # FIXME
             # Apply the LoRA after unet has been moved to its target device for faster patching.
             ModelPatcher.apply_lora_unet(
                 unet,
                 loras=_lora_loader(),
-                model_state_dict=model_state_dict,
+                cached_weights=cached_weights,
             ),
         ):
             assert isinstance(unet, UNet2DConditionModel)
@@ -788,7 +1008,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 context=context,
                 positive_conditioning_field=self.positive_conditioning,
                 negative_conditioning_field=self.negative_conditioning,
-                unet=unet,
+                device=unet.device,
+                dtype=unet.dtype,
                 latent_height=latent_height,
                 latent_width=latent_width,
                 cfg_scale=self.cfg_scale,

invokeai/app/invocations/fields.py

@@ -1,7 +1,7 @@
 from enum import Enum
 from typing import Any, Callable, Optional, Tuple
 
-from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter
+from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter, model_validator
 from pydantic.fields import _Unset
 from pydantic_core import PydanticUndefined
 
@@ -48,6 +48,7 @@ class UIType(str, Enum, metaclass=MetaEnum):
     ControlNetModel = "ControlNetModelField"
     IPAdapterModel = "IPAdapterModelField"
     T2IAdapterModel = "T2IAdapterModelField"
+    SpandrelImageToImageModel = "SpandrelImageToImageModelField"
     # endregion
 
     # region Misc Field Types
@@ -134,6 +135,7 @@ class FieldDescriptions:
     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"
+    spandrel_image_to_image_model = "Image-to-Image model"
     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)"
@@ -160,8 +162,7 @@ class FieldDescriptions:
     fp32 = "Whether or not to use full float32 precision"
     precision = "Precision to use"
     tiled = "Processing using overlapping tiles (reduce memory consumption)"
-    vae_tile_size = "The tile size for VAE tiling in pixels (image space). If set to 0, the default tile size for the "
-    "model will be used. Larger tile sizes generally produce better results at the cost of higher memory usage."
+    vae_tile_size = "The tile size for VAE tiling in pixels (image space). If set to 0, the default tile size for the model will be used. Larger tile sizes generally produce better results at the cost of higher memory usage."
     detect_res = "Pixel resolution for detection"
     image_res = "Pixel resolution for output image"
     safe_mode = "Whether or not to use safe mode"
@@ -241,6 +242,31 @@ class ConditioningField(BaseModel):
     )
 
 
+class BoundingBoxField(BaseModel):
+    """A bounding box primitive value."""
+
+    x_min: int = Field(ge=0, description="The minimum x-coordinate of the bounding box (inclusive).")
+    x_max: int = Field(ge=0, description="The maximum x-coordinate of the bounding box (exclusive).")
+    y_min: int = Field(ge=0, description="The minimum y-coordinate of the bounding box (inclusive).")
+    y_max: int = Field(ge=0, description="The maximum y-coordinate of the bounding box (exclusive).")
+
+    score: Optional[float] = Field(
+        default=None,
+        ge=0.0,
+        le=1.0,
+        description="The score associated with the bounding box. In the range [0, 1]. This value is typically set "
+        "when the bounding box was produced by a detector and has an associated confidence score.",
+    )
+
+    @model_validator(mode="after")
+    def check_coords(self):
+        if self.x_min > self.x_max:
+            raise ValueError(f"x_min ({self.x_min}) is greater than x_max ({self.x_max}).")
+        if self.y_min > self.y_max:
+            raise ValueError(f"y_min ({self.y_min}) is greater than y_max ({self.y_max}).")
+        return self
+
+
 class MetadataField(RootModel[dict[str, Any]]):
     """
     Pydantic model for metadata with custom root of type dict[str, Any].

invokeai/app/invocations/grounding_dino.py

@@ -0,0 +1,100 @@
+from pathlib import Path
+from typing import Literal
+
+import torch
+from PIL import Image
+from transformers import pipeline
+from transformers.pipelines import ZeroShotObjectDetectionPipeline
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
+from invokeai.app.invocations.fields import BoundingBoxField, ImageField, InputField
+from invokeai.app.invocations.primitives import BoundingBoxCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.image_util.grounding_dino.detection_result import DetectionResult
+from invokeai.backend.image_util.grounding_dino.grounding_dino_pipeline import GroundingDinoPipeline
+
+GroundingDinoModelKey = Literal["grounding-dino-tiny", "grounding-dino-base"]
+GROUNDING_DINO_MODEL_IDS: dict[GroundingDinoModelKey, str] = {
+    "grounding-dino-tiny": "IDEA-Research/grounding-dino-tiny",
+    "grounding-dino-base": "IDEA-Research/grounding-dino-base",
+}
+
+
+@invocation(
+    "grounding_dino",
+    title="Grounding DINO (Text Prompt Object Detection)",
+    tags=["prompt", "object detection"],
+    category="image",
+    version="1.0.0",
+)
+class GroundingDinoInvocation(BaseInvocation):
+    """Runs a Grounding DINO model. Performs zero-shot bounding-box object detection from a text prompt."""
+
+    # Reference:
+    # - https://arxiv.org/pdf/2303.05499
+    # - https://huggingface.co/docs/transformers/v4.43.3/en/model_doc/grounding-dino#grounded-sam
+    # - https://github.com/NielsRogge/Transformers-Tutorials/blob/a39f33ac1557b02ebfb191ea7753e332b5ca933f/Grounding%20DINO/GroundingDINO_with_Segment_Anything.ipynb
+
+    model: GroundingDinoModelKey = InputField(description="The Grounding DINO model to use.")
+    prompt: str = InputField(description="The prompt describing the object to segment.")
+    image: ImageField = InputField(description="The image to segment.")
+    detection_threshold: float = InputField(
+        description="The detection threshold for the Grounding DINO model. All detected bounding boxes with scores above this threshold will be returned.",
+        ge=0.0,
+        le=1.0,
+        default=0.3,
+    )
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> BoundingBoxCollectionOutput:
+        # The model expects a 3-channel RGB image.
+        image_pil = context.images.get_pil(self.image.image_name, mode="RGB")
+
+        detections = self._detect(
+            context=context, image=image_pil, labels=[self.prompt], threshold=self.detection_threshold
+        )
+
+        # Convert detections to BoundingBoxCollectionOutput.
+        bounding_boxes: list[BoundingBoxField] = []
+        for detection in detections:
+            bounding_boxes.append(
+                BoundingBoxField(
+                    x_min=detection.box.xmin,
+                    x_max=detection.box.xmax,
+                    y_min=detection.box.ymin,
+                    y_max=detection.box.ymax,
+                    score=detection.score,
+                )
+            )
+        return BoundingBoxCollectionOutput(collection=bounding_boxes)
+
+    @staticmethod
+    def _load_grounding_dino(model_path: Path):
+        grounding_dino_pipeline = pipeline(
+            model=str(model_path),
+            task="zero-shot-object-detection",
+            local_files_only=True,
+            # TODO(ryand): Setting the torch_dtype here doesn't work. Investigate whether fp16 is supported by the
+            # model, and figure out how to make it work in the pipeline.
+            # torch_dtype=TorchDevice.choose_torch_dtype(),
+        )
+        assert isinstance(grounding_dino_pipeline, ZeroShotObjectDetectionPipeline)
+        return GroundingDinoPipeline(grounding_dino_pipeline)
+
+    def _detect(
+        self,
+        context: InvocationContext,
+        image: Image.Image,
+        labels: list[str],
+        threshold: float = 0.3,
+    ) -> list[DetectionResult]:
+        """Use Grounding DINO to detect bounding boxes for a set of labels in an image."""
+        # TODO(ryand): I copied this "."-handling logic from the transformers example code. Test it and see if it
+        # actually makes a difference.
+        labels = [label if label.endswith(".") else label + "." for label in labels]
+
+        with context.models.load_remote_model(
+            source=GROUNDING_DINO_MODEL_IDS[self.model], loader=GroundingDinoInvocation._load_grounding_dino
+        ) as detector:
+            assert isinstance(detector, GroundingDinoPipeline)
+            return detector.detect(image=image, candidate_labels=labels, threshold=threshold)

invokeai/app/invocations/image.py

@@ -6,13 +6,19 @@ import cv2
 import numpy
 from PIL import Image, ImageChops, ImageFilter, ImageOps
 
-from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    Classification,
+    invocation,
+    invocation_output,
+)
 from invokeai.app.invocations.constants import IMAGE_MODES
 from invokeai.app.invocations.fields import (
     ColorField,
     FieldDescriptions,
     ImageField,
     InputField,
+    OutputField,
     WithBoard,
     WithMetadata,
 )
@@ -1007,3 +1013,62 @@ class MaskFromIDInvocation(BaseInvocation, WithMetadata, WithBoard):
         image_dto = context.images.save(image=mask, image_category=ImageCategory.MASK)
 
         return ImageOutput.build(image_dto)
+
+
+@invocation_output("canvas_v2_mask_and_crop_output")
+class CanvasV2MaskAndCropOutput(ImageOutput):
+    offset_x: int = OutputField(description="The x offset of the image, after cropping")
+    offset_y: int = OutputField(description="The y offset of the image, after cropping")
+
+
+@invocation(
+    "canvas_v2_mask_and_crop",
+    title="Canvas V2 Mask and Crop",
+    tags=["image", "mask", "id"],
+    category="image",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class CanvasV2MaskAndCropInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Handles Canvas V2 image output masking and cropping"""
+
+    source_image: ImageField | None = InputField(
+        default=None,
+        description="The source image onto which the masked generated image is pasted. If omitted, the masked generated image is returned with transparency.",
+    )
+    generated_image: ImageField = InputField(description="The image to apply the mask to")
+    mask: ImageField = InputField(description="The mask to apply")
+    mask_blur: int = InputField(default=0, ge=0, description="The amount to blur the mask by")
+
+    def _prepare_mask(self, mask: Image.Image) -> Image.Image:
+        mask_array = numpy.array(mask)
+        kernel = numpy.ones((self.mask_blur, self.mask_blur), numpy.uint8)
+        dilated_mask_array = cv2.erode(mask_array, kernel, iterations=3)
+        dilated_mask = Image.fromarray(dilated_mask_array)
+        if self.mask_blur > 0:
+            mask = dilated_mask.filter(ImageFilter.GaussianBlur(self.mask_blur))
+        return ImageOps.invert(mask.convert("L"))
+
+    def invoke(self, context: InvocationContext) -> CanvasV2MaskAndCropOutput:
+        mask = self._prepare_mask(context.images.get_pil(self.mask.image_name))
+
+        if self.source_image:
+            generated_image = context.images.get_pil(self.generated_image.image_name)
+            source_image = context.images.get_pil(self.source_image.image_name)
+            source_image.paste(generated_image, (0, 0), mask)
+            image_dto = context.images.save(image=source_image)
+        else:
+            generated_image = context.images.get_pil(self.generated_image.image_name)
+            generated_image.putalpha(mask)
+            image_dto = context.images.save(image=generated_image)
+
+        # bbox = image.getbbox()
+        # image = image.crop(bbox)
+
+        return CanvasV2MaskAndCropOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            offset_x=0,
+            offset_y=0,
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/latents_to_image.py

@@ -24,7 +24,7 @@ from invokeai.app.invocations.fields import (
 from invokeai.app.invocations.model import VAEField
 from invokeai.app.invocations.primitives import ImageOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.stable_diffusion import set_seamless
+from invokeai.backend.stable_diffusion.extensions.seamless import SeamlessExt
 from invokeai.backend.stable_diffusion.vae_tiling import patch_vae_tiling_params
 from invokeai.backend.util.devices import TorchDevice
 
@@ -59,7 +59,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
 
         vae_info = context.models.load(self.vae.vae)
         assert isinstance(vae_info.model, (AutoencoderKL, AutoencoderTiny))
-        with set_seamless(vae_info.model, self.vae.seamless_axes), vae_info as vae:
+        with SeamlessExt.static_patch_model(vae_info.model, self.vae.seamless_axes), vae_info as vae:
             assert isinstance(vae, (AutoencoderKL, AutoencoderTiny))
             latents = latents.to(vae.device)
             if self.fp32:

invokeai/app/invocations/mask.py

@@ -1,9 +1,10 @@
 import numpy as np
 import torch
+from PIL import Image
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, InvocationContext, invocation
-from invokeai.app.invocations.fields import ImageField, InputField, TensorField, WithMetadata
-from invokeai.app.invocations.primitives import MaskOutput
+from invokeai.app.invocations.fields import ImageField, InputField, TensorField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput, MaskOutput
 
 
 @invocation(
@@ -118,3 +119,27 @@ class ImageMaskToTensorInvocation(BaseInvocation, WithMetadata):
             height=mask.shape[1],
             width=mask.shape[2],
         )
+
+
+@invocation(
+    "tensor_mask_to_image",
+    title="Tensor Mask to Image",
+    tags=["mask"],
+    category="mask",
+    version="1.0.0",
+)
+class MaskTensorToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Convert a mask tensor to an image."""
+
+    mask: TensorField = InputField(description="The mask tensor to convert.")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        mask = context.tensors.load(self.mask.tensor_name)
+        # Ensure that the mask is binary.
+        if mask.dtype != torch.bool:
+            mask = mask > 0.5
+        mask_np = (mask.float() * 255).byte().cpu().numpy()
+
+        mask_pil = Image.fromarray(mask_np, mode="L")
+        image_dto = context.images.save(image=mask_pil)
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/primitives.py

@@ -7,6 +7,7 @@ import torch
 from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
 from invokeai.app.invocations.fields import (
+    BoundingBoxField,
     ColorField,
     ConditioningField,
     DenoiseMaskField,
@@ -469,3 +470,42 @@ class ConditioningCollectionInvocation(BaseInvocation):
 
 
 # endregion
+
+# region BoundingBox
+
+
+@invocation_output("bounding_box_output")
+class BoundingBoxOutput(BaseInvocationOutput):
+    """Base class for nodes that output a single bounding box"""
+
+    bounding_box: BoundingBoxField = OutputField(description="The output bounding box.")
+
+
+@invocation_output("bounding_box_collection_output")
+class BoundingBoxCollectionOutput(BaseInvocationOutput):
+    """Base class for nodes that output a collection of bounding boxes"""
+
+    collection: list[BoundingBoxField] = OutputField(description="The output bounding boxes.", title="Bounding Boxes")
+
+
+@invocation(
+    "bounding_box",
+    title="Bounding Box",
+    tags=["primitives", "segmentation", "collection", "bounding box"],
+    category="primitives",
+    version="1.0.0",
+)
+class BoundingBoxInvocation(BaseInvocation):
+    """Create a bounding box manually by supplying box coordinates"""
+
+    x_min: int = InputField(default=0, description="x-coordinate of the bounding box's top left vertex")
+    y_min: int = InputField(default=0, description="y-coordinate of the bounding box's top left vertex")
+    x_max: int = InputField(default=0, description="x-coordinate of the bounding box's bottom right vertex")
+    y_max: int = InputField(default=0, description="y-coordinate of the bounding box's bottom right vertex")
+
+    def invoke(self, context: InvocationContext) -> BoundingBoxOutput:
+        bounding_box = BoundingBoxField(x_min=self.x_min, y_min=self.y_min, x_max=self.x_max, y_max=self.y_max)
+        return BoundingBoxOutput(bounding_box=bounding_box)
+
+
+# endregion

invokeai/app/invocations/segment_anything.py

@@ -0,0 +1,161 @@
+from pathlib import Path
+from typing import Literal
+
+import numpy as np
+import torch
+from PIL import Image
+from transformers import AutoModelForMaskGeneration, AutoProcessor
+from transformers.models.sam import SamModel
+from transformers.models.sam.processing_sam import SamProcessor
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
+from invokeai.app.invocations.fields import BoundingBoxField, ImageField, InputField, TensorField
+from invokeai.app.invocations.primitives import MaskOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.image_util.segment_anything.mask_refinement import mask_to_polygon, polygon_to_mask
+from invokeai.backend.image_util.segment_anything.segment_anything_pipeline import SegmentAnythingPipeline
+
+SegmentAnythingModelKey = Literal["segment-anything-base", "segment-anything-large", "segment-anything-huge"]
+SEGMENT_ANYTHING_MODEL_IDS: dict[SegmentAnythingModelKey, str] = {
+    "segment-anything-base": "facebook/sam-vit-base",
+    "segment-anything-large": "facebook/sam-vit-large",
+    "segment-anything-huge": "facebook/sam-vit-huge",
+}
+
+
+@invocation(
+    "segment_anything",
+    title="Segment Anything",
+    tags=["prompt", "segmentation"],
+    category="segmentation",
+    version="1.0.0",
+)
+class SegmentAnythingInvocation(BaseInvocation):
+    """Runs a Segment Anything Model."""
+
+    # Reference:
+    # - https://arxiv.org/pdf/2304.02643
+    # - https://huggingface.co/docs/transformers/v4.43.3/en/model_doc/grounding-dino#grounded-sam
+    # - https://github.com/NielsRogge/Transformers-Tutorials/blob/a39f33ac1557b02ebfb191ea7753e332b5ca933f/Grounding%20DINO/GroundingDINO_with_Segment_Anything.ipynb
+
+    model: SegmentAnythingModelKey = InputField(description="The Segment Anything model to use.")
+    image: ImageField = InputField(description="The image to segment.")
+    bounding_boxes: list[BoundingBoxField] = InputField(description="The bounding boxes to prompt the SAM model with.")
+    apply_polygon_refinement: bool = InputField(
+        description="Whether to apply polygon refinement to the masks. This will smooth the edges of the masks slightly and ensure that each mask consists of a single closed polygon (before merging).",
+        default=True,
+    )
+    mask_filter: Literal["all", "largest", "highest_box_score"] = InputField(
+        description="The filtering to apply to the detected masks before merging them into a final output.",
+        default="all",
+    )
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        # The models expect a 3-channel RGB image.
+        image_pil = context.images.get_pil(self.image.image_name, mode="RGB")
+
+        if len(self.bounding_boxes) == 0:
+            combined_mask = torch.zeros(image_pil.size[::-1], dtype=torch.bool)
+        else:
+            masks = self._segment(context=context, image=image_pil)
+            masks = self._filter_masks(masks=masks, bounding_boxes=self.bounding_boxes)
+
+            # masks contains bool values, so we merge them via max-reduce.
+            combined_mask, _ = torch.stack(masks).max(dim=0)
+
+        mask_tensor_name = context.tensors.save(combined_mask)
+        height, width = combined_mask.shape
+        return MaskOutput(mask=TensorField(tensor_name=mask_tensor_name), width=width, height=height)
+
+    @staticmethod
+    def _load_sam_model(model_path: Path):
+        sam_model = AutoModelForMaskGeneration.from_pretrained(
+            model_path,
+            local_files_only=True,
+            # TODO(ryand): Setting the torch_dtype here doesn't work. Investigate whether fp16 is supported by the
+            # model, and figure out how to make it work in the pipeline.
+            # torch_dtype=TorchDevice.choose_torch_dtype(),
+        )
+        assert isinstance(sam_model, SamModel)
+
+        sam_processor = AutoProcessor.from_pretrained(model_path, local_files_only=True)
+        assert isinstance(sam_processor, SamProcessor)
+        return SegmentAnythingPipeline(sam_model=sam_model, sam_processor=sam_processor)
+
+    def _segment(
+        self,
+        context: InvocationContext,
+        image: Image.Image,
+    ) -> list[torch.Tensor]:
+        """Use Segment Anything (SAM) to generate masks given an image + a set of bounding boxes."""
+        # Convert the bounding boxes to the SAM input format.
+        sam_bounding_boxes = [[bb.x_min, bb.y_min, bb.x_max, bb.y_max] for bb in self.bounding_boxes]
+
+        with (
+            context.models.load_remote_model(
+                source=SEGMENT_ANYTHING_MODEL_IDS[self.model], loader=SegmentAnythingInvocation._load_sam_model
+            ) as sam_pipeline,
+        ):
+            assert isinstance(sam_pipeline, SegmentAnythingPipeline)
+            masks = sam_pipeline.segment(image=image, bounding_boxes=sam_bounding_boxes)
+
+        masks = self._process_masks(masks)
+        if self.apply_polygon_refinement:
+            masks = self._apply_polygon_refinement(masks)
+
+        return masks
+
+    def _process_masks(self, masks: torch.Tensor) -> list[torch.Tensor]:
+        """Convert the tensor output from the Segment Anything model from a tensor of shape
+        [num_masks, channels, height, width] to a list of tensors of shape [height, width].
+        """
+        assert masks.dtype == torch.bool
+        # [num_masks, channels, height, width] -> [num_masks, height, width]
+        masks, _ = masks.max(dim=1)
+        # Split the first dimension into a list of masks.
+        return list(masks.cpu().unbind(dim=0))
+
+    def _apply_polygon_refinement(self, masks: list[torch.Tensor]) -> list[torch.Tensor]:
+        """Apply polygon refinement to the masks.
+
+        Convert each mask to a polygon, then back to a mask. This has the following effect:
+        - Smooth the edges of the mask slightly.
+        - Ensure that each mask consists of a single closed polygon
+            - Removes small mask pieces.
+            - Removes holes from the mask.
+        """
+        # Convert tensor masks to np masks.
+        np_masks = [mask.cpu().numpy().astype(np.uint8) for mask in masks]
+
+        # Apply polygon refinement.
+        for idx, mask in enumerate(np_masks):
+            shape = mask.shape
+            assert len(shape) == 2  # Assert length to satisfy type checker.
+            polygon = mask_to_polygon(mask)
+            mask = polygon_to_mask(polygon, shape)
+            np_masks[idx] = mask
+
+        # Convert np masks back to tensor masks.
+        masks = [torch.tensor(mask, dtype=torch.bool) for mask in np_masks]
+
+        return masks
+
+    def _filter_masks(self, masks: list[torch.Tensor], bounding_boxes: list[BoundingBoxField]) -> list[torch.Tensor]:
+        """Filter the detected masks based on the specified mask filter."""
+        assert len(masks) == len(bounding_boxes)
+
+        if self.mask_filter == "all":
+            return masks
+        elif self.mask_filter == "largest":
+            # Find the largest mask.
+            return [max(masks, key=lambda x: float(x.sum()))]
+        elif self.mask_filter == "highest_box_score":
+            # Find the index of the bounding box with the highest score.
+            # Note that we fallback to -1.0 if the score is None. This is mainly to satisfy the type checker. In most
+            # cases the scores should all be non-None when using this filtering mode. That being said, -1.0 is a
+            # reasonable fallback since the expected score range is [0.0, 1.0].
+            max_score_idx = max(range(len(bounding_boxes)), key=lambda i: bounding_boxes[i].score or -1.0)
+            return [masks[max_score_idx]]
+        else:
+            raise ValueError(f"Invalid mask filter: {self.mask_filter}")

invokeai/app/invocations/spandrel_image_to_image.py

@@ -0,0 +1,253 @@
+from typing import Callable
+
+import numpy as np
+import torch
+from PIL import Image
+from tqdm import tqdm
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
+    InputField,
+    UIType,
+    WithBoard,
+    WithMetadata,
+)
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.session_processor.session_processor_common import CanceledException
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.spandrel_image_to_image_model import SpandrelImageToImageModel
+from invokeai.backend.tiles.tiles import calc_tiles_min_overlap
+from invokeai.backend.tiles.utils import TBLR, Tile
+
+
+@invocation("spandrel_image_to_image", title="Image-to-Image", tags=["upscale"], category="upscale", version="1.3.0")
+class SpandrelImageToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Run any spandrel image-to-image model (https://github.com/chaiNNer-org/spandrel)."""
+
+    image: ImageField = InputField(description="The input image")
+    image_to_image_model: ModelIdentifierField = InputField(
+        title="Image-to-Image Model",
+        description=FieldDescriptions.spandrel_image_to_image_model,
+        ui_type=UIType.SpandrelImageToImageModel,
+    )
+    tile_size: int = InputField(
+        default=512, description="The tile size for tiled image-to-image. Set to 0 to disable tiling."
+    )
+
+    @classmethod
+    def scale_tile(cls, tile: Tile, scale: int) -> Tile:
+        return Tile(
+            coords=TBLR(
+                top=tile.coords.top * scale,
+                bottom=tile.coords.bottom * scale,
+                left=tile.coords.left * scale,
+                right=tile.coords.right * scale,
+            ),
+            overlap=TBLR(
+                top=tile.overlap.top * scale,
+                bottom=tile.overlap.bottom * scale,
+                left=tile.overlap.left * scale,
+                right=tile.overlap.right * scale,
+            ),
+        )
+
+    @classmethod
+    def upscale_image(
+        cls,
+        image: Image.Image,
+        tile_size: int,
+        spandrel_model: SpandrelImageToImageModel,
+        is_canceled: Callable[[], bool],
+    ) -> Image.Image:
+        # Compute the image tiles.
+        if tile_size > 0:
+            min_overlap = 20
+            tiles = calc_tiles_min_overlap(
+                image_height=image.height,
+                image_width=image.width,
+                tile_height=tile_size,
+                tile_width=tile_size,
+                min_overlap=min_overlap,
+            )
+        else:
+            # No tiling. Generate a single tile that covers the entire image.
+            min_overlap = 0
+            tiles = [
+                Tile(
+                    coords=TBLR(top=0, bottom=image.height, left=0, right=image.width),
+                    overlap=TBLR(top=0, bottom=0, left=0, right=0),
+                )
+            ]
+
+        # Sort tiles first by left x coordinate, then by top y coordinate. During tile processing, we want to iterate
+        # over tiles left-to-right, top-to-bottom.
+        tiles = sorted(tiles, key=lambda x: x.coords.left)
+        tiles = sorted(tiles, key=lambda x: x.coords.top)
+
+        # Prepare input image for inference.
+        image_tensor = SpandrelImageToImageModel.pil_to_tensor(image)
+
+        # Scale the tiles for re-assembling the final image.
+        scale = spandrel_model.scale
+        scaled_tiles = [cls.scale_tile(tile, scale=scale) for tile in tiles]
+
+        # Prepare the output tensor.
+        _, channels, height, width = image_tensor.shape
+        output_tensor = torch.zeros(
+            (height * scale, width * scale, channels), dtype=torch.uint8, device=torch.device("cpu")
+        )
+
+        image_tensor = image_tensor.to(device=spandrel_model.device, dtype=spandrel_model.dtype)
+
+        # Run the model on each tile.
+        for tile, scaled_tile in tqdm(list(zip(tiles, scaled_tiles, strict=True)), desc="Upscaling Tiles"):
+            # Exit early if the invocation has been canceled.
+            if is_canceled():
+                raise CanceledException
+
+            # Extract the current tile from the input tensor.
+            input_tile = image_tensor[
+                :, :, tile.coords.top : tile.coords.bottom, tile.coords.left : tile.coords.right
+            ].to(device=spandrel_model.device, dtype=spandrel_model.dtype)
+
+            # Run the model on the tile.
+            output_tile = spandrel_model.run(input_tile)
+
+            # Convert the output tile into the output tensor's format.
+            # (N, C, H, W) -> (C, H, W)
+            output_tile = output_tile.squeeze(0)
+            # (C, H, W) -> (H, W, C)
+            output_tile = output_tile.permute(1, 2, 0)
+            output_tile = output_tile.clamp(0, 1)
+            output_tile = (output_tile * 255).to(dtype=torch.uint8, device=torch.device("cpu"))
+
+            # Merge the output tile into the output tensor.
+            # We only keep half of the overlap on the top and left side of the tile. We do this in case there are
+            # edge artifacts. We don't bother with any 'blending' in the current implementation - for most upscalers
+            # it seems unnecessary, but we may find a need in the future.
+            top_overlap = scaled_tile.overlap.top // 2
+            left_overlap = scaled_tile.overlap.left // 2
+            output_tensor[
+                scaled_tile.coords.top + top_overlap : scaled_tile.coords.bottom,
+                scaled_tile.coords.left + left_overlap : scaled_tile.coords.right,
+                :,
+            ] = output_tile[top_overlap:, left_overlap:, :]
+
+        # Convert the output tensor to a PIL image.
+        np_image = output_tensor.detach().numpy().astype(np.uint8)
+        pil_image = Image.fromarray(np_image)
+
+        return pil_image
+
+    @torch.inference_mode()
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Images are converted to RGB, because most models don't support an alpha channel. In the future, we may want to
+        # revisit this.
+        image = context.images.get_pil(self.image.image_name, mode="RGB")
+
+        # Load the model.
+        spandrel_model_info = context.models.load(self.image_to_image_model)
+
+        # Do the upscaling.
+        with spandrel_model_info as spandrel_model:
+            assert isinstance(spandrel_model, SpandrelImageToImageModel)
+
+            # Upscale the image
+            pil_image = self.upscale_image(image, self.tile_size, spandrel_model, context.util.is_canceled)
+
+        image_dto = context.images.save(image=pil_image)
+        return ImageOutput.build(image_dto)
+
+
+@invocation(
+    "spandrel_image_to_image_autoscale",
+    title="Image-to-Image (Autoscale)",
+    tags=["upscale"],
+    category="upscale",
+    version="1.0.0",
+)
+class SpandrelImageToImageAutoscaleInvocation(SpandrelImageToImageInvocation):
+    """Run any spandrel image-to-image model (https://github.com/chaiNNer-org/spandrel) until the target scale is reached."""
+
+    scale: float = InputField(
+        default=4.0,
+        gt=0.0,
+        le=16.0,
+        description="The final scale of the output image. If the model does not upscale the image, this will be ignored.",
+    )
+    fit_to_multiple_of_8: bool = InputField(
+        default=False,
+        description="If true, the output image will be resized to the nearest multiple of 8 in both dimensions.",
+    )
+
+    @torch.inference_mode()
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Images are converted to RGB, because most models don't support an alpha channel. In the future, we may want to
+        # revisit this.
+        image = context.images.get_pil(self.image.image_name, mode="RGB")
+
+        # Load the model.
+        spandrel_model_info = context.models.load(self.image_to_image_model)
+
+        # The target size of the image, determined by the provided scale. We'll run the upscaler until we hit this size.
+        # Later, we may mutate this value if the model doesn't upscale the image or if the user requested a multiple of 8.
+        target_width = int(image.width * self.scale)
+        target_height = int(image.height * self.scale)
+
+        # Do the upscaling.
+        with spandrel_model_info as spandrel_model:
+            assert isinstance(spandrel_model, SpandrelImageToImageModel)
+
+            # First pass of upscaling. Note: `pil_image` will be mutated.
+            pil_image = self.upscale_image(image, self.tile_size, spandrel_model, context.util.is_canceled)
+
+            # Some models don't upscale the image, but we have no way to know this in advance. We'll check if the model
+            # upscaled the image and run the loop below if it did. We'll require the model to upscale both dimensions
+            # to be considered an upscale model.
+            is_upscale_model = pil_image.width > image.width and pil_image.height > image.height
+
+            if is_upscale_model:
+                # This is an upscale model, so we should keep upscaling until we reach the target size.
+                iterations = 1
+                while pil_image.width < target_width or pil_image.height < target_height:
+                    pil_image = self.upscale_image(pil_image, self.tile_size, spandrel_model, context.util.is_canceled)
+                    iterations += 1
+
+                    # Sanity check to prevent excessive or infinite loops. All known upscaling models are at least 2x.
+                    # Our max scale is 16x, so with a 2x model, we should never exceed 16x == 2^4 -> 4 iterations.
+                    # We'll allow one extra iteration "just in case" and bail at 5 upscaling iterations. In practice,
+                    # we should never reach this limit.
+                    if iterations >= 5:
+                        context.logger.warning(
+                            "Upscale loop reached maximum iteration count of 5, stopping upscaling early."
+                        )
+                        break
+            else:
+                # This model doesn't upscale the image. We should ignore the scale parameter, modifying the output size
+                # to be the same as the processed image size.
+
+                # The output size is now the size of the processed image.
+                target_width = pil_image.width
+                target_height = pil_image.height
+
+                # Warn the user if they requested a scale greater than 1.
+                if self.scale > 1:
+                    context.logger.warning(
+                        "Model does not increase the size of the image, but a greater scale than 1 was requested. Image will not be scaled."
+                    )
+
+        # We may need to resize the image to a multiple of 8. Use floor division to ensure we don't scale the image up
+        # in the final resize
+        if self.fit_to_multiple_of_8:
+            target_width = int(target_width // 8 * 8)
+            target_height = int(target_height // 8 * 8)
+
+        # Final resize. Per PIL documentation, Lanczos provides the best quality for both upscale and downscale.
+        # See: https://pillow.readthedocs.io/en/stable/handbook/concepts.html#filters-comparison-table
+        pil_image = pil_image.resize((target_width, target_height), resample=Image.Resampling.LANCZOS)
+
+        image_dto = context.images.save(image=pil_image)
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/tiled_multi_diffusion_denoise_latents.py

@@ -175,6 +175,10 @@ class TiledMultiDiffusionDenoiseLatents(BaseInvocation):
         _, _, latent_height, latent_width = latents.shape
 
         # Calculate the tile locations to cover the latent-space image.
+        # TODO(ryand): In the future, we may want to revisit the tile overlap strategy. Things to consider:
+        # - How much overlap 'context' to provide for each denoising step.
+        # - How much overlap to use during merging/blending.
+        # - Should we 'jitter' the tile locations in each step so that the seams are in different places?
         tiles = calc_tiles_min_overlap(
             image_height=latent_height,
             image_width=latent_width,
@@ -218,7 +222,8 @@ class TiledMultiDiffusionDenoiseLatents(BaseInvocation):
                 context=context,
                 positive_conditioning_field=self.positive_conditioning,
                 negative_conditioning_field=self.negative_conditioning,
-                unet=unet,
+                device=unet.device,
+                dtype=unet.dtype,
                 latent_height=latent_tile_height,
                 latent_width=latent_tile_width,
                 cfg_scale=self.cfg_scale,

invokeai/app/services/config/config_default.py

@@ -91,6 +91,7 @@ class InvokeAIAppConfig(BaseSettings):
         db_dir: Path to InvokeAI databases directory.
         outputs_dir: Path to directory for outputs.
         custom_nodes_dir: Path to directory for custom nodes.
+        style_presets_dir: Path to directory for style presets.
         log_handlers: Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>".
         log_format: Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style.<br>Valid values: `plain`, `color`, `syslog`, `legacy`
         log_level: Emit logging messages at this level or higher.<br>Valid values: `debug`, `info`, `warning`, `error`, `critical`
@@ -153,6 +154,7 @@ class InvokeAIAppConfig(BaseSettings):
     db_dir:                        Path = Field(default=Path("databases"),  description="Path to InvokeAI databases directory.")
     outputs_dir:                   Path = Field(default=Path("outputs"),    description="Path to directory for outputs.")
     custom_nodes_dir:              Path = Field(default=Path("nodes"),      description="Path to directory for custom nodes.")
+    style_presets_dir:      Path = Field(default=Path("style_presets"),      description="Path to directory for style presets.")
 
     # LOGGING
     log_handlers:             list[str] = Field(default=["console"],        description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>".')
@@ -300,6 +302,11 @@ class InvokeAIAppConfig(BaseSettings):
         """Path to the models directory, resolved to an absolute path.."""
         return self._resolve(self.models_dir)
 
+    @property
+    def style_presets_path(self) -> Path:
+        """Path to the style presets directory, resolved to an absolute path.."""
+        return self._resolve(self.style_presets_dir)
+
     @property
     def convert_cache_path(self) -> Path:
         """Path to the converted cache models directory, resolved to an absolute path.."""

invokeai/app/services/events/events_common.py

@@ -88,6 +88,7 @@ class QueueItemEventBase(QueueEventBase):
 
     item_id: int = Field(description="The ID of the queue item")
     batch_id: str = Field(description="The ID of the queue batch")
+    origin: str | None = Field(default=None, description="The origin of the batch")
 
 
 class InvocationEventBase(QueueItemEventBase):
@@ -95,8 +96,6 @@ class InvocationEventBase(QueueItemEventBase):
 
     session_id: str = Field(description="The ID of the session (aka graph execution state)")
     queue_id: str = Field(description="The ID of the queue")
-    item_id: int = Field(description="The ID of the queue item")
-    batch_id: str = Field(description="The ID of the queue batch")
     session_id: str = Field(description="The ID of the session (aka graph execution state)")
     invocation: AnyInvocation = Field(description="The ID of the invocation")
     invocation_source_id: str = Field(description="The ID of the prepared invocation's source node")
@@ -114,6 +113,7 @@ class InvocationStartedEvent(InvocationEventBase):
             queue_id=queue_item.queue_id,
             item_id=queue_item.item_id,
             batch_id=queue_item.batch_id,
+            origin=queue_item.origin,
             session_id=queue_item.session_id,
             invocation=invocation,
             invocation_source_id=queue_item.session.prepared_source_mapping[invocation.id],
@@ -147,6 +147,7 @@ class InvocationDenoiseProgressEvent(InvocationEventBase):
             queue_id=queue_item.queue_id,
             item_id=queue_item.item_id,
             batch_id=queue_item.batch_id,
+            origin=queue_item.origin,
             session_id=queue_item.session_id,
             invocation=invocation,
             invocation_source_id=queue_item.session.prepared_source_mapping[invocation.id],
@@ -184,6 +185,7 @@ class InvocationCompleteEvent(InvocationEventBase):
             queue_id=queue_item.queue_id,
             item_id=queue_item.item_id,
             batch_id=queue_item.batch_id,
+            origin=queue_item.origin,
             session_id=queue_item.session_id,
             invocation=invocation,
             invocation_source_id=queue_item.session.prepared_source_mapping[invocation.id],
@@ -216,6 +218,7 @@ class InvocationErrorEvent(InvocationEventBase):
             queue_id=queue_item.queue_id,
             item_id=queue_item.item_id,
             batch_id=queue_item.batch_id,
+            origin=queue_item.origin,
             session_id=queue_item.session_id,
             invocation=invocation,
             invocation_source_id=queue_item.session.prepared_source_mapping[invocation.id],
@@ -253,6 +256,7 @@ class QueueItemStatusChangedEvent(QueueItemEventBase):
             queue_id=queue_item.queue_id,
             item_id=queue_item.item_id,
             batch_id=queue_item.batch_id,
+            origin=queue_item.origin,
             session_id=queue_item.session_id,
             status=queue_item.status,
             error_type=queue_item.error_type,
@@ -279,12 +283,14 @@ class BatchEnqueuedEvent(QueueEventBase):
         description="The number of invocations initially requested to be enqueued (may be less than enqueued if queue was full)"
     )
     priority: int = Field(description="The priority of the batch")
+    origin: str | None = Field(default=None, description="The origin of the batch")
 
     @classmethod
     def build(cls, enqueue_result: EnqueueBatchResult) -> "BatchEnqueuedEvent":
         return cls(
             queue_id=enqueue_result.queue_id,
             batch_id=enqueue_result.batch.batch_id,
+            origin=enqueue_result.batch.origin,
             enqueued=enqueue_result.enqueued,
             requested=enqueue_result.requested,
             priority=enqueue_result.priority,

invokeai/app/services/events/events_fastapievents.py

@@ -1,46 +1,44 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
 import asyncio
 import threading
-from queue import Empty, Queue
 
 from fastapi_events.dispatcher import dispatch
 
 from invokeai.app.services.events.events_base import EventServiceBase
-from invokeai.app.services.events.events_common import (
-    EventBase,
-)
+from invokeai.app.services.events.events_common import EventBase
 
 
 class FastAPIEventService(EventServiceBase):
-    def __init__(self, event_handler_id: int) -> None:
+    def __init__(self, event_handler_id: int, loop: asyncio.AbstractEventLoop) -> None:
         self.event_handler_id = event_handler_id
-        self._queue = Queue[EventBase | None]()
+        self._queue = asyncio.Queue[EventBase | None]()
         self._stop_event = threading.Event()
-        asyncio.create_task(self._dispatch_from_queue(stop_event=self._stop_event))
+        self._loop = loop
+
+        # We need to store a reference to the task so it doesn't get GC'd
+        # See: https://docs.python.org/3/library/asyncio-task.html#creating-tasks
+        self._background_tasks: set[asyncio.Task[None]] = set()
+        task = self._loop.create_task(self._dispatch_from_queue(stop_event=self._stop_event))
+        self._background_tasks.add(task)
+        task.add_done_callback(self._background_tasks.remove)
 
         super().__init__()
 
     def stop(self, *args, **kwargs):
         self._stop_event.set()
-        self._queue.put(None)
+        self._loop.call_soon_threadsafe(self._queue.put_nowait, None)
 
     def dispatch(self, event: EventBase) -> None:
-        self._queue.put(event)
+        self._loop.call_soon_threadsafe(self._queue.put_nowait, event)
 
     async def _dispatch_from_queue(self, stop_event: threading.Event):
         """Get events on from the queue and dispatch them, from the correct thread"""
         while not stop_event.is_set():
             try:
-                event = self._queue.get(block=False)
+                event = await self._queue.get()
                 if not event:  # Probably stopping
                     continue
                 # Leave the payloads as live pydantic models
                 dispatch(event, middleware_id=self.event_handler_id, payload_schema_dump=False)
 
-            except Empty:
-                await asyncio.sleep(0.1)
-                pass
-
             except asyncio.CancelledError as e:
                 raise e  # Raise a proper error

invokeai/app/services/image_files/image_files_disk.py

@@ -1,11 +1,10 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 from pathlib import Path
 from queue import Queue
-from typing import Dict, Optional, Union
+from typing import Optional, Union
 
 from PIL import Image, PngImagePlugin
 from PIL.Image import Image as PILImageType
-from send2trash import send2trash
 
 from invokeai.app.services.image_files.image_files_base import ImageFileStorageBase
 from invokeai.app.services.image_files.image_files_common import (
@@ -20,18 +19,12 @@ from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
 class DiskImageFileStorage(ImageFileStorageBase):
     """Stores images on disk"""
 
-    __output_folder: Path
-    __cache_ids: Queue  # TODO: this is an incredibly naive cache
-    __cache: Dict[Path, PILImageType]
-    __max_cache_size: int
-    __invoker: Invoker
-
     def __init__(self, output_folder: Union[str, Path]):
-        self.__cache = {}
-        self.__cache_ids = Queue()
+        self.__cache: dict[Path, PILImageType] = {}
+        self.__cache_ids = Queue[Path]()
         self.__max_cache_size = 10  # TODO: get this from config
 
-        self.__output_folder: Path = output_folder if isinstance(output_folder, Path) else Path(output_folder)
+        self.__output_folder = output_folder if isinstance(output_folder, Path) else Path(output_folder)
         self.__thumbnails_folder = self.__output_folder / "thumbnails"
         # Validate required output folders at launch
         self.__validate_storage_folders()
@@ -103,7 +96,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
             image_path = self.get_path(image_name)
 
             if image_path.exists():
-                send2trash(image_path)
+                image_path.unlink()
             if image_path in self.__cache:
                 del self.__cache[image_path]
 
@@ -111,7 +104,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
             thumbnail_path = self.get_path(thumbnail_name, True)
 
             if thumbnail_path.exists():
-                send2trash(thumbnail_path)
+                thumbnail_path.unlink()
             if thumbnail_path in self.__cache:
                 del self.__cache[thumbnail_path]
         except Exception as e:

invokeai/app/services/invocation_services.py

@@ -4,6 +4,8 @@ from __future__ import annotations
 from typing import TYPE_CHECKING
 
 from invokeai.app.services.object_serializer.object_serializer_base import ObjectSerializerBase
+from invokeai.app.services.style_preset_images.style_preset_images_base import StylePresetImageFileStorageBase
+from invokeai.app.services.style_preset_records.style_preset_records_base import StylePresetRecordsStorageBase
 
 if TYPE_CHECKING:
     from logging import Logger
@@ -61,6 +63,8 @@ class InvocationServices:
         workflow_records: "WorkflowRecordsStorageBase",
         tensors: "ObjectSerializerBase[torch.Tensor]",
         conditioning: "ObjectSerializerBase[ConditioningFieldData]",
+        style_preset_records: "StylePresetRecordsStorageBase",
+        style_preset_image_files: "StylePresetImageFileStorageBase",
     ):
         self.board_images = board_images
         self.board_image_records = board_image_records
@@ -85,3 +89,5 @@ class InvocationServices:
         self.workflow_records = workflow_records
         self.tensors = tensors
         self.conditioning = conditioning
+        self.style_preset_records = style_preset_records
+        self.style_preset_image_files = style_preset_image_files

invokeai/app/services/model_images/model_images_default.py

@@ -2,7 +2,6 @@ from pathlib import Path
 
 from PIL import Image
 from PIL.Image import Image as PILImageType
-from send2trash import send2trash
 
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.model_images.model_images_base import ModelImageFileStorageBase
@@ -70,7 +69,7 @@ class ModelImageFileStorageDisk(ModelImageFileStorageBase):
             if not self._validate_path(path):
                 raise ModelImageFileNotFoundException
 
-            send2trash(path)
+            path.unlink()
 
         except Exception as e:
             raise ModelImageFileDeleteException from e

invokeai/app/services/model_install/model_install_base.py

@@ -3,7 +3,7 @@
 
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Union
+from typing import List, Optional, Union
 
 from pydantic.networks import AnyHttpUrl
 
@@ -12,7 +12,7 @@ from invokeai.app.services.download import DownloadQueueServiceBase
 from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.model_install.model_install_common import ModelInstallJob, ModelSource
-from invokeai.app.services.model_records import ModelRecordServiceBase
+from invokeai.app.services.model_records import ModelRecordChanges, ModelRecordServiceBase
 from invokeai.backend.model_manager import AnyModelConfig
 
 
@@ -64,7 +64,7 @@ class ModelInstallServiceBase(ABC):
     def register_path(
         self,
         model_path: Union[Path, str],
-        config: Optional[Dict[str, Any]] = None,
+        config: Optional[ModelRecordChanges] = None,
     ) -> str:
         """
         Probe and register the model at model_path.
@@ -72,7 +72,7 @@ class ModelInstallServiceBase(ABC):
         This keeps the model in its current location.
 
         :param model_path: Filesystem Path to the model.
-        :param config: Dict of attributes that will override autoassigned values.
+        :param config: ModelRecordChanges object that will override autoassigned model record values.
         :returns id: The string ID of the registered model.
         """
 
@@ -92,7 +92,7 @@ class ModelInstallServiceBase(ABC):
     def install_path(
         self,
         model_path: Union[Path, str],
-        config: Optional[Dict[str, Any]] = None,
+        config: Optional[ModelRecordChanges] = None,
     ) -> str:
         """
         Probe, register and install the model in the models directory.
@@ -101,7 +101,7 @@ class ModelInstallServiceBase(ABC):
         the models directory handled by InvokeAI.
 
         :param model_path: Filesystem Path to the model.
-        :param config: Dict of attributes that will override autoassigned values.
+        :param config: ModelRecordChanges object that will override autoassigned model record values.
         :returns id: The string ID of the registered model.
         """
 
@@ -109,14 +109,14 @@ class ModelInstallServiceBase(ABC):
     def heuristic_import(
         self,
         source: str,
-        config: Optional[Dict[str, Any]] = None,
+        config: Optional[ModelRecordChanges] = None,
         access_token: Optional[str] = None,
         inplace: Optional[bool] = False,
     ) -> 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
+        :param config: Optional ModelRecordChanges object. Any fields in this object
          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.
@@ -147,7 +147,7 @@ class ModelInstallServiceBase(ABC):
     def import_model(
         self,
         source: ModelSource,
-        config: Optional[Dict[str, Any]] = None,
+        config: Optional[ModelRecordChanges] = None,
     ) -> ModelInstallJob:
         """Install the indicated model.
 

invokeai/app/services/model_install/model_install_common.py

@@ -2,13 +2,14 @@ import re
 import traceback
 from enum import Enum
 from pathlib import Path
-from typing import Any, Dict, Literal, Optional, Set, Union
+from typing import Literal, Optional, Set, Union
 
 from pydantic import BaseModel, Field, PrivateAttr, field_validator
 from pydantic.networks import AnyHttpUrl
 from typing_extensions import Annotated
 
 from invokeai.app.services.download import DownloadJob, MultiFileDownloadJob
+from invokeai.app.services.model_records import ModelRecordChanges
 from invokeai.backend.model_manager import AnyModelConfig, ModelRepoVariant
 from invokeai.backend.model_manager.config import ModelSourceType
 from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
@@ -133,8 +134,9 @@ class ModelInstallJob(BaseModel):
     id: int = Field(description="Unique ID for this job")
     status: InstallStatus = Field(default=InstallStatus.WAITING, description="Current status of install process")
     error_reason: Optional[str] = Field(default=None, description="Information about why the job failed")
-    config_in: Dict[str, Any] = Field(
-        default_factory=dict, description="Configuration information (e.g. 'description') to apply to model."
+    config_in: ModelRecordChanges = Field(
+        default_factory=ModelRecordChanges,
+        description="Configuration information (e.g. 'description') to apply to model.",
     )
     config_out: Optional[AnyModelConfig] = Field(
         default=None, description="After successful installation, this will hold the configuration object."

invokeai/app/services/model_install/model_install_default.py

@@ -163,26 +163,27 @@ class ModelInstallService(ModelInstallServiceBase):
     def register_path(
         self,
         model_path: Union[Path, str],
-        config: Optional[Dict[str, Any]] = None,
+        config: Optional[ModelRecordChanges] = None,
     ) -> str:  # noqa D102
         model_path = Path(model_path)
-        config = config or {}
-        if not config.get("source"):
-            config["source"] = model_path.resolve().as_posix()
-        config["source_type"] = ModelSourceType.Path
+        config = config or ModelRecordChanges()
+        if not config.source:
+            config.source = model_path.resolve().as_posix()
+        config.source_type = ModelSourceType.Path
         return self._register(model_path, config)
 
     def install_path(
         self,
         model_path: Union[Path, str],
-        config: Optional[Dict[str, Any]] = None,
+        config: Optional[ModelRecordChanges] = None,
     ) -> str:  # noqa D102
         model_path = Path(model_path)
-        config = config or {}
+        config = config or ModelRecordChanges()
+        info: AnyModelConfig = ModelProbe.probe(
+            Path(model_path), config.model_dump(), hash_algo=self._app_config.hashing_algorithm
+        )  # type: ignore
 
-        info: AnyModelConfig = ModelProbe.probe(Path(model_path), config, hash_algo=self._app_config.hashing_algorithm)
-
-        if preferred_name := config.get("name"):
+        if preferred_name := config.name:
             preferred_name = Path(preferred_name).with_suffix(model_path.suffix)
 
         dest_path = (
@@ -204,7 +205,7 @@ class ModelInstallService(ModelInstallServiceBase):
     def heuristic_import(
         self,
         source: str,
-        config: Optional[Dict[str, Any]] = None,
+        config: Optional[ModelRecordChanges] = None,
         access_token: Optional[str] = None,
         inplace: Optional[bool] = False,
     ) -> ModelInstallJob:
@@ -216,7 +217,7 @@ class ModelInstallService(ModelInstallServiceBase):
             source_obj.access_token = access_token
         return self.import_model(source_obj, config)
 
-    def import_model(self, source: ModelSource, config: Optional[Dict[str, Any]] = None) -> ModelInstallJob:  # noqa D102
+    def import_model(self, source: ModelSource, config: Optional[ModelRecordChanges] = 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.")
@@ -318,16 +319,17 @@ class ModelInstallService(ModelInstallServiceBase):
                         model_path = self._app_config.models_path / model_path
                     model_path = model_path.resolve()
 
-                    config: dict[str, Any] = {}
-                    config["name"] = model_name
-                    config["description"] = stanza.get("description")
+                    config = ModelRecordChanges(
+                        name=model_name,
+                        description=stanza.get("description"),
+                    )
                     legacy_config_path = stanza.get("config")
                     if legacy_config_path:
                         # In v3, these paths were relative to the root. Migrate them to be relative to the legacy_conf_dir.
                         legacy_config_path = self._app_config.root_path / legacy_config_path
                         if legacy_config_path.is_relative_to(self._app_config.legacy_conf_path):
                             legacy_config_path = legacy_config_path.relative_to(self._app_config.legacy_conf_path)
-                        config["config_path"] = str(legacy_config_path)
+                        config.config_path = str(legacy_config_path)
                     try:
                         id = self.register_path(model_path=model_path, config=config)
                         self._logger.info(f"Migrated {model_name} with id {id}")
@@ -500,11 +502,11 @@ 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)
-        job.config_in["source_type"] = MODEL_SOURCE_TO_TYPE_MAP[job.source.__class__]
+        job.config_in.source = str(job.source)
+        job.config_in.source_type = MODEL_SOURCE_TO_TYPE_MAP[job.source.__class__]
         # enter the metadata, if there is any
         if isinstance(job.source_metadata, (HuggingFaceMetadata)):
-            job.config_in["source_api_response"] = job.source_metadata.api_response
+            job.config_in.source_api_response = job.source_metadata.api_response
 
         if job.inplace:
             key = self.register_path(job.local_path, job.config_in)
@@ -639,11 +641,11 @@ class ModelInstallService(ModelInstallServiceBase):
         return new_path
 
     def _register(
-        self, model_path: Path, config: Optional[Dict[str, Any]] = None, info: Optional[AnyModelConfig] = None
+        self, model_path: Path, config: Optional[ModelRecordChanges] = None, info: Optional[AnyModelConfig] = None
     ) -> str:
-        config = config or {}
+        config = config or ModelRecordChanges()
 
-        info = info or ModelProbe.probe(model_path, config, hash_algo=self._app_config.hashing_algorithm)
+        info = info or ModelProbe.probe(model_path, config.model_dump(), hash_algo=self._app_config.hashing_algorithm)  # type: ignore
 
         model_path = model_path.resolve()
 
@@ -674,11 +676,13 @@ class ModelInstallService(ModelInstallServiceBase):
         precision = TorchDevice.choose_torch_dtype()
         return ModelRepoVariant.FP16 if precision == torch.float16 else None
 
-    def _import_local_model(self, source: LocalModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
+    def _import_local_model(
+        self, source: LocalModelSource, config: Optional[ModelRecordChanges] = None
+    ) -> ModelInstallJob:
         return ModelInstallJob(
             id=self._next_id(),
             source=source,
-            config_in=config or {},
+            config_in=config or ModelRecordChanges(),
             local_path=Path(source.path),
             inplace=source.inplace or False,
         )
@@ -686,7 +690,7 @@ class ModelInstallService(ModelInstallServiceBase):
     def _import_from_hf(
         self,
         source: HFModelSource,
-        config: Optional[Dict[str, Any]] = None,
+        config: Optional[ModelRecordChanges] = None,
     ) -> ModelInstallJob:
         # Add user's cached access token to HuggingFace requests
         if source.access_token is None:
@@ -702,7 +706,7 @@ class ModelInstallService(ModelInstallServiceBase):
     def _import_from_url(
         self,
         source: URLModelSource,
-        config: Optional[Dict[str, Any]],
+        config: Optional[ModelRecordChanges] = None,
     ) -> ModelInstallJob:
         remote_files, metadata = self._remote_files_from_source(source)
         return self._import_remote_model(
@@ -717,7 +721,7 @@ class ModelInstallService(ModelInstallServiceBase):
         source: HFModelSource | URLModelSource,
         remote_files: List[RemoteModelFile],
         metadata: Optional[AnyModelRepoMetadata],
-        config: Optional[Dict[str, Any]],
+        config: Optional[ModelRecordChanges],
     ) -> ModelInstallJob:
         if len(remote_files) == 0:
             raise ValueError(f"{source}: No downloadable files found")
@@ -730,7 +734,7 @@ class ModelInstallService(ModelInstallServiceBase):
         install_job = ModelInstallJob(
             id=self._next_id(),
             source=source,
-            config_in=config or {},
+            config_in=config or ModelRecordChanges(),
             source_metadata=metadata,
             local_path=destdir,  # local path may change once the download has started due to content-disposition handling
             bytes=0,

invokeai/app/services/model_records/model_records_base.py

@@ -18,6 +18,7 @@ from invokeai.backend.model_manager.config import (
     ControlAdapterDefaultSettings,
     MainModelDefaultSettings,
     ModelFormat,
+    ModelSourceType,
     ModelType,
     ModelVariantType,
     SchedulerPredictionType,
@@ -66,10 +67,16 @@ class ModelRecordChanges(BaseModelExcludeNull):
     """A set of changes to apply to a model."""
 
     # Changes applicable to all models
+    source: Optional[str] = Field(description="original source of the model", default=None)
+    source_type: Optional[ModelSourceType] = Field(description="type of model source", default=None)
+    source_api_response: Optional[str] = Field(description="metadata from remote source", default=None)
     name: Optional[str] = Field(description="Name of the model.", default=None)
     path: Optional[str] = Field(description="Path to the model.", default=None)
     description: Optional[str] = Field(description="Model description", default=None)
     base: Optional[BaseModelType] = Field(description="The base model.", default=None)
+    type: Optional[ModelType] = Field(description="Type of model", default=None)
+    key: Optional[str] = Field(description="Database ID for this model", default=None)
+    hash: Optional[str] = Field(description="hash of model file", default=None)
     trigger_phrases: Optional[set[str]] = Field(description="Set of trigger phrases for this model", default=None)
     default_settings: Optional[MainModelDefaultSettings | ControlAdapterDefaultSettings] = Field(
         description="Default settings for this model", default=None

invokeai/app/services/model_records/model_records_sql.py

@@ -40,11 +40,14 @@ Typical usage:
 """
 
 import json
+import logging
 import sqlite3
 from math import ceil
 from pathlib import Path
 from typing import List, Optional, Union
 
+import pydantic
+
 from invokeai.app.services.model_records.model_records_base import (
     DuplicateModelException,
     ModelRecordChanges,
@@ -67,7 +70,7 @@ from invokeai.backend.model_manager.config import (
 class ModelRecordServiceSQL(ModelRecordServiceBase):
     """Implementation of the ModelConfigStore ABC using a SQL database."""
 
-    def __init__(self, db: SqliteDatabase):
+    def __init__(self, db: SqliteDatabase, logger: logging.Logger):
         """
         Initialize a new object from preexisting sqlite3 connection and threading lock objects.
 
@@ -76,6 +79,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         super().__init__()
         self._db = db
         self._cursor = db.conn.cursor()
+        self._logger = logger
 
     @property
     def db(self) -> SqliteDatabase:
@@ -291,7 +295,20 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
                 tuple(bindings),
             )
             result = self._cursor.fetchall()
-            results = [ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in result]
+
+        # Parse the model configs.
+        results: list[AnyModelConfig] = []
+        for row in result:
+            try:
+                model_config = ModelConfigFactory.make_config(json.loads(row[0]), timestamp=row[1])
+            except pydantic.ValidationError:
+                # We catch this error so that the app can still run if there are invalid model configs in the database.
+                # One reason that an invalid model config might be in the database is if someone had to rollback from a
+                # newer version of the app that added a new model type.
+                self._logger.warning(f"Found an invalid model config in the database. Ignoring this model. ({row[0]})")
+            else:
+                results.append(model_config)
+
         return results
 
     def search_by_path(self, path: Union[str, Path]) -> List[AnyModelConfig]:

invokeai/app/services/session_queue/session_queue_base.py

@@ -6,6 +6,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     Batch,
     BatchStatus,
     CancelByBatchIDsResult,
+    CancelByOriginResult,
     CancelByQueueIDResult,
     ClearResult,
     EnqueueBatchResult,
@@ -95,6 +96,11 @@ class SessionQueueBase(ABC):
         """Cancels all queue items with matching batch IDs"""
         pass
 
+    @abstractmethod
+    def cancel_by_origin(self, queue_id: str, origin: str) -> CancelByOriginResult:
+        """Cancels all queue items with the given batch origin"""
+        pass
+
     @abstractmethod
     def cancel_by_queue_id(self, queue_id: str) -> CancelByQueueIDResult:
         """Cancels all queue items with matching queue ID"""

invokeai/app/services/session_queue/session_queue_common.py

@@ -77,6 +77,7 @@ BatchDataCollection: TypeAlias = list[list[BatchDatum]]
 
 class Batch(BaseModel):
     batch_id: str = Field(default_factory=uuid_string, description="The ID of the batch")
+    origin: str | None = Field(default=None, description="The origin of this batch.")
     data: Optional[BatchDataCollection] = Field(default=None, description="The batch data collection.")
     graph: Graph = Field(description="The graph to initialize the session with")
     workflow: Optional[WorkflowWithoutID] = Field(
@@ -195,6 +196,7 @@ class SessionQueueItemWithoutGraph(BaseModel):
     status: QUEUE_ITEM_STATUS = Field(default="pending", description="The status of this queue item")
     priority: int = Field(default=0, description="The priority of this queue item")
     batch_id: str = Field(description="The ID of the batch associated with this queue item")
+    origin: str | None = Field(default=None, description="The origin of this queue item. ")
     session_id: str = Field(
         description="The ID of the session associated with this queue item. The session doesn't exist in graph_executions until the queue item is executed."
     )
@@ -294,6 +296,7 @@ class SessionQueueStatus(BaseModel):
 class BatchStatus(BaseModel):
     queue_id: str = Field(..., description="The ID of the queue")
     batch_id: str = Field(..., description="The ID of the batch")
+    origin: str | None = Field(..., description="The origin of the batch")
     pending: int = Field(..., description="Number of queue items with status 'pending'")
     in_progress: int = Field(..., description="Number of queue items with status 'in_progress'")
     completed: int = Field(..., description="Number of queue items with status 'complete'")
@@ -328,6 +331,12 @@ class CancelByBatchIDsResult(BaseModel):
     canceled: int = Field(..., description="Number of queue items canceled")
 
 
+class CancelByOriginResult(BaseModel):
+    """Result of canceling by list of batch ids"""
+
+    canceled: int = Field(..., description="Number of queue items canceled")
+
+
 class CancelByQueueIDResult(CancelByBatchIDsResult):
     """Result of canceling by queue id"""
 
@@ -433,6 +442,7 @@ class SessionQueueValueToInsert(NamedTuple):
     field_values: Optional[str]  # field_values json
     priority: int  # priority
     workflow: Optional[str]  # workflow json
+    origin: str | None
 
 
 ValuesToInsert: TypeAlias = list[SessionQueueValueToInsert]
@@ -453,6 +463,7 @@ def prepare_values_to_insert(queue_id: str, batch: Batch, priority: int, max_new
                 json.dumps(field_values, default=to_jsonable_python) if field_values else None,  # field_values (json)
                 priority,  # priority
                 json.dumps(workflow, default=to_jsonable_python) if workflow else None,  # workflow (json)
+                batch.origin,  # origin
             )
         )
     return values_to_insert

invokeai/app/services/session_queue/session_queue_sqlite.py

@@ -10,6 +10,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
     Batch,
     BatchStatus,
     CancelByBatchIDsResult,
+    CancelByOriginResult,
     CancelByQueueIDResult,
     ClearResult,
     EnqueueBatchResult,
@@ -127,8 +128,8 @@ class SqliteSessionQueue(SessionQueueBase):
 
             self.__cursor.executemany(
                 """--sql
-                INSERT INTO session_queue (queue_id, session, session_id, batch_id, field_values, priority, workflow)
-                VALUES (?, ?, ?, ?, ?, ?, ?)
+                INSERT INTO session_queue (queue_id, session, session_id, batch_id, field_values, priority, workflow, origin)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?)
                 """,
                 values_to_insert,
             )
@@ -417,11 +418,7 @@ class SqliteSessionQueue(SessionQueueBase):
             )
             self.__conn.commit()
             if current_queue_item is not None and current_queue_item.batch_id in batch_ids:
-                batch_status = self.get_batch_status(queue_id=queue_id, batch_id=current_queue_item.batch_id)
-                queue_status = self.get_queue_status(queue_id=queue_id)
-                self.__invoker.services.events.emit_queue_item_status_changed(
-                    current_queue_item, batch_status, queue_status
-                )
+                self._set_queue_item_status(current_queue_item.item_id, "canceled")
         except Exception:
             self.__conn.rollback()
             raise
@@ -429,6 +426,46 @@ class SqliteSessionQueue(SessionQueueBase):
             self.__lock.release()
         return CancelByBatchIDsResult(canceled=count)
 
+    def cancel_by_origin(self, queue_id: str, origin: str) -> CancelByOriginResult:
+        try:
+            current_queue_item = self.get_current(queue_id)
+            self.__lock.acquire()
+            where = """--sql
+                WHERE
+                  queue_id == ?
+                  AND origin == ?
+                  AND status != 'canceled'
+                  AND status != 'completed'
+                  AND status != 'failed'
+                """
+            params = (queue_id, origin)
+            self.__cursor.execute(
+                f"""--sql
+                SELECT COUNT(*)
+                FROM session_queue
+                {where};
+                """,
+                params,
+            )
+            count = self.__cursor.fetchone()[0]
+            self.__cursor.execute(
+                f"""--sql
+                UPDATE session_queue
+                SET status = 'canceled'
+                {where};
+                """,
+                params,
+            )
+            self.__conn.commit()
+            if current_queue_item is not None and current_queue_item.origin == origin:
+                self._set_queue_item_status(current_queue_item.item_id, "canceled")
+        except Exception:
+            self.__conn.rollback()
+            raise
+        finally:
+            self.__lock.release()
+        return CancelByOriginResult(canceled=count)
+
     def cancel_by_queue_id(self, queue_id: str) -> CancelByQueueIDResult:
         try:
             current_queue_item = self.get_current(queue_id)
@@ -541,7 +578,8 @@ class SqliteSessionQueue(SessionQueueBase):
                     started_at,
                     session_id,
                     batch_id,
-                    queue_id
+                    queue_id,
+                    origin
                 FROM session_queue
                 WHERE queue_id = ?
             """
@@ -621,7 +659,7 @@ class SqliteSessionQueue(SessionQueueBase):
             self.__lock.acquire()
             self.__cursor.execute(
                 """--sql
-                SELECT status, count(*)
+                SELECT status, count(*), origin
                 FROM session_queue
                 WHERE
                   queue_id = ?
@@ -633,6 +671,7 @@ class SqliteSessionQueue(SessionQueueBase):
             result = cast(list[sqlite3.Row], self.__cursor.fetchall())
             total = sum(row[1] for row in result)
             counts: dict[str, int] = {row[0]: row[1] for row in result}
+            origin = result[0]["origin"] if result else None
         except Exception:
             self.__conn.rollback()
             raise
@@ -641,6 +680,7 @@ class SqliteSessionQueue(SessionQueueBase):
 
         return BatchStatus(
             batch_id=batch_id,
+            origin=origin,
             queue_id=queue_id,
             pending=counts.get("pending", 0),
             in_progress=counts.get("in_progress", 0),

invokeai/app/services/shared/sqlite/sqlite_util.py

@@ -16,6 +16,8 @@ from invokeai.app.services.shared.sqlite_migrator.migrations.migration_10 import
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_11 import build_migration_11
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_12 import build_migration_12
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_13 import build_migration_13
+from invokeai.app.services.shared.sqlite_migrator.migrations.migration_14 import build_migration_14
+from invokeai.app.services.shared.sqlite_migrator.migrations.migration_15 import build_migration_15
 from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_impl import SqliteMigrator
 
 
@@ -49,6 +51,8 @@ def init_db(config: InvokeAIAppConfig, logger: Logger, image_files: ImageFileSto
     migrator.register_migration(build_migration_11(app_config=config, logger=logger))
     migrator.register_migration(build_migration_12(app_config=config))
     migrator.register_migration(build_migration_13())
+    migrator.register_migration(build_migration_14())
+    migrator.register_migration(build_migration_15())
     migrator.run_migrations()
 
     return db

invokeai/app/services/shared/sqlite_migrator/migrations/migration_14.py

@@ -0,0 +1,61 @@
+import sqlite3
+
+from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
+
+
+class Migration14Callback:
+    def __call__(self, cursor: sqlite3.Cursor) -> None:
+        self._create_style_presets(cursor)
+
+    def _create_style_presets(self, cursor: sqlite3.Cursor) -> None:
+        """Create the table used to store style presets."""
+        tables = [
+            """--sql
+            CREATE TABLE IF NOT EXISTS style_presets (
+                id TEXT NOT NULL PRIMARY KEY,
+                name TEXT NOT NULL,
+                preset_data TEXT NOT NULL,
+                type TEXT NOT NULL DEFAULT "user",
+                created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
+                -- Updated via trigger
+                updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW'))
+            );
+            """
+        ]
+
+        # Add trigger for `updated_at`.
+        triggers = [
+            """--sql
+            CREATE TRIGGER IF NOT EXISTS style_presets
+            AFTER UPDATE
+            ON style_presets FOR EACH ROW
+            BEGIN
+                UPDATE style_presets SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
+                    WHERE id = old.id;
+            END;
+            """
+        ]
+
+        # Add indexes for searchable fields
+        indices = [
+            "CREATE INDEX IF NOT EXISTS idx_style_presets_name ON style_presets(name);",
+        ]
+
+        for stmt in tables + indices + triggers:
+            cursor.execute(stmt)
+
+
+def build_migration_14() -> Migration:
+    """
+    Build the migration from database version 13 to 14..
+
+    This migration does the following:
+    - Create the table used to store style presets.
+    """
+    migration_14 = Migration(
+        from_version=13,
+        to_version=14,
+        callback=Migration14Callback(),
+    )
+
+    return migration_14

invokeai/app/services/shared/sqlite_migrator/migrations/migration_15.py

@@ -0,0 +1,31 @@
+import sqlite3
+
+from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
+
+
+class Migration15Callback:
+    def __call__(self, cursor: sqlite3.Cursor) -> None:
+        self._add_origin_col(cursor)
+
+    def _add_origin_col(self, cursor: sqlite3.Cursor) -> None:
+        """
+        - Adds `origin` column to the session queue table.
+        """
+
+        cursor.execute("ALTER TABLE session_queue ADD COLUMN origin TEXT;")
+
+
+def build_migration_15() -> Migration:
+    """
+    Build the migration from database version 14 to 15.
+
+    This migration does the following:
+        - Adds `origin` column to the session queue table.
+    """
+    migration_15 = Migration(
+        from_version=14,
+        to_version=15,
+        callback=Migration15Callback(),
+    )
+
+    return migration_15

invokeai/app/services/style_preset_images/style_preset_images_base.py

@@ -0,0 +1,33 @@
+from abc import ABC, abstractmethod
+from pathlib import Path
+
+from PIL.Image import Image as PILImageType
+
+
+class StylePresetImageFileStorageBase(ABC):
+    """Low-level service responsible for storing and retrieving image files."""
+
+    @abstractmethod
+    def get(self, style_preset_id: str) -> PILImageType:
+        """Retrieves a style preset image as PIL Image."""
+        pass
+
+    @abstractmethod
+    def get_path(self, style_preset_id: str) -> Path:
+        """Gets the internal path to a style preset image."""
+        pass
+
+    @abstractmethod
+    def get_url(self, style_preset_id: str) -> str | None:
+        """Gets the URL to fetch a style preset image."""
+        pass
+
+    @abstractmethod
+    def save(self, style_preset_id: str, image: PILImageType) -> None:
+        """Saves a style preset image."""
+        pass
+
+    @abstractmethod
+    def delete(self, style_preset_id: str) -> None:
+        """Deletes a style preset image."""
+        pass

invokeai/app/services/style_preset_images/style_preset_images_common.py

@@ -0,0 +1,19 @@
+class StylePresetImageFileNotFoundException(Exception):
+    """Raised when an image file is not found in storage."""
+
+    def __init__(self, message: str = "Style preset image file not found"):
+        super().__init__(message)
+
+
+class StylePresetImageFileSaveException(Exception):
+    """Raised when an image cannot be saved."""
+
+    def __init__(self, message: str = "Style preset image file not saved"):
+        super().__init__(message)
+
+
+class StylePresetImageFileDeleteException(Exception):
+    """Raised when an image cannot be deleted."""
+
+    def __init__(self, message: str = "Style preset image file not deleted"):
+        super().__init__(message)

invokeai/app/services/style_preset_images/style_preset_images_disk.py

@@ -0,0 +1,88 @@
+from pathlib import Path
+
+from PIL import Image
+from PIL.Image import Image as PILImageType
+
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.style_preset_images.style_preset_images_base import StylePresetImageFileStorageBase
+from invokeai.app.services.style_preset_images.style_preset_images_common import (
+    StylePresetImageFileDeleteException,
+    StylePresetImageFileNotFoundException,
+    StylePresetImageFileSaveException,
+)
+from invokeai.app.services.style_preset_records.style_preset_records_common import PresetType
+from invokeai.app.util.misc import uuid_string
+from invokeai.app.util.thumbnails import make_thumbnail
+
+
+class StylePresetImageFileStorageDisk(StylePresetImageFileStorageBase):
+    """Stores images on disk"""
+
+    def __init__(self, style_preset_images_folder: Path):
+        self._style_preset_images_folder = style_preset_images_folder
+        self._validate_storage_folders()
+
+    def start(self, invoker: Invoker) -> None:
+        self._invoker = invoker
+
+    def get(self, style_preset_id: str) -> PILImageType:
+        try:
+            path = self.get_path(style_preset_id)
+
+            return Image.open(path)
+        except FileNotFoundError as e:
+            raise StylePresetImageFileNotFoundException from e
+
+    def save(self, style_preset_id: str, image: PILImageType) -> None:
+        try:
+            self._validate_storage_folders()
+            image_path = self._style_preset_images_folder / (style_preset_id + ".webp")
+            thumbnail = make_thumbnail(image, 256)
+            thumbnail.save(image_path, format="webp")
+
+        except Exception as e:
+            raise StylePresetImageFileSaveException from e
+
+    def get_path(self, style_preset_id: str) -> Path:
+        style_preset = self._invoker.services.style_preset_records.get(style_preset_id)
+        if style_preset.type is PresetType.Default:
+            default_images_dir = Path(__file__).parent / Path("default_style_preset_images")
+            path = default_images_dir / (style_preset.name + ".png")
+        else:
+            path = self._style_preset_images_folder / (style_preset_id + ".webp")
+
+        return path
+
+    def get_url(self, style_preset_id: str) -> str | None:
+        path = self.get_path(style_preset_id)
+        if not self._validate_path(path):
+            return
+
+        url = self._invoker.services.urls.get_style_preset_image_url(style_preset_id)
+
+        # The image URL never changes, so we must add random query string to it to prevent caching
+        url += f"?{uuid_string()}"
+
+        return url
+
+    def delete(self, style_preset_id: str) -> None:
+        try:
+            path = self.get_path(style_preset_id)
+
+            if not self._validate_path(path):
+                raise StylePresetImageFileNotFoundException
+
+            path.unlink()
+
+        except StylePresetImageFileNotFoundException as e:
+            raise StylePresetImageFileNotFoundException from e
+        except Exception as e:
+            raise StylePresetImageFileDeleteException from e
+
+    def _validate_path(self, path: Path) -> bool:
+        """Validates the path given for an image."""
+        return path.exists()
+
+    def _validate_storage_folders(self) -> None:
+        """Checks if the required folders exist and create them if they don't"""
+        self._style_preset_images_folder.mkdir(parents=True, exist_ok=True)

invokeai/app/services/style_preset_records/default_style_presets.json

@@ -0,0 +1,146 @@
+[
+  {
+    "name": "Photography (General)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt}. photography. f/2.8 macro photo, bokeh, photorealism",
+      "negative_prompt": "painting, digital art. sketch, blurry"
+    }
+  },
+  {
+    "name": "Photography (Studio Lighting)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt}, photography. f/8 photo. centered subject, studio lighting.",
+      "negative_prompt": "painting, digital art. sketch, blurry"
+    }
+  },
+  {
+    "name": "Photography (Landscape)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt}, landscape photograph, f/12, lifelike,  highly detailed.",
+      "negative_prompt": "painting, digital art. sketch, blurry"
+    }
+  },
+  {
+    "name": "Photography (Portrait)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt}. photography. portraiture. catch light in eyes. one flash. rembrandt lighting. Soft box. dark shadows. High contrast. 80mm lens. F2.8.",
+      "negative_prompt": "painting, digital art. sketch, blurry"
+    }
+  },
+  {
+    "name": "Photography (Black and White)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} photography. natural light. 80mm lens. F1.4. strong contrast, hard light. dark contrast. blurred background. black and white",
+      "negative_prompt": "painting, digital art. sketch, colour+"
+    }
+  },
+  {
+    "name": "Architectural Visualization",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt}. architectural photography, f/12, luxury, aesthetically pleasing form and function.",
+      "negative_prompt": "painting, digital art. sketch, blurry"
+    }
+  },
+  {
+    "name": "Concept Art (Fantasy)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "concept artwork of a {prompt}. (digital painterly art style)++, mythological, (textured 2d dry media brushpack)++, glazed brushstrokes, otherworldly. painting+, illustration+",
+      "negative_prompt": "photo. distorted, blurry, out of focus. sketch. (cgi, 3d.)++"
+    }
+  },
+  {
+    "name": "Concept Art (Sci-Fi)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "(concept art)++, {prompt}, (sleek futurism)++, (textured 2d dry media)++, metallic highlights, digital painting style",
+      "negative_prompt": "photo. distorted, blurry, out of focus. sketch. (cgi, 3d.)++"
+    }
+  },
+  {
+    "name": "Concept Art (Character)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "(character concept art)++, stylized painterly digital painting of {prompt}, (painterly, impasto. Dry brush.)++",
+      "negative_prompt": "photo. distorted, blurry, out of focus. sketch. (cgi, 3d.)++"
+    }
+  },
+  {
+    "name": "Concept Art (Painterly)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} oil painting. high contrast. impasto. sfumato. chiaroscuro. Palette knife.",
+      "negative_prompt": "photo. smooth. border. frame"
+    }
+  },
+  {
+    "name": "Environment Art",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} environment artwork, hyper-realistic digital painting style with cinematic composition, atmospheric, depth and detail, voluminous. textured dry brush 2d media",
+      "negative_prompt": "photo, distorted, blurry, out of focus. sketch."
+    }
+  },
+  {
+    "name": "Interior Design (Visualization)",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} interior design photo, gentle shadows, light mid-tones, dimension, mix of smooth and textured surfaces, focus on negative space and clean lines, focus",
+      "negative_prompt": "photo, distorted. sketch."
+    }
+  },
+  {
+    "name": "Product Rendering",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} high quality product photography, 3d rendering with key lighting, shallow depth of field, simple plain background, studio lighting.",
+      "negative_prompt": "blurry, sketch, messy, dirty. unfinished."
+    }
+  },
+  {
+    "name": "Sketch",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} black and white pencil drawing, off-center composition, cross-hatching for shadows, bold strokes, textured paper. sketch+++",
+      "negative_prompt": "blurry, photo, painting, color. messy, dirty. unfinished. frame, borders."
+    }
+  },
+  {
+    "name": "Line Art",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} Line art. bold outline. simplistic. white background. 2d",
+      "negative_prompt": "photo. digital art. greyscale. solid black. painting"
+    }
+  },
+  {
+    "name": "Anime",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} anime++, bold outline, cel-shaded coloring, shounen, seinen",
+      "negative_prompt": "(photo)+++. greyscale. solid black. painting"
+    }
+  },
+  {
+    "name": "Illustration",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "{prompt} illustration, bold linework, illustrative details, vector art style, flat coloring",
+      "negative_prompt": "(photo)+++. greyscale. painting, black and white."
+    }
+  },
+  {
+    "name": "Vehicles",
+    "type": "default",
+    "preset_data": {
+      "positive_prompt": "A weird futuristic normal auto, {prompt} elegant design, nice color, nice wheels",
+      "negative_prompt": "sketch. digital art. greyscale. painting"
+    }
+  }
+]

invokeai/app/services/style_preset_records/style_preset_records_base.py

@@ -0,0 +1,42 @@
+from abc import ABC, abstractmethod
+
+from invokeai.app.services.style_preset_records.style_preset_records_common import (
+    PresetType,
+    StylePresetChanges,
+    StylePresetRecordDTO,
+    StylePresetWithoutId,
+)
+
+
+class StylePresetRecordsStorageBase(ABC):
+    """Base class for style preset storage services."""
+
+    @abstractmethod
+    def get(self, style_preset_id: str) -> StylePresetRecordDTO:
+        """Get style preset by id."""
+        pass
+
+    @abstractmethod
+    def create(self, style_preset: StylePresetWithoutId) -> StylePresetRecordDTO:
+        """Creates a style preset."""
+        pass
+
+    @abstractmethod
+    def create_many(self, style_presets: list[StylePresetWithoutId]) -> None:
+        """Creates many style presets."""
+        pass
+
+    @abstractmethod
+    def update(self, style_preset_id: str, changes: StylePresetChanges) -> StylePresetRecordDTO:
+        """Updates a style preset."""
+        pass
+
+    @abstractmethod
+    def delete(self, style_preset_id: str) -> None:
+        """Deletes a style preset."""
+        pass
+
+    @abstractmethod
+    def get_many(self, type: PresetType | None = None) -> list[StylePresetRecordDTO]:
+        """Gets many workflows."""
+        pass

invokeai/app/services/style_preset_records/style_preset_records_common.py

@@ -0,0 +1,139 @@
+import codecs
+import csv
+import json
+from enum import Enum
+from typing import Any, Optional
+
+import pydantic
+from fastapi import UploadFile
+from pydantic import AliasChoices, BaseModel, ConfigDict, Field, TypeAdapter
+
+from invokeai.app.util.metaenum import MetaEnum
+
+
+class StylePresetNotFoundError(Exception):
+    """Raised when a style preset is not found"""
+
+
+class PresetData(BaseModel, extra="forbid"):
+    positive_prompt: str = Field(description="Positive prompt")
+    negative_prompt: str = Field(description="Negative prompt")
+
+
+PresetDataValidator = TypeAdapter(PresetData)
+
+
+class PresetType(str, Enum, metaclass=MetaEnum):
+    User = "user"
+    Default = "default"
+    Project = "project"
+
+
+class StylePresetChanges(BaseModel, extra="forbid"):
+    name: Optional[str] = Field(default=None, description="The style preset's new name.")
+    preset_data: Optional[PresetData] = Field(default=None, description="The updated data for style preset.")
+    type: Optional[PresetType] = Field(description="The updated type of the style preset")
+
+
+class StylePresetWithoutId(BaseModel):
+    name: str = Field(description="The name of the style preset.")
+    preset_data: PresetData = Field(description="The preset data")
+    type: PresetType = Field(description="The type of style preset")
+
+
+class StylePresetRecordDTO(StylePresetWithoutId):
+    id: str = Field(description="The style preset ID.")
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "StylePresetRecordDTO":
+        data["preset_data"] = PresetDataValidator.validate_json(data.get("preset_data", ""))
+        return StylePresetRecordDTOValidator.validate_python(data)
+
+
+StylePresetRecordDTOValidator = TypeAdapter(StylePresetRecordDTO)
+
+
+class StylePresetRecordWithImage(StylePresetRecordDTO):
+    image: Optional[str] = Field(description="The path for image")
+
+
+class StylePresetImportRow(BaseModel):
+    name: str = Field(min_length=1, description="The name of the preset.")
+    positive_prompt: str = Field(
+        default="",
+        description="The positive prompt for the preset.",
+        validation_alias=AliasChoices("positive_prompt", "prompt"),
+    )
+    negative_prompt: str = Field(default="", description="The negative prompt for the preset.")
+
+    model_config = ConfigDict(str_strip_whitespace=True, extra="forbid")
+
+
+StylePresetImportList = list[StylePresetImportRow]
+StylePresetImportListTypeAdapter = TypeAdapter(StylePresetImportList)
+
+
+class UnsupportedFileTypeError(ValueError):
+    """Raised when an unsupported file type is encountered"""
+
+    pass
+
+
+class InvalidPresetImportDataError(ValueError):
+    """Raised when invalid preset import data is encountered"""
+
+    pass
+
+
+async def parse_presets_from_file(file: UploadFile) -> list[StylePresetWithoutId]:
+    """Parses style presets from a file. The file must be a CSV or JSON file.
+
+    If CSV, the file must have the following columns:
+    - name
+    - prompt (or positive_prompt)
+    - negative_prompt
+
+    If JSON, the file must be a list of objects with the following keys:
+    - name
+    - prompt (or positive_prompt)
+    - negative_prompt
+
+    Args:
+        file (UploadFile): The file to parse.
+
+    Returns:
+        list[StylePresetWithoutId]: The parsed style presets.
+
+    Raises:
+        UnsupportedFileTypeError: If the file type is not supported.
+        InvalidPresetImportDataError: If the data in the file is invalid.
+    """
+    if file.content_type not in ["text/csv", "application/json"]:
+        raise UnsupportedFileTypeError()
+
+    if file.content_type == "text/csv":
+        csv_reader = csv.DictReader(codecs.iterdecode(file.file, "utf-8"))
+        data = list(csv_reader)
+    else:  # file.content_type == "application/json":
+        json_data = await file.read()
+        data = json.loads(json_data)
+
+    try:
+        imported_presets = StylePresetImportListTypeAdapter.validate_python(data)
+
+        style_presets: list[StylePresetWithoutId] = []
+
+        for imported in imported_presets:
+            preset_data = PresetData(positive_prompt=imported.positive_prompt, negative_prompt=imported.negative_prompt)
+            style_preset = StylePresetWithoutId(name=imported.name, preset_data=preset_data, type=PresetType.User)
+            style_presets.append(style_preset)
+    except pydantic.ValidationError as e:
+        if file.content_type == "text/csv":
+            msg = "Invalid CSV format: must include columns 'name', 'prompt', and 'negative_prompt' and name cannot be blank"
+        else:  # file.content_type == "application/json":
+            msg = "Invalid JSON format: must be a list of objects with keys 'name', 'prompt', and 'negative_prompt' and name cannot be blank"
+        raise InvalidPresetImportDataError(msg) from e
+    finally:
+        file.file.close()
+
+    return style_presets

invokeai/app/services/style_preset_records/style_preset_records_sqlite.py

@@ -0,0 +1,215 @@
+import json
+from pathlib import Path
+
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
+from invokeai.app.services.style_preset_records.style_preset_records_base import StylePresetRecordsStorageBase
+from invokeai.app.services.style_preset_records.style_preset_records_common import (
+    PresetType,
+    StylePresetChanges,
+    StylePresetNotFoundError,
+    StylePresetRecordDTO,
+    StylePresetWithoutId,
+)
+from invokeai.app.util.misc import uuid_string
+
+
+class SqliteStylePresetRecordsStorage(StylePresetRecordsStorageBase):
+    def __init__(self, db: SqliteDatabase) -> None:
+        super().__init__()
+        self._lock = db.lock
+        self._conn = db.conn
+        self._cursor = self._conn.cursor()
+
+    def start(self, invoker: Invoker) -> None:
+        self._invoker = invoker
+        self._sync_default_style_presets()
+
+    def get(self, style_preset_id: str) -> StylePresetRecordDTO:
+        """Gets a style preset by ID."""
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT *
+                FROM style_presets
+                WHERE id = ?;
+                """,
+                (style_preset_id,),
+            )
+            row = self._cursor.fetchone()
+            if row is None:
+                raise StylePresetNotFoundError(f"Style preset with id {style_preset_id} not found")
+            return StylePresetRecordDTO.from_dict(dict(row))
+        except Exception:
+            self._conn.rollback()
+            raise
+        finally:
+            self._lock.release()
+
+    def create(self, style_preset: StylePresetWithoutId) -> StylePresetRecordDTO:
+        style_preset_id = uuid_string()
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                INSERT OR IGNORE INTO style_presets (
+                    id,
+                    name,
+                    preset_data,
+                    type
+                )
+                VALUES (?, ?, ?, ?);
+                """,
+                (
+                    style_preset_id,
+                    style_preset.name,
+                    style_preset.preset_data.model_dump_json(),
+                    style_preset.type,
+                ),
+            )
+            self._conn.commit()
+        except Exception:
+            self._conn.rollback()
+            raise
+        finally:
+            self._lock.release()
+        return self.get(style_preset_id)
+
+    def create_many(self, style_presets: list[StylePresetWithoutId]) -> None:
+        style_preset_ids = []
+        try:
+            self._lock.acquire()
+            for style_preset in style_presets:
+                style_preset_id = uuid_string()
+                style_preset_ids.append(style_preset_id)
+                self._cursor.execute(
+                    """--sql
+                    INSERT OR IGNORE INTO style_presets (
+                        id,
+                        name,
+                        preset_data,
+                        type
+                    )
+                    VALUES (?, ?, ?, ?);
+                    """,
+                    (
+                        style_preset_id,
+                        style_preset.name,
+                        style_preset.preset_data.model_dump_json(),
+                        style_preset.type,
+                    ),
+                )
+            self._conn.commit()
+        except Exception:
+            self._conn.rollback()
+            raise
+        finally:
+            self._lock.release()
+
+        return None
+
+    def update(self, style_preset_id: str, changes: StylePresetChanges) -> StylePresetRecordDTO:
+        try:
+            self._lock.acquire()
+            # Change the name of a style preset
+            if changes.name is not None:
+                self._cursor.execute(
+                    """--sql
+                    UPDATE style_presets
+                    SET name = ?
+                    WHERE id = ?;
+                    """,
+                    (changes.name, style_preset_id),
+                )
+
+            # Change the preset data for a style preset
+            if changes.preset_data is not None:
+                self._cursor.execute(
+                    """--sql
+                    UPDATE style_presets
+                    SET preset_data = ?
+                    WHERE id = ?;
+                    """,
+                    (changes.preset_data.model_dump_json(), style_preset_id),
+                )
+
+            self._conn.commit()
+        except Exception:
+            self._conn.rollback()
+            raise
+        finally:
+            self._lock.release()
+        return self.get(style_preset_id)
+
+    def delete(self, style_preset_id: str) -> None:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                DELETE from style_presets
+                WHERE id = ?;
+                """,
+                (style_preset_id,),
+            )
+            self._conn.commit()
+        except Exception:
+            self._conn.rollback()
+            raise
+        finally:
+            self._lock.release()
+        return None
+
+    def get_many(self, type: PresetType | None = None) -> list[StylePresetRecordDTO]:
+        try:
+            self._lock.acquire()
+            main_query = """
+                SELECT
+                    *
+                FROM style_presets
+                """
+
+            if type is not None:
+                main_query += "WHERE type = ? "
+
+            main_query += "ORDER BY LOWER(name) ASC"
+
+            if type is not None:
+                self._cursor.execute(main_query, (type,))
+            else:
+                self._cursor.execute(main_query)
+
+            rows = self._cursor.fetchall()
+            style_presets = [StylePresetRecordDTO.from_dict(dict(row)) for row in rows]
+
+            return style_presets
+        except Exception:
+            self._conn.rollback()
+            raise
+        finally:
+            self._lock.release()
+
+    def _sync_default_style_presets(self) -> None:
+        """Syncs default style presets to the database. Internal use only."""
+
+        # First delete all existing default style presets
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                DELETE FROM style_presets
+                WHERE type = "default";
+                """
+            )
+            self._conn.commit()
+        except Exception:
+            self._conn.rollback()
+            raise
+        finally:
+            self._lock.release()
+        # Next, parse and create the default style presets
+        with self._lock, open(Path(__file__).parent / Path("default_style_presets.json"), "r") as file:
+            presets = json.load(file)
+            for preset in presets:
+                style_preset = StylePresetWithoutId.model_validate(preset)
+                self.create(style_preset)

invokeai/app/services/urls/urls_base.py

@@ -13,3 +13,8 @@ class UrlServiceBase(ABC):
     def get_model_image_url(self, model_key: str) -> str:
         """Gets the URL for a model image"""
         pass
+
+    @abstractmethod
+    def get_style_preset_image_url(self, style_preset_id: str) -> str:
+        """Gets the URL for a style preset image"""
+        pass

invokeai/app/services/urls/urls_default.py

@@ -19,3 +19,6 @@ class LocalUrlService(UrlServiceBase):
 
     def get_model_image_url(self, model_key: str) -> str:
         return f"{self._base_url_v2}/models/i/{model_key}/image"
+
+    def get_style_preset_image_url(self, style_preset_id: str) -> str:
+        return f"{self._base_url}/style_presets/i/{style_preset_id}/image"

invokeai/app/services/workflow_records/default_workflows/ESRGAN Upscaling with Canny ControlNet.json

@@ -2,7 +2,7 @@
   "name": "ESRGAN Upscaling with Canny ControlNet",
   "author": "InvokeAI",
   "description": "Sample workflow for using Upscaling with ControlNet with SD1.5",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "upscale, controlnet, default",
   "notes": "",
@@ -36,14 +36,13 @@
     "version": "3.0.0",
     "category": "default"
   },
-  "id": "0e71a27e-a22b-4a9b-b20a-6d789abff2bc",
   "nodes": [
     {
-      "id": "e8bf67fe-67de-4227-87eb-79e86afdfc74",
+      "id": "63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16b",
       "type": "invocation",
       "data": {
-        "id": "e8bf67fe-67de-4227-87eb-79e86afdfc74",
-        "version": "1.1.1",
+        "id": "63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16b",
+        "version": "1.2.0",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
@@ -57,6 +56,10 @@
           "clip": {
             "name": "clip",
             "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
           }
         },
         "isOpen": true,
@@ -65,122 +68,63 @@
       },
       "position": {
         "x": 1250,
-        "y": 1500
+        "y": 1200
       }
     },
     {
-      "id": "d8ace142-c05f-4f1d-8982-88dc7473958d",
+      "id": "5ca498a4-c8c8-4580-a396-0c984317205d",
       "type": "invocation",
       "data": {
-        "id": "d8ace142-c05f-4f1d-8982-88dc7473958d",
-        "version": "1.0.2",
+        "id": "5ca498a4-c8c8-4580-a396-0c984317205d",
+        "version": "1.1.0",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
-        "type": "main_model_loader",
+        "type": "i2l",
         "inputs": {
-          "model": {
-            "name": "model",
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
             "label": "",
-            "value": {
-              "key": "5cd43ca0-dd0a-418d-9f7e-35b2b9d5e106",
-              "hash": "blake3:6987f323017f597213cc3264250edf57056d21a40a0a85d83a1a33a7d44dc41a",
-              "name": "Deliberate_v5",
-              "base": "sd-1",
-              "type": "main"
-            }
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 700,
-        "y": 1375
-      }
-    },
-    {
-      "id": "771bdf6a-0813-4099-a5d8-921a138754d4",
-      "type": "invocation",
-      "data": {
-        "id": "771bdf6a-0813-4099-a5d8-921a138754d4",
-        "version": "1.0.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "image",
-        "inputs": {
-          "image": {
-            "name": "image",
-            "label": "Image To Upscale",
-            "value": {
-              "image_name": "d2e42ba6-d420-496b-82db-91c9b75956c1.png"
-            }
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 344.5593065887157,
-        "y": 1698.161491368619
-      }
-    },
-    {
-      "id": "f7564dd2-9539-47f2-ac13-190804461f4e",
-      "type": "invocation",
-      "data": {
-        "id": "f7564dd2-9539-47f2-ac13-190804461f4e",
-        "version": "1.3.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "esrgan",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "model_name": {
-            "name": "model_name",
-            "label": "Upscaler Model",
-            "value": "RealESRGAN_x2plus.pth"
+            "value": false
           },
           "tile_size": {
             "name": "tile_size",
             "label": "",
-            "value": 400
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": false
           }
         },
-        "isOpen": true,
+        "isOpen": false,
         "isIntermediate": true,
         "useCache": true
       },
       "position": {
-        "x": 717.3863693661265,
-        "y": 1721.9215053134815
+        "x": 1650,
+        "y": 1675
       }
     },
     {
-      "id": "1d887701-df21-4966-ae6e-a7d82307d7bd",
+      "id": "3ed9b2ef-f4ec-40a7-94db-92e63b583ec0",
       "type": "invocation",
       "data": {
-        "id": "1d887701-df21-4966-ae6e-a7d82307d7bd",
-        "version": "1.3.2",
+        "id": "3ed9b2ef-f4ec-40a7-94db-92e63b583ec0",
+        "version": "1.3.0",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
-        "type": "canny_image_processor",
+        "type": "l2i",
         "inputs": {
           "board": {
             "name": "board",
@@ -190,38 +134,37 @@
             "name": "metadata",
             "label": ""
           },
-          "image": {
-            "name": "image",
+          "latents": {
+            "name": "latents",
             "label": ""
           },
-          "detect_resolution": {
-            "name": "detect_resolution",
-            "label": "",
-            "value": 512
+          "vae": {
+            "name": "vae",
+            "label": ""
           },
-          "image_resolution": {
-            "name": "image_resolution",
+          "tiled": {
+            "name": "tiled",
             "label": "",
-            "value": 512
+            "value": false
           },
-          "low_threshold": {
-            "name": "low_threshold",
+          "tile_size": {
+            "name": "tile_size",
             "label": "",
-            "value": 100
+            "value": 0
           },
-          "high_threshold": {
-            "name": "high_threshold",
+          "fp32": {
+            "name": "fp32",
             "label": "",
-            "value": 200
+            "value": false
           }
         },
         "isOpen": true,
-        "isIntermediate": true,
+        "isIntermediate": false,
         "useCache": true
       },
       "position": {
-        "x": 1200,
-        "y": 1900
+        "x": 2559.4751127537957,
+        "y": 1246.6000376741406
       }
     },
     {
@@ -229,7 +172,7 @@
       "type": "invocation",
       "data": {
         "id": "ca1d020c-89a8-4958-880a-016d28775cfa",
-        "version": "1.1.1",
+        "version": "1.1.2",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
@@ -285,6 +228,193 @@
         "y": 1902.9649340196056
       }
     },
+    {
+      "id": "1d887701-df21-4966-ae6e-a7d82307d7bd",
+      "type": "invocation",
+      "data": {
+        "id": "1d887701-df21-4966-ae6e-a7d82307d7bd",
+        "version": "1.3.3",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "canny_image_processor",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "detect_resolution": {
+            "name": "detect_resolution",
+            "label": "",
+            "value": 512
+          },
+          "image_resolution": {
+            "name": "image_resolution",
+            "label": "",
+            "value": 512
+          },
+          "low_threshold": {
+            "name": "low_threshold",
+            "label": "",
+            "value": 100
+          },
+          "high_threshold": {
+            "name": "high_threshold",
+            "label": "",
+            "value": 200
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 1200,
+        "y": 1900
+      }
+    },
+    {
+      "id": "d8ace142-c05f-4f1d-8982-88dc7473958d",
+      "type": "invocation",
+      "data": {
+        "id": "d8ace142-c05f-4f1d-8982-88dc7473958d",
+        "version": "1.0.3",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "main_model_loader",
+        "inputs": {
+          "model": {
+            "name": "model",
+            "label": "",
+            "value": {
+              "key": "5cd43ca0-dd0a-418d-9f7e-35b2b9d5e106",
+              "hash": "blake3:6987f323017f597213cc3264250edf57056d21a40a0a85d83a1a33a7d44dc41a",
+              "name": "Deliberate_v5",
+              "base": "sd-1",
+              "type": "main"
+            }
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 700,
+        "y": 1375
+      }
+    },
+    {
+      "id": "e8bf67fe-67de-4227-87eb-79e86afdfc74",
+      "type": "invocation",
+      "data": {
+        "id": "e8bf67fe-67de-4227-87eb-79e86afdfc74",
+        "version": "1.2.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "compel",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "",
+            "value": ""
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 1250,
+        "y": 1500
+      }
+    },
+    {
+      "id": "771bdf6a-0813-4099-a5d8-921a138754d4",
+      "type": "invocation",
+      "data": {
+        "id": "771bdf6a-0813-4099-a5d8-921a138754d4",
+        "version": "1.0.2",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "image",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": "Image To Upscale"
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 344.5593065887157,
+        "y": 1698.161491368619
+      }
+    },
+    {
+      "id": "f7564dd2-9539-47f2-ac13-190804461f4e",
+      "type": "invocation",
+      "data": {
+        "id": "f7564dd2-9539-47f2-ac13-190804461f4e",
+        "version": "1.3.2",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "esrgan",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "model_name": {
+            "name": "model_name",
+            "label": "Upscaler Model",
+            "value": "RealESRGAN_x2plus.pth"
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 400
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 717.3863693661265,
+        "y": 1721.9215053134815
+      }
+    },
     {
       "id": "f50624ce-82bf-41d0-bdf7-8aab11a80d48",
       "type": "invocation",
@@ -413,122 +543,6 @@
         "y": 1232.6219060454753
       }
     },
-    {
-      "id": "3ed9b2ef-f4ec-40a7-94db-92e63b583ec0",
-      "type": "invocation",
-      "data": {
-        "id": "3ed9b2ef-f4ec-40a7-94db-92e63b583ec0",
-        "version": "1.2.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "l2i",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "latents": {
-            "name": "latents",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": false
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": false,
-        "useCache": true
-      },
-      "position": {
-        "x": 2559.4751127537957,
-        "y": 1246.6000376741406
-      }
-    },
-    {
-      "id": "5ca498a4-c8c8-4580-a396-0c984317205d",
-      "type": "invocation",
-      "data": {
-        "id": "5ca498a4-c8c8-4580-a396-0c984317205d",
-        "version": "1.0.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "i2l",
-        "inputs": {
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": false
-          }
-        },
-        "isOpen": false,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 1650,
-        "y": 1675
-      }
-    },
-    {
-      "id": "63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16b",
-      "type": "invocation",
-      "data": {
-        "id": "63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16b",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "",
-            "value": ""
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 1250,
-        "y": 1200
-      }
-    },
     {
       "id": "eb8f6f8a-c7b1-4914-806e-045ee2717a35",
       "type": "invocation",

invokeai/app/services/workflow_records/default_workflows/Face Detailer with IP-Adapter & Canny (See Note in Details).json

@@ -2,7 +2,7 @@
   "name": "Face Detailer with IP-Adapter & Canny (See Note in Details)",
   "author": "kosmoskatten",
   "description": "A workflow to add detail to and improve faces. This workflow is most effective when used with a model that creates realistic outputs. ",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "face detailer, IP-Adapter, Canny",
   "notes": "Set this image as the blur mask: https://i.imgur.com/Gxi61zP.png",
@@ -37,16 +37,219 @@
     }
   ],
   "meta": {
-    "category": "default",
-    "version": "3.0.0"
+    "version": "3.0.0",
+    "category": "default"
   },
   "nodes": [
     {
-      "id": "44f2c190-eb03-460d-8d11-a94d13b33f19",
+      "id": "c6359181-6479-40ec-bf3a-b7e8451683b8",
       "type": "invocation",
       "data": {
-        "id": "44f2c190-eb03-460d-8d11-a94d13b33f19",
-        "version": "1.1.1",
+        "id": "c6359181-6479-40ec-bf3a-b7e8451683b8",
+        "version": "1.0.3",
+        "label": "",
+        "notes": "",
+        "type": "main_model_loader",
+        "inputs": {
+          "model": {
+            "name": "model",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 2031.5518710051792,
+        "y": -492.1742944307074
+      }
+    },
+    {
+      "id": "8fe598c6-d447-44fa-a165-4975af77d080",
+      "type": "invocation",
+      "data": {
+        "id": "8fe598c6-d447-44fa-a165-4975af77d080",
+        "version": "1.3.3",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "canny_image_processor",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "detect_resolution": {
+            "name": "detect_resolution",
+            "label": "",
+            "value": 512
+          },
+          "image_resolution": {
+            "name": "image_resolution",
+            "label": "",
+            "value": 512
+          },
+          "low_threshold": {
+            "name": "low_threshold",
+            "label": "",
+            "value": 100
+          },
+          "high_threshold": {
+            "name": "high_threshold",
+            "label": "",
+            "value": 200
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 3519.4131037388597,
+        "y": 576.7946795840575
+      }
+    },
+    {
+      "id": "f60b6161-8f26-42f6-89ff-545e6011e501",
+      "type": "invocation",
+      "data": {
+        "id": "f60b6161-8f26-42f6-89ff-545e6011e501",
+        "version": "1.1.2",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "controlnet",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "control_model": {
+            "name": "control_model",
+            "label": "Control Model (select canny)",
+            "value": {
+              "key": "5bdaacf7-a7a3-4fb8-b394-cc0ffbb8941d",
+              "hash": "blake3:260c7f8e10aefea9868cfc68d89970e91033bd37132b14b903e70ee05ebf530e",
+              "name": "sd-controlnet-canny",
+              "base": "sd-1",
+              "type": "controlnet"
+            }
+          },
+          "control_weight": {
+            "name": "control_weight",
+            "label": "",
+            "value": 0.5
+          },
+          "begin_step_percent": {
+            "name": "begin_step_percent",
+            "label": "",
+            "value": 0
+          },
+          "end_step_percent": {
+            "name": "end_step_percent",
+            "label": "",
+            "value": 0.5
+          },
+          "control_mode": {
+            "name": "control_mode",
+            "label": "",
+            "value": "balanced"
+          },
+          "resize_mode": {
+            "name": "resize_mode",
+            "label": "",
+            "value": "just_resize"
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 3950,
+        "y": 150
+      }
+    },
+    {
+      "id": "22b750db-b85e-486b-b278-ac983e329813",
+      "type": "invocation",
+      "data": {
+        "id": "22b750db-b85e-486b-b278-ac983e329813",
+        "version": "1.4.1",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "ip_adapter",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "ip_adapter_model": {
+            "name": "ip_adapter_model",
+            "label": "IP-Adapter Model (select IP Adapter Face)",
+            "value": {
+              "key": "1cc210bb-4d0a-4312-b36c-b5d46c43768e",
+              "hash": "blake3:3d669dffa7471b357b4df088b99ffb6bf4d4383d5e0ef1de5ec1c89728a3d5a5",
+              "name": "ip_adapter_sd15",
+              "base": "sd-1",
+              "type": "ip_adapter"
+            }
+          },
+          "clip_vision_model": {
+            "name": "clip_vision_model",
+            "label": "",
+            "value": "ViT-H"
+          },
+          "weight": {
+            "name": "weight",
+            "label": "",
+            "value": 0.5
+          },
+          "method": {
+            "name": "method",
+            "label": "",
+            "value": "full"
+          },
+          "begin_step_percent": {
+            "name": "begin_step_percent",
+            "label": "",
+            "value": 0
+          },
+          "end_step_percent": {
+            "name": "end_step_percent",
+            "label": "",
+            "value": 0.8
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 3575,
+        "y": -200
+      }
+    },
+    {
+      "id": "f4d15b64-c4a6-42a5-90fc-e4ed07a0ca65",
+      "type": "invocation",
+      "data": {
+        "id": "f4d15b64-c4a6-42a5-90fc-e4ed07a0ca65",
+        "version": "1.2.0",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
@@ -60,6 +263,140 @@
           "clip": {
             "name": "clip",
             "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 2550,
+        "y": -525
+      }
+    },
+    {
+      "id": "2224ed72-2453-4252-bd89-3085240e0b6f",
+      "type": "invocation",
+      "data": {
+        "id": "2224ed72-2453-4252-bd89-3085240e0b6f",
+        "version": "1.3.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "l2i",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "latents": {
+            "name": "latents",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
+            "label": "",
+            "value": false
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": true
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": false,
+        "useCache": true
+      },
+      "position": {
+        "x": 4980.1395106966565,
+        "y": -255.9158921745602
+      }
+    },
+    {
+      "id": "de8b1a48-a2e4-42ca-90bb-66058bffd534",
+      "type": "invocation",
+      "data": {
+        "id": "de8b1a48-a2e4-42ca-90bb-66058bffd534",
+        "version": "1.1.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "i2l",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
+            "label": "",
+            "value": false
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": true
+          }
+        },
+        "isOpen": false,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 3100,
+        "y": -275
+      }
+    },
+    {
+      "id": "44f2c190-eb03-460d-8d11-a94d13b33f19",
+      "type": "invocation",
+      "data": {
+        "id": "44f2c190-eb03-460d-8d11-a94d13b33f19",
+        "version": "1.2.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "compel",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "",
+            "value": ""
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
           }
         },
         "isOpen": true,
@@ -251,45 +588,6 @@
         "y": 0
       }
     },
-    {
-      "id": "de8b1a48-a2e4-42ca-90bb-66058bffd534",
-      "type": "invocation",
-      "data": {
-        "id": "de8b1a48-a2e4-42ca-90bb-66058bffd534",
-        "version": "1.0.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "i2l",
-        "inputs": {
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": true
-          }
-        },
-        "isOpen": false,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 3100,
-        "y": -275
-      }
-    },
     {
       "id": "bd06261d-a74a-4d1f-8374-745ed6194bc2",
       "type": "invocation",
@@ -418,53 +716,6 @@
         "y": -175
       }
     },
-    {
-      "id": "2224ed72-2453-4252-bd89-3085240e0b6f",
-      "type": "invocation",
-      "data": {
-        "id": "2224ed72-2453-4252-bd89-3085240e0b6f",
-        "version": "1.2.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "l2i",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "latents": {
-            "name": "latents",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": true
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": false,
-        "useCache": true
-      },
-      "position": {
-        "x": 4980.1395106966565,
-        "y": -255.9158921745602
-      }
-    },
     {
       "id": "2974e5b3-3d41-4b6f-9953-cd21e8f3a323",
       "type": "invocation",
@@ -692,201 +943,6 @@
         "y": -275
       }
     },
-    {
-      "id": "f4d15b64-c4a6-42a5-90fc-e4ed07a0ca65",
-      "type": "invocation",
-      "data": {
-        "id": "f4d15b64-c4a6-42a5-90fc-e4ed07a0ca65",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "",
-            "value": ""
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 2550,
-        "y": -525
-      }
-    },
-    {
-      "id": "22b750db-b85e-486b-b278-ac983e329813",
-      "type": "invocation",
-      "data": {
-        "id": "22b750db-b85e-486b-b278-ac983e329813",
-        "version": "1.2.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "ip_adapter",
-        "inputs": {
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "ip_adapter_model": {
-            "name": "ip_adapter_model",
-            "label": "IP-Adapter Model (select IP Adapter Face)",
-            "value": {
-              "key": "1cc210bb-4d0a-4312-b36c-b5d46c43768e",
-              "hash": "blake3:3d669dffa7471b357b4df088b99ffb6bf4d4383d5e0ef1de5ec1c89728a3d5a5",
-              "name": "ip_adapter_sd15",
-              "base": "sd-1",
-              "type": "ip_adapter"
-            }
-          },
-          "weight": {
-            "name": "weight",
-            "label": "",
-            "value": 0.5
-          },
-          "begin_step_percent": {
-            "name": "begin_step_percent",
-            "label": "",
-            "value": 0
-          },
-          "end_step_percent": {
-            "name": "end_step_percent",
-            "label": "",
-            "value": 0.8
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 3575,
-        "y": -200
-      }
-    },
-    {
-      "id": "f60b6161-8f26-42f6-89ff-545e6011e501",
-      "type": "invocation",
-      "data": {
-        "id": "f60b6161-8f26-42f6-89ff-545e6011e501",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "controlnet",
-        "inputs": {
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "control_model": {
-            "name": "control_model",
-            "label": "Control Model (select canny)",
-            "value": {
-              "key": "5bdaacf7-a7a3-4fb8-b394-cc0ffbb8941d",
-              "hash": "blake3:260c7f8e10aefea9868cfc68d89970e91033bd37132b14b903e70ee05ebf530e",
-              "name": "sd-controlnet-canny",
-              "base": "sd-1",
-              "type": "controlnet"
-            }
-          },
-          "control_weight": {
-            "name": "control_weight",
-            "label": "",
-            "value": 0.5
-          },
-          "begin_step_percent": {
-            "name": "begin_step_percent",
-            "label": "",
-            "value": 0
-          },
-          "end_step_percent": {
-            "name": "end_step_percent",
-            "label": "",
-            "value": 0.5
-          },
-          "control_mode": {
-            "name": "control_mode",
-            "label": "",
-            "value": "balanced"
-          },
-          "resize_mode": {
-            "name": "resize_mode",
-            "label": "",
-            "value": "just_resize"
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 3950,
-        "y": 150
-      }
-    },
-    {
-      "id": "8fe598c6-d447-44fa-a165-4975af77d080",
-      "type": "invocation",
-      "data": {
-        "id": "8fe598c6-d447-44fa-a165-4975af77d080",
-        "version": "1.3.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "canny_image_processor",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "detect_resolution": {
-            "name": "detect_resolution",
-            "label": "",
-            "value": 512
-          },
-          "image_resolution": {
-            "name": "image_resolution",
-            "label": "",
-            "value": 512
-          },
-          "low_threshold": {
-            "name": "low_threshold",
-            "label": "",
-            "value": 100
-          },
-          "high_threshold": {
-            "name": "high_threshold",
-            "label": "",
-            "value": 200
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 3519.4131037388597,
-        "y": 576.7946795840575
-      }
-    },
     {
       "id": "4bd4ae80-567f-4366-b8c6-3bb06f4fb46a",
       "type": "invocation",
@@ -1035,30 +1091,6 @@
         "x": 2578.2364832140506,
         "y": 78.7948456497351
       }
-    },
-    {
-      "id": "c6359181-6479-40ec-bf3a-b7e8451683b8",
-      "type": "invocation",
-      "data": {
-        "id": "c6359181-6479-40ec-bf3a-b7e8451683b8",
-        "version": "1.0.2",
-        "label": "",
-        "notes": "",
-        "type": "main_model_loader",
-        "inputs": {
-          "model": {
-            "name": "model",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 2031.5518710051792,
-        "y": -492.1742944307074
-      }
     }
   ],
   "edges": [

invokeai/app/services/workflow_records/default_workflows/Multi ControlNet (Canny & Depth).json

@@ -2,7 +2,7 @@
   "name": "Multi ControlNet (Canny & Depth)",
   "author": "InvokeAI",
   "description": "A sample workflow using canny & depth ControlNets to guide the generation process. ",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "ControlNet, canny, depth",
   "notes": "",
@@ -37,140 +37,104 @@
     }
   ],
   "meta": {
-    "category": "default",
-    "version": "3.0.0"
+    "version": "3.0.0",
+    "category": "default"
   },
   "nodes": [
     {
-      "id": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
+      "id": "9db25398-c869-4a63-8815-c6559341ef12",
       "type": "invocation",
       "data": {
-        "id": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
-        "version": "1.0.2",
+        "id": "9db25398-c869-4a63-8815-c6559341ef12",
+        "version": "1.3.0",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
-        "type": "image",
+        "type": "l2i",
         "inputs": {
-          "image": {
-            "name": "image",
-            "label": "Depth Input Image"
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 3666.135718057363,
-        "y": 186.66887319822808
-      }
-    },
-    {
-      "id": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
-      "type": "invocation",
-      "data": {
-        "id": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "controlnet",
-        "inputs": {
-          "image": {
-            "name": "image",
+          "board": {
+            "name": "board",
             "label": ""
           },
-          "control_model": {
-            "name": "control_model",
-            "label": "Control Model (select depth)",
-            "value": {
-              "key": "87e8855c-671f-4c9e-bbbb-8ed47ccb4aac",
-              "hash": "blake3:2550bf22a53942dfa28ab2fed9d10d80851112531f44d977168992edf9d0534c",
-              "name": "control_v11f1p_sd15_depth",
-              "base": "sd-1",
-              "type": "controlnet"
-            }
+          "metadata": {
+            "name": "metadata",
+            "label": ""
           },
-          "control_weight": {
-            "name": "control_weight",
+          "latents": {
+            "name": "latents",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
             "label": "",
-            "value": 1
+            "value": false
           },
-          "begin_step_percent": {
-            "name": "begin_step_percent",
+          "tile_size": {
+            "name": "tile_size",
             "label": "",
             "value": 0
           },
-          "end_step_percent": {
-            "name": "end_step_percent",
+          "fp32": {
+            "name": "fp32",
             "label": "",
-            "value": 1
-          },
-          "control_mode": {
-            "name": "control_mode",
-            "label": "",
-            "value": "balanced"
-          },
-          "resize_mode": {
-            "name": "resize_mode",
-            "label": "",
-            "value": "just_resize"
+            "value": false
           }
         },
         "isOpen": true,
-        "isIntermediate": true,
+        "isIntermediate": false,
         "useCache": true
       },
       "position": {
-        "x": 4477.604342844504,
-        "y": -49.39005411272677
-      }
-    },
-    {
-      "id": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
-      "type": "invocation",
-      "data": {
-        "id": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "Negative Prompt",
-            "value": ""
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 4075,
+        "x": 5675,
         "y": -825
       }
     },
     {
-      "id": "54486974-835b-4d81-8f82-05f9f32ce9e9",
+      "id": "c826ba5e-9676-4475-b260-07b85e88753c",
       "type": "invocation",
       "data": {
-        "id": "54486974-835b-4d81-8f82-05f9f32ce9e9",
-        "version": "1.0.2",
+        "id": "c826ba5e-9676-4475-b260-07b85e88753c",
+        "version": "1.3.3",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
-        "type": "main_model_loader",
+        "type": "canny_image_processor",
         "inputs": {
-          "model": {
-            "name": "model",
+          "board": {
+            "name": "board",
             "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "detect_resolution": {
+            "name": "detect_resolution",
+            "label": "",
+            "value": 512
+          },
+          "image_resolution": {
+            "name": "image_resolution",
+            "label": "",
+            "value": 512
+          },
+          "low_threshold": {
+            "name": "low_threshold",
+            "label": "",
+            "value": 100
+          },
+          "high_threshold": {
+            "name": "high_threshold",
+            "label": "",
+            "value": 200
           }
         },
         "isOpen": true,
@@ -178,29 +142,52 @@
         "useCache": true
       },
       "position": {
-        "x": 3600,
-        "y": -1000
+        "x": 4095.757337055795,
+        "y": -455.63440891935863
       }
     },
     {
-      "id": "7ce68934-3419-42d4-ac70-82cfc9397306",
+      "id": "018b1214-c2af-43a7-9910-fb687c6726d7",
       "type": "invocation",
       "data": {
-        "id": "7ce68934-3419-42d4-ac70-82cfc9397306",
-        "version": "1.1.1",
+        "id": "018b1214-c2af-43a7-9910-fb687c6726d7",
+        "version": "1.2.4",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
-        "type": "compel",
+        "type": "midas_depth_image_processor",
         "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "Positive Prompt",
-            "value": ""
-          },
-          "clip": {
-            "name": "clip",
+          "board": {
+            "name": "board",
             "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "a_mult": {
+            "name": "a_mult",
+            "label": "",
+            "value": 2
+          },
+          "bg_th": {
+            "name": "bg_th",
+            "label": "",
+            "value": 0.1
+          },
+          "detect_resolution": {
+            "name": "detect_resolution",
+            "label": "",
+            "value": 512
+          },
+          "image_resolution": {
+            "name": "image_resolution",
+            "label": "",
+            "value": 512
           }
         },
         "isOpen": true,
@@ -208,8 +195,8 @@
         "useCache": true
       },
       "position": {
-        "x": 4075,
-        "y": -1125
+        "x": 4082.783145980783,
+        "y": 0.01629251229994111
       }
     },
     {
@@ -217,7 +204,7 @@
       "type": "invocation",
       "data": {
         "id": "d204d184-f209-4fae-a0a1-d152800844e1",
-        "version": "1.1.1",
+        "version": "1.1.2",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
@@ -273,6 +260,185 @@
         "y": -618.4221638099414
       }
     },
+    {
+      "id": "7ce68934-3419-42d4-ac70-82cfc9397306",
+      "type": "invocation",
+      "data": {
+        "id": "7ce68934-3419-42d4-ac70-82cfc9397306",
+        "version": "1.2.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "compel",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "Positive Prompt",
+            "value": ""
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 4075,
+        "y": -1125
+      }
+    },
+    {
+      "id": "54486974-835b-4d81-8f82-05f9f32ce9e9",
+      "type": "invocation",
+      "data": {
+        "id": "54486974-835b-4d81-8f82-05f9f32ce9e9",
+        "version": "1.0.3",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "main_model_loader",
+        "inputs": {
+          "model": {
+            "name": "model",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 3600,
+        "y": -1000
+      }
+    },
+    {
+      "id": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
+      "type": "invocation",
+      "data": {
+        "id": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
+        "version": "1.2.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "compel",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "Negative Prompt",
+            "value": ""
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 4075,
+        "y": -825
+      }
+    },
+    {
+      "id": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
+      "type": "invocation",
+      "data": {
+        "id": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
+        "version": "1.1.2",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "controlnet",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "control_model": {
+            "name": "control_model",
+            "label": "Control Model (select depth)",
+            "value": {
+              "key": "87e8855c-671f-4c9e-bbbb-8ed47ccb4aac",
+              "hash": "blake3:2550bf22a53942dfa28ab2fed9d10d80851112531f44d977168992edf9d0534c",
+              "name": "control_v11f1p_sd15_depth",
+              "base": "sd-1",
+              "type": "controlnet"
+            }
+          },
+          "control_weight": {
+            "name": "control_weight",
+            "label": "",
+            "value": 1
+          },
+          "begin_step_percent": {
+            "name": "begin_step_percent",
+            "label": "",
+            "value": 0
+          },
+          "end_step_percent": {
+            "name": "end_step_percent",
+            "label": "",
+            "value": 1
+          },
+          "control_mode": {
+            "name": "control_mode",
+            "label": "",
+            "value": "balanced"
+          },
+          "resize_mode": {
+            "name": "resize_mode",
+            "label": "",
+            "value": "just_resize"
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 4477.604342844504,
+        "y": -49.39005411272677
+      }
+    },
+    {
+      "id": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
+      "type": "invocation",
+      "data": {
+        "id": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
+        "version": "1.0.2",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "image",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": "Depth Input Image"
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 3666.135718057363,
+        "y": 186.66887319822808
+      }
+    },
     {
       "id": "c4b23e64-7986-40c4-9cad-46327b12e204",
       "type": "invocation",
@@ -322,159 +488,6 @@
         "y": -575
       }
     },
-    {
-      "id": "018b1214-c2af-43a7-9910-fb687c6726d7",
-      "type": "invocation",
-      "data": {
-        "id": "018b1214-c2af-43a7-9910-fb687c6726d7",
-        "version": "1.2.3",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "midas_depth_image_processor",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "a_mult": {
-            "name": "a_mult",
-            "label": "",
-            "value": 2
-          },
-          "bg_th": {
-            "name": "bg_th",
-            "label": "",
-            "value": 0.1
-          },
-          "detect_resolution": {
-            "name": "detect_resolution",
-            "label": "",
-            "value": 512
-          },
-          "image_resolution": {
-            "name": "image_resolution",
-            "label": "",
-            "value": 512
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 4082.783145980783,
-        "y": 0.01629251229994111
-      }
-    },
-    {
-      "id": "c826ba5e-9676-4475-b260-07b85e88753c",
-      "type": "invocation",
-      "data": {
-        "id": "c826ba5e-9676-4475-b260-07b85e88753c",
-        "version": "1.3.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "canny_image_processor",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "detect_resolution": {
-            "name": "detect_resolution",
-            "label": "",
-            "value": 512
-          },
-          "image_resolution": {
-            "name": "image_resolution",
-            "label": "",
-            "value": 512
-          },
-          "low_threshold": {
-            "name": "low_threshold",
-            "label": "",
-            "value": 100
-          },
-          "high_threshold": {
-            "name": "high_threshold",
-            "label": "",
-            "value": 200
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 4095.757337055795,
-        "y": -455.63440891935863
-      }
-    },
-    {
-      "id": "9db25398-c869-4a63-8815-c6559341ef12",
-      "type": "invocation",
-      "data": {
-        "id": "9db25398-c869-4a63-8815-c6559341ef12",
-        "version": "1.2.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "l2i",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "latents": {
-            "name": "latents",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": false
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": false,
-        "useCache": true
-      },
-      "position": {
-        "x": 5675,
-        "y": -825
-      }
-    },
     {
       "id": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
       "type": "invocation",

invokeai/app/services/workflow_records/default_workflows/Prompt from File.json

@@ -2,7 +2,7 @@
   "name": "Prompt from File",
   "author": "InvokeAI",
   "description": "Sample workflow using Prompt from File node",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "text2image, prompt from file, default",
   "notes": "",
@@ -37,16 +37,68 @@
     }
   ],
   "meta": {
-    "category": "default",
-    "version": "3.0.0"
+    "version": "3.0.0",
+    "category": "default"
   },
   "nodes": [
     {
-      "id": "c2eaf1ba-5708-4679-9e15-945b8b432692",
+      "id": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
       "type": "invocation",
       "data": {
-        "id": "c2eaf1ba-5708-4679-9e15-945b8b432692",
-        "version": "1.1.1",
+        "id": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
+        "version": "1.3.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "l2i",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "latents": {
+            "name": "latents",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
+            "label": "",
+            "value": false
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": false
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 2037.861329274915,
+        "y": -329.8393457509562
+      }
+    },
+    {
+      "id": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
+      "type": "invocation",
+      "data": {
+        "id": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
+        "version": "1.2.0",
         "nodePack": "invokeai",
         "label": "",
         "notes": "",
@@ -60,6 +112,69 @@
           "clip": {
             "name": "clip",
             "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": false,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 925,
+        "y": -275
+      }
+    },
+    {
+      "id": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
+      "type": "invocation",
+      "data": {
+        "id": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
+        "version": "1.0.3",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "main_model_loader",
+        "inputs": {
+          "model": {
+            "name": "model",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 0,
+        "y": -375
+      }
+    },
+    {
+      "id": "c2eaf1ba-5708-4679-9e15-945b8b432692",
+      "type": "invocation",
+      "data": {
+        "id": "c2eaf1ba-5708-4679-9e15-945b8b432692",
+        "version": "1.2.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "compel",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "",
+            "value": ""
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
           }
         },
         "isOpen": false,
@@ -141,61 +256,6 @@
         "y": -400
       }
     },
-    {
-      "id": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
-      "type": "invocation",
-      "data": {
-        "id": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
-        "version": "1.0.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "main_model_loader",
-        "inputs": {
-          "model": {
-            "name": "model",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 0,
-        "y": -375
-      }
-    },
-    {
-      "id": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
-      "type": "invocation",
-      "data": {
-        "id": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "",
-            "value": ""
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          }
-        },
-        "isOpen": false,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 925,
-        "y": -275
-      }
-    },
     {
       "id": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
       "type": "invocation",
@@ -268,53 +328,6 @@
         "y": -50
       }
     },
-    {
-      "id": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
-      "type": "invocation",
-      "data": {
-        "id": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
-        "version": "1.2.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "l2i",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "latents": {
-            "name": "latents",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": false
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 2037.861329274915,
-        "y": -329.8393457509562
-      }
-    },
     {
       "id": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
       "type": "invocation",

invokeai/app/services/workflow_records/default_workflows/Text to Image - SD1.5.json

@@ -2,7 +2,7 @@
   "name": "Text to Image - SD1.5",
   "author": "InvokeAI",
   "description": "Sample text to image workflow for Stable Diffusion 1.5/2",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "text2image, SD1.5, SD2, default",
   "notes": "",
@@ -33,16 +33,127 @@
     }
   ],
   "meta": {
-    "category": "default",
-    "version": "3.0.0"
+    "version": "3.0.0",
+    "category": "default"
   },
   "nodes": [
+    {
+      "id": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
+      "type": "invocation",
+      "data": {
+        "id": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
+        "version": "1.3.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "l2i",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "latents": {
+            "name": "latents",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
+            "label": "",
+            "value": false
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": true
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": false,
+        "useCache": true
+      },
+      "position": {
+        "x": 1800,
+        "y": 25
+      }
+    },
+    {
+      "id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
+      "type": "invocation",
+      "data": {
+        "id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
+        "version": "1.2.0",
+        "nodePack": "invokeai",
+        "label": "Positive Compel Prompt",
+        "notes": "",
+        "type": "compel",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "Positive Prompt",
+            "value": "Super cute tiger cub, national geographic award-winning photograph"
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 1000,
+        "y": 25
+      }
+    },
+    {
+      "id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
+      "type": "invocation",
+      "data": {
+        "id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
+        "version": "1.0.3",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "main_model_loader",
+        "inputs": {
+          "model": {
+            "name": "model",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 600,
+        "y": 25
+      }
+    },
     {
       "id": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
       "type": "invocation",
       "data": {
         "id": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
-        "version": "1.1.1",
+        "version": "1.2.0",
         "nodePack": "invokeai",
         "label": "Negative Compel Prompt",
         "notes": "",
@@ -56,6 +167,10 @@
           "clip": {
             "name": "clip",
             "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
           }
         },
         "isOpen": true,
@@ -108,61 +223,6 @@
         "y": 325
       }
     },
-    {
-      "id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "type": "invocation",
-      "data": {
-        "id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-        "version": "1.0.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "main_model_loader",
-        "inputs": {
-          "model": {
-            "name": "model",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 600,
-        "y": 25
-      }
-    },
-    {
-      "id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-      "type": "invocation",
-      "data": {
-        "id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "Positive Compel Prompt",
-        "notes": "",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "Positive Prompt",
-            "value": "Super cute tiger cub, national geographic award-winning photograph"
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 1000,
-        "y": 25
-      }
-    },
     {
       "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
       "type": "invocation",
@@ -280,53 +340,6 @@
         "x": 1400,
         "y": 25
       }
-    },
-    {
-      "id": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
-      "type": "invocation",
-      "data": {
-        "id": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
-        "version": "1.2.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "l2i",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "latents": {
-            "name": "latents",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": true
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": false,
-        "useCache": true
-      },
-      "position": {
-        "x": 1800,
-        "y": 25
-      }
     }
   ],
   "edges": [

invokeai/app/services/workflow_records/default_workflows/Text to Image - SDXL.json

@@ -2,7 +2,7 @@
   "name": "Text to Image - SDXL",
   "author": "InvokeAI",
   "description": "Sample text to image workflow for SDXL",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "text2image, SDXL, default",
   "notes": "",
@@ -29,10 +29,271 @@
     }
   ],
   "meta": {
-    "category": "default",
-    "version": "3.0.0"
+    "version": "3.0.0",
+    "category": "default"
   },
   "nodes": [
+    {
+      "id": "0093692f-9cf4-454d-a5b8-62f0e3eb3bb8",
+      "type": "invocation",
+      "data": {
+        "id": "0093692f-9cf4-454d-a5b8-62f0e3eb3bb8",
+        "version": "1.0.3",
+        "label": "",
+        "notes": "",
+        "type": "vae_loader",
+        "inputs": {
+          "vae_model": {
+            "name": "vae_model",
+            "label": "VAE (use the FP16 model)",
+            "value": {
+              "key": "f20f9e5c-1bce-4c46-a84d-34ebfa7df069",
+              "hash": "blake3:9705ab1c31fa96b308734214fb7571a958621c7a9247eed82b7d277145f8d9fa",
+              "name": "sdxl-vae-fp16-fix",
+              "base": "sdxl",
+              "type": "vae"
+            }
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 375,
+        "y": -225
+      }
+    },
+    {
+      "id": "63e91020-83b2-4f35-b174-ad9692aabb48",
+      "type": "invocation",
+      "data": {
+        "id": "63e91020-83b2-4f35-b174-ad9692aabb48",
+        "version": "1.3.0",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "l2i",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "latents": {
+            "name": "latents",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
+            "label": "",
+            "value": false
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": false
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": false,
+        "useCache": false
+      },
+      "position": {
+        "x": 1475,
+        "y": -500
+      }
+    },
+    {
+      "id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
+      "type": "invocation",
+      "data": {
+        "id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
+        "version": "1.2.0",
+        "nodePack": "invokeai",
+        "label": "SDXL Positive Compel Prompt",
+        "notes": "",
+        "type": "sdxl_compel_prompt",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "Positive Prompt",
+            "value": ""
+          },
+          "style": {
+            "name": "style",
+            "label": "Positive Style",
+            "value": ""
+          },
+          "original_width": {
+            "name": "original_width",
+            "label": "",
+            "value": 1024
+          },
+          "original_height": {
+            "name": "original_height",
+            "label": "",
+            "value": 1024
+          },
+          "crop_top": {
+            "name": "crop_top",
+            "label": "",
+            "value": 0
+          },
+          "crop_left": {
+            "name": "crop_left",
+            "label": "",
+            "value": 0
+          },
+          "target_width": {
+            "name": "target_width",
+            "label": "",
+            "value": 1024
+          },
+          "target_height": {
+            "name": "target_height",
+            "label": "",
+            "value": 1024
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "clip2": {
+            "name": "clip2",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": false,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 750,
+        "y": -175
+      }
+    },
+    {
+      "id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
+      "type": "invocation",
+      "data": {
+        "id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
+        "version": "1.0.3",
+        "nodePack": "invokeai",
+        "label": "",
+        "notes": "",
+        "type": "sdxl_model_loader",
+        "inputs": {
+          "model": {
+            "name": "model",
+            "label": "",
+            "value": {
+              "key": "4a63b226-e8ff-4da4-854e-0b9f04b562ba",
+              "hash": "blake3:d279309ea6e5ee6e8fd52504275865cc280dac71cbf528c5b07c98b888bddaba",
+              "name": "dreamshaper-xl-v2-turbo",
+              "base": "sdxl",
+              "type": "main"
+            }
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 375,
+        "y": -500
+      }
+    },
+    {
+      "id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
+      "type": "invocation",
+      "data": {
+        "id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
+        "version": "1.2.0",
+        "nodePack": "invokeai",
+        "label": "SDXL Negative Compel Prompt",
+        "notes": "",
+        "type": "sdxl_compel_prompt",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "Negative Prompt",
+            "value": ""
+          },
+          "style": {
+            "name": "style",
+            "label": "Negative Style",
+            "value": ""
+          },
+          "original_width": {
+            "name": "original_width",
+            "label": "",
+            "value": 1024
+          },
+          "original_height": {
+            "name": "original_height",
+            "label": "",
+            "value": 1024
+          },
+          "crop_top": {
+            "name": "crop_top",
+            "label": "",
+            "value": 0
+          },
+          "crop_left": {
+            "name": "crop_left",
+            "label": "",
+            "value": 0
+          },
+          "target_width": {
+            "name": "target_width",
+            "label": "",
+            "value": 1024
+          },
+          "target_height": {
+            "name": "target_height",
+            "label": "",
+            "value": 1024
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "clip2": {
+            "name": "clip2",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": false,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 750,
+        "y": 200
+      }
+    },
     {
       "id": "3774ec24-a69e-4254-864c-097d07a6256f",
       "type": "invocation",
@@ -88,75 +349,6 @@
         "y": -125
       }
     },
-    {
-      "id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-      "type": "invocation",
-      "data": {
-        "id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "SDXL Negative Compel Prompt",
-        "notes": "",
-        "type": "sdxl_compel_prompt",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "Negative Prompt",
-            "value": ""
-          },
-          "style": {
-            "name": "style",
-            "label": "Negative Style",
-            "value": ""
-          },
-          "original_width": {
-            "name": "original_width",
-            "label": "",
-            "value": 1024
-          },
-          "original_height": {
-            "name": "original_height",
-            "label": "",
-            "value": 1024
-          },
-          "crop_top": {
-            "name": "crop_top",
-            "label": "",
-            "value": 0
-          },
-          "crop_left": {
-            "name": "crop_left",
-            "label": "",
-            "value": 0
-          },
-          "target_width": {
-            "name": "target_width",
-            "label": "",
-            "value": 1024
-          },
-          "target_height": {
-            "name": "target_height",
-            "label": "",
-            "value": 1024
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          },
-          "clip2": {
-            "name": "clip2",
-            "label": ""
-          }
-        },
-        "isOpen": false,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 750,
-        "y": 200
-      }
-    },
     {
       "id": "55705012-79b9-4aac-9f26-c0b10309785b",
       "type": "invocation",
@@ -229,154 +421,6 @@
         "y": -50
       }
     },
-    {
-      "id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "type": "invocation",
-      "data": {
-        "id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-        "version": "1.0.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "sdxl_model_loader",
-        "inputs": {
-          "model": {
-            "name": "model",
-            "label": "",
-            "value": {
-              "key": "4a63b226-e8ff-4da4-854e-0b9f04b562ba",
-              "hash": "blake3:d279309ea6e5ee6e8fd52504275865cc280dac71cbf528c5b07c98b888bddaba",
-              "name": "dreamshaper-xl-v2-turbo",
-              "base": "sdxl",
-              "type": "main"
-            }
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 375,
-        "y": -500
-      }
-    },
-    {
-      "id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-      "type": "invocation",
-      "data": {
-        "id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-        "version": "1.1.1",
-        "nodePack": "invokeai",
-        "label": "SDXL Positive Compel Prompt",
-        "notes": "",
-        "type": "sdxl_compel_prompt",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "Positive Prompt",
-            "value": ""
-          },
-          "style": {
-            "name": "style",
-            "label": "Positive Style",
-            "value": ""
-          },
-          "original_width": {
-            "name": "original_width",
-            "label": "",
-            "value": 1024
-          },
-          "original_height": {
-            "name": "original_height",
-            "label": "",
-            "value": 1024
-          },
-          "crop_top": {
-            "name": "crop_top",
-            "label": "",
-            "value": 0
-          },
-          "crop_left": {
-            "name": "crop_left",
-            "label": "",
-            "value": 0
-          },
-          "target_width": {
-            "name": "target_width",
-            "label": "",
-            "value": 1024
-          },
-          "target_height": {
-            "name": "target_height",
-            "label": "",
-            "value": 1024
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          },
-          "clip2": {
-            "name": "clip2",
-            "label": ""
-          }
-        },
-        "isOpen": false,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 750,
-        "y": -175
-      }
-    },
-    {
-      "id": "63e91020-83b2-4f35-b174-ad9692aabb48",
-      "type": "invocation",
-      "data": {
-        "id": "63e91020-83b2-4f35-b174-ad9692aabb48",
-        "version": "1.2.2",
-        "nodePack": "invokeai",
-        "label": "",
-        "notes": "",
-        "type": "l2i",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "latents": {
-            "name": "latents",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": false
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": false,
-        "useCache": false
-      },
-      "position": {
-        "x": 1475,
-        "y": -500
-      }
-    },
     {
       "id": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
       "type": "invocation",
@@ -464,37 +508,6 @@
         "y": -500
       }
     },
-    {
-      "id": "0093692f-9cf4-454d-a5b8-62f0e3eb3bb8",
-      "type": "invocation",
-      "data": {
-        "id": "0093692f-9cf4-454d-a5b8-62f0e3eb3bb8",
-        "version": "1.0.2",
-        "label": "",
-        "notes": "",
-        "type": "vae_loader",
-        "inputs": {
-          "vae_model": {
-            "name": "vae_model",
-            "label": "VAE (use the FP16 model)",
-            "value": {
-              "key": "f20f9e5c-1bce-4c46-a84d-34ebfa7df069",
-              "hash": "blake3:9705ab1c31fa96b308734214fb7571a958621c7a9247eed82b7d277145f8d9fa",
-              "name": "sdxl-vae-fp16-fix",
-              "base": "sdxl",
-              "type": "vae"
-            }
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 375,
-        "y": -225
-      }
-    },
     {
       "id": "ade2c0d3-0384-4157-b39b-29ce429cfa15",
       "type": "invocation",

invokeai/app/services/workflow_records/default_workflows/Text to Image with LoRA.json

@@ -2,7 +2,7 @@
   "name": "Text to Image with LoRA",
   "author": "InvokeAI",
   "description": "Simple text to image workflow with a LoRA",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "text to image, lora, default",
   "notes": "",
@@ -37,28 +37,83 @@
     }
   ],
   "meta": {
-    "category": "default",
-    "version": "3.0.0"
+    "version": "3.0.0",
+    "category": "default"
   },
   "nodes": [
     {
-      "id": "85b77bb2-c67a-416a-b3e8-291abe746c44",
+      "id": "a9683c0a-6b1f-4a5e-8187-c57e764b3400",
       "type": "invocation",
       "data": {
-        "id": "85b77bb2-c67a-416a-b3e8-291abe746c44",
-        "version": "1.1.1",
+        "id": "a9683c0a-6b1f-4a5e-8187-c57e764b3400",
+        "version": "1.3.0",
+        "label": "",
+        "notes": "",
+        "type": "l2i",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "latents": {
+            "name": "latents",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
+            "label": "",
+            "value": false
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": false
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": false,
+        "useCache": true
+      },
+      "position": {
+        "x": 4450,
+        "y": -550
+      }
+    },
+    {
+      "id": "c3fa6872-2599-4a82-a596-b3446a66cf8b",
+      "type": "invocation",
+      "data": {
+        "id": "c3fa6872-2599-4a82-a596-b3446a66cf8b",
+        "version": "1.2.0",
         "label": "",
         "notes": "",
         "type": "compel",
         "inputs": {
           "prompt": {
             "name": "prompt",
-            "label": "Negative Prompt",
-            "value": ""
+            "label": "Positive Prompt",
+            "value": "super cute tiger cub"
           },
           "clip": {
             "name": "clip",
             "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
           }
         },
         "isOpen": true,
@@ -67,31 +122,7 @@
       },
       "position": {
         "x": 3425,
-        "y": -300
-      }
-    },
-    {
-      "id": "24e9d7ed-4836-4ec4-8f9e-e747721f9818",
-      "type": "invocation",
-      "data": {
-        "id": "24e9d7ed-4836-4ec4-8f9e-e747721f9818",
-        "version": "1.0.2",
-        "label": "",
-        "notes": "",
-        "type": "main_model_loader",
-        "inputs": {
-          "model": {
-            "name": "model",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": 2500,
-        "y": -600
+        "y": -575
       }
     },
     {
@@ -99,7 +130,7 @@
       "type": "invocation",
       "data": {
         "id": "c41e705b-f2e3-4d1a-83c4-e34bb9344966",
-        "version": "1.0.2",
+        "version": "1.0.3",
         "label": "",
         "notes": "",
         "type": "lora_loader",
@@ -132,23 +163,51 @@
       }
     },
     {
-      "id": "c3fa6872-2599-4a82-a596-b3446a66cf8b",
+      "id": "24e9d7ed-4836-4ec4-8f9e-e747721f9818",
       "type": "invocation",
       "data": {
-        "id": "c3fa6872-2599-4a82-a596-b3446a66cf8b",
-        "version": "1.1.1",
+        "id": "24e9d7ed-4836-4ec4-8f9e-e747721f9818",
+        "version": "1.0.3",
+        "label": "",
+        "notes": "",
+        "type": "main_model_loader",
+        "inputs": {
+          "model": {
+            "name": "model",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": 2500,
+        "y": -600
+      }
+    },
+    {
+      "id": "85b77bb2-c67a-416a-b3e8-291abe746c44",
+      "type": "invocation",
+      "data": {
+        "id": "85b77bb2-c67a-416a-b3e8-291abe746c44",
+        "version": "1.2.0",
         "label": "",
         "notes": "",
         "type": "compel",
         "inputs": {
           "prompt": {
             "name": "prompt",
-            "label": "Positive Prompt",
-            "value": "super cute tiger cub"
+            "label": "Negative Prompt",
+            "value": ""
           },
           "clip": {
             "name": "clip",
             "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
           }
         },
         "isOpen": true,
@@ -157,7 +216,7 @@
       },
       "position": {
         "x": 3425,
-        "y": -575
+        "y": -300
       }
     },
     {
@@ -315,52 +374,6 @@
         "x": 3425,
         "y": 0
       }
-    },
-    {
-      "id": "a9683c0a-6b1f-4a5e-8187-c57e764b3400",
-      "type": "invocation",
-      "data": {
-        "id": "a9683c0a-6b1f-4a5e-8187-c57e764b3400",
-        "version": "1.2.2",
-        "label": "",
-        "notes": "",
-        "type": "l2i",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "latents": {
-            "name": "latents",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": false
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": false,
-        "useCache": true
-      },
-      "position": {
-        "x": 4450,
-        "y": -550
-      }
     }
   ],
   "edges": [

invokeai/app/services/workflow_records/default_workflows/Tiled Upscaling (Beta).json

@@ -2,7 +2,7 @@
   "name": "Tiled Upscaling (Beta)",
   "author": "Invoke",
   "description": "A workflow to upscale an input image with tiled upscaling. ",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "contact": "invoke@invoke.ai",
   "tags": "tiled, upscaling, sd1.5",
   "notes": "",
@@ -41,10 +41,318 @@
     }
   ],
   "meta": {
-    "category": "default",
-    "version": "3.0.0"
+    "version": "3.0.0",
+    "category": "default"
   },
   "nodes": [
+    {
+      "id": "2ff466b8-5e2a-4d8f-923a-a3884c7ecbc5",
+      "type": "invocation",
+      "data": {
+        "id": "2ff466b8-5e2a-4d8f-923a-a3884c7ecbc5",
+        "version": "1.0.3",
+        "label": "",
+        "notes": "",
+        "type": "main_model_loader",
+        "inputs": {
+          "model": {
+            "name": "model",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": -4514.466823162653,
+        "y": -1235.7908800002283
+      }
+    },
+    {
+      "id": "287f134f-da8d-41d1-884e-5940e8f7b816",
+      "type": "invocation",
+      "data": {
+        "id": "287f134f-da8d-41d1-884e-5940e8f7b816",
+        "version": "1.4.1",
+        "label": "",
+        "notes": "",
+        "type": "ip_adapter",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "ip_adapter_model": {
+            "name": "ip_adapter_model",
+            "label": "IP-Adapter Model (select ip_adapter_sd15)",
+            "value": {
+              "key": "1cc210bb-4d0a-4312-b36c-b5d46c43768e",
+              "hash": "blake3:3d669dffa7471b357b4df088b99ffb6bf4d4383d5e0ef1de5ec1c89728a3d5a5",
+              "name": "ip_adapter_sd15",
+              "base": "sd-1",
+              "type": "ip_adapter"
+            }
+          },
+          "clip_vision_model": {
+            "name": "clip_vision_model",
+            "label": "",
+            "value": "ViT-H"
+          },
+          "weight": {
+            "name": "weight",
+            "label": "",
+            "value": 0.2
+          },
+          "method": {
+            "name": "method",
+            "label": "",
+            "value": "full"
+          },
+          "begin_step_percent": {
+            "name": "begin_step_percent",
+            "label": "",
+            "value": 0
+          },
+          "end_step_percent": {
+            "name": "end_step_percent",
+            "label": "",
+            "value": 1
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": -2855.8555540799207,
+        "y": -183.58854843775742
+      }
+    },
+    {
+      "id": "b76fe66f-7884-43ad-b72c-fadc81d7a73c",
+      "type": "invocation",
+      "data": {
+        "id": "b76fe66f-7884-43ad-b72c-fadc81d7a73c",
+        "version": "1.3.0",
+        "label": "",
+        "notes": "",
+        "type": "l2i",
+        "inputs": {
+          "board": {
+            "name": "board",
+            "label": ""
+          },
+          "metadata": {
+            "name": "metadata",
+            "label": ""
+          },
+          "latents": {
+            "name": "latents",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
+            "label": "",
+            "value": false
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": false
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": -1999.770193862987,
+        "y": -1075
+      }
+    },
+    {
+      "id": "d334f2da-016a-4524-9911-bdab85546888",
+      "type": "invocation",
+      "data": {
+        "id": "d334f2da-016a-4524-9911-bdab85546888",
+        "version": "1.1.2",
+        "label": "",
+        "notes": "",
+        "type": "controlnet",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "control_model": {
+            "name": "control_model",
+            "label": "Control Model (select contro_v11f1e_sd15_tile)",
+            "value": {
+              "key": "773843c8-db1f-4502-8f65-59782efa7960",
+              "hash": "blake3:f0812e13758f91baf4e54b7dbb707b70642937d3b2098cd2b94cc36d3eba308e",
+              "name": "control_v11f1e_sd15_tile",
+              "base": "sd-1",
+              "type": "controlnet"
+            }
+          },
+          "control_weight": {
+            "name": "control_weight",
+            "label": "",
+            "value": 1
+          },
+          "begin_step_percent": {
+            "name": "begin_step_percent",
+            "label": "",
+            "value": 0
+          },
+          "end_step_percent": {
+            "name": "end_step_percent",
+            "label": "Structural Control",
+            "value": 1
+          },
+          "control_mode": {
+            "name": "control_mode",
+            "label": "",
+            "value": "more_control"
+          },
+          "resize_mode": {
+            "name": "resize_mode",
+            "label": "",
+            "value": "just_resize"
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": -2481.9569385477016,
+        "y": -181.06590482739782
+      }
+    },
+    {
+      "id": "338b883c-3728-4f18-b3a6-6e7190c2f850",
+      "type": "invocation",
+      "data": {
+        "id": "338b883c-3728-4f18-b3a6-6e7190c2f850",
+        "version": "1.1.0",
+        "label": "",
+        "notes": "",
+        "type": "i2l",
+        "inputs": {
+          "image": {
+            "name": "image",
+            "label": ""
+          },
+          "vae": {
+            "name": "vae",
+            "label": ""
+          },
+          "tiled": {
+            "name": "tiled",
+            "label": "",
+            "value": false
+          },
+          "tile_size": {
+            "name": "tile_size",
+            "label": "",
+            "value": 0
+          },
+          "fp32": {
+            "name": "fp32",
+            "label": "",
+            "value": false
+          }
+        },
+        "isOpen": false,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": -2908.4791167517287,
+        "y": -408.87504820159086
+      }
+    },
+    {
+      "id": "947c3f88-0305-4695-8355-df4abac64b1c",
+      "type": "invocation",
+      "data": {
+        "id": "947c3f88-0305-4695-8355-df4abac64b1c",
+        "version": "1.2.0",
+        "label": "",
+        "notes": "",
+        "type": "compel",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "",
+            "value": ""
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": -4014.4136788915944,
+        "y": -968.5677253775948
+      }
+    },
+    {
+      "id": "9b2d8c58-ce8f-4162-a5a1-48de854040d6",
+      "type": "invocation",
+      "data": {
+        "id": "9b2d8c58-ce8f-4162-a5a1-48de854040d6",
+        "version": "1.2.0",
+        "label": "",
+        "notes": "",
+        "type": "compel",
+        "inputs": {
+          "prompt": {
+            "name": "prompt",
+            "label": "Positive Prompt",
+            "value": ""
+          },
+          "clip": {
+            "name": "clip",
+            "label": ""
+          },
+          "mask": {
+            "name": "mask",
+            "label": ""
+          }
+        },
+        "isOpen": true,
+        "isIntermediate": true,
+        "useCache": true
+      },
+      "position": {
+        "x": -4014.4136788915944,
+        "y": -1243.5677253775948
+      }
+    },
     {
       "id": "b875cae6-d8a3-4fdc-b969-4d53cbd03f9a",
       "type": "invocation",
@@ -181,64 +489,6 @@
         "y": 3.422855503409039
       }
     },
-    {
-      "id": "9b2d8c58-ce8f-4162-a5a1-48de854040d6",
-      "type": "invocation",
-      "data": {
-        "id": "9b2d8c58-ce8f-4162-a5a1-48de854040d6",
-        "version": "1.1.1",
-        "label": "",
-        "notes": "",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "Positive Prompt",
-            "value": ""
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": -4014.4136788915944,
-        "y": -1243.5677253775948
-      }
-    },
-    {
-      "id": "947c3f88-0305-4695-8355-df4abac64b1c",
-      "type": "invocation",
-      "data": {
-        "id": "947c3f88-0305-4695-8355-df4abac64b1c",
-        "version": "1.1.1",
-        "label": "",
-        "notes": "",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "name": "prompt",
-            "label": "",
-            "value": ""
-          },
-          "clip": {
-            "name": "clip",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": -4014.4136788915944,
-        "y": -968.5677253775948
-      }
-    },
     {
       "id": "b3513fed-ed42-408d-b382-128fdb0de523",
       "type": "invocation",
@@ -379,104 +629,6 @@
         "y": -29.08699277598673
       }
     },
-    {
-      "id": "338b883c-3728-4f18-b3a6-6e7190c2f850",
-      "type": "invocation",
-      "data": {
-        "id": "338b883c-3728-4f18-b3a6-6e7190c2f850",
-        "version": "1.0.2",
-        "label": "",
-        "notes": "",
-        "type": "i2l",
-        "inputs": {
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": false
-          }
-        },
-        "isOpen": false,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": -2908.4791167517287,
-        "y": -408.87504820159086
-      }
-    },
-    {
-      "id": "d334f2da-016a-4524-9911-bdab85546888",
-      "type": "invocation",
-      "data": {
-        "id": "d334f2da-016a-4524-9911-bdab85546888",
-        "version": "1.1.1",
-        "label": "",
-        "notes": "",
-        "type": "controlnet",
-        "inputs": {
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "control_model": {
-            "name": "control_model",
-            "label": "Control Model (select contro_v11f1e_sd15_tile)",
-            "value": {
-              "key": "773843c8-db1f-4502-8f65-59782efa7960",
-              "hash": "blake3:f0812e13758f91baf4e54b7dbb707b70642937d3b2098cd2b94cc36d3eba308e",
-              "name": "control_v11f1e_sd15_tile",
-              "base": "sd-1",
-              "type": "controlnet"
-            }
-          },
-          "control_weight": {
-            "name": "control_weight",
-            "label": "",
-            "value": 1
-          },
-          "begin_step_percent": {
-            "name": "begin_step_percent",
-            "label": "",
-            "value": 0
-          },
-          "end_step_percent": {
-            "name": "end_step_percent",
-            "label": "Structural Control",
-            "value": 1
-          },
-          "control_mode": {
-            "name": "control_mode",
-            "label": "",
-            "value": "more_control"
-          },
-          "resize_mode": {
-            "name": "resize_mode",
-            "label": "",
-            "value": "just_resize"
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": -2481.9569385477016,
-        "y": -181.06590482739782
-      }
-    },
     {
       "id": "1011539e-85de-4e02-a003-0b22358491b8",
       "type": "invocation",
@@ -563,52 +715,6 @@
         "y": -1006.415909408244
       }
     },
-    {
-      "id": "b76fe66f-7884-43ad-b72c-fadc81d7a73c",
-      "type": "invocation",
-      "data": {
-        "id": "b76fe66f-7884-43ad-b72c-fadc81d7a73c",
-        "version": "1.2.2",
-        "label": "",
-        "notes": "",
-        "type": "l2i",
-        "inputs": {
-          "board": {
-            "name": "board",
-            "label": ""
-          },
-          "metadata": {
-            "name": "metadata",
-            "label": ""
-          },
-          "latents": {
-            "name": "latents",
-            "label": ""
-          },
-          "vae": {
-            "name": "vae",
-            "label": ""
-          },
-          "tiled": {
-            "name": "tiled",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "name": "fp32",
-            "label": "",
-            "value": false
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": -1999.770193862987,
-        "y": -1075
-      }
-    },
     {
       "id": "ab6f5dda-4b60-4ddf-99f2-f61fb5937527",
       "type": "invocation",
@@ -779,56 +885,6 @@
         "y": -78.2819050861178
       }
     },
-    {
-      "id": "287f134f-da8d-41d1-884e-5940e8f7b816",
-      "type": "invocation",
-      "data": {
-        "id": "287f134f-da8d-41d1-884e-5940e8f7b816",
-        "version": "1.2.2",
-        "label": "",
-        "notes": "",
-        "type": "ip_adapter",
-        "inputs": {
-          "image": {
-            "name": "image",
-            "label": ""
-          },
-          "ip_adapter_model": {
-            "name": "ip_adapter_model",
-            "label": "IP-Adapter Model (select ip_adapter_sd15)",
-            "value": {
-              "key": "1cc210bb-4d0a-4312-b36c-b5d46c43768e",
-              "hash": "blake3:3d669dffa7471b357b4df088b99ffb6bf4d4383d5e0ef1de5ec1c89728a3d5a5",
-              "name": "ip_adapter_sd15",
-              "base": "sd-1",
-              "type": "ip_adapter"
-            }
-          },
-          "weight": {
-            "name": "weight",
-            "label": "",
-            "value": 0.2
-          },
-          "begin_step_percent": {
-            "name": "begin_step_percent",
-            "label": "",
-            "value": 0
-          },
-          "end_step_percent": {
-            "name": "end_step_percent",
-            "label": "",
-            "value": 1
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": -2855.8555540799207,
-        "y": -183.58854843775742
-      }
-    },
     {
       "id": "1f86c8bf-06f9-4e28-abee-02f46f445ac4",
       "type": "invocation",
@@ -899,30 +955,6 @@
         "y": -41.810810454906914
       }
     },
-    {
-      "id": "2ff466b8-5e2a-4d8f-923a-a3884c7ecbc5",
-      "type": "invocation",
-      "data": {
-        "id": "2ff466b8-5e2a-4d8f-923a-a3884c7ecbc5",
-        "version": "1.0.2",
-        "label": "",
-        "notes": "",
-        "type": "main_model_loader",
-        "inputs": {
-          "model": {
-            "name": "model",
-            "label": ""
-          }
-        },
-        "isOpen": true,
-        "isIntermediate": true,
-        "useCache": true
-      },
-      "position": {
-        "x": -4514.466823162653,
-        "y": -1235.7908800002283
-      }
-    },
     {
       "id": "f5d9bf3b-2646-4b17-9894-20fd2b4218ea",
       "type": "invocation",

invokeai/app/util/custom_openapi.py

@@ -81,7 +81,7 @@ def get_openapi_func(
         # Add the output map to the schema
         openapi_schema["components"]["schemas"]["InvocationOutputMap"] = {
             "type": "object",
-            "properties": invocation_output_map_properties,
+            "properties": dict(sorted(invocation_output_map_properties.items())),
             "required": invocation_output_map_required,
         }
 

invokeai/backend/image_util/depth_anything/__init__.py

@@ -1,90 +0,0 @@
-from pathlib import Path
-from typing import Literal
-
-import cv2
-import numpy as np
-import torch
-import torch.nn.functional as F
-from einops import repeat
-from PIL import Image
-from torchvision.transforms import Compose
-
-from invokeai.app.services.config.config_default import get_config
-from invokeai.backend.image_util.depth_anything.model.dpt import DPT_DINOv2
-from invokeai.backend.image_util.depth_anything.utilities.util import NormalizeImage, PrepareForNet, Resize
-from invokeai.backend.util.logging import InvokeAILogger
-
-config = get_config()
-logger = InvokeAILogger.get_logger(config=config)
-
-DEPTH_ANYTHING_MODELS = {
-    "large": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitl14.pth?download=true",
-    "base": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitb14.pth?download=true",
-    "small": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vits14.pth?download=true",
-}
-
-
-transform = Compose(
-    [
-        Resize(
-            width=518,
-            height=518,
-            resize_target=False,
-            keep_aspect_ratio=True,
-            ensure_multiple_of=14,
-            resize_method="lower_bound",
-            image_interpolation_method=cv2.INTER_CUBIC,
-        ),
-        NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-        PrepareForNet(),
-    ]
-)
-
-
-class DepthAnythingDetector:
-    def __init__(self, model: DPT_DINOv2, device: torch.device) -> None:
-        self.model = model
-        self.device = device
-
-    @staticmethod
-    def load_model(
-        model_path: Path, device: torch.device, model_size: Literal["large", "base", "small"] = "small"
-    ) -> DPT_DINOv2:
-        match model_size:
-            case "small":
-                model = DPT_DINOv2(encoder="vits", features=64, out_channels=[48, 96, 192, 384])
-            case "base":
-                model = DPT_DINOv2(encoder="vitb", features=128, out_channels=[96, 192, 384, 768])
-            case "large":
-                model = DPT_DINOv2(encoder="vitl", features=256, out_channels=[256, 512, 1024, 1024])
-
-        model.load_state_dict(torch.load(model_path.as_posix(), map_location="cpu"))
-        model.eval()
-
-        model.to(device)
-        return model
-
-    def __call__(self, image: Image.Image, resolution: int = 512) -> Image.Image:
-        if not self.model:
-            logger.warn("DepthAnything model was not loaded. Returning original image")
-            return image
-
-        np_image = np.array(image, dtype=np.uint8)
-        np_image = np_image[:, :, ::-1] / 255.0
-
-        image_height, image_width = np_image.shape[:2]
-        np_image = transform({"image": np_image})["image"]
-        tensor_image = torch.from_numpy(np_image).unsqueeze(0).to(self.device)
-
-        with torch.no_grad():
-            depth = self.model(tensor_image)
-            depth = F.interpolate(depth[None], (image_height, image_width), mode="bilinear", align_corners=False)[0, 0]
-            depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
-
-        depth_map = repeat(depth, "h w -> h w 3").cpu().numpy().astype(np.uint8)
-        depth_map = Image.fromarray(depth_map)
-
-        new_height = int(image_height * (resolution / image_width))
-        depth_map = depth_map.resize((resolution, new_height))
-
-        return depth_map

invokeai/backend/image_util/depth_anything/depth_anything_pipeline.py

@@ -0,0 +1,31 @@
+from typing import Optional
+
+import torch
+from PIL import Image
+from transformers.pipelines import DepthEstimationPipeline
+
+from invokeai.backend.raw_model import RawModel
+
+
+class DepthAnythingPipeline(RawModel):
+    """Custom wrapper for the Depth Estimation pipeline from transformers adding compatibility
+    for Invoke's Model Management System"""
+
+    def __init__(self, pipeline: DepthEstimationPipeline) -> None:
+        self._pipeline = pipeline
+
+    def generate_depth(self, image: Image.Image) -> Image.Image:
+        depth_map = self._pipeline(image)["depth"]
+        assert isinstance(depth_map, Image.Image)
+        return depth_map
+
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None):
+        if device is not None and device.type not in {"cpu", "cuda"}:
+            device = None
+        self._pipeline.model.to(device=device, dtype=dtype)
+        self._pipeline.device = self._pipeline.model.device
+
+    def calc_size(self) -> int:
+        from invokeai.backend.model_manager.load.model_util import calc_module_size
+
+        return calc_module_size(self._pipeline.model)

invokeai/backend/image_util/depth_anything/model/blocks.py

@@ -1,145 +0,0 @@
-import torch.nn as nn
-
-
-def _make_scratch(in_shape, out_shape, groups=1, expand=False):
-    scratch = nn.Module()
-
-    out_shape1 = out_shape
-    out_shape2 = out_shape
-    out_shape3 = out_shape
-    if len(in_shape) >= 4:
-        out_shape4 = out_shape
-
-    if expand:
-        out_shape1 = out_shape
-        out_shape2 = out_shape * 2
-        out_shape3 = out_shape * 4
-        if len(in_shape) >= 4:
-            out_shape4 = out_shape * 8
-
-    scratch.layer1_rn = nn.Conv2d(
-        in_shape[0], out_shape1, kernel_size=3, stride=1, padding=1, bias=False, groups=groups
-    )
-    scratch.layer2_rn = nn.Conv2d(
-        in_shape[1], out_shape2, kernel_size=3, stride=1, padding=1, bias=False, groups=groups
-    )
-    scratch.layer3_rn = nn.Conv2d(
-        in_shape[2], out_shape3, kernel_size=3, stride=1, padding=1, bias=False, groups=groups
-    )
-    if len(in_shape) >= 4:
-        scratch.layer4_rn = nn.Conv2d(
-            in_shape[3], out_shape4, kernel_size=3, stride=1, padding=1, bias=False, groups=groups
-        )
-
-    return scratch
-
-
-class ResidualConvUnit(nn.Module):
-    """Residual convolution module."""
-
-    def __init__(self, features, activation, bn):
-        """Init.
-
-        Args:
-            features (int): number of features
-        """
-        super().__init__()
-
-        self.bn = bn
-
-        self.groups = 1
-
-        self.conv1 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups)
-
-        self.conv2 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups)
-
-        if self.bn:
-            self.bn1 = nn.BatchNorm2d(features)
-            self.bn2 = nn.BatchNorm2d(features)
-
-        self.activation = activation
-
-        self.skip_add = nn.quantized.FloatFunctional()
-
-    def forward(self, x):
-        """Forward pass.
-
-        Args:
-            x (tensor): input
-
-        Returns:
-            tensor: output
-        """
-
-        out = self.activation(x)
-        out = self.conv1(out)
-        if self.bn:
-            out = self.bn1(out)
-
-        out = self.activation(out)
-        out = self.conv2(out)
-        if self.bn:
-            out = self.bn2(out)
-
-        if self.groups > 1:
-            out = self.conv_merge(out)
-
-        return self.skip_add.add(out, x)
-
-
-class FeatureFusionBlock(nn.Module):
-    """Feature fusion block."""
-
-    def __init__(self, features, activation, deconv=False, bn=False, expand=False, align_corners=True, size=None):
-        """Init.
-
-        Args:
-            features (int): number of features
-        """
-        super(FeatureFusionBlock, self).__init__()
-
-        self.deconv = deconv
-        self.align_corners = align_corners
-
-        self.groups = 1
-
-        self.expand = expand
-        out_features = features
-        if self.expand:
-            out_features = features // 2
-
-        self.out_conv = nn.Conv2d(features, out_features, kernel_size=1, stride=1, padding=0, bias=True, groups=1)
-
-        self.resConfUnit1 = ResidualConvUnit(features, activation, bn)
-        self.resConfUnit2 = ResidualConvUnit(features, activation, bn)
-
-        self.skip_add = nn.quantized.FloatFunctional()
-
-        self.size = size
-
-    def forward(self, *xs, size=None):
-        """Forward pass.
-
-        Returns:
-            tensor: output
-        """
-        output = xs[0]
-
-        if len(xs) == 2:
-            res = self.resConfUnit1(xs[1])
-            output = self.skip_add.add(output, res)
-
-        output = self.resConfUnit2(output)
-
-        if (size is None) and (self.size is None):
-            modifier = {"scale_factor": 2}
-        elif size is None:
-            modifier = {"size": self.size}
-        else:
-            modifier = {"size": size}
-
-        output = nn.functional.interpolate(output, **modifier, mode="bilinear", align_corners=self.align_corners)
-
-        output = self.out_conv(output)
-
-        return output

invokeai/backend/image_util/depth_anything/model/dpt.py

@@ -1,183 +0,0 @@
-from pathlib import Path
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-from invokeai.backend.image_util.depth_anything.model.blocks import FeatureFusionBlock, _make_scratch
-
-torchhub_path = Path(__file__).parent.parent / "torchhub"
-
-
-def _make_fusion_block(features, use_bn, size=None):
-    return FeatureFusionBlock(
-        features,
-        nn.ReLU(False),
-        deconv=False,
-        bn=use_bn,
-        expand=False,
-        align_corners=True,
-        size=size,
-    )
-
-
-class DPTHead(nn.Module):
-    def __init__(self, nclass, in_channels, features, out_channels, use_bn=False, use_clstoken=False):
-        super(DPTHead, self).__init__()
-
-        self.nclass = nclass
-        self.use_clstoken = use_clstoken
-
-        self.projects = nn.ModuleList(
-            [
-                nn.Conv2d(
-                    in_channels=in_channels,
-                    out_channels=out_channel,
-                    kernel_size=1,
-                    stride=1,
-                    padding=0,
-                )
-                for out_channel in out_channels
-            ]
-        )
-
-        self.resize_layers = nn.ModuleList(
-            [
-                nn.ConvTranspose2d(
-                    in_channels=out_channels[0], out_channels=out_channels[0], kernel_size=4, stride=4, padding=0
-                ),
-                nn.ConvTranspose2d(
-                    in_channels=out_channels[1], out_channels=out_channels[1], kernel_size=2, stride=2, padding=0
-                ),
-                nn.Identity(),
-                nn.Conv2d(
-                    in_channels=out_channels[3], out_channels=out_channels[3], kernel_size=3, stride=2, padding=1
-                ),
-            ]
-        )
-
-        if use_clstoken:
-            self.readout_projects = nn.ModuleList()
-            for _ in range(len(self.projects)):
-                self.readout_projects.append(nn.Sequential(nn.Linear(2 * in_channels, in_channels), nn.GELU()))
-
-        self.scratch = _make_scratch(
-            out_channels,
-            features,
-            groups=1,
-            expand=False,
-        )
-
-        self.scratch.stem_transpose = None
-
-        self.scratch.refinenet1 = _make_fusion_block(features, use_bn)
-        self.scratch.refinenet2 = _make_fusion_block(features, use_bn)
-        self.scratch.refinenet3 = _make_fusion_block(features, use_bn)
-        self.scratch.refinenet4 = _make_fusion_block(features, use_bn)
-
-        head_features_1 = features
-        head_features_2 = 32
-
-        if nclass > 1:
-            self.scratch.output_conv = nn.Sequential(
-                nn.Conv2d(head_features_1, head_features_1, kernel_size=3, stride=1, padding=1),
-                nn.ReLU(True),
-                nn.Conv2d(head_features_1, nclass, kernel_size=1, stride=1, padding=0),
-            )
-        else:
-            self.scratch.output_conv1 = nn.Conv2d(
-                head_features_1, head_features_1 // 2, kernel_size=3, stride=1, padding=1
-            )
-
-            self.scratch.output_conv2 = nn.Sequential(
-                nn.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1),
-                nn.ReLU(True),
-                nn.Conv2d(head_features_2, 1, kernel_size=1, stride=1, padding=0),
-                nn.ReLU(True),
-                nn.Identity(),
-            )
-
-    def forward(self, out_features, patch_h, patch_w):
-        out = []
-        for i, x in enumerate(out_features):
-            if self.use_clstoken:
-                x, cls_token = x[0], x[1]
-                readout = cls_token.unsqueeze(1).expand_as(x)
-                x = self.readout_projects[i](torch.cat((x, readout), -1))
-            else:
-                x = x[0]
-
-            x = x.permute(0, 2, 1).reshape((x.shape[0], x.shape[-1], patch_h, patch_w))
-
-            x = self.projects[i](x)
-            x = self.resize_layers[i](x)
-
-            out.append(x)
-
-        layer_1, layer_2, layer_3, layer_4 = out
-
-        layer_1_rn = self.scratch.layer1_rn(layer_1)
-        layer_2_rn = self.scratch.layer2_rn(layer_2)
-        layer_3_rn = self.scratch.layer3_rn(layer_3)
-        layer_4_rn = self.scratch.layer4_rn(layer_4)
-
-        path_4 = self.scratch.refinenet4(layer_4_rn, size=layer_3_rn.shape[2:])
-        path_3 = self.scratch.refinenet3(path_4, layer_3_rn, size=layer_2_rn.shape[2:])
-        path_2 = self.scratch.refinenet2(path_3, layer_2_rn, size=layer_1_rn.shape[2:])
-        path_1 = self.scratch.refinenet1(path_2, layer_1_rn)
-
-        out = self.scratch.output_conv1(path_1)
-        out = F.interpolate(out, (int(patch_h * 14), int(patch_w * 14)), mode="bilinear", align_corners=True)
-        out = self.scratch.output_conv2(out)
-
-        return out
-
-
-class DPT_DINOv2(nn.Module):
-    def __init__(
-        self,
-        features,
-        out_channels,
-        encoder="vitl",
-        use_bn=False,
-        use_clstoken=False,
-    ):
-        super(DPT_DINOv2, self).__init__()
-
-        assert encoder in ["vits", "vitb", "vitl"]
-
-        # # in case the Internet connection is not stable, please load the DINOv2 locally
-        # if use_local:
-        #     self.pretrained = torch.hub.load(
-        #         torchhub_path / "facebookresearch_dinov2_main",
-        #         "dinov2_{:}14".format(encoder),
-        #         source="local",
-        #         pretrained=False,
-        #     )
-        # else:
-        #     self.pretrained = torch.hub.load(
-        #         "facebookresearch/dinov2",
-        #         "dinov2_{:}14".format(encoder),
-        #     )
-
-        self.pretrained = torch.hub.load(
-            "facebookresearch/dinov2",
-            "dinov2_{:}14".format(encoder),
-        )
-
-        dim = self.pretrained.blocks[0].attn.qkv.in_features
-
-        self.depth_head = DPTHead(1, dim, features, out_channels=out_channels, use_bn=use_bn, use_clstoken=use_clstoken)
-
-    def forward(self, x):
-        h, w = x.shape[-2:]
-
-        features = self.pretrained.get_intermediate_layers(x, 4, return_class_token=True)
-
-        patch_h, patch_w = h // 14, w // 14
-
-        depth = self.depth_head(features, patch_h, patch_w)
-        depth = F.interpolate(depth, size=(h, w), mode="bilinear", align_corners=True)
-        depth = F.relu(depth)
-
-        return depth.squeeze(1)

invokeai/backend/image_util/depth_anything/utilities/util.py

@@ -1,227 +0,0 @@
-import math
-
-import cv2
-import numpy as np
-import torch
-import torch.nn.functional as F
-
-
-def apply_min_size(sample, size, image_interpolation_method=cv2.INTER_AREA):
-    """Rezise the sample to ensure the given size. Keeps aspect ratio.
-
-    Args:
-        sample (dict): sample
-        size (tuple): image size
-
-    Returns:
-        tuple: new size
-    """
-    shape = list(sample["disparity"].shape)
-
-    if shape[0] >= size[0] and shape[1] >= size[1]:
-        return sample
-
-    scale = [0, 0]
-    scale[0] = size[0] / shape[0]
-    scale[1] = size[1] / shape[1]
-
-    scale = max(scale)
-
-    shape[0] = math.ceil(scale * shape[0])
-    shape[1] = math.ceil(scale * shape[1])
-
-    # resize
-    sample["image"] = cv2.resize(sample["image"], tuple(shape[::-1]), interpolation=image_interpolation_method)
-
-    sample["disparity"] = cv2.resize(sample["disparity"], tuple(shape[::-1]), interpolation=cv2.INTER_NEAREST)
-    sample["mask"] = cv2.resize(
-        sample["mask"].astype(np.float32),
-        tuple(shape[::-1]),
-        interpolation=cv2.INTER_NEAREST,
-    )
-    sample["mask"] = sample["mask"].astype(bool)
-
-    return tuple(shape)
-
-
-class Resize(object):
-    """Resize sample to given size (width, height)."""
-
-    def __init__(
-        self,
-        width,
-        height,
-        resize_target=True,
-        keep_aspect_ratio=False,
-        ensure_multiple_of=1,
-        resize_method="lower_bound",
-        image_interpolation_method=cv2.INTER_AREA,
-    ):
-        """Init.
-
-        Args:
-            width (int): desired output width
-            height (int): desired output height
-            resize_target (bool, optional):
-                True: Resize the full sample (image, mask, target).
-                False: Resize image only.
-                Defaults to True.
-            keep_aspect_ratio (bool, optional):
-                True: Keep the aspect ratio of the input sample.
-                Output sample might not have the given width and height, and
-                resize behaviour depends on the parameter 'resize_method'.
-                Defaults to False.
-            ensure_multiple_of (int, optional):
-                Output width and height is constrained to be multiple of this parameter.
-                Defaults to 1.
-            resize_method (str, optional):
-                "lower_bound": Output will be at least as large as the given size.
-                "upper_bound": Output will be at max as large as the given size. (Output size might be smaller
-                    than given size.)
-                "minimal": Scale as least as possible.  (Output size might be smaller than given size.)
-                Defaults to "lower_bound".
-        """
-        self.__width = width
-        self.__height = height
-
-        self.__resize_target = resize_target
-        self.__keep_aspect_ratio = keep_aspect_ratio
-        self.__multiple_of = ensure_multiple_of
-        self.__resize_method = resize_method
-        self.__image_interpolation_method = image_interpolation_method
-
-    def constrain_to_multiple_of(self, x, min_val=0, max_val=None):
-        y = (np.round(x / self.__multiple_of) * self.__multiple_of).astype(int)
-
-        if max_val is not None and y > max_val:
-            y = (np.floor(x / self.__multiple_of) * self.__multiple_of).astype(int)
-
-        if y < min_val:
-            y = (np.ceil(x / self.__multiple_of) * self.__multiple_of).astype(int)
-
-        return y
-
-    def get_size(self, width, height):
-        # determine new height and width
-        scale_height = self.__height / height
-        scale_width = self.__width / width
-
-        if self.__keep_aspect_ratio:
-            if self.__resize_method == "lower_bound":
-                # scale such that output size is lower bound
-                if scale_width > scale_height:
-                    # fit width
-                    scale_height = scale_width
-                else:
-                    # fit height
-                    scale_width = scale_height
-            elif self.__resize_method == "upper_bound":
-                # scale such that output size is upper bound
-                if scale_width < scale_height:
-                    # fit width
-                    scale_height = scale_width
-                else:
-                    # fit height
-                    scale_width = scale_height
-            elif self.__resize_method == "minimal":
-                # scale as least as possbile
-                if abs(1 - scale_width) < abs(1 - scale_height):
-                    # fit width
-                    scale_height = scale_width
-                else:
-                    # fit height
-                    scale_width = scale_height
-            else:
-                raise ValueError(f"resize_method {self.__resize_method} not implemented")
-
-        if self.__resize_method == "lower_bound":
-            new_height = self.constrain_to_multiple_of(scale_height * height, min_val=self.__height)
-            new_width = self.constrain_to_multiple_of(scale_width * width, min_val=self.__width)
-        elif self.__resize_method == "upper_bound":
-            new_height = self.constrain_to_multiple_of(scale_height * height, max_val=self.__height)
-            new_width = self.constrain_to_multiple_of(scale_width * width, max_val=self.__width)
-        elif self.__resize_method == "minimal":
-            new_height = self.constrain_to_multiple_of(scale_height * height)
-            new_width = self.constrain_to_multiple_of(scale_width * width)
-        else:
-            raise ValueError(f"resize_method {self.__resize_method} not implemented")
-
-        return (new_width, new_height)
-
-    def __call__(self, sample):
-        width, height = self.get_size(sample["image"].shape[1], sample["image"].shape[0])
-
-        # resize sample
-        sample["image"] = cv2.resize(
-            sample["image"],
-            (width, height),
-            interpolation=self.__image_interpolation_method,
-        )
-
-        if self.__resize_target:
-            if "disparity" in sample:
-                sample["disparity"] = cv2.resize(
-                    sample["disparity"],
-                    (width, height),
-                    interpolation=cv2.INTER_NEAREST,
-                )
-
-            if "depth" in sample:
-                sample["depth"] = cv2.resize(sample["depth"], (width, height), interpolation=cv2.INTER_NEAREST)
-
-            if "semseg_mask" in sample:
-                # sample["semseg_mask"] = cv2.resize(
-                #     sample["semseg_mask"], (width, height), interpolation=cv2.INTER_NEAREST
-                # )
-                sample["semseg_mask"] = F.interpolate(
-                    torch.from_numpy(sample["semseg_mask"]).float()[None, None, ...], (height, width), mode="nearest"
-                ).numpy()[0, 0]
-
-            if "mask" in sample:
-                sample["mask"] = cv2.resize(
-                    sample["mask"].astype(np.float32),
-                    (width, height),
-                    interpolation=cv2.INTER_NEAREST,
-                )
-                # sample["mask"] = sample["mask"].astype(bool)
-
-        # print(sample['image'].shape, sample['depth'].shape)
-        return sample
-
-
-class NormalizeImage(object):
-    """Normlize image by given mean and std."""
-
-    def __init__(self, mean, std):
-        self.__mean = mean
-        self.__std = std
-
-    def __call__(self, sample):
-        sample["image"] = (sample["image"] - self.__mean) / self.__std
-
-        return sample
-
-
-class PrepareForNet(object):
-    """Prepare sample for usage as network input."""
-
-    def __init__(self):
-        pass
-
-    def __call__(self, sample):
-        image = np.transpose(sample["image"], (2, 0, 1))
-        sample["image"] = np.ascontiguousarray(image).astype(np.float32)
-
-        if "mask" in sample:
-            sample["mask"] = sample["mask"].astype(np.float32)
-            sample["mask"] = np.ascontiguousarray(sample["mask"])
-
-        if "depth" in sample:
-            depth = sample["depth"].astype(np.float32)
-            sample["depth"] = np.ascontiguousarray(depth)
-
-        if "semseg_mask" in sample:
-            sample["semseg_mask"] = sample["semseg_mask"].astype(np.float32)
-            sample["semseg_mask"] = np.ascontiguousarray(sample["semseg_mask"])
-
-        return sample

invokeai/backend/image_util/grounding_dino/detection_result.py

@@ -0,0 +1,22 @@
+from pydantic import BaseModel, ConfigDict
+
+
+class BoundingBox(BaseModel):
+    """Bounding box helper class."""
+
+    xmin: int
+    ymin: int
+    xmax: int
+    ymax: int
+
+
+class DetectionResult(BaseModel):
+    """Detection result from Grounding DINO."""
+
+    score: float
+    label: str
+    box: BoundingBox
+    model_config = ConfigDict(
+        # Allow arbitrary types for mask, since it will be a numpy array.
+        arbitrary_types_allowed=True
+    )

invokeai/backend/image_util/grounding_dino/grounding_dino_pipeline.py

@@ -0,0 +1,37 @@
+from typing import Optional
+
+import torch
+from PIL import Image
+from transformers.pipelines import ZeroShotObjectDetectionPipeline
+
+from invokeai.backend.image_util.grounding_dino.detection_result import DetectionResult
+from invokeai.backend.raw_model import RawModel
+
+
+class GroundingDinoPipeline(RawModel):
+    """A wrapper class for a ZeroShotObjectDetectionPipeline that makes it compatible with the model manager's memory
+    management system.
+    """
+
+    def __init__(self, pipeline: ZeroShotObjectDetectionPipeline):
+        self._pipeline = pipeline
+
+    def detect(self, image: Image.Image, candidate_labels: list[str], threshold: float = 0.1) -> list[DetectionResult]:
+        results = self._pipeline(image=image, candidate_labels=candidate_labels, threshold=threshold)
+        assert results is not None
+        results = [DetectionResult.model_validate(result) for result in results]
+        return results
+
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None):
+        # HACK(ryand): The GroundingDinoPipeline does not work on MPS devices. We only allow it to be moved to CPU or
+        # CUDA.
+        if device is not None and device.type not in {"cpu", "cuda"}:
+            device = None
+        self._pipeline.model.to(device=device, dtype=dtype)
+        self._pipeline.device = self._pipeline.model.device
+
+    def calc_size(self) -> int:
+        # HACK(ryand): Fix the circular import issue.
+        from invokeai.backend.model_manager.load.model_util import calc_module_size
+
+        return calc_module_size(self._pipeline.model)

invokeai/backend/image_util/lineart_anime.py

@@ -98,7 +98,7 @@ class UnetSkipConnectionBlock(nn.Module):
         """
         super(UnetSkipConnectionBlock, self).__init__()
         self.outermost = outermost
-        if type(norm_layer) == functools.partial:
+        if isinstance(norm_layer, functools.partial):
             use_bias = norm_layer.func == nn.InstanceNorm2d
         else:
             use_bias = norm_layer == nn.InstanceNorm2d

invokeai/backend/image_util/segment_anything/mask_refinement.py

@@ -0,0 +1,50 @@
+# This file contains utilities for Grounded-SAM mask refinement based on:
+# https://github.com/NielsRogge/Transformers-Tutorials/blob/a39f33ac1557b02ebfb191ea7753e332b5ca933f/Grounding%20DINO/GroundingDINO_with_Segment_Anything.ipynb
+
+
+import cv2
+import numpy as np
+import numpy.typing as npt
+
+
+def mask_to_polygon(mask: npt.NDArray[np.uint8]) -> list[tuple[int, int]]:
+    """Convert a binary mask to a polygon.
+
+    Returns:
+        list[list[int]]: List of (x, y) coordinates representing the vertices of the polygon.
+    """
+    # Find contours in the binary mask.
+    contours, _ = cv2.findContours(mask.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+
+    # Find the contour with the largest area.
+    largest_contour = max(contours, key=cv2.contourArea)
+
+    # Extract the vertices of the contour.
+    polygon = largest_contour.reshape(-1, 2).tolist()
+
+    return polygon
+
+
+def polygon_to_mask(
+    polygon: list[tuple[int, int]], image_shape: tuple[int, int], fill_value: int = 1
+) -> npt.NDArray[np.uint8]:
+    """Convert a polygon to a segmentation mask.
+
+    Args:
+        polygon (list): List of (x, y) coordinates representing the vertices of the polygon.
+        image_shape (tuple): Shape of the image (height, width) for the mask.
+        fill_value (int): Value to fill the polygon with.
+
+    Returns:
+        np.ndarray: Segmentation mask with the polygon filled (with value 255).
+    """
+    # Create an empty mask.
+    mask = np.zeros(image_shape, dtype=np.uint8)
+
+    # Convert polygon to an array of points.
+    pts = np.array(polygon, dtype=np.int32)
+
+    # Fill the polygon with white color (255).
+    cv2.fillPoly(mask, [pts], color=(fill_value,))
+
+    return mask

invokeai/backend/image_util/segment_anything/segment_anything_pipeline.py

@@ -0,0 +1,53 @@
+from typing import Optional
+
+import torch
+from PIL import Image
+from transformers.models.sam import SamModel
+from transformers.models.sam.processing_sam import SamProcessor
+
+from invokeai.backend.raw_model import RawModel
+
+
+class SegmentAnythingPipeline(RawModel):
+    """A wrapper class for the transformers SAM model and processor that makes it compatible with the model manager."""
+
+    def __init__(self, sam_model: SamModel, sam_processor: SamProcessor):
+        self._sam_model = sam_model
+        self._sam_processor = sam_processor
+
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None):
+        # HACK(ryand): The SAM pipeline does not work on MPS devices. We only allow it to be moved to CPU or CUDA.
+        if device is not None and device.type not in {"cpu", "cuda"}:
+            device = None
+        self._sam_model.to(device=device, dtype=dtype)
+
+    def calc_size(self) -> int:
+        # HACK(ryand): Fix the circular import issue.
+        from invokeai.backend.model_manager.load.model_util import calc_module_size
+
+        return calc_module_size(self._sam_model)
+
+    def segment(self, image: Image.Image, bounding_boxes: list[list[int]]) -> torch.Tensor:
+        """Run the SAM model.
+
+        Args:
+            image (Image.Image): The image to segment.
+            bounding_boxes (list[list[int]]): The bounding box prompts. Each bounding box is in the format
+                [xmin, ymin, xmax, ymax].
+
+        Returns:
+            torch.Tensor: The segmentation masks. dtype: torch.bool. shape: [num_masks, channels, height, width].
+        """
+        # Add batch dimension of 1 to the bounding boxes.
+        boxes = [bounding_boxes]
+        inputs = self._sam_processor(images=image, input_boxes=boxes, return_tensors="pt").to(self._sam_model.device)
+        outputs = self._sam_model(**inputs)
+        masks = self._sam_processor.post_process_masks(
+            masks=outputs.pred_masks,
+            original_sizes=inputs.original_sizes,
+            reshaped_input_sizes=inputs.reshaped_input_sizes,
+        )
+
+        # There should be only one batch.
+        assert len(masks) == 1
+        return masks[0]

invokeai/backend/ip_adapter/ip_adapter.py

@@ -124,16 +124,14 @@ class IPAdapter(RawModel):
             self.device, dtype=self.dtype
         )
 
-    def to(
-        self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None, non_blocking: bool = False
-    ):
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None):
         if device is not None:
             self.device = device
         if dtype is not None:
             self.dtype = dtype
 
-        self._image_proj_model.to(device=self.device, dtype=self.dtype, non_blocking=non_blocking)
-        self.attn_weights.to(device=self.device, dtype=self.dtype, non_blocking=non_blocking)
+        self._image_proj_model.to(device=self.device, dtype=self.dtype)
+        self.attn_weights.to(device=self.device, dtype=self.dtype)
 
     def calc_size(self) -> int:
         # HACK(ryand): Fix this issue with circular imports.

invokeai/backend/lora.py

@@ -3,15 +3,15 @@
 
 import bisect
 from pathlib import Path
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Dict, List, Optional, Set, Tuple, Union
 
 import torch
 from safetensors.torch import load_file
 from typing_extensions import Self
 
+import invokeai.backend.util.logging as logger
 from invokeai.backend.model_manager import BaseModelType
 from invokeai.backend.raw_model import RawModel
-from invokeai.backend.util.devices import TorchDevice
 
 
 class LoRALayerBase:
@@ -47,9 +47,19 @@ class LoRALayerBase:
         self.rank = None  # set in layer implementation
         self.layer_key = layer_key
 
-    def get_weight(self, orig_weight: Optional[torch.Tensor]) -> torch.Tensor:
+    def get_weight(self, orig_weight: torch.Tensor) -> torch.Tensor:
         raise NotImplementedError()
 
+    def get_bias(self, orig_bias: torch.Tensor) -> Optional[torch.Tensor]:
+        return self.bias
+
+    def get_parameters(self, orig_module: torch.nn.Module) -> Dict[str, torch.Tensor]:
+        params = {"weight": self.get_weight(orig_module.weight)}
+        bias = self.get_bias(orig_module.bias)
+        if bias is not None:
+            params["bias"] = bias
+        return params
+
     def calc_size(self) -> int:
         model_size = 0
         for val in [self.bias]:
@@ -57,14 +67,20 @@ class LoRALayerBase:
                 model_size += val.nelement() * val.element_size()
         return model_size
 
-    def to(
-        self,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-        non_blocking: bool = False,
-    ) -> None:
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
         if self.bias is not None:
-            self.bias = self.bias.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            self.bias = self.bias.to(device=device, dtype=dtype)
+
+    def check_keys(self, values: Dict[str, torch.Tensor], known_keys: Set[str]):
+        """Log a warning if values contains unhandled keys."""
+        # {"alpha", "bias_indices", "bias_values", "bias_size"} are hard-coded, because they are handled by
+        # `LoRALayerBase`. Sub-classes should provide the known_keys that they handled.
+        all_known_keys = known_keys | {"alpha", "bias_indices", "bias_values", "bias_size"}
+        unknown_keys = set(values.keys()) - all_known_keys
+        if unknown_keys:
+            logger.warning(
+                f"Unexpected keys found in LoRA/LyCORIS layer, model might work incorrectly! Keys: {unknown_keys}"
+            )
 
 
 # TODO: find and debug lora/locon with bias
@@ -82,14 +98,19 @@ class LoRALayer(LoRALayerBase):
 
         self.up = values["lora_up.weight"]
         self.down = values["lora_down.weight"]
-        if "lora_mid.weight" in values:
-            self.mid: Optional[torch.Tensor] = values["lora_mid.weight"]
-        else:
-            self.mid = None
+        self.mid = values.get("lora_mid.weight", None)
 
         self.rank = self.down.shape[0]
+        self.check_keys(
+            values,
+            {
+                "lora_up.weight",
+                "lora_down.weight",
+                "lora_mid.weight",
+            },
+        )
 
-    def get_weight(self, orig_weight: Optional[torch.Tensor]) -> torch.Tensor:
+    def get_weight(self, orig_weight: torch.Tensor) -> torch.Tensor:
         if self.mid is not None:
             up = self.up.reshape(self.up.shape[0], self.up.shape[1])
             down = self.down.reshape(self.down.shape[0], self.down.shape[1])
@@ -106,19 +127,14 @@ class LoRALayer(LoRALayerBase):
                 model_size += val.nelement() * val.element_size()
         return model_size
 
-    def to(
-        self,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-        non_blocking: bool = False,
-    ) -> None:
-        super().to(device=device, dtype=dtype, non_blocking=non_blocking)
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
+        super().to(device=device, dtype=dtype)
 
-        self.up = self.up.to(device=device, dtype=dtype, non_blocking=non_blocking)
-        self.down = self.down.to(device=device, dtype=dtype, non_blocking=non_blocking)
+        self.up = self.up.to(device=device, dtype=dtype)
+        self.down = self.down.to(device=device, dtype=dtype)
 
         if self.mid is not None:
-            self.mid = self.mid.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            self.mid = self.mid.to(device=device, dtype=dtype)
 
 
 class LoHALayer(LoRALayerBase):
@@ -136,20 +152,23 @@ class LoHALayer(LoRALayerBase):
         self.w1_b = values["hada_w1_b"]
         self.w2_a = values["hada_w2_a"]
         self.w2_b = values["hada_w2_b"]
-
-        if "hada_t1" in values:
-            self.t1: Optional[torch.Tensor] = values["hada_t1"]
-        else:
-            self.t1 = None
-
-        if "hada_t2" in values:
-            self.t2: Optional[torch.Tensor] = values["hada_t2"]
-        else:
-            self.t2 = None
+        self.t1 = values.get("hada_t1", None)
+        self.t2 = values.get("hada_t2", None)
 
         self.rank = self.w1_b.shape[0]
+        self.check_keys(
+            values,
+            {
+                "hada_w1_a",
+                "hada_w1_b",
+                "hada_w2_a",
+                "hada_w2_b",
+                "hada_t1",
+                "hada_t2",
+            },
+        )
 
-    def get_weight(self, orig_weight: Optional[torch.Tensor]) -> torch.Tensor:
+    def get_weight(self, orig_weight: torch.Tensor) -> torch.Tensor:
         if self.t1 is None:
             weight: torch.Tensor = (self.w1_a @ self.w1_b) * (self.w2_a @ self.w2_b)
 
@@ -167,23 +186,18 @@ class LoHALayer(LoRALayerBase):
                 model_size += val.nelement() * val.element_size()
         return model_size
 
-    def to(
-        self,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-        non_blocking: bool = False,
-    ) -> None:
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
         super().to(device=device, dtype=dtype)
 
-        self.w1_a = self.w1_a.to(device=device, dtype=dtype, non_blocking=non_blocking)
-        self.w1_b = self.w1_b.to(device=device, dtype=dtype, non_blocking=non_blocking)
+        self.w1_a = self.w1_a.to(device=device, dtype=dtype)
+        self.w1_b = self.w1_b.to(device=device, dtype=dtype)
         if self.t1 is not None:
-            self.t1 = self.t1.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            self.t1 = self.t1.to(device=device, dtype=dtype)
 
-        self.w2_a = self.w2_a.to(device=device, dtype=dtype, non_blocking=non_blocking)
-        self.w2_b = self.w2_b.to(device=device, dtype=dtype, non_blocking=non_blocking)
+        self.w2_a = self.w2_a.to(device=device, dtype=dtype)
+        self.w2_b = self.w2_b.to(device=device, dtype=dtype)
         if self.t2 is not None:
-            self.t2 = self.t2.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            self.t2 = self.t2.to(device=device, dtype=dtype)
 
 
 class LoKRLayer(LoRALayerBase):
@@ -202,37 +216,45 @@ class LoKRLayer(LoRALayerBase):
     ):
         super().__init__(layer_key, values)
 
-        if "lokr_w1" in values:
-            self.w1: Optional[torch.Tensor] = values["lokr_w1"]
-            self.w1_a = None
-            self.w1_b = None
-        else:
-            self.w1 = None
+        self.w1 = values.get("lokr_w1", None)
+        if self.w1 is None:
             self.w1_a = values["lokr_w1_a"]
             self.w1_b = values["lokr_w1_b"]
-
-        if "lokr_w2" in values:
-            self.w2: Optional[torch.Tensor] = values["lokr_w2"]
-            self.w2_a = None
-            self.w2_b = None
         else:
-            self.w2 = None
+            self.w1_b = None
+            self.w1_a = None
+
+        self.w2 = values.get("lokr_w2", None)
+        if self.w2 is None:
             self.w2_a = values["lokr_w2_a"]
             self.w2_b = values["lokr_w2_b"]
-
-        if "lokr_t2" in values:
-            self.t2: Optional[torch.Tensor] = values["lokr_t2"]
         else:
-            self.t2 = None
+            self.w2_a = None
+            self.w2_b = None
 
-        if "lokr_w1_b" in values:
-            self.rank = values["lokr_w1_b"].shape[0]
-        elif "lokr_w2_b" in values:
-            self.rank = values["lokr_w2_b"].shape[0]
+        self.t2 = values.get("lokr_t2", None)
+
+        if self.w1_b is not None:
+            self.rank = self.w1_b.shape[0]
+        elif self.w2_b is not None:
+            self.rank = self.w2_b.shape[0]
         else:
             self.rank = None  # unscaled
 
-    def get_weight(self, orig_weight: Optional[torch.Tensor]) -> torch.Tensor:
+        self.check_keys(
+            values,
+            {
+                "lokr_w1",
+                "lokr_w1_a",
+                "lokr_w1_b",
+                "lokr_w2",
+                "lokr_w2_a",
+                "lokr_w2_b",
+                "lokr_t2",
+            },
+        )
+
+    def get_weight(self, orig_weight: torch.Tensor) -> torch.Tensor:
         w1: Optional[torch.Tensor] = self.w1
         if w1 is None:
             assert self.w1_a is not None
@@ -264,12 +286,7 @@ class LoKRLayer(LoRALayerBase):
                 model_size += val.nelement() * val.element_size()
         return model_size
 
-    def to(
-        self,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-        non_blocking: bool = False,
-    ) -> None:
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
         super().to(device=device, dtype=dtype)
 
         if self.w1 is not None:
@@ -277,23 +294,25 @@ class LoKRLayer(LoRALayerBase):
         else:
             assert self.w1_a is not None
             assert self.w1_b is not None
-            self.w1_a = self.w1_a.to(device=device, dtype=dtype, non_blocking=non_blocking)
-            self.w1_b = self.w1_b.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            self.w1_a = self.w1_a.to(device=device, dtype=dtype)
+            self.w1_b = self.w1_b.to(device=device, dtype=dtype)
 
         if self.w2 is not None:
-            self.w2 = self.w2.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            self.w2 = self.w2.to(device=device, dtype=dtype)
         else:
             assert self.w2_a is not None
             assert self.w2_b is not None
-            self.w2_a = self.w2_a.to(device=device, dtype=dtype, non_blocking=non_blocking)
-            self.w2_b = self.w2_b.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            self.w2_a = self.w2_a.to(device=device, dtype=dtype)
+            self.w2_b = self.w2_b.to(device=device, dtype=dtype)
 
         if self.t2 is not None:
-            self.t2 = self.t2.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            self.t2 = self.t2.to(device=device, dtype=dtype)
 
 
 class FullLayer(LoRALayerBase):
+    # bias handled in LoRALayerBase(calc_size, to)
     # weight: torch.Tensor
+    # bias: Optional[torch.Tensor]
 
     def __init__(
         self,
@@ -303,15 +322,12 @@ class FullLayer(LoRALayerBase):
         super().__init__(layer_key, values)
 
         self.weight = values["diff"]
-
-        if len(values.keys()) > 1:
-            _keys = list(values.keys())
-            _keys.remove("diff")
-            raise NotImplementedError(f"Unexpected keys in lora diff layer: {_keys}")
+        self.bias = values.get("diff_b", None)
 
         self.rank = None  # unscaled
+        self.check_keys(values, {"diff", "diff_b"})
 
-    def get_weight(self, orig_weight: Optional[torch.Tensor]) -> torch.Tensor:
+    def get_weight(self, orig_weight: torch.Tensor) -> torch.Tensor:
         return self.weight
 
     def calc_size(self) -> int:
@@ -319,15 +335,10 @@ class FullLayer(LoRALayerBase):
         model_size += self.weight.nelement() * self.weight.element_size()
         return model_size
 
-    def to(
-        self,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-        non_blocking: bool = False,
-    ) -> None:
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
         super().to(device=device, dtype=dtype)
 
-        self.weight = self.weight.to(device=device, dtype=dtype, non_blocking=non_blocking)
+        self.weight = self.weight.to(device=device, dtype=dtype)
 
 
 class IA3Layer(LoRALayerBase):
@@ -345,8 +356,9 @@ class IA3Layer(LoRALayerBase):
         self.on_input = values["on_input"]
 
         self.rank = None  # unscaled
+        self.check_keys(values, {"weight", "on_input"})
 
-    def get_weight(self, orig_weight: Optional[torch.Tensor]) -> torch.Tensor:
+    def get_weight(self, orig_weight: torch.Tensor) -> torch.Tensor:
         weight = self.weight
         if not self.on_input:
             weight = weight.reshape(-1, 1)
@@ -359,19 +371,46 @@ class IA3Layer(LoRALayerBase):
         model_size += self.on_input.nelement() * self.on_input.element_size()
         return model_size
 
-    def to(
-        self,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-        non_blocking: bool = False,
-    ):
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None):
         super().to(device=device, dtype=dtype)
 
-        self.weight = self.weight.to(device=device, dtype=dtype, non_blocking=non_blocking)
-        self.on_input = self.on_input.to(device=device, dtype=dtype, non_blocking=non_blocking)
+        self.weight = self.weight.to(device=device, dtype=dtype)
+        self.on_input = self.on_input.to(device=device, dtype=dtype)
 
 
-AnyLoRALayer = Union[LoRALayer, LoHALayer, LoKRLayer, FullLayer, IA3Layer]
+class NormLayer(LoRALayerBase):
+    # bias handled in LoRALayerBase(calc_size, to)
+    # weight: torch.Tensor
+    # bias: Optional[torch.Tensor]
+
+    def __init__(
+        self,
+        layer_key: str,
+        values: Dict[str, torch.Tensor],
+    ):
+        super().__init__(layer_key, values)
+
+        self.weight = values["w_norm"]
+        self.bias = values.get("b_norm", None)
+
+        self.rank = None  # unscaled
+        self.check_keys(values, {"w_norm", "b_norm"})
+
+    def get_weight(self, orig_weight: torch.Tensor) -> torch.Tensor:
+        return self.weight
+
+    def calc_size(self) -> int:
+        model_size = super().calc_size()
+        model_size += self.weight.nelement() * self.weight.element_size()
+        return model_size
+
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
+        super().to(device=device, dtype=dtype)
+
+        self.weight = self.weight.to(device=device, dtype=dtype)
+
+
+AnyLoRALayer = Union[LoRALayer, LoHALayer, LoKRLayer, FullLayer, IA3Layer, NormLayer]
 
 
 class LoRAModelRaw(RawModel):  # (torch.nn.Module):
@@ -390,15 +429,10 @@ class LoRAModelRaw(RawModel):  # (torch.nn.Module):
     def name(self) -> str:
         return self._name
 
-    def to(
-        self,
-        device: Optional[torch.device] = None,
-        dtype: Optional[torch.dtype] = None,
-        non_blocking: bool = False,
-    ) -> None:
+    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
         # TODO: try revert if exception?
         for _key, layer in self.layers.items():
-            layer.to(device=device, dtype=dtype, non_blocking=non_blocking)
+            layer.to(device=device, dtype=dtype)
 
     def calc_size(self) -> int:
         model_size = 0
@@ -494,16 +528,19 @@ class LoRAModelRaw(RawModel):  # (torch.nn.Module):
             state_dict = cls._convert_sdxl_keys_to_diffusers_format(state_dict)
 
         for layer_key, values in state_dict.items():
+            # Detect layers according to LyCORIS detection logic(`weight_list_det`)
+            # https://github.com/KohakuBlueleaf/LyCORIS/tree/8ad8000efb79e2b879054da8c9356e6143591bad/lycoris/modules
+
             # lora and locon
-            if "lora_down.weight" in values:
+            if "lora_up.weight" in values:
                 layer: AnyLoRALayer = LoRALayer(layer_key, values)
 
             # loha
-            elif "hada_w1_b" in values:
+            elif "hada_w1_a" in values:
                 layer = LoHALayer(layer_key, values)
 
             # lokr
-            elif "lokr_w1_b" in values or "lokr_w1" in values:
+            elif "lokr_w1" in values or "lokr_w1_a" in values:
                 layer = LoKRLayer(layer_key, values)
 
             # diff
@@ -511,9 +548,13 @@ class LoRAModelRaw(RawModel):  # (torch.nn.Module):
                 layer = FullLayer(layer_key, values)
 
             # ia3
-            elif "weight" in values and "on_input" in values:
+            elif "on_input" in values:
                 layer = IA3Layer(layer_key, values)
 
+            # norms
+            elif "w_norm" in values:
+                layer = NormLayer(layer_key, values)
+
             else:
                 print(f">> Encountered unknown lora layer module in {model.name}: {layer_key} - {list(values.keys())}")
                 raise Exception("Unknown lora format!")
@@ -521,7 +562,7 @@ class LoRAModelRaw(RawModel):  # (torch.nn.Module):
             # lower memory consumption by removing already parsed layer values
             state_dict[layer_key].clear()
 
-            layer.to(device=device, dtype=dtype, non_blocking=TorchDevice.get_non_blocking(device))
+            layer.to(device=device, dtype=dtype)
             model.layers[layer_key] = layer
 
         return model

invokeai/backend/model_manager/config.py

@@ -67,6 +67,7 @@ class ModelType(str, Enum):
     IPAdapter = "ip_adapter"
     CLIPVision = "clip_vision"
     T2IAdapter = "t2i_adapter"
+    SpandrelImageToImage = "spandrel_image_to_image"
 
 
 class SubModelType(str, Enum):
@@ -353,7 +354,7 @@ class CLIPVisionDiffusersConfig(DiffusersConfigBase):
     """Model config for CLIPVision."""
 
     type: Literal[ModelType.CLIPVision] = ModelType.CLIPVision
-    format: Literal[ModelFormat.Diffusers]
+    format: Literal[ModelFormat.Diffusers] = ModelFormat.Diffusers
 
     @staticmethod
     def get_tag() -> Tag:
@@ -364,13 +365,24 @@ class T2IAdapterConfig(DiffusersConfigBase, ControlAdapterConfigBase):
     """Model config for T2I."""
 
     type: Literal[ModelType.T2IAdapter] = ModelType.T2IAdapter
-    format: Literal[ModelFormat.Diffusers]
+    format: Literal[ModelFormat.Diffusers] = ModelFormat.Diffusers
 
     @staticmethod
     def get_tag() -> Tag:
         return Tag(f"{ModelType.T2IAdapter.value}.{ModelFormat.Diffusers.value}")
 
 
+class SpandrelImageToImageConfig(ModelConfigBase):
+    """Model config for Spandrel Image to Image models."""
+
+    type: Literal[ModelType.SpandrelImageToImage] = ModelType.SpandrelImageToImage
+    format: Literal[ModelFormat.Checkpoint] = ModelFormat.Checkpoint
+
+    @staticmethod
+    def get_tag() -> Tag:
+        return Tag(f"{ModelType.SpandrelImageToImage.value}.{ModelFormat.Checkpoint.value}")
+
+
 def get_model_discriminator_value(v: Any) -> str:
     """
     Computes the discriminator value for a model config.
@@ -407,6 +419,7 @@ AnyModelConfig = Annotated[
         Annotated[IPAdapterInvokeAIConfig, IPAdapterInvokeAIConfig.get_tag()],
         Annotated[IPAdapterCheckpointConfig, IPAdapterCheckpointConfig.get_tag()],
         Annotated[T2IAdapterConfig, T2IAdapterConfig.get_tag()],
+        Annotated[SpandrelImageToImageConfig, SpandrelImageToImageConfig.get_tag()],
         Annotated[CLIPVisionDiffusersConfig, CLIPVisionDiffusersConfig.get_tag()],
     ],
     Discriminator(get_model_discriminator_value),

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

@@ -167,7 +167,8 @@ class ModelCache(ModelCacheBase[AnyModel]):
         size = calc_model_size_by_data(self.logger, model)
         self.make_room(size)
 
-        state_dict = model.state_dict() if isinstance(model, torch.nn.Module) else None
+        running_on_cpu = self.execution_device == torch.device("cpu")
+        state_dict = model.state_dict() if isinstance(model, torch.nn.Module) and not running_on_cpu else None
         cache_record = CacheRecord(key=key, model=model, device=self.storage_device, state_dict=state_dict, size=size)
         self._cached_models[key] = cache_record
         self._cache_stack.append(key)
@@ -289,11 +290,9 @@ class ModelCache(ModelCacheBase[AnyModel]):
                 else:
                     new_dict: Dict[str, torch.Tensor] = {}
                     for k, v in cache_entry.state_dict.items():
-                        new_dict[k] = v.to(
-                            target_device, copy=True, non_blocking=TorchDevice.get_non_blocking(target_device)
-                        )
+                        new_dict[k] = v.to(target_device, copy=True)
                     cache_entry.model.load_state_dict(new_dict, assign=True)
-            cache_entry.model.to(target_device, non_blocking=TorchDevice.get_non_blocking(target_device))
+            cache_entry.model.to(target_device)
             cache_entry.device = target_device
         except Exception as e:  # blow away cache entry
             self._delete_cache_entry(cache_entry)

invokeai/backend/model_manager/load/model_loaders/spandrel_image_to_image.py

@@ -0,0 +1,45 @@
+from pathlib import Path
+from typing import Optional
+
+import torch
+
+from invokeai.backend.model_manager.config import (
+    AnyModel,
+    AnyModelConfig,
+    BaseModelType,
+    ModelFormat,
+    ModelType,
+    SubModelType,
+)
+from invokeai.backend.model_manager.load.load_default import ModelLoader
+from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry
+from invokeai.backend.spandrel_image_to_image_model import SpandrelImageToImageModel
+
+
+@ModelLoaderRegistry.register(
+    base=BaseModelType.Any, type=ModelType.SpandrelImageToImage, format=ModelFormat.Checkpoint
+)
+class SpandrelImageToImageModelLoader(ModelLoader):
+    """Class for loading Spandrel Image-to-Image models (i.e. models wrapped by spandrel.ImageModelDescriptor)."""
+
+    def _load_model(
+        self,
+        config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+    ) -> AnyModel:
+        if submodel_type is not None:
+            raise ValueError("Unexpected submodel requested for Spandrel model.")
+
+        model_path = Path(config.path)
+        model = SpandrelImageToImageModel.load_from_file(model_path)
+
+        torch_dtype = self._torch_dtype
+        if not model.supports_dtype(torch_dtype):
+            self._logger.warning(
+                f"The configured dtype ('{self._torch_dtype}') is not supported by the {model.get_model_type_name()} "
+                "model. Falling back to 'float32'."
+            )
+            torch_dtype = torch.float32
+        model.to(dtype=torch_dtype)
+
+        return model

invokeai/backend/model_manager/load/model_loaders/stable_diffusion.py

@@ -98,6 +98,9 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
                 ModelVariantType.Normal: StableDiffusionXLPipeline,
                 ModelVariantType.Inpaint: StableDiffusionXLInpaintPipeline,
             },
+            BaseModelType.StableDiffusionXLRefiner: {
+                ModelVariantType.Normal: StableDiffusionXLPipeline,
+            },
         }
         assert isinstance(config, MainCheckpointConfig)
         try:

invokeai/backend/model_manager/load/model_util.py

@@ -11,10 +11,14 @@ from diffusers.pipelines.pipeline_utils import DiffusionPipeline
 from diffusers.schedulers.scheduling_utils import SchedulerMixin
 from transformers import CLIPTokenizer
 
+from invokeai.backend.image_util.depth_anything.depth_anything_pipeline import DepthAnythingPipeline
+from invokeai.backend.image_util.grounding_dino.grounding_dino_pipeline import GroundingDinoPipeline
+from invokeai.backend.image_util.segment_anything.segment_anything_pipeline import SegmentAnythingPipeline
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
 from invokeai.backend.lora import LoRAModelRaw
 from invokeai.backend.model_manager.config import AnyModel
 from invokeai.backend.onnx.onnx_runtime import IAIOnnxRuntimeModel
+from invokeai.backend.spandrel_image_to_image_model import SpandrelImageToImageModel
 from invokeai.backend.textual_inversion import TextualInversionModelRaw
 
 
@@ -33,7 +37,18 @@ def calc_model_size_by_data(logger: logging.Logger, model: AnyModel) -> int:
     elif isinstance(model, CLIPTokenizer):
         # TODO(ryand): Accurately calculate the tokenizer's size. It's small enough that it shouldn't matter for now.
         return 0
-    elif isinstance(model, (TextualInversionModelRaw, IPAdapter, LoRAModelRaw)):
+    elif isinstance(
+        model,
+        (
+            TextualInversionModelRaw,
+            IPAdapter,
+            LoRAModelRaw,
+            SpandrelImageToImageModel,
+            GroundingDinoPipeline,
+            SegmentAnythingPipeline,
+            DepthAnythingPipeline,
+        ),
+    ):
         return model.calc_size()
     else:
         # TODO(ryand): Promote this from a log to an exception once we are confident that we are handling all of the