chore(ui): lint

The root cause was the active style preset not being reset when it was deleted, or no longer present in the list of style presets.

- Add extra reducer to `stylePresetSlice` to reset the active preset if it is deleted or otherwise unavailable
- Update the dynamic prompts listener to trigger on delete/update/list of style presets

.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

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()
@@ -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={
@@ -231,6 +230,18 @@ 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"),
 ) -> Response:
@@ -242,6 +253,7 @@ async def get_image_full(
             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)

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)
 
@@ -184,8 +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

@@ -37,9 +37,9 @@ 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,
@@ -60,8 +60,13 @@ from invokeai.backend.stable_diffusion.diffusion_backend import StableDiffusionB
 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
@@ -498,6 +503,33 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 )
             )
 
+    @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,
@@ -707,7 +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(
@@ -765,10 +797,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
         dtype = TorchDevice.choose_torch_dtype()
 
         seed, noise, latents = self.prepare_noise_and_latents(context, self.noise, self.latents)
-        latents = latents.to(device=device, dtype=dtype)
-        if noise is not None:
-            noise = noise.to(device=device, dtype=dtype)
-
         _, _, latent_height, latent_width = latents.shape
 
         conditioning_data = self.get_conditioning_data(
@@ -801,21 +829,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
             denoising_end=self.denoising_end,
         )
 
-        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,
-        )
-
         # 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)
 
@@ -833,6 +846,50 @@ class DenoiseLatentsInvocation(BaseInvocation):
         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:
@@ -840,6 +897,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             #    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)
@@ -871,6 +929,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
         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.
@@ -913,14 +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)

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
 
@@ -242,6 +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/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/prompt_augmentation.py

@@ -1,85 +0,0 @@
-from pathlib import Path
-
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
-from invokeai.app.invocations.fields import (
-    InputField,
-)
-from invokeai.app.invocations.primitives import StringOutput
-from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.util.devices import TorchDevice
-
-AUGMENT_PROMPT_INSTRUCTION = """Your task is to translate a short image caption and a style caption to a more detailed caption for the same image. The detailed caption should adhere to the following:
-- be 1 sentence long
-- use descriptive language that relates to the subject of interest
-- it may add new details, but shouldn't change the subject of the original caption
-Here are some examples:
-Original caption: "A cat on a table"
-Detailed caption: "A fluffy cat with a curious expression, sitting on a wooden table next to a vase of flowers."
-Original caption: "medieval armor"
-Detailed caption: "The gleaming suit of medieval armor stands proudly in the museum, its intricate engravings telling tales of long-forgotten battles and chivalry."
-Original caption: "A panda bear as a mad scientist"
-Detailed caption: "Clad in a tiny lab coat and goggles, the panda bear feverishly mixes colorful potions, embodying the eccentricity of a mad scientist in its whimsical laboratory."
-Here is the prompt to translate:
-Original caption: "{}"
-Detailed caption:"""
-
-
-@invocation("promp_augment", title="Prompt Augmentation", tags=["prompt"], category="conditioning", version="1.0.0")
-class PrompAugmentationInvocation(BaseInvocation):
-    """Use an LLM to augment a text prompt."""
-
-    prompt: str = InputField(description="The text prompt to augment.")
-
-    @torch.inference_mode()
-    def invoke(self, context: InvocationContext) -> StringOutput:
-        # TODO(ryand): Address the following situations in the input prompt:
-        # - Prompt contains a TI embeddings.
-        # - Prompt contains .and() compel syntax. (Is ther any other compel syntax we need to handle?)
-        # - Prompt contains quotation marks that could cause confusion when embedded in an LLM instruct prompt.
-
-        # Load the model and tokenizer.
-        model_source = "microsoft/Phi-3-mini-4k-instruct"
-
-        def model_loader(model_path: Path):
-            return AutoModelForCausalLM.from_pretrained(
-                model_path, torch_dtype=TorchDevice.choose_torch_dtype(), local_files_only=True
-            )
-
-        def tokenizer_loader(model_path: Path):
-            return AutoTokenizer.from_pretrained(model_path, local_files_only=True)
-
-        with (
-            context.models.load_remote_model(source=model_source, loader=model_loader) as model,
-            context.models.load_remote_model(source=model_source, loader=tokenizer_loader) as tokenizer,
-        ):
-            # Tokenize the input prompt.
-            augmented_prompt = self._run_instruct_model(model, tokenizer, self.prompt)
-
-        return StringOutput(value=augmented_prompt)
-
-    def _run_instruct_model(self, model: AutoModelForCausalLM, tokenizer: AutoTokenizer, prompt: str) -> str:
-        messages = [
-            {
-                "role": "user",
-                "content": AUGMENT_PROMPT_INSTRUCTION.format(prompt),
-            }
-        ]
-        inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
-        inputs = inputs.to(model.device)
-
-        outputs = model.generate(
-            inputs,
-            max_new_tokens=200,
-            temperature=0.9,
-            do_sample=True,
-        )
-        text = tokenizer.batch_decode(outputs)[0]
-        assert isinstance(text, str)
-
-        output = text.split("<|assistant|>")[-1].strip()
-        output = output.split("<|end|>")[0].strip()
-
-        return output

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/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_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/shared/sqlite/sqlite_util.py

@@ -16,6 +16,7 @@ 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.sqlite_migrator_impl import SqliteMigrator
 
 
@@ -49,6 +50,7 @@ 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.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/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/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/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/lora.py

@@ -3,12 +3,13 @@
 
 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
 
@@ -46,9 +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]:
@@ -60,6 +71,17 @@ class LoRALayerBase:
         if self.bias is not None:
             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
 class LoRALayer(LoRALayerBase):
@@ -76,14 +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])
@@ -125,20 +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)
 
@@ -186,37 +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
@@ -272,7 +310,9 @@ class LoKRLayer(LoRALayerBase):
 
 
 class FullLayer(LoRALayerBase):
+    # bias handled in LoRALayerBase(calc_size, to)
     # weight: torch.Tensor
+    # bias: Optional[torch.Tensor]
 
     def __init__(
         self,
@@ -282,15 +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:
@@ -319,8 +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)
@@ -340,7 +378,39 @@ class IA3Layer(LoRALayerBase):
         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):
@@ -458,16 +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
@@ -475,9 +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!")

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

@@ -11,6 +11,9 @@ 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
@@ -34,7 +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, SpandrelImageToImageModel)):
+    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

invokeai/backend/model_manager/starter_models.py

@@ -187,164 +187,171 @@ STARTER_MODELS: list[StarterModel] = [
     # endregion
     # region ControlNet
     StarterModel(
-        name="QRCode Monster",
+        name="QRCode Monster v2 (SD1.5)",
         base=BaseModelType.StableDiffusion1,
-        source="monster-labs/control_v1p_sd15_qrcode_monster",
-        description="Controlnet model that generates scannable creative QR codes",
+        source="monster-labs/control_v1p_sd15_qrcode_monster::v2",
+        description="ControlNet model that generates scannable creative QR codes",
+        type=ModelType.ControlNet,
+    ),
+    StarterModel(
+        name="QRCode Monster (SDXL)",
+        base=BaseModelType.StableDiffusionXL,
+        source="monster-labs/control_v1p_sdxl_qrcode_monster",
+        description="ControlNet model that generates scannable creative QR codes",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="canny",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_canny",
-        description="Controlnet weights trained on sd-1.5 with canny conditioning.",
+        description="ControlNet weights trained on sd-1.5 with canny conditioning.",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="inpaint",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_inpaint",
-        description="Controlnet weights trained on sd-1.5 with canny conditioning, inpaint version",
+        description="ControlNet weights trained on sd-1.5 with canny conditioning, inpaint version",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="mlsd",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_mlsd",
-        description="Controlnet weights trained on sd-1.5 with canny conditioning, MLSD version",
+        description="ControlNet weights trained on sd-1.5 with canny conditioning, MLSD version",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="depth",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11f1p_sd15_depth",
-        description="Controlnet weights trained on sd-1.5 with depth conditioning",
+        description="ControlNet weights trained on sd-1.5 with depth conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="normal_bae",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_normalbae",
-        description="Controlnet weights trained on sd-1.5 with normalbae image conditioning",
+        description="ControlNet weights trained on sd-1.5 with normalbae image conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="seg",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_seg",
-        description="Controlnet weights trained on sd-1.5 with seg image conditioning",
+        description="ControlNet weights trained on sd-1.5 with seg image conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="lineart",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_lineart",
-        description="Controlnet weights trained on sd-1.5 with lineart image conditioning",
+        description="ControlNet weights trained on sd-1.5 with lineart image conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="lineart_anime",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15s2_lineart_anime",
-        description="Controlnet weights trained on sd-1.5 with anime image conditioning",
+        description="ControlNet weights trained on sd-1.5 with anime image conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="openpose",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_openpose",
-        description="Controlnet weights trained on sd-1.5 with openpose image conditioning",
+        description="ControlNet weights trained on sd-1.5 with openpose image conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="scribble",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_scribble",
-        description="Controlnet weights trained on sd-1.5 with scribble image conditioning",
+        description="ControlNet weights trained on sd-1.5 with scribble image conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="softedge",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11p_sd15_softedge",
-        description="Controlnet weights trained on sd-1.5 with soft edge conditioning",
+        description="ControlNet weights trained on sd-1.5 with soft edge conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="shuffle",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11e_sd15_shuffle",
-        description="Controlnet weights trained on sd-1.5 with shuffle image conditioning",
+        description="ControlNet weights trained on sd-1.5 with shuffle image conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="tile",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11f1e_sd15_tile",
-        description="Controlnet weights trained on sd-1.5 with tiled image conditioning",
+        description="ControlNet weights trained on sd-1.5 with tiled image conditioning",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="ip2p",
         base=BaseModelType.StableDiffusion1,
         source="lllyasviel/control_v11e_sd15_ip2p",
-        description="Controlnet weights trained on sd-1.5 with ip2p conditioning.",
+        description="ControlNet weights trained on sd-1.5 with ip2p conditioning.",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="canny-sdxl",
         base=BaseModelType.StableDiffusionXL,
-        source="xinsir/controlnet-canny-sdxl-1.0",
-        description="Controlnet weights trained on sdxl-1.0 with canny conditioning, by Xinsir.",
+        source="xinsir/controlNet-canny-sdxl-1.0",
+        description="ControlNet weights trained on sdxl-1.0 with canny conditioning, by Xinsir.",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="depth-sdxl",
         base=BaseModelType.StableDiffusionXL,
-        source="diffusers/controlnet-depth-sdxl-1.0",
-        description="Controlnet weights trained on sdxl-1.0 with depth conditioning.",
+        source="diffusers/controlNet-depth-sdxl-1.0",
+        description="ControlNet weights trained on sdxl-1.0 with depth conditioning.",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="softedge-dexined-sdxl",
         base=BaseModelType.StableDiffusionXL,
-        source="SargeZT/controlnet-sd-xl-1.0-softedge-dexined",
-        description="Controlnet weights trained on sdxl-1.0 with dexined soft edge preprocessing.",
+        source="SargeZT/controlNet-sd-xl-1.0-softedge-dexined",
+        description="ControlNet weights trained on sdxl-1.0 with dexined soft edge preprocessing.",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="depth-16bit-zoe-sdxl",
         base=BaseModelType.StableDiffusionXL,
-        source="SargeZT/controlnet-sd-xl-1.0-depth-16bit-zoe",
-        description="Controlnet weights trained on sdxl-1.0 with Zoe's preprocessor (16 bits).",
+        source="SargeZT/controlNet-sd-xl-1.0-depth-16bit-zoe",
+        description="ControlNet weights trained on sdxl-1.0 with Zoe's preprocessor (16 bits).",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="depth-zoe-sdxl",
         base=BaseModelType.StableDiffusionXL,
-        source="diffusers/controlnet-zoe-depth-sdxl-1.0",
-        description="Controlnet weights trained on sdxl-1.0 with Zoe's preprocessor (32 bits).",
+        source="diffusers/controlNet-zoe-depth-sdxl-1.0",
+        description="ControlNet weights trained on sdxl-1.0 with Zoe's preprocessor (32 bits).",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="openpose-sdxl",
         base=BaseModelType.StableDiffusionXL,
-        source="xinsir/controlnet-openpose-sdxl-1.0",
-        description="Controlnet weights trained on sdxl-1.0 compatible with the DWPose processor by Xinsir.",
+        source="xinsir/controlNet-openpose-sdxl-1.0",
+        description="ControlNet weights trained on sdxl-1.0 compatible with the DWPose processor by Xinsir.",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="scribble-sdxl",
         base=BaseModelType.StableDiffusionXL,
-        source="xinsir/controlnet-scribble-sdxl-1.0",
-        description="Controlnet weights trained on sdxl-1.0 compatible with various lineart processors and black/white sketches by Xinsir.",
+        source="xinsir/controlNet-scribble-sdxl-1.0",
+        description="ControlNet weights trained on sdxl-1.0 compatible with various lineart processors and black/white sketches by Xinsir.",
         type=ModelType.ControlNet,
     ),
     StarterModel(
         name="tile-sdxl",
         base=BaseModelType.StableDiffusionXL,
-        source="xinsir/controlnet-tile-sdxl-1.0",
-        description="Controlnet weights trained on sdxl-1.0 with tiled image conditioning",
+        source="xinsir/controlNet-tile-sdxl-1.0",
+        description="ControlNet weights trained on sdxl-1.0 with tiled image conditioning",
         type=ModelType.ControlNet,
     ),
     # endregion

invokeai/backend/model_manager/util/select_hf_files.py

@@ -62,13 +62,7 @@ def filter_files(
         # downloading random checkpoints that might also be in the repo. However there is no guarantee
         # that a checkpoint doesn't contain "model" in its name, and no guarantee that future diffusers models
         # will adhere to this naming convention, so this is an area to be careful of.
-        #
-        # On July 24, 2024, this regex filter was modified to support downloading the `microsoft/Phi-3-mini-4k-instruct`
-        # model. I am making this note in case it is relevant as we continue to improve this logic and make it less
-        # brittle.
-        #   - Before: r"model(\.[^.]+)?\.(safetensors|bin|onnx|xml|pth|pt|ckpt|msgpack)$"
-        #   - After: r"model.*\.(safetensors|bin|onnx|xml|pth|pt|ckpt|msgpack)$"
-        elif re.search(r"model.*\.(safetensors|bin|onnx|xml|pth|pt|ckpt|msgpack)$", file.name):
+        elif re.search(r"model(\.[^.]+)?\.(safetensors|bin|onnx|xml|pth|pt|ckpt|msgpack)$", file.name):
             paths.append(file)
 
     # limit search to subfolder if requested

invokeai/backend/model_patcher.py

@@ -17,8 +17,9 @@ from invokeai.backend.lora import LoRAModelRaw
 from invokeai.backend.model_manager import AnyModel
 from invokeai.backend.model_manager.load.optimizations import skip_torch_weight_init
 from invokeai.backend.onnx.onnx_runtime import IAIOnnxRuntimeModel
+from invokeai.backend.stable_diffusion.extensions.lora import LoRAExt
 from invokeai.backend.textual_inversion import TextualInversionManager, TextualInversionModelRaw
-from invokeai.backend.util.devices import TorchDevice
+from invokeai.backend.util.original_weights_storage import OriginalWeightsStorage
 
 """
 loras = [
@@ -85,13 +86,13 @@ class ModelPatcher:
         cls,
         unet: UNet2DConditionModel,
         loras: Iterator[Tuple[LoRAModelRaw, float]],
-        model_state_dict: Optional[Dict[str, torch.Tensor]] = None,
+        cached_weights: Optional[Dict[str, torch.Tensor]] = None,
     ) -> Generator[None, None, None]:
         with cls.apply_lora(
             unet,
             loras=loras,
             prefix="lora_unet_",
-            model_state_dict=model_state_dict,
+            cached_weights=cached_weights,
         ):
             yield
 
@@ -101,9 +102,9 @@ class ModelPatcher:
         cls,
         text_encoder: CLIPTextModel,
         loras: Iterator[Tuple[LoRAModelRaw, float]],
-        model_state_dict: Optional[Dict[str, torch.Tensor]] = None,
+        cached_weights: Optional[Dict[str, torch.Tensor]] = None,
     ) -> Generator[None, None, None]:
-        with cls.apply_lora(text_encoder, loras=loras, prefix="lora_te_", model_state_dict=model_state_dict):
+        with cls.apply_lora(text_encoder, loras=loras, prefix="lora_te_", cached_weights=cached_weights):
             yield
 
     @classmethod
@@ -113,7 +114,7 @@ class ModelPatcher:
         model: AnyModel,
         loras: Iterator[Tuple[LoRAModelRaw, float]],
         prefix: str,
-        model_state_dict: Optional[Dict[str, torch.Tensor]] = None,
+        cached_weights: Optional[Dict[str, torch.Tensor]] = None,
     ) -> Generator[None, None, None]:
         """
         Apply one or more LoRAs to a model.
@@ -121,66 +122,26 @@ class ModelPatcher:
         :param model: The model to patch.
         :param loras: An iterator that returns the LoRA to patch in and its patch weight.
         :param prefix: A string prefix that precedes keys used in the LoRAs weight layers.
-        :model_state_dict: Read-only copy of the model's state dict in CPU, for unpatching purposes.
+        :cached_weights: Read-only copy of the model's state dict in CPU, for unpatching purposes.
         """
-        original_weights = {}
+        original_weights = OriginalWeightsStorage(cached_weights)
         try:
-            with torch.no_grad():
-                for lora, lora_weight in loras:
-                    # assert lora.device.type == "cpu"
-                    for layer_key, layer in lora.layers.items():
-                        if not layer_key.startswith(prefix):
-                            continue
+            for lora_model, lora_weight in loras:
+                LoRAExt.patch_model(
+                    model=model,
+                    prefix=prefix,
+                    lora=lora_model,
+                    lora_weight=lora_weight,
+                    original_weights=original_weights,
+                )
+                del lora_model
 
-                        # TODO(ryand): A non-negligible amount of time is currently spent resolving LoRA keys. This
-                        # should be improved in the following ways:
-                        # 1. The key mapping could be more-efficiently pre-computed. This would save time every time a
-                        #    LoRA model is applied.
-                        # 2. From an API perspective, there's no reason that the `ModelPatcher` should be aware of the
-                        #    intricacies of Stable Diffusion key resolution. It should just expect the input LoRA
-                        #    weights to have valid keys.
-                        assert isinstance(model, torch.nn.Module)
-                        module_key, module = cls._resolve_lora_key(model, layer_key, prefix)
-
-                        # All of the LoRA weight calculations will be done on the same device as the module weight.
-                        # (Performance will be best if this is a CUDA device.)
-                        device = module.weight.device
-                        dtype = module.weight.dtype
-
-                        if module_key not in original_weights:
-                            if model_state_dict is not None:  # we were provided with the CPU copy of the state dict
-                                original_weights[module_key] = model_state_dict[module_key + ".weight"]
-                            else:
-                                original_weights[module_key] = module.weight.detach().to(device="cpu", copy=True)
-
-                        layer_scale = layer.alpha / layer.rank if (layer.alpha and layer.rank) else 1.0
-
-                        # We intentionally move to the target device first, then cast. Experimentally, this was found to
-                        # be significantly faster for 16-bit CPU tensors being moved to a CUDA device than doing the
-                        # same thing in a single call to '.to(...)'.
-                        layer.to(device=device)
-                        layer.to(dtype=torch.float32)
-                        # TODO(ryand): Using torch.autocast(...) over explicit casting may offer a speed benefit on CUDA
-                        # devices here. Experimentally, it was found to be very slow on CPU. More investigation needed.
-                        layer_weight = layer.get_weight(module.weight) * (lora_weight * layer_scale)
-                        layer.to(device=TorchDevice.CPU_DEVICE)
-
-                        assert isinstance(layer_weight, torch.Tensor)  # mypy thinks layer_weight is a float|Any ??!
-                        if module.weight.shape != layer_weight.shape:
-                            # TODO: debug on lycoris
-                            assert hasattr(layer_weight, "reshape")
-                            layer_weight = layer_weight.reshape(module.weight.shape)
-
-                        assert isinstance(layer_weight, torch.Tensor)  # mypy thinks layer_weight is a float|Any ??!
-                        module.weight += layer_weight.to(dtype=dtype)
-
-            yield  # wait for context manager exit
+            yield
 
         finally:
-            assert hasattr(model, "get_submodule")  # mypy not picking up fact that torch.nn.Module has get_submodule()
             with torch.no_grad():
-                for module_key, weight in original_weights.items():
-                    model.get_submodule(module_key).weight.copy_(weight)
+                for param_key, weight in original_weights.get_changed_weights():
+                    model.get_parameter(param_key).copy_(weight)
 
     @classmethod
     @contextmanager

invokeai/backend/stable_diffusion/__init__.py

@@ -7,11 +7,9 @@ from invokeai.backend.stable_diffusion.diffusers_pipeline import (  # noqa: F401
     StableDiffusionGeneratorPipeline,
 )
 from invokeai.backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent  # noqa: F401
-from invokeai.backend.stable_diffusion.seamless import set_seamless  # noqa: F401
 
 __all__ = [
     "PipelineIntermediateState",
     "StableDiffusionGeneratorPipeline",
     "InvokeAIDiffuserComponent",
-    "set_seamless",
 ]

invokeai/backend/stable_diffusion/extensions/base.py

@@ -2,14 +2,14 @@ from __future__ import annotations
 
 from contextlib import contextmanager
 from dataclasses import dataclass
-from typing import TYPE_CHECKING, Callable, Dict, List, Optional
+from typing import TYPE_CHECKING, Callable, Dict, List
 
-import torch
 from diffusers import UNet2DConditionModel
 
 if TYPE_CHECKING:
     from invokeai.backend.stable_diffusion.denoise_context import DenoiseContext
     from invokeai.backend.stable_diffusion.extension_callback_type import ExtensionCallbackType
+    from invokeai.backend.util.original_weights_storage import OriginalWeightsStorage
 
 
 @dataclass
@@ -56,5 +56,17 @@ class ExtensionBase:
         yield None
 
     @contextmanager
-    def patch_unet(self, unet: UNet2DConditionModel, cached_weights: Optional[Dict[str, torch.Tensor]] = None):
-        yield None
+    def patch_unet(self, unet: UNet2DConditionModel, original_weights: OriginalWeightsStorage):
+        """A context manager for applying patches to the UNet model. The context manager's lifetime spans the entire
+        diffusion process. Weight unpatching is handled upstream, and is achieved by saving unchanged weights by
+        `original_weights.save` function. Note that this enables some performance optimization by avoiding redundant
+        operations. All other patches (e.g. changes to tensor shapes, function monkey-patches, etc.) should be unpatched
+        by this context manager.
+
+        Args:
+            unet (UNet2DConditionModel): The UNet model on execution device to patch.
+            original_weights (OriginalWeightsStorage): A storage with copy of the model's original weights in CPU, for
+                unpatching purposes. Extension should save tensor which being modified in this storage, also extensions
+                can access original weights values.
+        """
+        yield

invokeai/backend/stable_diffusion/extensions/freeu.py

@@ -1,15 +1,15 @@
 from __future__ import annotations
 
 from contextlib import contextmanager
-from typing import TYPE_CHECKING, Dict, Optional
+from typing import TYPE_CHECKING
 
-import torch
 from diffusers import UNet2DConditionModel
 
 from invokeai.backend.stable_diffusion.extensions.base import ExtensionBase
 
 if TYPE_CHECKING:
     from invokeai.app.shared.models import FreeUConfig
+    from invokeai.backend.util.original_weights_storage import OriginalWeightsStorage
 
 
 class FreeUExt(ExtensionBase):
@@ -21,7 +21,7 @@ class FreeUExt(ExtensionBase):
         self._freeu_config = freeu_config
 
     @contextmanager
-    def patch_unet(self, unet: UNet2DConditionModel, cached_weights: Optional[Dict[str, torch.Tensor]] = None):
+    def patch_unet(self, unet: UNet2DConditionModel, original_weights: OriginalWeightsStorage):
         unet.enable_freeu(
             b1=self._freeu_config.b1,
             b2=self._freeu_config.b2,

invokeai/backend/stable_diffusion/extensions/inpaint.py

@@ -0,0 +1,120 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Optional
+
+import einops
+import torch
+from diffusers import UNet2DConditionModel
+
+from invokeai.backend.stable_diffusion.extension_callback_type import ExtensionCallbackType
+from invokeai.backend.stable_diffusion.extensions.base import ExtensionBase, callback
+
+if TYPE_CHECKING:
+    from invokeai.backend.stable_diffusion.denoise_context import DenoiseContext
+
+
+class InpaintExt(ExtensionBase):
+    """An extension for inpainting with non-inpainting models. See `InpaintModelExt` for inpainting with inpainting
+    models.
+    """
+
+    def __init__(
+        self,
+        mask: torch.Tensor,
+        is_gradient_mask: bool,
+    ):
+        """Initialize InpaintExt.
+        Args:
+            mask (torch.Tensor): The inpainting mask. Shape: (1, 1, latent_height, latent_width). Values are
+                expected to be in the range [0, 1]. A value of 1 means that the corresponding 'pixel' should not be
+                inpainted.
+            is_gradient_mask (bool): If True, mask is interpreted as a gradient mask meaning that the mask values range
+                from 0 to 1. If False, mask is interpreted as binary mask meaning that the mask values are either 0 or
+                1.
+        """
+        super().__init__()
+        self._mask = mask
+        self._is_gradient_mask = is_gradient_mask
+
+        # Noise, which used to noisify unmasked part of image
+        # if noise provided to context, then it will be used
+        # if no noise provided, then noise will be generated based on seed
+        self._noise: Optional[torch.Tensor] = None
+
+    @staticmethod
+    def _is_normal_model(unet: UNet2DConditionModel):
+        """Checks if the provided UNet belongs to a regular model.
+        The `in_channels` of a UNet vary depending on model type:
+        - normal - 4
+        - depth - 5
+        - inpaint - 9
+        """
+        return unet.conv_in.in_channels == 4
+
+    def _apply_mask(self, ctx: DenoiseContext, latents: torch.Tensor, t: torch.Tensor) -> torch.Tensor:
+        batch_size = latents.size(0)
+        mask = einops.repeat(self._mask, "b c h w -> (repeat b) c h w", repeat=batch_size)
+        if t.dim() == 0:
+            # some schedulers expect t to be one-dimensional.
+            # TODO: file diffusers bug about inconsistency?
+            t = einops.repeat(t, "-> batch", batch=batch_size)
+        # Noise shouldn't be re-randomized between steps here. The multistep schedulers
+        # get very confused about what is happening from step to step when we do that.
+        mask_latents = ctx.scheduler.add_noise(ctx.inputs.orig_latents, self._noise, t)
+        # TODO: Do we need to also apply scheduler.scale_model_input? Or is add_noise appropriately scaled already?
+        # mask_latents = self.scheduler.scale_model_input(mask_latents, t)
+        mask_latents = einops.repeat(mask_latents, "b c h w -> (repeat b) c h w", repeat=batch_size)
+        if self._is_gradient_mask:
+            threshold = (t.item()) / ctx.scheduler.config.num_train_timesteps
+            mask_bool = mask < 1 - threshold
+            masked_input = torch.where(mask_bool, latents, mask_latents)
+        else:
+            masked_input = torch.lerp(latents, mask_latents.to(dtype=latents.dtype), mask.to(dtype=latents.dtype))
+        return masked_input
+
+    @callback(ExtensionCallbackType.PRE_DENOISE_LOOP)
+    def init_tensors(self, ctx: DenoiseContext):
+        if not self._is_normal_model(ctx.unet):
+            raise ValueError(
+                "InpaintExt should be used only on normal (non-inpainting) models. This could be caused by an "
+                "inpainting model that was incorrectly marked as a non-inpainting model. In some cases, this can be "
+                "fixed by removing and re-adding the model (so that it gets re-probed)."
+            )
+
+        self._mask = self._mask.to(device=ctx.latents.device, dtype=ctx.latents.dtype)
+
+        self._noise = ctx.inputs.noise
+        # 'noise' might be None if the latents have already been noised (e.g. when running the SDXL refiner).
+        # We still need noise for inpainting, so we generate it from the seed here.
+        if self._noise is None:
+            self._noise = torch.randn(
+                ctx.latents.shape,
+                dtype=torch.float32,
+                device="cpu",
+                generator=torch.Generator(device="cpu").manual_seed(ctx.seed),
+            ).to(device=ctx.latents.device, dtype=ctx.latents.dtype)
+
+    # Use negative order to make extensions with default order work with patched latents
+    @callback(ExtensionCallbackType.PRE_STEP, order=-100)
+    def apply_mask_to_initial_latents(self, ctx: DenoiseContext):
+        ctx.latents = self._apply_mask(ctx, ctx.latents, ctx.timestep)
+
+    # TODO: redo this with preview events rewrite
+    # Use negative order to make extensions with default order work with patched latents
+    @callback(ExtensionCallbackType.POST_STEP, order=-100)
+    def apply_mask_to_step_output(self, ctx: DenoiseContext):
+        timestep = ctx.scheduler.timesteps[-1]
+        if hasattr(ctx.step_output, "denoised"):
+            ctx.step_output.denoised = self._apply_mask(ctx, ctx.step_output.denoised, timestep)
+        elif hasattr(ctx.step_output, "pred_original_sample"):
+            ctx.step_output.pred_original_sample = self._apply_mask(ctx, ctx.step_output.pred_original_sample, timestep)
+        else:
+            ctx.step_output.pred_original_sample = self._apply_mask(ctx, ctx.step_output.prev_sample, timestep)
+
+    # Restore unmasked part after the last step is completed
+    @callback(ExtensionCallbackType.POST_DENOISE_LOOP)
+    def restore_unmasked(self, ctx: DenoiseContext):
+        if self._is_gradient_mask:
+            ctx.latents = torch.where(self._mask < 1, ctx.latents, ctx.inputs.orig_latents)
+        else:
+            ctx.latents = torch.lerp(ctx.latents, ctx.inputs.orig_latents, self._mask)

invokeai/backend/stable_diffusion/extensions/inpaint_model.py

@@ -0,0 +1,88 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Optional
+
+import torch
+from diffusers import UNet2DConditionModel
+
+from invokeai.backend.stable_diffusion.extension_callback_type import ExtensionCallbackType
+from invokeai.backend.stable_diffusion.extensions.base import ExtensionBase, callback
+
+if TYPE_CHECKING:
+    from invokeai.backend.stable_diffusion.denoise_context import DenoiseContext
+
+
+class InpaintModelExt(ExtensionBase):
+    """An extension for inpainting with inpainting models. See `InpaintExt` for inpainting with non-inpainting
+    models.
+    """
+
+    def __init__(
+        self,
+        mask: Optional[torch.Tensor],
+        masked_latents: Optional[torch.Tensor],
+        is_gradient_mask: bool,
+    ):
+        """Initialize InpaintModelExt.
+        Args:
+            mask (Optional[torch.Tensor]): The inpainting mask. Shape: (1, 1, latent_height, latent_width). Values are
+                expected to be in the range [0, 1]. A value of 1 means that the corresponding 'pixel' should not be
+                inpainted.
+            masked_latents (Optional[torch.Tensor]): Latents of initial image, with masked out by black color inpainted area.
+                If mask provided, then too should be provided. Shape: (1, 1, latent_height, latent_width)
+            is_gradient_mask (bool): If True, mask is interpreted as a gradient mask meaning that the mask values range
+                from 0 to 1. If False, mask is interpreted as binary mask meaning that the mask values are either 0 or
+                1.
+        """
+        super().__init__()
+        if mask is not None and masked_latents is None:
+            raise ValueError("Source image required for inpaint mask when inpaint model used!")
+
+        # Inverse mask, because inpaint models treat mask as: 0 - remain same, 1 - inpaint
+        self._mask = None
+        if mask is not None:
+            self._mask = 1 - mask
+        self._masked_latents = masked_latents
+        self._is_gradient_mask = is_gradient_mask
+
+    @staticmethod
+    def _is_inpaint_model(unet: UNet2DConditionModel):
+        """Checks if the provided UNet belongs to a regular model.
+        The `in_channels` of a UNet vary depending on model type:
+        - normal - 4
+        - depth - 5
+        - inpaint - 9
+        """
+        return unet.conv_in.in_channels == 9
+
+    @callback(ExtensionCallbackType.PRE_DENOISE_LOOP)
+    def init_tensors(self, ctx: DenoiseContext):
+        if not self._is_inpaint_model(ctx.unet):
+            raise ValueError("InpaintModelExt should be used only on inpaint models!")
+
+        if self._mask is None:
+            self._mask = torch.ones_like(ctx.latents[:1, :1])
+        self._mask = self._mask.to(device=ctx.latents.device, dtype=ctx.latents.dtype)
+
+        if self._masked_latents is None:
+            self._masked_latents = torch.zeros_like(ctx.latents[:1])
+        self._masked_latents = self._masked_latents.to(device=ctx.latents.device, dtype=ctx.latents.dtype)
+
+    # Do last so that other extensions works with normal latents
+    @callback(ExtensionCallbackType.PRE_UNET, order=1000)
+    def append_inpaint_layers(self, ctx: DenoiseContext):
+        batch_size = ctx.unet_kwargs.sample.shape[0]
+        b_mask = torch.cat([self._mask] * batch_size)
+        b_masked_latents = torch.cat([self._masked_latents] * batch_size)
+        ctx.unet_kwargs.sample = torch.cat(
+            [ctx.unet_kwargs.sample, b_mask, b_masked_latents],
+            dim=1,
+        )
+
+    # Restore unmasked part as inpaint model can change unmasked part slightly
+    @callback(ExtensionCallbackType.POST_DENOISE_LOOP)
+    def restore_unmasked(self, ctx: DenoiseContext):
+        if self._is_gradient_mask:
+            ctx.latents = torch.where(self._mask > 0, ctx.latents, ctx.inputs.orig_latents)
+        else:
+            ctx.latents = torch.lerp(ctx.inputs.orig_latents, ctx.latents, self._mask)

invokeai/backend/stable_diffusion/extensions/lora.py

@@ -0,0 +1,137 @@
+from __future__ import annotations
+
+from contextlib import contextmanager
+from typing import TYPE_CHECKING, Tuple
+
+import torch
+from diffusers import UNet2DConditionModel
+
+from invokeai.backend.stable_diffusion.extensions.base import ExtensionBase
+from invokeai.backend.util.devices import TorchDevice
+
+if TYPE_CHECKING:
+    from invokeai.app.invocations.model import ModelIdentifierField
+    from invokeai.app.services.shared.invocation_context import InvocationContext
+    from invokeai.backend.lora import LoRAModelRaw
+    from invokeai.backend.util.original_weights_storage import OriginalWeightsStorage
+
+
+class LoRAExt(ExtensionBase):
+    def __init__(
+        self,
+        node_context: InvocationContext,
+        model_id: ModelIdentifierField,
+        weight: float,
+    ):
+        super().__init__()
+        self._node_context = node_context
+        self._model_id = model_id
+        self._weight = weight
+
+    @contextmanager
+    def patch_unet(self, unet: UNet2DConditionModel, original_weights: OriginalWeightsStorage):
+        lora_model = self._node_context.models.load(self._model_id).model
+        self.patch_model(
+            model=unet,
+            prefix="lora_unet_",
+            lora=lora_model,
+            lora_weight=self._weight,
+            original_weights=original_weights,
+        )
+        del lora_model
+
+        yield
+
+    @classmethod
+    @torch.no_grad()
+    def patch_model(
+        cls,
+        model: torch.nn.Module,
+        prefix: str,
+        lora: LoRAModelRaw,
+        lora_weight: float,
+        original_weights: OriginalWeightsStorage,
+    ):
+        """
+        Apply one or more LoRAs to a model.
+        :param model: The model to patch.
+        :param lora: LoRA model to patch in.
+        :param lora_weight: LoRA patch weight.
+        :param prefix: A string prefix that precedes keys used in the LoRAs weight layers.
+        :param original_weights: Storage with original weights, filled by weights which lora patches, used for unpatching.
+        """
+
+        if lora_weight == 0:
+            return
+
+        # assert lora.device.type == "cpu"
+        for layer_key, layer in lora.layers.items():
+            if not layer_key.startswith(prefix):
+                continue
+
+            # TODO(ryand): A non-negligible amount of time is currently spent resolving LoRA keys. This
+            # should be improved in the following ways:
+            # 1. The key mapping could be more-efficiently pre-computed. This would save time every time a
+            #    LoRA model is applied.
+            # 2. From an API perspective, there's no reason that the `ModelPatcher` should be aware of the
+            #    intricacies of Stable Diffusion key resolution. It should just expect the input LoRA
+            #    weights to have valid keys.
+            assert isinstance(model, torch.nn.Module)
+            module_key, module = cls._resolve_lora_key(model, layer_key, prefix)
+
+            # All of the LoRA weight calculations will be done on the same device as the module weight.
+            # (Performance will be best if this is a CUDA device.)
+            device = module.weight.device
+            dtype = module.weight.dtype
+
+            layer_scale = layer.alpha / layer.rank if (layer.alpha and layer.rank) else 1.0
+
+            # We intentionally move to the target device first, then cast. Experimentally, this was found to
+            # be significantly faster for 16-bit CPU tensors being moved to a CUDA device than doing the
+            # same thing in a single call to '.to(...)'.
+            layer.to(device=device)
+            layer.to(dtype=torch.float32)
+
+            # TODO(ryand): Using torch.autocast(...) over explicit casting may offer a speed benefit on CUDA
+            # devices here. Experimentally, it was found to be very slow on CPU. More investigation needed.
+            for param_name, lora_param_weight in layer.get_parameters(module).items():
+                param_key = module_key + "." + param_name
+                module_param = module.get_parameter(param_name)
+
+                # save original weight
+                original_weights.save(param_key, module_param)
+
+                if module_param.shape != lora_param_weight.shape:
+                    # TODO: debug on lycoris
+                    lora_param_weight = lora_param_weight.reshape(module_param.shape)
+
+                lora_param_weight *= lora_weight * layer_scale
+                module_param += lora_param_weight.to(dtype=dtype)
+
+            layer.to(device=TorchDevice.CPU_DEVICE)
+
+    @staticmethod
+    def _resolve_lora_key(model: torch.nn.Module, lora_key: str, prefix: str) -> Tuple[str, torch.nn.Module]:
+        assert "." not in lora_key
+
+        if not lora_key.startswith(prefix):
+            raise Exception(f"lora_key with invalid prefix: {lora_key}, {prefix}")
+
+        module = model
+        module_key = ""
+        key_parts = lora_key[len(prefix) :].split("_")
+
+        submodule_name = key_parts.pop(0)
+
+        while len(key_parts) > 0:
+            try:
+                module = module.get_submodule(submodule_name)
+                module_key += "." + submodule_name
+                submodule_name = key_parts.pop(0)
+            except Exception:
+                submodule_name += "_" + key_parts.pop(0)
+
+        module = module.get_submodule(submodule_name)
+        module_key = (module_key + "." + submodule_name).lstrip(".")
+
+        return (module_key, module)

invokeai/backend/stable_diffusion/extensions/seamless.py

@@ -0,0 +1,71 @@
+from __future__ import annotations
+
+from contextlib import contextmanager
+from typing import Callable, Dict, List, Optional, Tuple
+
+import torch
+import torch.nn as nn
+from diffusers import UNet2DConditionModel
+from diffusers.models.lora import LoRACompatibleConv
+
+from invokeai.backend.stable_diffusion.extensions.base import ExtensionBase
+
+
+class SeamlessExt(ExtensionBase):
+    def __init__(
+        self,
+        seamless_axes: List[str],
+    ):
+        super().__init__()
+        self._seamless_axes = seamless_axes
+
+    @contextmanager
+    def patch_unet(self, unet: UNet2DConditionModel, cached_weights: Optional[Dict[str, torch.Tensor]] = None):
+        with self.static_patch_model(
+            model=unet,
+            seamless_axes=self._seamless_axes,
+        ):
+            yield
+
+    @staticmethod
+    @contextmanager
+    def static_patch_model(
+        model: torch.nn.Module,
+        seamless_axes: List[str],
+    ):
+        if not seamless_axes:
+            yield
+            return
+
+        x_mode = "circular" if "x" in seamless_axes else "constant"
+        y_mode = "circular" if "y" in seamless_axes else "constant"
+
+        # override conv_forward
+        # https://github.com/huggingface/diffusers/issues/556#issuecomment-1993287019
+        def _conv_forward_asymmetric(
+            self, input: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor] = None
+        ):
+            self.paddingX = (self._reversed_padding_repeated_twice[0], self._reversed_padding_repeated_twice[1], 0, 0)
+            self.paddingY = (0, 0, self._reversed_padding_repeated_twice[2], self._reversed_padding_repeated_twice[3])
+            working = torch.nn.functional.pad(input, self.paddingX, mode=x_mode)
+            working = torch.nn.functional.pad(working, self.paddingY, mode=y_mode)
+            return torch.nn.functional.conv2d(
+                working, weight, bias, self.stride, torch.nn.modules.utils._pair(0), self.dilation, self.groups
+            )
+
+        original_layers: List[Tuple[nn.Conv2d, Callable]] = []
+        try:
+            for layer in model.modules():
+                if not isinstance(layer, torch.nn.Conv2d):
+                    continue
+
+                if isinstance(layer, LoRACompatibleConv) and layer.lora_layer is None:
+                    layer.lora_layer = lambda *x: 0
+                original_layers.append((layer, layer._conv_forward))
+                layer._conv_forward = _conv_forward_asymmetric.__get__(layer, torch.nn.Conv2d)
+
+            yield
+
+        finally:
+            for layer, orig_conv_forward in original_layers:
+                layer._conv_forward = orig_conv_forward

invokeai/backend/stable_diffusion/extensions/t2i_adapter.py

@@ -0,0 +1,120 @@
+from __future__ import annotations
+
+import math
+from typing import TYPE_CHECKING, List, Optional, Union
+
+import torch
+from diffusers import T2IAdapter
+from PIL.Image import Image
+
+from invokeai.app.util.controlnet_utils import prepare_control_image
+from invokeai.backend.model_manager import BaseModelType
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningMode
+from invokeai.backend.stable_diffusion.extension_callback_type import ExtensionCallbackType
+from invokeai.backend.stable_diffusion.extensions.base import ExtensionBase, callback
+
+if TYPE_CHECKING:
+    from invokeai.app.invocations.model import ModelIdentifierField
+    from invokeai.app.services.shared.invocation_context import InvocationContext
+    from invokeai.app.util.controlnet_utils import CONTROLNET_RESIZE_VALUES
+    from invokeai.backend.stable_diffusion.denoise_context import DenoiseContext
+
+
+class T2IAdapterExt(ExtensionBase):
+    def __init__(
+        self,
+        node_context: InvocationContext,
+        model_id: ModelIdentifierField,
+        image: Image,
+        weight: Union[float, List[float]],
+        begin_step_percent: float,
+        end_step_percent: float,
+        resize_mode: CONTROLNET_RESIZE_VALUES,
+    ):
+        super().__init__()
+        self._node_context = node_context
+        self._model_id = model_id
+        self._image = image
+        self._weight = weight
+        self._resize_mode = resize_mode
+        self._begin_step_percent = begin_step_percent
+        self._end_step_percent = end_step_percent
+
+        self._adapter_state: Optional[List[torch.Tensor]] = None
+
+        # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
+        model_config = self._node_context.models.get_config(self._model_id.key)
+        if model_config.base == BaseModelType.StableDiffusion1:
+            self._max_unet_downscale = 8
+        elif model_config.base == BaseModelType.StableDiffusionXL:
+            self._max_unet_downscale = 4
+        else:
+            raise ValueError(f"Unexpected T2I-Adapter base model type: '{model_config.base}'.")
+
+    @callback(ExtensionCallbackType.SETUP)
+    def setup(self, ctx: DenoiseContext):
+        t2i_model: T2IAdapter
+        with self._node_context.models.load(self._model_id) as t2i_model:
+            _, _, latents_height, latents_width = ctx.inputs.orig_latents.shape
+
+            self._adapter_state = self._run_model(
+                model=t2i_model,
+                image=self._image,
+                latents_height=latents_height,
+                latents_width=latents_width,
+            )
+
+    def _run_model(
+        self,
+        model: T2IAdapter,
+        image: Image,
+        latents_height: int,
+        latents_width: int,
+    ):
+        # Resize the T2I-Adapter input image.
+        # We select the resize dimensions so that after the T2I-Adapter's total_downscale_factor is applied, the
+        # result will match the latent image's dimensions after max_unet_downscale is applied.
+        input_height = latents_height // self._max_unet_downscale * model.total_downscale_factor
+        input_width = latents_width // self._max_unet_downscale * model.total_downscale_factor
+
+        # Note: We have hard-coded `do_classifier_free_guidance=False`. This is because we only want to prepare
+        # a single image. If CFG is enabled, we will duplicate the resultant tensor after applying the
+        # T2I-Adapter model.
+        #
+        # Note: We re-use the `prepare_control_image(...)` from ControlNet for T2I-Adapter, because it has many
+        # of the same requirements (e.g. preserving binary masks during resize).
+        t2i_image = prepare_control_image(
+            image=image,
+            do_classifier_free_guidance=False,
+            width=input_width,
+            height=input_height,
+            num_channels=model.config["in_channels"],
+            device=model.device,
+            dtype=model.dtype,
+            resize_mode=self._resize_mode,
+        )
+
+        return model(t2i_image)
+
+    @callback(ExtensionCallbackType.PRE_UNET)
+    def pre_unet_step(self, ctx: DenoiseContext):
+        # skip if model not active in current step
+        total_steps = len(ctx.inputs.timesteps)
+        first_step = math.floor(self._begin_step_percent * total_steps)
+        last_step = math.ceil(self._end_step_percent * total_steps)
+        if ctx.step_index < first_step or ctx.step_index > last_step:
+            return
+
+        weight = self._weight
+        if isinstance(weight, list):
+            weight = weight[ctx.step_index]
+
+        adapter_state = self._adapter_state
+        if ctx.conditioning_mode == ConditioningMode.Both:
+            adapter_state = [torch.cat([v] * 2) for v in adapter_state]
+
+        if ctx.unet_kwargs.down_intrablock_additional_residuals is None:
+            ctx.unet_kwargs.down_intrablock_additional_residuals = [v * weight for v in adapter_state]
+        else:
+            for i, value in enumerate(adapter_state):
+                ctx.unet_kwargs.down_intrablock_additional_residuals[i] += value * weight

invokeai/backend/stable_diffusion/extensions_manager.py

@@ -7,6 +7,7 @@ import torch
 from diffusers import UNet2DConditionModel
 
 from invokeai.app.services.session_processor.session_processor_common import CanceledException
+from invokeai.backend.util.original_weights_storage import OriginalWeightsStorage
 
 if TYPE_CHECKING:
     from invokeai.backend.stable_diffusion.denoise_context import DenoiseContext
@@ -67,9 +68,15 @@ class ExtensionsManager:
         if self._is_canceled and self._is_canceled():
             raise CanceledException
 
-        # TODO: create weight patch logic in PR with extension which uses it
-        with ExitStack() as exit_stack:
-            for ext in self._extensions:
-                exit_stack.enter_context(ext.patch_unet(unet, cached_weights))
+        original_weights = OriginalWeightsStorage(cached_weights)
+        try:
+            with ExitStack() as exit_stack:
+                for ext in self._extensions:
+                    exit_stack.enter_context(ext.patch_unet(unet, original_weights))
 
-            yield None
+                yield None
+
+        finally:
+            with torch.no_grad():
+                for param_key, weight in original_weights.get_changed_weights():
+                    unet.get_parameter(param_key).copy_(weight)

invokeai/backend/stable_diffusion/schedulers/schedulers.py

@@ -20,10 +20,14 @@ from diffusers import (
 )
 from diffusers.schedulers.scheduling_utils import SchedulerMixin
 
+# TODO: add dpmpp_3s/dpmpp_3s_k when fix released
+# https://github.com/huggingface/diffusers/issues/9007
+
 SCHEDULER_NAME_VALUES = Literal[
     "ddim",
     "ddpm",
     "deis",
+    "deis_k",
     "lms",
     "lms_k",
     "pndm",
@@ -33,16 +37,21 @@ SCHEDULER_NAME_VALUES = Literal[
     "euler_k",
     "euler_a",
     "kdpm_2",
+    "kdpm_2_k",
     "kdpm_2_a",
+    "kdpm_2_a_k",
     "dpmpp_2s",
     "dpmpp_2s_k",
     "dpmpp_2m",
     "dpmpp_2m_k",
     "dpmpp_2m_sde",
     "dpmpp_2m_sde_k",
+    "dpmpp_3m",
+    "dpmpp_3m_k",
     "dpmpp_sde",
     "dpmpp_sde_k",
     "unipc",
+    "unipc_k",
     "lcm",
     "tcd",
 ]
@@ -50,7 +59,8 @@ SCHEDULER_NAME_VALUES = Literal[
 SCHEDULER_MAP: dict[SCHEDULER_NAME_VALUES, tuple[Type[SchedulerMixin], dict[str, Any]]] = {
     "ddim": (DDIMScheduler, {}),
     "ddpm": (DDPMScheduler, {}),
-    "deis": (DEISMultistepScheduler, {}),
+    "deis": (DEISMultistepScheduler, {"use_karras_sigmas": False}),
+    "deis_k": (DEISMultistepScheduler, {"use_karras_sigmas": True}),
     "lms": (LMSDiscreteScheduler, {"use_karras_sigmas": False}),
     "lms_k": (LMSDiscreteScheduler, {"use_karras_sigmas": True}),
     "pndm": (PNDMScheduler, {}),
@@ -59,17 +69,28 @@ SCHEDULER_MAP: dict[SCHEDULER_NAME_VALUES, tuple[Type[SchedulerMixin], dict[str,
     "euler": (EulerDiscreteScheduler, {"use_karras_sigmas": False}),
     "euler_k": (EulerDiscreteScheduler, {"use_karras_sigmas": True}),
     "euler_a": (EulerAncestralDiscreteScheduler, {}),
-    "kdpm_2": (KDPM2DiscreteScheduler, {}),
-    "kdpm_2_a": (KDPM2AncestralDiscreteScheduler, {}),
-    "dpmpp_2s": (DPMSolverSinglestepScheduler, {"use_karras_sigmas": False}),
-    "dpmpp_2s_k": (DPMSolverSinglestepScheduler, {"use_karras_sigmas": True}),
-    "dpmpp_2m": (DPMSolverMultistepScheduler, {"use_karras_sigmas": False}),
-    "dpmpp_2m_k": (DPMSolverMultistepScheduler, {"use_karras_sigmas": True}),
-    "dpmpp_2m_sde": (DPMSolverMultistepScheduler, {"use_karras_sigmas": False, "algorithm_type": "sde-dpmsolver++"}),
-    "dpmpp_2m_sde_k": (DPMSolverMultistepScheduler, {"use_karras_sigmas": True, "algorithm_type": "sde-dpmsolver++"}),
+    "kdpm_2": (KDPM2DiscreteScheduler, {"use_karras_sigmas": False}),
+    "kdpm_2_k": (KDPM2DiscreteScheduler, {"use_karras_sigmas": True}),
+    "kdpm_2_a": (KDPM2AncestralDiscreteScheduler, {"use_karras_sigmas": False}),
+    "kdpm_2_a_k": (KDPM2AncestralDiscreteScheduler, {"use_karras_sigmas": True}),
+    "dpmpp_2s": (DPMSolverSinglestepScheduler, {"use_karras_sigmas": False, "solver_order": 2}),
+    "dpmpp_2s_k": (DPMSolverSinglestepScheduler, {"use_karras_sigmas": True, "solver_order": 2}),
+    "dpmpp_2m": (DPMSolverMultistepScheduler, {"use_karras_sigmas": False, "solver_order": 2}),
+    "dpmpp_2m_k": (DPMSolverMultistepScheduler, {"use_karras_sigmas": True, "solver_order": 2}),
+    "dpmpp_2m_sde": (
+        DPMSolverMultistepScheduler,
+        {"use_karras_sigmas": False, "solver_order": 2, "algorithm_type": "sde-dpmsolver++"},
+    ),
+    "dpmpp_2m_sde_k": (
+        DPMSolverMultistepScheduler,
+        {"use_karras_sigmas": True, "solver_order": 2, "algorithm_type": "sde-dpmsolver++"},
+    ),
+    "dpmpp_3m": (DPMSolverMultistepScheduler, {"use_karras_sigmas": False, "solver_order": 3}),
+    "dpmpp_3m_k": (DPMSolverMultistepScheduler, {"use_karras_sigmas": True, "solver_order": 3}),
     "dpmpp_sde": (DPMSolverSDEScheduler, {"use_karras_sigmas": False, "noise_sampler_seed": 0}),
     "dpmpp_sde_k": (DPMSolverSDEScheduler, {"use_karras_sigmas": True, "noise_sampler_seed": 0}),
-    "unipc": (UniPCMultistepScheduler, {"cpu_only": True}),
+    "unipc": (UniPCMultistepScheduler, {"use_karras_sigmas": False, "cpu_only": True}),
+    "unipc_k": (UniPCMultistepScheduler, {"use_karras_sigmas": True, "cpu_only": True}),
     "lcm": (LCMScheduler, {}),
     "tcd": (TCDScheduler, {}),
 }

invokeai/backend/stable_diffusion/seamless.py

@@ -1,51 +0,0 @@
-from contextlib import contextmanager
-from typing import Callable, List, Optional, Tuple, Union
-
-import torch
-import torch.nn as nn
-from diffusers.models.autoencoders.autoencoder_kl import AutoencoderKL
-from diffusers.models.autoencoders.autoencoder_tiny import AutoencoderTiny
-from diffusers.models.lora import LoRACompatibleConv
-from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
-
-
-@contextmanager
-def set_seamless(model: Union[UNet2DConditionModel, AutoencoderKL, AutoencoderTiny], seamless_axes: List[str]):
-    if not seamless_axes:
-        yield
-        return
-
-    # override conv_forward
-    # https://github.com/huggingface/diffusers/issues/556#issuecomment-1993287019
-    def _conv_forward_asymmetric(self, input: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor] = None):
-        self.paddingX = (self._reversed_padding_repeated_twice[0], self._reversed_padding_repeated_twice[1], 0, 0)
-        self.paddingY = (0, 0, self._reversed_padding_repeated_twice[2], self._reversed_padding_repeated_twice[3])
-        working = torch.nn.functional.pad(input, self.paddingX, mode=x_mode)
-        working = torch.nn.functional.pad(working, self.paddingY, mode=y_mode)
-        return torch.nn.functional.conv2d(
-            working, weight, bias, self.stride, torch.nn.modules.utils._pair(0), self.dilation, self.groups
-        )
-
-    original_layers: List[Tuple[nn.Conv2d, Callable]] = []
-
-    try:
-        x_mode = "circular" if "x" in seamless_axes else "constant"
-        y_mode = "circular" if "y" in seamless_axes else "constant"
-
-        conv_layers: List[torch.nn.Conv2d] = []
-
-        for module in model.modules():
-            if isinstance(module, torch.nn.Conv2d):
-                conv_layers.append(module)
-
-        for layer in conv_layers:
-            if isinstance(layer, LoRACompatibleConv) and layer.lora_layer is None:
-                layer.lora_layer = lambda *x: 0
-            original_layers.append((layer, layer._conv_forward))
-            layer._conv_forward = _conv_forward_asymmetric.__get__(layer, torch.nn.Conv2d)
-
-        yield
-
-    finally:
-        for layer, orig_conv_forward in original_layers:
-            layer._conv_forward = orig_conv_forward

invokeai/backend/util/original_weights_storage.py

@@ -0,0 +1,39 @@
+from __future__ import annotations
+
+from typing import Dict, Iterator, Optional, Tuple
+
+import torch
+
+from invokeai.backend.util.devices import TorchDevice
+
+
+class OriginalWeightsStorage:
+    """A class for tracking the original weights of a model for patch/unpatch operations."""
+
+    def __init__(self, cached_weights: Optional[Dict[str, torch.Tensor]] = None):
+        # The original weights of the model.
+        self._weights: dict[str, torch.Tensor] = {}
+        # The keys of the weights that have been changed (via `save()`) during the lifetime of this instance.
+        self._changed_weights: set[str] = set()
+        if cached_weights:
+            self._weights.update(cached_weights)
+
+    def save(self, key: str, weight: torch.Tensor, copy: bool = True):
+        self._changed_weights.add(key)
+        if key in self._weights:
+            return
+
+        self._weights[key] = weight.detach().to(device=TorchDevice.CPU_DEVICE, copy=copy)
+
+    def get(self, key: str, copy: bool = False) -> Optional[torch.Tensor]:
+        weight = self._weights.get(key, None)
+        if weight is not None and copy:
+            weight = weight.clone()
+        return weight
+
+    def contains(self, key: str) -> bool:
+        return key in self._weights
+
+    def get_changed_weights(self) -> Iterator[Tuple[str, torch.Tensor]]:
+        for key in self._changed_weights:
+            yield key, self._weights[key]

invokeai/frontend/web/package.json

@@ -53,64 +53,63 @@
   },
   "dependencies": {
     "@chakra-ui/react-use-size": "^2.1.0",
-    "@dagrejs/dagre": "^1.1.2",
-    "@dagrejs/graphlib": "^2.2.2",
+    "@dagrejs/dagre": "^1.1.3",
+    "@dagrejs/graphlib": "^2.2.3",
     "@dnd-kit/core": "^6.1.0",
     "@dnd-kit/sortable": "^8.0.0",
     "@dnd-kit/utilities": "^3.2.2",
-    "@fontsource-variable/inter": "^5.0.18",
-    "@invoke-ai/ui-library": "^0.0.25",
-    "@nanostores/react": "^0.7.2",
+    "@fontsource-variable/inter": "^5.0.20",
+    "@invoke-ai/ui-library": "^0.0.29",
+    "@nanostores/react": "^0.7.3",
     "@reduxjs/toolkit": "2.2.3",
     "@roarr/browser-log-writer": "^1.3.0",
-    "chakra-react-select": "^4.7.6",
-    "compare-versions": "^6.1.0",
+    "chakra-react-select": "^4.9.1",
+    "compare-versions": "^6.1.1",
     "dateformat": "^5.0.3",
-    "fracturedjsonjs": "^4.0.1",
-    "framer-motion": "^11.1.8",
-    "i18next": "^23.11.3",
-    "i18next-http-backend": "^2.5.1",
+    "fracturedjsonjs": "^4.0.2",
+    "framer-motion": "^11.3.24",
+    "i18next": "^23.12.2",
+    "i18next-http-backend": "^2.5.2",
     "idb-keyval": "^6.2.1",
     "jsondiffpatch": "^0.6.0",
-    "konva": "^9.3.6",
+    "konva": "^9.3.14",
     "lodash-es": "^4.17.21",
-    "nanostores": "^0.10.3",
+    "nanostores": "^0.11.2",
     "new-github-issue-url": "^1.0.0",
-    "overlayscrollbars": "^2.7.3",
+    "overlayscrollbars": "^2.10.0",
     "overlayscrollbars-react": "^0.5.6",
-    "query-string": "^9.0.0",
+    "query-string": "^9.1.0",
     "react": "^18.3.1",
     "react-colorful": "^5.6.1",
     "react-dom": "^18.3.1",
     "react-dropzone": "^14.2.3",
     "react-error-boundary": "^4.0.13",
-    "react-hook-form": "^7.51.4",
+    "react-hook-form": "^7.52.2",
     "react-hotkeys-hook": "4.5.0",
-    "react-i18next": "^14.1.1",
-    "react-icons": "^5.2.0",
+    "react-i18next": "^14.1.3",
+    "react-icons": "^5.2.1",
     "react-konva": "^18.2.10",
     "react-redux": "9.1.2",
-    "react-resizable-panels": "^2.0.19",
+    "react-resizable-panels": "^2.0.23",
     "react-select": "5.8.0",
-    "react-use": "^17.5.0",
-    "react-virtuoso": "^4.7.10",
-    "reactflow": "^11.11.3",
+    "react-use": "^17.5.1",
+    "react-virtuoso": "^4.9.0",
+    "reactflow": "^11.11.4",
     "redux-dynamic-middlewares": "^2.2.0",
     "redux-remember": "^5.1.0",
     "redux-undo": "^1.1.0",
-    "rfdc": "^1.3.1",
+    "rfdc": "^1.4.1",
     "roarr": "^7.21.1",
     "serialize-error": "^11.0.3",
     "socket.io-client": "^4.7.5",
-    "use-debounce": "^10.0.0",
+    "use-debounce": "^10.0.2",
     "use-device-pixel-ratio": "^1.1.2",
     "use-image": "^1.1.1",
-    "uuid": "^9.0.1",
-    "zod": "^3.23.6",
-    "zod-validation-error": "^3.2.0"
+    "uuid": "^10.0.0",
+    "zod": "^3.23.8",
+    "zod-validation-error": "^3.3.1"
   },
   "peerDependencies": {
-    "@chakra-ui/react": "^2.8.2",
     "react": "^18.2.0",
     "react-dom": "^18.2.0",
     "ts-toolbelt": "^9.6.0"
@@ -118,38 +117,38 @@
   "devDependencies": {
     "@invoke-ai/eslint-config-react": "^0.0.14",
     "@invoke-ai/prettier-config-react": "^0.0.7",
-    "@storybook/addon-essentials": "^8.0.10",
-    "@storybook/addon-interactions": "^8.0.10",
-    "@storybook/addon-links": "^8.0.10",
-    "@storybook/addon-storysource": "^8.0.10",
-    "@storybook/manager-api": "^8.0.10",
-    "@storybook/react": "^8.0.10",
-    "@storybook/react-vite": "^8.0.10",
-    "@storybook/theming": "^8.0.10",
+    "@storybook/addon-essentials": "^8.2.8",
+    "@storybook/addon-interactions": "^8.2.8",
+    "@storybook/addon-links": "^8.2.8",
+    "@storybook/addon-storysource": "^8.2.8",
+    "@storybook/manager-api": "^8.2.8",
+    "@storybook/react": "^8.2.8",
+    "@storybook/react-vite": "^8.2.8",
+    "@storybook/theming": "^8.2.8",
     "@types/dateformat": "^5.0.2",
     "@types/lodash-es": "^4.17.12",
-    "@types/node": "^20.12.10",
-    "@types/react": "^18.3.1",
+    "@types/node": "^20.14.15",
+    "@types/react": "^18.3.3",
     "@types/react-dom": "^18.3.0",
-    "@types/uuid": "^9.0.8",
-    "@vitejs/plugin-react-swc": "^3.6.0",
+    "@types/uuid": "^10.0.0",
+    "@vitejs/plugin-react-swc": "^3.7.0",
     "@vitest/coverage-v8": "^1.5.0",
     "@vitest/ui": "^1.5.0",
     "concurrently": "^8.2.2",
     "dpdm": "^3.14.0",
     "eslint": "^8.57.0",
-    "eslint-plugin-i18next": "^6.0.3",
+    "eslint-plugin-i18next": "^6.0.9",
     "eslint-plugin-path": "^1.3.0",
-    "knip": "^5.12.3",
+    "knip": "^5.27.2",
     "openapi-types": "^12.1.3",
-    "openapi-typescript": "^6.7.5",
-    "prettier": "^3.2.5",
+    "openapi-typescript": "^7.3.0",
+    "prettier": "^3.3.3",
     "rollup-plugin-visualizer": "^5.12.0",
-    "storybook": "^8.0.10",
+    "storybook": "^8.2.8",
     "ts-toolbelt": "^9.6.0",
-    "tsafe": "^1.6.6",
-    "typescript": "^5.4.5",
-    "vite": "^5.2.11",
+    "tsafe": "^1.7.2",
+    "typescript": "^5.5.4",
+    "vite": "^5.4.0",
     "vite-plugin-css-injected-by-js": "^3.5.1",
     "vite-plugin-dts": "^3.9.1",
     "vite-plugin-eslint": "^1.8.1",

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

@@ -77,10 +77,6 @@
             "title": "استعادة الوجوه",
             "desc": "استعادة الصورة الحالية"
         },
-        "upscale": {
-            "title": "تحسين الحجم",
-            "desc": "تحسين حجم الصورة الحالية"
-        },
         "showInfo": {
             "title": "عرض المعلومات",
             "desc": "عرض معلومات البيانات الخاصة بالصورة الحالية"
@@ -255,8 +251,6 @@
         "type": "نوع",
         "strength": "قوة",
         "upscaling": "تصغير",
-        "upscale": "تصغير",
-        "upscaleImage": "تصغير الصورة",
         "scale": "مقياس",
         "imageFit": "ملائمة الصورة الأولية لحجم الخرج",
         "scaleBeforeProcessing": "تحجيم قبل المعالجة",

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

@@ -91,7 +91,8 @@
         "viewingDesc": "Bilder in großer Galerie ansehen",
         "tab": "Tabulator",
         "enabled": "Aktiviert",
-        "disabled": "Ausgeschaltet"
+        "disabled": "Ausgeschaltet",
+        "dontShowMeThese": "Zeig mir diese nicht"
     },
     "gallery": {
         "galleryImageSize": "Bildgröße",
@@ -106,7 +107,6 @@
         "download": "Runterladen",
         "setCurrentImage": "Setze aktuelle Bild",
         "featuresWillReset": "Wenn Sie dieses Bild löschen, werden diese Funktionen sofort zurückgesetzt.",
-        "deleteImageBin": "Gelöschte Bilder werden an den Papierkorb Ihres Betriebssystems gesendet.",
         "unableToLoad": "Galerie kann nicht geladen werden",
         "downloadSelection": "Auswahl herunterladen",
         "currentlyInUse": "Dieses Bild wird derzeit in den folgenden Funktionen verwendet:",
@@ -187,10 +187,6 @@
             "title": "Gesicht restaurieren",
             "desc": "Das aktuelle Bild restaurieren"
         },
-        "upscale": {
-            "title": "Hochskalieren",
-            "desc": "Das aktuelle Bild hochskalieren"
-        },
         "showInfo": {
             "title": "Info anzeigen",
             "desc": "Metadaten des aktuellen Bildes anzeigen"
@@ -433,8 +429,6 @@
         "type": "Art",
         "strength": "Stärke",
         "upscaling": "Hochskalierung",
-        "upscale": "Hochskalieren (Shift + U)",
-        "upscaleImage": "Bild hochskalieren",
         "scale": "Maßstab",
         "imageFit": "Ausgangsbild an Ausgabegröße anpassen",
         "scaleBeforeProcessing": "Skalieren vor der Verarbeitung",
@@ -634,7 +628,10 @@
         "private": "Private Ordner",
         "shared": "Geteilte Ordner",
         "archiveBoard": "Ordner archivieren",
-        "archived": "Archiviert"
+        "archived": "Archiviert",
+        "noBoards": "Kein {boardType}} Ordner",
+        "hideBoards": "Ordner verstecken",
+        "viewBoards": "Ordner ansehen"
     },
     "controlnet": {
         "showAdvanced": "Zeige Erweitert",
@@ -949,6 +946,21 @@
             "paragraphs": [
                 "Reduziert das Ausgangsbild auf die Breite und Höhe des Ausgangsbildes. Empfohlen zu aktivieren."
             ]
+        },
+        "structure": {
+            "paragraphs": [
+                "Die Struktur steuert, wie genau sich das Ausgabebild an das Layout des Originals hält. Eine niedrige Struktur erlaubt größere Änderungen, während eine hohe Struktur die ursprüngliche Komposition und das Layout strikter beibehält."
+            ]
+        },
+        "creativity": {
+            "paragraphs": [
+                "Die Kreativität bestimmt den Grad der Freiheit, die dem Modell beim Hinzufügen von Details gewährt wird. Eine niedrige Kreativität hält sich eng an das Originalbild, während eine hohe Kreativität mehr Veränderungen zulässt. Bei der Verwendung eines Prompts erhöht eine hohe Kreativität den Einfluss des Prompts."
+            ]
+        },
+        "scale": {
+            "paragraphs": [
+                "Die Skalierung steuert die Größe des Ausgabebildes und basiert auf einem Vielfachen der Auflösung des Originalbildes. So würde z. B. eine 2-fache Hochskalierung eines 1024x1024px Bildes eine 2048x2048px große Ausgabe erzeugen."
+            ]
         }
     },
     "invocationCache": {

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

@@ -31,7 +31,8 @@
         "deleteBoard": "Delete Board",
         "deleteBoardAndImages": "Delete Board and Images",
         "deleteBoardOnly": "Delete Board Only",
-        "deletedBoardsCannotbeRestored": "Deleted boards cannot be restored",
+        "deletedBoardsCannotbeRestored": "Deleted boards cannot be restored. Selecting 'Delete Board Only' will move images to an uncategorized state.",
+        "deletedPrivateBoardsCannotbeRestored": "Deleted boards cannot be restored. Selecting 'Delete Board Only' will move images to a private uncategorized state for the image's creator.",
         "hideBoards": "Hide Boards",
         "loading": "Loading...",
         "menuItemAutoAdd": "Auto-add to this Board",
@@ -105,6 +106,7 @@
         "negativePrompt": "Negative Prompt",
         "discordLabel": "Discord",
         "dontAskMeAgain": "Don't ask me again",
+        "dontShowMeThese": "Don't show me these",
         "editor": "Editor",
         "error": "Error",
         "file": "File",
@@ -198,6 +200,7 @@
         "delete": "Delete",
         "depthAnything": "Depth Anything",
         "depthAnythingDescription": "Depth map generation using the Depth Anything technique",
+        "depthAnythingSmallV2": "Small V2",
         "depthMidas": "Depth (Midas)",
         "depthMidasDescription": "Depth map generation using Midas",
         "depthZoe": "Depth (Zoe)",
@@ -371,7 +374,6 @@
         "dropToUpload": "$t(gallery.drop) to Upload",
         "deleteImage_one": "Delete Image",
         "deleteImage_other": "Delete {{count}} Images",
-        "deleteImageBin": "Deleted images will be sent to your operating system's Bin.",
         "deleteImagePermanent": "Deleted images cannot be restored.",
         "displayBoardSearch": "Display Board Search",
         "displaySearch": "Display Search",
@@ -381,7 +383,9 @@
         "featuresWillReset": "If you delete this image, those features will immediately be reset.",
         "galleryImageSize": "Image Size",
         "gallerySettings": "Gallery Settings",
+        "go": "Go",
         "image": "image",
+        "jump": "Jump",
         "loading": "Loading",
         "loadMore": "Load More",
         "newestFirst": "Newest First",
@@ -1049,11 +1053,7 @@
         "remixImage": "Remix Image",
         "usePrompt": "Use Prompt",
         "useSeed": "Use Seed",
-        "width": "Width",
-        "isAllowedToUpscale": {
-            "useX2Model": "Image is too large to upscale with x4 model, use x2 model",
-            "tooLarge": "Image is too large to upscale, select smaller image"
-        }
+        "width": "Width"
     },
     "dynamicPrompts": {
         "showDynamicPrompts": "Show Dynamic Prompts",
@@ -1097,6 +1097,8 @@
         "displayInProgress": "Display Progress Images",
         "enableImageDebugging": "Enable Image Debugging",
         "enableInformationalPopovers": "Enable Informational Popovers",
+        "informationalPopoversDisabled": "Informational Popovers Disabled",
+        "informationalPopoversDisabledDesc": "Informational popovers have been disabled. Enable them in Settings.",
         "enableInvisibleWatermark": "Enable Invisible Watermark",
         "enableNSFWChecker": "Enable NSFW Checker",
         "general": "General",
@@ -1139,6 +1141,8 @@
         "imageSavingFailed": "Image Saving Failed",
         "imageUploaded": "Image Uploaded",
         "imageUploadFailed": "Image Upload Failed",
+        "importFailed": "Import Failed",
+        "importSuccessful": "Import Successful",
         "invalidUpload": "Invalid Upload",
         "loadedWithWarnings": "Workflow Loaded with Warnings",
         "maskSavedAssets": "Mask Saved to Assets",
@@ -1504,6 +1508,30 @@
         "seamlessTilingYAxis": {
             "heading": "Seamless Tiling Y Axis",
             "paragraphs": ["Seamlessly tile an image along the vertical axis."]
+        },
+        "upscaleModel": {
+            "heading": "Upscale Model",
+            "paragraphs": [
+                "The upscale model scales the image to the output size before details are added. Any supported upscale model may be used, but some are specialized for different kinds of images, like photos or line drawings."
+            ]
+        },
+        "scale": {
+            "heading": "Scale",
+            "paragraphs": [
+                "Scale controls the output image size, and is based on a multiple of the input image resolution. For example a 2x upscale on a 1024x1024 image would produce a 2048 x 2048 output."
+            ]
+        },
+        "creativity": {
+            "heading": "Creativity",
+            "paragraphs": [
+                "Creativity controls the amount of freedom granted to the model when adding details. Low creativity stays close to the original image, while high creativity allows for more change. When using a prompt, high creativity increases the influence of the prompt."
+            ]
+        },
+        "structure": {
+            "heading": "Structure",
+            "paragraphs": [
+                "Structure controls how closely the output image will keep to the layout of the original. Low structure allows major changes, while high structure strictly maintains the original composition and layout."
+            ]
         }
     },
     "unifiedCanvas": {
@@ -1647,7 +1675,10 @@
         "layers_other": "Layers"
     },
     "upscaling": {
+        "upscale": "Upscale",
         "creativity": "Creativity",
+        "exceedsMaxSize": "Upscale settings exceed max size limit",
+        "exceedsMaxSizeDetails": "Max upscale limit is {{maxUpscaleDimension}}x{{maxUpscaleDimension}} pixels. Please try a smaller image or decrease your scale selection.",
         "structure": "Structure",
         "upscaleModel": "Upscale Model",
         "postProcessingModel": "Post-Processing Model",
@@ -1661,6 +1692,53 @@
         "missingUpscaleModel": "Missing upscale model",
         "missingTileControlNetModel": "No valid tile ControlNet models installed"
     },
+    "stylePresets": {
+        "active": "Active",
+        "choosePromptTemplate": "Choose Prompt Template",
+        "clearTemplateSelection": "Clear Template Selection",
+        "copyTemplate": "Copy Template",
+        "createPromptTemplate": "Create Prompt Template",
+        "defaultTemplates": "Default Templates",
+        "deleteImage": "Delete Image",
+        "deleteTemplate": "Delete Template",
+        "deleteTemplate2": "Are you sure you want to delete this template? This cannot be undone.",
+        "exportPromptTemplates": "Export My Prompt Templates (CSV)",
+        "editTemplate": "Edit Template",
+        "exportDownloaded": "Export Downloaded",
+        "exportFailed": "Unable to generate and download CSV",
+        "flatten": "Flatten selected template into current prompt",
+        "importTemplates": "Import Prompt Templates (CSV/JSON)",
+        "acceptedColumnsKeys": "Accepted columns/keys:",
+        "nameColumn": "'name'",
+        "positivePromptColumn": "'prompt' or 'positive_prompt'",
+        "negativePromptColumn": "'negative_prompt'",
+        "insertPlaceholder": "Insert placeholder",
+        "myTemplates": "My Templates",
+        "name": "Name",
+        "negativePrompt": "Negative Prompt",
+        "noTemplates": "No templates",
+        "noMatchingTemplates": "No matching templates",
+        "promptTemplatesDesc1": "Prompt templates add text to the prompts you write in the prompt box.",
+        "promptTemplatesDesc2": "Use the placeholder string <Pre>{{placeholder}}</Pre> to specify where your prompt should be included in the template.",
+        "promptTemplatesDesc3": "If you omit the placeholder, the template will be appended to the end of your prompt.",
+        "positivePrompt": "Positive Prompt",
+        "preview": "Preview",
+        "private": "Private",
+        "promptTemplateCleared": "Prompt Template Cleared",
+        "searchByName": "Search by name",
+        "shared": "Shared",
+        "sharedTemplates": "Shared Templates",
+        "templateActions": "Template Actions",
+        "templateDeleted": "Prompt template deleted",
+        "toggleViewMode": "Toggle View Mode",
+        "type": "Type",
+        "unableToDeleteTemplate": "Unable to delete prompt template",
+        "updatePromptTemplate": "Update Prompt Template",
+        "uploadImage": "Upload Image",
+        "useForTemplate": "Use For Prompt Template",
+        "viewList": "View Template List",
+        "viewModeTooltip": "This is how your prompt will look with your currently selected template. To edit your prompt, click anywhere in the text box."
+    },
     "upsell": {
         "inviteTeammates": "Invite Teammates",
         "professional": "Professional",

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

@@ -88,7 +88,6 @@
         "deleteImage_one": "Eliminar Imagen",
         "deleteImage_many": "",
         "deleteImage_other": "",
-        "deleteImageBin": "Las imágenes eliminadas se enviarán a la papelera de tu sistema operativo.",
         "deleteImagePermanent": "Las imágenes eliminadas no se pueden restaurar.",
         "assets": "Activos",
         "autoAssignBoardOnClick": "Asignación automática de tableros al hacer clic"
@@ -151,10 +150,6 @@
             "title": "Restaurar rostros",
             "desc": "Restaurar rostros en la imagen actual"
         },
-        "upscale": {
-            "title": "Aumentar resolución",
-            "desc": "Aumentar la resolución de la imagen actual"
-        },
         "showInfo": {
             "title": "Mostrar información",
             "desc": "Mostar metadatos de la imagen actual"
@@ -360,8 +355,6 @@
         "type": "Tipo",
         "strength": "Fuerza",
         "upscaling": "Aumento de resolución",
-        "upscale": "Aumentar resolución",
-        "upscaleImage": "Aumentar la resolución de la imagen",
         "scale": "Escala",
         "imageFit": "Ajuste tamaño de imagen inicial al tamaño objetivo",
         "scaleBeforeProcessing": "Redimensionar antes de procesar",
@@ -408,7 +401,12 @@
         "showProgressInViewer": "Mostrar las imágenes del progreso en el visor",
         "ui": "Interfaz del usuario",
         "generation": "Generación",
-        "beta": "Beta"
+        "beta": "Beta",
+        "reloadingIn": "Recargando en",
+        "intermediatesClearedFailed": "Error limpiando los intermediarios",
+        "intermediatesCleared_one": "Borrado {{count}} intermediario",
+        "intermediatesCleared_many": "Borrados {{count}} intermediarios",
+        "intermediatesCleared_other": "Borrados {{count}} intermediarios"
     },
     "toast": {
         "uploadFailed": "Error al subir archivo",
@@ -426,7 +424,12 @@
         "parameterSet": "Conjunto de parámetros",
         "parameterNotSet": "Parámetro no configurado",
         "problemCopyingImage": "No se puede copiar la imagen",
-        "errorCopied": "Error al copiar"
+        "errorCopied": "Error al copiar",
+        "baseModelChanged": "Modelo base cambiado",
+        "addedToBoard": "Añadido al tablero",
+        "baseModelChangedCleared_one": "Borrado o desactivado {{count}} submodelo incompatible",
+        "baseModelChangedCleared_many": "Borrados o desactivados {{count}} submodelos incompatibles",
+        "baseModelChangedCleared_other": "Borrados o desactivados {{count}} submodelos incompatibles"
     },
     "tooltip": {
         "feature": {
@@ -540,7 +543,13 @@
         "downloadBoard": "Descargar panel",
         "deleteBoardOnly": "Borrar solo el panel",
         "myBoard": "Mi panel",
-        "noMatching": "No hay paneles que coincidan"
+        "noMatching": "No hay paneles que coincidan",
+        "imagesWithCount_one": "{{count}} imagen",
+        "imagesWithCount_many": "{{count}} imágenes",
+        "imagesWithCount_other": "{{count}} imágenes",
+        "assetsWithCount_one": "{{count}} activo",
+        "assetsWithCount_many": "{{count}} activos",
+        "assetsWithCount_other": "{{count}} activos"
     },
     "accordions": {
         "compositing": {
@@ -590,6 +599,27 @@
         "balanced": "Equilibrado",
         "beginEndStepPercent": "Inicio / Final Porcentaje de pasos",
         "detectResolution": "Detectar resolución",
-        "beginEndStepPercentShort": "Inicio / Final %"
+        "beginEndStepPercentShort": "Inicio / Final %",
+        "t2i_adapter": "$t(controlnet.controlAdapter_one) #{{number}} ($t(common.t2iAdapter))",
+        "controlnet": "$t(controlnet.controlAdapter_one) #{{number}} ($t(common.controlNet))",
+        "ip_adapter": "$t(controlnet.controlAdapter_one) #{{number}} ($t(common.ipAdapter))",
+        "addControlNet": "Añadir $t(common.controlNet)",
+        "addIPAdapter": "Añadir $t(common.ipAdapter)",
+        "controlAdapter_one": "Adaptador de control",
+        "controlAdapter_many": "Adaptadores de control",
+        "controlAdapter_other": "Adaptadores de control",
+        "addT2IAdapter": "Añadir $t(common.t2iAdapter)"
+    },
+    "queue": {
+        "back": "Atrás",
+        "front": "Delante",
+        "batchQueuedDesc_one": "Se agregó {{count}} sesión a {{direction}} la cola",
+        "batchQueuedDesc_many": "Se agregaron {{count}} sesiones a {{direction}} la cola",
+        "batchQueuedDesc_other": "Se agregaron {{count}} sesiones a {{direction}} la cola"
+    },
+    "upsell": {
+        "inviteTeammates": "Invitar compañeros de equipo",
+        "shareAccess": "Compartir acceso",
+        "professionalUpsell": "Disponible en la edición profesional de Invoke. Haz clic aquí o visita invoke.com/pricing para obtener más detalles."
     }
 }

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

@@ -130,10 +130,6 @@
             "title": "Restaurer les visages",
             "desc": "Restaurer l'image actuelle"
         },
-        "upscale": {
-            "title": "Agrandir",
-            "desc": "Agrandir l'image actuelle"
-        },
         "showInfo": {
             "title": "Afficher les informations",
             "desc": "Afficher les informations de métadonnées de l'image actuelle"
@@ -308,8 +304,6 @@
         "type": "Type",
         "strength": "Force",
         "upscaling": "Agrandissement",
-        "upscale": "Agrandir",
-        "upscaleImage": "Image en Agrandissement",
         "scale": "Echelle",
         "imageFit": "Ajuster Image Initiale à la Taille de Sortie",
         "scaleBeforeProcessing": "Echelle Avant Traitement",

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

@@ -90,10 +90,6 @@
             "desc": "שחזור התמונה הנוכחית",
             "title": "שחזור פרצופים"
         },
-        "upscale": {
-            "title": "הגדלת קנה מידה",
-            "desc": "הגדל את התמונה הנוכחית"
-        },
         "showInfo": {
             "title": "הצג מידע",
             "desc": "הצגת פרטי מטא-נתונים של התמונה הנוכחית"
@@ -263,8 +259,6 @@
         "seed": "זרע",
         "type": "סוג",
         "strength": "חוזק",
-        "upscale": "הגדלת קנה מידה",
-        "upscaleImage": "הגדלת קנה מידת התמונה",
         "denoisingStrength": "חוזק מנטרל הרעש",
         "scaleBeforeProcessing": "שנה קנה מידה לפני עיבוד",
         "scaledWidth": "קנה מידה לאחר שינוי W",

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

@@ -89,7 +89,8 @@
         "enabled": "Abilitato",
         "disabled": "Disabilitato",
         "comparingDesc": "Confronta due immagini",
-        "comparing": "Confronta"
+        "comparing": "Confronta",
+        "dontShowMeThese": "Non mostrare più"
     },
     "gallery": {
         "galleryImageSize": "Dimensione dell'immagine",
@@ -101,7 +102,6 @@
         "deleteImage_many": "Elimina {{count}} immagini",
         "deleteImage_other": "Elimina {{count}} immagini",
         "deleteImagePermanent": "Le immagini eliminate non possono essere ripristinate.",
-        "deleteImageBin": "Le immagini eliminate verranno spostate nel cestino del tuo sistema operativo.",
         "assets": "Risorse",
         "autoAssignBoardOnClick": "Assegna automaticamente la bacheca al clic",
         "featuresWillReset": "Se elimini questa immagine, quelle funzionalità verranno immediatamente ripristinate.",
@@ -150,7 +150,13 @@
         "showArchivedBoards": "Mostra le bacheche archiviate",
         "searchImages": "Ricerca per metadati",
         "displayBoardSearch": "Mostra la ricerca nelle Bacheche",
-        "displaySearch": "Mostra la ricerca"
+        "displaySearch": "Mostra la ricerca",
+        "selectAllOnPage": "Seleziona tutto nella pagina",
+        "selectAllOnBoard": "Seleziona tutto nella bacheca",
+        "exitBoardSearch": "Esci da Ricerca bacheca",
+        "exitSearch": "Esci dalla ricerca",
+        "go": "Vai",
+        "jump": "Salta"
     },
     "hotkeys": {
         "keyboardShortcuts": "Tasti di scelta rapida",
@@ -210,10 +216,6 @@
             "title": "Restaura volti",
             "desc": "Restaura l'immagine corrente"
         },
-        "upscale": {
-            "title": "Amplia",
-            "desc": "Amplia l'immagine corrente"
-        },
         "showInfo": {
             "title": "Mostra informazioni",
             "desc": "Mostra le informazioni sui metadati dell'immagine corrente"
@@ -377,6 +379,10 @@
         "toggleViewer": {
             "title": "Attiva/disattiva il visualizzatore di immagini",
             "desc": "Passa dal visualizzatore immagini all'area di lavoro per la scheda corrente."
+        },
+        "postProcess": {
+            "desc": "Elabora l'immagine corrente utilizzando il modello di post-elaborazione selezionato",
+            "title": "Elabora immagine"
         }
     },
     "modelManager": {
@@ -505,8 +511,6 @@
         "type": "Tipo",
         "strength": "Forza",
         "upscaling": "Ampliamento",
-        "upscale": "Amplia (Shift + U)",
-        "upscaleImage": "Amplia Immagine",
         "scale": "Scala",
         "imageFit": "Adatta l'immagine iniziale alle dimensioni di output",
         "scaleBeforeProcessing": "Scala prima dell'elaborazione",
@@ -569,10 +573,6 @@
         },
         "useCpuNoise": "Usa la CPU per generare rumore",
         "iterations": "Iterazioni",
-        "isAllowedToUpscale": {
-            "useX2Model": "L'immagine è troppo grande per l'ampliamento con il modello x4, utilizza il modello x2",
-            "tooLarge": "L'immagine è troppo grande per l'ampliamento, seleziona un'immagine più piccola"
-        },
         "imageActions": "Azioni Immagine",
         "cfgRescaleMultiplier": "Moltiplicatore riscala CFG",
         "useSize": "Usa Dimensioni",
@@ -591,7 +591,10 @@
         "infillColorValue": "Colore di riempimento",
         "globalSettings": "Impostazioni globali",
         "globalPositivePromptPlaceholder": "Prompt positivo globale",
-        "globalNegativePromptPlaceholder": "Prompt negativo globale"
+        "globalNegativePromptPlaceholder": "Prompt negativo globale",
+        "processImage": "Elabora Immagine",
+        "sendToUpscale": "Invia a Ampliare",
+        "postProcessing": "Post-elaborazione (Shift + U)"
     },
     "settings": {
         "models": "Modelli",
@@ -625,7 +628,9 @@
         "enableNSFWChecker": "Abilita controllo NSFW",
         "enableInvisibleWatermark": "Abilita filigrana invisibile",
         "enableInformationalPopovers": "Abilita testo informativo a comparsa",
-        "reloadingIn": "Ricaricando in"
+        "reloadingIn": "Ricaricando in",
+        "informationalPopoversDisabled": "Testo informativo a comparsa disabilitato",
+        "informationalPopoversDisabledDesc": "I testi informativi a comparsa sono disabilitati. Attivali nelle impostazioni."
     },
     "toast": {
         "uploadFailed": "Caricamento fallito",
@@ -696,7 +701,9 @@
         "baseModelChanged": "Modello base modificato",
         "sessionRef": "Sessione: {{sessionId}}",
         "somethingWentWrong": "Qualcosa è andato storto",
-        "outOfMemoryErrorDesc": "Le impostazioni della generazione attuale superano la capacità del sistema. Modifica le impostazioni e riprova."
+        "outOfMemoryErrorDesc": "Le impostazioni della generazione attuale superano la capacità del sistema. Modifica le impostazioni e riprova.",
+        "importFailed": "Importazione non riuscita",
+        "importSuccessful": "Importazione riuscita"
     },
     "tooltip": {
         "feature": {
@@ -922,7 +929,7 @@
         "missingInvocationTemplate": "Modello di invocazione mancante",
         "missingFieldTemplate": "Modello di campo mancante",
         "singleFieldType": "{{name}} (Singola)",
-        "imageAccessError": "Impossibile trovare l'immagine {{image_name}}, ripristino delle impostazioni predefinite",
+        "imageAccessError": "Impossibile trovare l'immagine {{image_name}}, ripristino ai valori predefiniti",
         "boardAccessError": "Impossibile trovare la bacheca {{board_id}}, ripristino ai valori predefiniti",
         "modelAccessError": "Impossibile trovare il modello {{key}}, ripristino ai valori predefiniti"
     },
@@ -946,7 +953,7 @@
         "deleteBoardOnly": "solo la Bacheca",
         "deleteBoard": "Elimina Bacheca",
         "deleteBoardAndImages": "Bacheca e Immagini",
-        "deletedBoardsCannotbeRestored": "Le bacheche eliminate non possono essere ripristinate",
+        "deletedBoardsCannotbeRestored": "Le bacheche eliminate non possono essere ripristinate. Selezionando \"Elimina solo bacheca\" le immagini verranno spostate nella bacheca \"Non categorizzato\".",
         "movingImagesToBoard_one": "Spostare {{count}} immagine nella bacheca:",
         "movingImagesToBoard_many": "Spostare {{count}} immagini nella bacheca:",
         "movingImagesToBoard_other": "Spostare {{count}} immagini nella bacheca:",
@@ -964,7 +971,11 @@
         "boards": "Bacheche",
         "private": "Bacheche private",
         "shared": "Bacheche condivise",
-        "addPrivateBoard": "Aggiungi una Bacheca Privata"
+        "addPrivateBoard": "Aggiungi una Bacheca Privata",
+        "noBoards": "Nessuna bacheca {{boardType}}",
+        "hideBoards": "Nascondi bacheche",
+        "viewBoards": "Visualizza bacheche",
+        "deletedPrivateBoardsCannotbeRestored": "Le bacheche cancellate non possono essere ripristinate. Selezionando 'Cancella solo bacheca', le immagini verranno spostate nella bacheca \"Non categorizzato\" privata dell'autore dell'immagine."
     },
     "controlnet": {
         "contentShuffleDescription": "Rimescola il contenuto di un'immagine",
@@ -1508,6 +1519,30 @@
             "paragraphs": [
                 "Metodo con cui applicare l'adattatore IP corrente."
             ]
+        },
+        "scale": {
+            "heading": "Scala",
+            "paragraphs": [
+                "La scala controlla la dimensione dell'immagine di uscita e si basa su un multiplo della risoluzione dell'immagine di ingresso. Ad esempio, un ampliamento 2x su un'immagine 1024x1024 produrrebbe in uscita a 2048x2048."
+            ]
+        },
+        "upscaleModel": {
+            "paragraphs": [
+                "Il modello di ampliamento (Upscale), scala l'immagine alle dimensioni di uscita prima di aggiungere i dettagli. È possibile utilizzare qualsiasi modello di ampliamento supportato, ma alcuni sono specializzati per diversi tipi di immagini, come foto o disegni al tratto."
+            ],
+            "heading": "Modello di ampliamento"
+        },
+        "creativity": {
+            "heading": "Creatività",
+            "paragraphs": [
+                "La creatività controlla quanta libertà è concessa al modello quando si aggiungono dettagli. Una creatività bassa rimane vicina all'immagine originale, mentre una creatività alta consente più cambiamenti. Quando si usa un prompt, una creatività alta aumenta l'influenza del prompt."
+            ]
+        },
+        "structure": {
+            "heading": "Struttura",
+            "paragraphs": [
+                "La struttura determina quanto l'immagine finale rispecchierà il layout dell'originale. Una struttura bassa permette cambiamenti significativi, mentre una struttura alta conserva la composizione e il layout originali."
+            ]
         }
     },
     "sdxl": {
@@ -1684,7 +1719,76 @@
             "models": "Modelli",
             "modelsTab": "$t(ui.tabs.models) $t(common.tab)",
             "queue": "Coda",
-            "queueTab": "$t(ui.tabs.queue) $t(common.tab)"
+            "queueTab": "$t(ui.tabs.queue) $t(common.tab)",
+            "upscaling": "Ampliamento",
+            "upscalingTab": "$t(ui.tabs.upscaling) $t(common.tab)"
         }
+    },
+    "upscaling": {
+        "creativity": "Creatività",
+        "structure": "Struttura",
+        "upscaleModel": "Modello di Ampliamento",
+        "scale": "Scala",
+        "missingModelsWarning": "Visita <LinkComponent>Gestione modelli</LinkComponent> per installare i modelli richiesti:",
+        "mainModelDesc": "Modello principale (architettura SD1.5 o SDXL)",
+        "tileControlNetModelDesc": "Modello Tile ControlNet per l'architettura del modello principale scelto",
+        "upscaleModelDesc": "Modello per l'ampliamento (da immagine a immagine)",
+        "missingUpscaleInitialImage": "Immagine iniziale mancante per l'ampliamento",
+        "missingUpscaleModel": "Modello per l’ampliamento mancante",
+        "missingTileControlNetModel": "Nessun modello ControlNet Tile valido installato",
+        "postProcessingModel": "Modello di post-elaborazione",
+        "postProcessingMissingModelWarning": "Visita <LinkComponent>Gestione modelli</LinkComponent> per installare un modello di post-elaborazione (da immagine a immagine).",
+        "exceedsMaxSize": "Le impostazioni di ampliamento superano il limite massimo delle dimensioni",
+        "exceedsMaxSizeDetails": "Il limite massimo di ampliamento è {{maxUpscaleDimension}}x{{maxUpscaleDimension}} pixel. Prova un'immagine più piccola o diminuisci la scala selezionata."
+    },
+    "upsell": {
+        "inviteTeammates": "Invita collaboratori",
+        "shareAccess": "Condividi l'accesso",
+        "professional": "Professionale",
+        "professionalUpsell": "Disponibile nell'edizione Professional di Invoke. Fai clic qui o visita invoke.com/pricing per ulteriori dettagli."
+    },
+    "stylePresets": {
+        "active": "Attivo",
+        "choosePromptTemplate": "Scegli un modello di prompt",
+        "clearTemplateSelection": "Cancella selezione modello",
+        "copyTemplate": "Copia modello",
+        "createPromptTemplate": "Crea modello di prompt",
+        "defaultTemplates": "Modelli predefiniti",
+        "deleteImage": "Elimina immagine",
+        "deleteTemplate": "Elimina modello",
+        "editTemplate": "Modifica modello",
+        "flatten": "Unisci il modello selezionato al prompt corrente",
+        "insertPlaceholder": "Inserisci segnaposto",
+        "myTemplates": "I miei modelli",
+        "name": "Nome",
+        "negativePrompt": "Prompt Negativo",
+        "noMatchingTemplates": "Nessun modello corrispondente",
+        "promptTemplatesDesc1": "I modelli di prompt aggiungono testo ai prompt che scrivi nelle caselle dei prompt.",
+        "promptTemplatesDesc3": "Se si omette il segnaposto, il modello verrà aggiunto alla fine del prompt.",
+        "positivePrompt": "Prompt Positivo",
+        "preview": "Anteprima",
+        "private": "Privato",
+        "searchByName": "Cerca per nome",
+        "shared": "Condiviso",
+        "sharedTemplates": "Modelli condivisi",
+        "templateDeleted": "Modello di prompt eliminato",
+        "toggleViewMode": "Attiva/disattiva visualizzazione",
+        "uploadImage": "Carica immagine",
+        "useForTemplate": "Usa per modello di prompt",
+        "viewList": "Visualizza l'elenco dei modelli",
+        "viewModeTooltip": "Ecco come apparirà il tuo prompt con il modello attualmente selezionato. Per modificare il tuo prompt, clicca in un punto qualsiasi della casella di testo.",
+        "deleteTemplate2": "Vuoi davvero eliminare questo modello? Questa operazione non può essere annullata.",
+        "unableToDeleteTemplate": "Impossibile eliminare il modello di prompt",
+        "updatePromptTemplate": "Aggiorna il modello di prompt",
+        "type": "Tipo",
+        "promptTemplatesDesc2": "Utilizza la stringa segnaposto <Pre>{{placeholder}}</Pre> per specificare dove inserire il tuo prompt nel modello.",
+        "importTemplates": "Importa modelli di prompt (CSV/JSON)",
+        "exportDownloaded": "Esportazione completata",
+        "exportFailed": "Impossibile generare e scaricare il file CSV",
+        "exportPromptTemplates": "Esporta i miei modelli di prompt (CSV)",
+        "positivePromptColumn": "'prompt' o 'positive_prompt'",
+        "noTemplates": "Nessun modello",
+        "acceptedColumnsKeys": "Colonne/chiavi accettate:",
+        "templateActions": "Azioni modello"
     }
 }

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

@@ -109,7 +109,6 @@
         "drop": "ドロップ",
         "dropOrUpload": "$t(gallery.drop) またはアップロード",
         "deleteImage_other": "画像を削除",
-        "deleteImageBin": "削除された画像はOSのゴミ箱に送られます。",
         "deleteImagePermanent": "削除された画像は復元できません。",
         "download": "ダウンロード",
         "unableToLoad": "ギャラリーをロードできません",
@@ -199,10 +198,6 @@
             "title": "顔の修復",
             "desc": "現在の画像を修復"
         },
-        "upscale": {
-            "title": "アップスケール",
-            "desc": "現在の画像をアップスケール"
-        },
         "showInfo": {
             "title": "情報を見る",
             "desc": "現在の画像のメタデータ情報を表示"
@@ -427,8 +422,6 @@
         "shuffle": "シャッフル",
         "strength": "強度",
         "upscaling": "アップスケーリング",
-        "upscale": "アップスケール",
-        "upscaleImage": "画像をアップスケール",
         "scale": "Scale",
         "scaleBeforeProcessing": "処理前のスケール",
         "scaledWidth": "幅のスケール",

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

@@ -70,7 +70,6 @@
         "gallerySettings": "갤러리 설정",
         "deleteSelection": "선택 항목 삭제",
         "featuresWillReset": "이 이미지를 삭제하면 해당 기능이 즉시 재설정됩니다.",
-        "deleteImageBin": "삭제된 이미지는 운영 체제의 Bin으로 전송됩니다.",
         "assets": "자산",
         "problemDeletingImagesDesc": "하나 이상의 이미지를 삭제할 수 없습니다",
         "noImagesInGallery": "보여줄 이미지가 없음",
@@ -258,10 +257,6 @@
             "desc": "캔버스 브러시를 선택",
             "title": "브러시 선택"
         },
-        "upscale": {
-            "desc": "현재 이미지를 업스케일",
-            "title": "업스케일"
-        },
         "previousImage": {
             "title": "이전 이미지",
             "desc": "갤러리에 이전 이미지 표시"

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

@@ -97,7 +97,6 @@
         "noImagesInGallery": "Geen afbeeldingen om te tonen",
         "deleteImage_one": "Verwijder afbeelding",
         "deleteImage_other": "",
-        "deleteImageBin": "Verwijderde afbeeldingen worden naar de prullenbak van je besturingssysteem gestuurd.",
         "deleteImagePermanent": "Verwijderde afbeeldingen kunnen niet worden hersteld.",
         "assets": "Eigen onderdelen",
         "autoAssignBoardOnClick": "Ken automatisch bord toe bij klikken",
@@ -168,10 +167,6 @@
             "title": "Herstel gezichten",
             "desc": "Herstelt de huidige afbeelding"
         },
-        "upscale": {
-            "title": "Schaal op",
-            "desc": "Schaalt de huidige afbeelding op"
-        },
         "showInfo": {
             "title": "Toon info",
             "desc": "Toont de metagegevens van de huidige afbeelding"
@@ -412,8 +407,6 @@
         "type": "Soort",
         "strength": "Sterkte",
         "upscaling": "Opschalen",
-        "upscale": "Vergroot (Shift + U)",
-        "upscaleImage": "Schaal afbeelding op",
         "scale": "Schaal",
         "imageFit": "Pas initiële afbeelding in uitvoergrootte",
         "scaleBeforeProcessing": "Schalen voor verwerking",
@@ -473,10 +466,6 @@
             },
             "imageNotProcessedForControlAdapter": "De afbeelding van controle-adapter #{{number}} is niet verwerkt"
         },
-        "isAllowedToUpscale": {
-            "useX2Model": "Afbeelding is te groot om te vergroten met het x4-model. Gebruik hiervoor het x2-model",
-            "tooLarge": "Afbeelding is te groot om te vergoten. Kies een kleinere afbeelding"
-        },
         "patchmatchDownScaleSize": "Verklein",
         "useCpuNoise": "Gebruik CPU-ruis",
         "imageActions": "Afbeeldingshandeling",

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

@@ -78,10 +78,6 @@
             "title": "Popraw twarze",
             "desc": "Uruchamia proces poprawiania twarzy dla aktywnego obrazu"
         },
-        "upscale": {
-            "title": "Powiększ",
-            "desc": "Uruchamia proces powiększania aktywnego obrazu"
-        },
         "showInfo": {
             "title": "Pokaż informacje",
             "desc": "Pokazuje metadane zapisane w aktywnym obrazie"
@@ -232,8 +228,6 @@
         "type": "Metoda",
         "strength": "Siła",
         "upscaling": "Powiększanie",
-        "upscale": "Powiększ",
-        "upscaleImage": "Powiększ obraz",
         "scale": "Skala",
         "imageFit": "Przeskaluj oryginalny obraz",
         "scaleBeforeProcessing": "Tryb skalowania",

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

@@ -160,10 +160,6 @@
             "title": "Restaurar Rostos",
             "desc": "Restaurar a imagem atual"
         },
-        "upscale": {
-            "title": "Redimensionar",
-            "desc": "Redimensionar a imagem atual"
-        },
         "showInfo": {
             "title": "Mostrar Informações",
             "desc": "Mostrar metadados de informações da imagem atual"
@@ -275,8 +271,6 @@
         "showOptionsPanel": "Mostrar Painel de Opções",
         "strength": "Força",
         "upscaling": "Redimensionando",
-        "upscale": "Redimensionar",
-        "upscaleImage": "Redimensionar Imagem",
         "scaleBeforeProcessing": "Escala Antes do Processamento",
         "images": "Imagems",
         "steps": "Passos",