chore: bump version to v5.3.0

- Restore dedicated `Apply` buttons
- Remove icons from the buttons, too much noise when the words are short and clear
- Update loading state to show a spinner next to the `Process` button instead of on _every_ button

docker/Dockerfile

@@ -38,9 +38,9 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ] || [ "$GPU_DRIVER" = "cpu" ]; then \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cpu"; \
     elif [ "$GPU_DRIVER" = "rocm" ]; then \
-        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm5.6"; \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm6.1"; \
     else \
-        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu124"; \
     fi &&\
 
     # xformers + triton fails to install on arm64

docs/contributing/dev-environment.md

@@ -17,46 +17,49 @@ If you just want to use Invoke, you should use the [installer][installer link].
 ## Setup
 
 1. Run through the [requirements][requirements link].
-1. [Fork and clone][forking link] the [InvokeAI repo][repo link].
-1. Create an directory for user data (images, models, db, etc). This is typically at `~/invokeai`, but if you already have a non-dev install, you may want to create a separate directory for the dev install.
-1. Create a python virtual environment inside the directory you just created:
+2. [Fork and clone][forking link] the [InvokeAI repo][repo link].
+3. Create an directory for user data (images, models, db, etc). This is typically at `~/invokeai`, but if you already have a non-dev install, you may want to create a separate directory for the dev install.
+4. Create a python virtual environment inside the directory you just created:
 
-   ```sh
-   python3 -m venv .venv --prompt InvokeAI-Dev
-   ```
+      ```sh
+      python3 -m venv .venv --prompt InvokeAI-Dev
+      ```
 
-1. Activate the venv (you'll need to do this every time you want to run the app):
+5. Activate the venv (you'll need to do this every time you want to run the app):
 
-   ```sh
-   source .venv/bin/activate
-   ```
+        ```sh
+        source .venv/bin/activate
+        ```
 
-1. Install the repo as an [editable install][editable install link]:
+6. Install the repo as an [editable install][editable install link]:
 
-   ```sh
-   pip install -e ".[dev,test,xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
-   ```
+      ```sh
+      pip install -e ".[dev,test,xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu121
+      ```
 
-   Refer to the [manual installation][manual install link]] instructions for more determining the correct install options. `xformers` is optional, but `dev` and `test` are not.
+      Refer to the [manual installation][manual install link]] instructions for more determining the correct install options. `xformers` is optional, but `dev` and `test` are not.
 
-1. Install the frontend dev toolchain:
+7. Install the frontend dev toolchain:
 
    - [`nodejs`](https://nodejs.org/) (recommend v20 LTS)
-   - [`pnpm`](https://pnpm.io/installation#installing-a-specific-version) (must be v8 - not v9!)
+   - [`pnpm`](https://pnpm.io/8.x/installation) (must be v8 - not v9!)
 
-1. Do a production build of the frontend:
+8. Do a production build of the frontend:
 
-   ```sh
-   pnpm build
-   ```
+      ```sh
+      cd PATH_TO_INVOKEAI_REPO/invokeai/frontend/web
+      pnpm i
+      pnpm build
+      ```
 
-1. Start the application:
+9. Start the application:
 
-   ```sh
-   python scripts/invokeai-web.py
-   ```
+      ```sh
+      cd PATH_TO_INVOKEAI_REPO
+      python scripts/invokeai-web.py
+      ```
 
-1. Access the UI at `localhost:9090`.
+10. Access the UI at `localhost:9090`.
 
 ## Updating the UI
 

installer/install.sh.in

@@ -12,7 +12,7 @@ MINIMUM_PYTHON_VERSION=3.10.0
 MAXIMUM_PYTHON_VERSION=3.11.100
 PYTHON=""
 for candidate in python3.11 python3.10 python3 python ; do
-    if ppath=`which $candidate`; then
+    if ppath=`which $candidate 2>/dev/null`; then
         # when using `pyenv`, the executable for an inactive Python version will exist but will not be operational
         # we check that this found executable can actually run
         if [ $($candidate --version &>/dev/null; echo ${PIPESTATUS}) -gt 0 ]; then continue; fi
@@ -30,10 +30,11 @@ done
 if [ -z "$PYTHON" ]; then
     echo "A suitable Python interpreter could not be found"
     echo "Please install Python $MINIMUM_PYTHON_VERSION or higher (maximum $MAXIMUM_PYTHON_VERSION) before running this script. See instructions at $INSTRUCTIONS for help."
-    echo "For the best user experience we suggest enlarging or maximizing this window now."
     read -p "Press any key to exit"
     exit -1
 fi
 
+echo "For the best user experience we suggest enlarging or maximizing this window now."
+
 exec $PYTHON ./lib/main.py ${@}
 read -p "Press any key to exit"

installer/lib/installer.py

@@ -245,6 +245,9 @@ class InvokeAiInstance:
 
         pip = local[self.pip]
 
+        # Uninstall xformers if it is present; the correct version of it will be reinstalled if needed
+        _ = pip["uninstall", "-yqq", "xformers"] & FG
+
         pipeline = pip[
             "install",
             "--require-virtualenv",
@@ -282,12 +285,6 @@ class InvokeAiInstance:
             shutil.copy(src, dest)
             os.chmod(dest, 0o0755)
 
-    def update(self):
-        pass
-
-    def remove(self):
-        pass
-
 
 ### Utility functions ###
 
@@ -402,7 +399,7 @@ def get_torch_source() -> Tuple[str | None, str | None]:
     :rtype: list
     """
 
-    from messages import select_gpu
+    from messages import GpuType, select_gpu
 
     # device can be one of: "cuda", "rocm", "cpu", "cuda_and_dml, autodetect"
     device = select_gpu()
@@ -412,15 +409,21 @@ def get_torch_source() -> Tuple[str | None, str | None]:
     url = None
     optional_modules: str | None = None
     if OS == "Linux":
-        if device.value == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.6"
-        elif device.value == "cpu":
+        if device == GpuType.ROCM:
+            url = "https://download.pytorch.org/whl/rocm6.1"
+        elif device == GpuType.CPU:
             url = "https://download.pytorch.org/whl/cpu"
-        elif device.value == "cuda":
-            # CUDA uses the default PyPi index
+        elif device == GpuType.CUDA:
+            url = "https://download.pytorch.org/whl/cu124"
+            optional_modules = "[onnx-cuda]"
+        elif device == GpuType.CUDA_WITH_XFORMERS:
+            url = "https://download.pytorch.org/whl/cu124"
             optional_modules = "[xformers,onnx-cuda]"
     elif OS == "Windows":
-        if device.value == "cuda":
+        if device == GpuType.CUDA:
+            url = "https://download.pytorch.org/whl/cu124"
+            optional_modules = "[onnx-cuda]"
+        elif device == GpuType.CUDA_WITH_XFORMERS:
             url = "https://download.pytorch.org/whl/cu124"
             optional_modules = "[xformers,onnx-cuda]"
         elif device.value == "cpu":

installer/lib/messages.py

@@ -206,6 +206,7 @@ def dest_path(dest: Optional[str | Path] = None) -> Path | None:
 
 
 class GpuType(Enum):
+    CUDA_WITH_XFORMERS = "xformers"
     CUDA = "cuda"
     ROCM = "rocm"
     CPU = "cpu"
@@ -221,11 +222,15 @@ def select_gpu() -> GpuType:
         return GpuType.CPU
 
     nvidia = (
-        "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
+        "an [gold1 b]NVIDIA[/] RTX 3060 or newer GPU using CUDA",
         GpuType.CUDA,
     )
+    vintage_nvidia = (
+        "an [gold1 b]NVIDIA[/] RTX 20xx or older GPU using CUDA+xFormers",
+        GpuType.CUDA_WITH_XFORMERS,
+    )
     amd = (
-        "an [gold1 b]AMD[/] GPU (using ROCm™)",
+        "an [gold1 b]AMD[/] GPU using ROCm",
         GpuType.ROCM,
     )
     cpu = (
@@ -235,14 +240,13 @@ def select_gpu() -> GpuType:
 
     options = []
     if OS == "Windows":
-        options = [nvidia, cpu]
+        options = [nvidia, vintage_nvidia, cpu]
     if OS == "Linux":
-        options = [nvidia, amd, cpu]
+        options = [nvidia, vintage_nvidia, amd, cpu]
     elif OS == "Darwin":
         options = [cpu]
 
     if len(options) == 1:
-        print(f'Your platform [gold1]{OS}-{ARCH}[/] only supports the "{options[0][1]}" driver. Proceeding with that.')
         return options[0][1]
 
     options = {str(i): opt for i, opt in enumerate(options, 1)}

invokeai/app/api/routers/boards.py

@@ -5,9 +5,10 @@ from fastapi.routing import APIRouter
 from pydantic import BaseModel, Field
 
 from invokeai.app.api.dependencies import ApiDependencies
-from invokeai.app.services.board_records.board_records_common import BoardChanges
+from invokeai.app.services.board_records.board_records_common import BoardChanges, BoardRecordOrderBy
 from invokeai.app.services.boards.boards_common import BoardDTO
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+from invokeai.app.services.shared.sqlite.sqlite_common import SQLiteDirection
 
 boards_router = APIRouter(prefix="/v1/boards", tags=["boards"])
 
@@ -115,6 +116,8 @@ async def delete_board(
     response_model=Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]],
 )
 async def list_boards(
+    order_by: BoardRecordOrderBy = Query(default=BoardRecordOrderBy.CreatedAt, description="The attribute to order by"),
+    direction: SQLiteDirection = Query(default=SQLiteDirection.Descending, description="The direction to order by"),
     all: Optional[bool] = Query(default=None, description="Whether to list all boards"),
     offset: Optional[int] = Query(default=None, description="The page offset"),
     limit: Optional[int] = Query(default=None, description="The number of boards per page"),
@@ -122,9 +125,9 @@ async def list_boards(
 ) -> Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]]:
     """Gets a list of boards"""
     if all:
-        return ApiDependencies.invoker.services.boards.get_all(include_archived)
+        return ApiDependencies.invoker.services.boards.get_all(order_by, direction, include_archived)
     elif offset is not None and limit is not None:
-        return ApiDependencies.invoker.services.boards.get_many(offset, limit, include_archived)
+        return ApiDependencies.invoker.services.boards.get_many(order_by, direction, offset, limit, include_archived)
     else:
         raise HTTPException(
             status_code=400,

invokeai/app/api/routers/model_manager.py

@@ -38,7 +38,12 @@ from invokeai.backend.model_manager.load.model_cache.model_cache_base import Cac
 from invokeai.backend.model_manager.metadata.fetch.huggingface import HuggingFaceMetadataFetch
 from invokeai.backend.model_manager.metadata.metadata_base import ModelMetadataWithFiles, UnknownMetadataException
 from invokeai.backend.model_manager.search import ModelSearch
-from invokeai.backend.model_manager.starter_models import STARTER_MODELS, StarterModel, StarterModelWithoutDependencies
+from invokeai.backend.model_manager.starter_models import (
+    STARTER_BUNDLES,
+    STARTER_MODELS,
+    StarterModel,
+    StarterModelWithoutDependencies,
+)
 
 model_manager_router = APIRouter(prefix="/v2/models", tags=["model_manager"])
 
@@ -792,22 +797,52 @@ async def convert_model(
     return new_config
 
 
-@model_manager_router.get("/starter_models", operation_id="get_starter_models", response_model=list[StarterModel])
-async def get_starter_models() -> list[StarterModel]:
+class StarterModelResponse(BaseModel):
+    starter_models: list[StarterModel]
+    starter_bundles: dict[str, list[StarterModel]]
+
+
+def get_is_installed(
+    starter_model: StarterModel | StarterModelWithoutDependencies, installed_models: list[AnyModelConfig]
+) -> bool:
+    for model in installed_models:
+        if model.source == starter_model.source:
+            return True
+        if (
+            (model.name == starter_model.name or model.name in starter_model.previous_names)
+            and model.base == starter_model.base
+            and model.type == starter_model.type
+        ):
+            return True
+    return False
+
+
+@model_manager_router.get("/starter_models", operation_id="get_starter_models", response_model=StarterModelResponse)
+async def get_starter_models() -> StarterModelResponse:
     installed_models = ApiDependencies.invoker.services.model_manager.store.search_by_attr()
-    installed_model_sources = {m.source for m in installed_models}
     starter_models = deepcopy(STARTER_MODELS)
+    starter_bundles = deepcopy(STARTER_BUNDLES)
     for model in starter_models:
-        if model.source in installed_model_sources:
-            model.is_installed = True
+        model.is_installed = get_is_installed(model, installed_models)
         # Remove already-installed dependencies
         missing_deps: list[StarterModelWithoutDependencies] = []
+
         for dep in model.dependencies or []:
-            if dep.source not in installed_model_sources:
+            if not get_is_installed(dep, installed_models):
                 missing_deps.append(dep)
         model.dependencies = missing_deps
 
-    return starter_models
+    for bundle in starter_bundles.values():
+        for model in bundle:
+            model.is_installed = get_is_installed(model, installed_models)
+            # Remove already-installed dependencies
+            missing_deps: list[StarterModelWithoutDependencies] = []
+            for dep in model.dependencies or []:
+                if not get_is_installed(dep, installed_models):
+                    missing_deps.append(dep)
+            model.dependencies = missing_deps
+
+    return StarterModelResponse(starter_models=starter_models, starter_bundles=starter_bundles)
 
 
 @model_manager_router.get(

invokeai/app/api/routers/workflows.py

@@ -88,7 +88,7 @@ async def list_workflows(
         default=WorkflowRecordOrderBy.Name, description="The attribute to order by"
     ),
     direction: SQLiteDirection = Query(default=SQLiteDirection.Ascending, description="The direction to order by"),
-    category: Optional[WorkflowCategory] = Query(default=None, description="The category of workflow to get"),
+    category: WorkflowCategory = Query(default=WorkflowCategory.User, description="The category of workflow to get"),
     query: Optional[str] = Query(default=None, description="The text to query by (matches name and description)"),
 ) -> PaginatedResults[WorkflowRecordListItemDTO]:
     """Gets a page of workflows"""

invokeai/app/invocations/denoise_latents.py

@@ -547,7 +547,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 if not isinstance(single_ipa_image_fields, list):
                     single_ipa_image_fields = [single_ipa_image_fields]
 
-                single_ipa_images = [context.images.get_pil(image.image_name) for image in single_ipa_image_fields]
+                single_ipa_images = [
+                    context.images.get_pil(image.image_name, mode="RGB") for image in single_ipa_image_fields
+                ]
                 with image_encoder_model_info as image_encoder_model:
                     assert isinstance(image_encoder_model, CLIPVisionModelWithProjection)
                     # Get image embeddings from CLIP and ImageProjModel.

invokeai/app/invocations/fields.py

@@ -192,6 +192,7 @@ class FieldDescriptions:
     freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
     freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
     freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."
+    instantx_control_mode = "The control mode for InstantX ControlNet union models. Ignored for other ControlNet models. The standard mapping is: canny (0), tile (1), depth (2), blur (3), pose (4), gray (5), low quality (6). Negative values will be treated as 'None'."
 
 
 class ImageField(BaseModel):

invokeai/app/invocations/flux_controlnet.py

@@ -0,0 +1,99 @@
+from pydantic import BaseModel, Field, field_validator, model_validator
+
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    Classification,
+    invocation,
+    invocation_output,
+)
+from invokeai.app.invocations.fields import FieldDescriptions, ImageField, InputField, OutputField, UIType
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.controlnet_utils import CONTROLNET_RESIZE_VALUES
+
+
+class FluxControlNetField(BaseModel):
+    image: ImageField = Field(description="The control image")
+    control_model: ModelIdentifierField = Field(description="The ControlNet model to use")
+    control_weight: float | list[float] = Field(default=1, description="The weight given to the ControlNet")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the ControlNet is last applied (% of total steps)"
+    )
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+    instantx_control_mode: int | None = Field(default=-1, description=FieldDescriptions.instantx_control_mode)
+
+    @field_validator("control_weight")
+    @classmethod
+    def validate_control_weight(cls, v: float | list[float]) -> float | list[float]:
+        validate_weights(v)
+        return v
+
+    @model_validator(mode="after")
+    def validate_begin_end_step_percent(self):
+        validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
+        return self
+
+
+@invocation_output("flux_controlnet_output")
+class FluxControlNetOutput(BaseInvocationOutput):
+    """FLUX ControlNet info"""
+
+    control: FluxControlNetField = OutputField(description=FieldDescriptions.control)
+
+
+@invocation(
+    "flux_controlnet",
+    title="FLUX ControlNet",
+    tags=["controlnet", "flux"],
+    category="controlnet",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class FluxControlNetInvocation(BaseInvocation):
+    """Collect FLUX ControlNet info to pass to other nodes."""
+
+    image: ImageField = InputField(description="The control image")
+    control_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.controlnet_model, ui_type=UIType.ControlNetModel
+    )
+    control_weight: float | list[float] = InputField(
+        default=1.0, ge=-1, le=2, description="The weight given to the ControlNet"
+    )
+    begin_step_percent: float = InputField(
+        default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
+    )
+    end_step_percent: float = InputField(
+        default=1, ge=0, le=1, description="When the ControlNet is last applied (% of total steps)"
+    )
+    resize_mode: CONTROLNET_RESIZE_VALUES = InputField(default="just_resize", description="The resize mode used")
+    # Note: We default to -1 instead of None, because in the workflow editor UI None is not currently supported.
+    instantx_control_mode: int | None = InputField(default=-1, description=FieldDescriptions.instantx_control_mode)
+
+    @field_validator("control_weight")
+    @classmethod
+    def validate_control_weight(cls, v: float | list[float]) -> float | list[float]:
+        validate_weights(v)
+        return v
+
+    @model_validator(mode="after")
+    def validate_begin_end_step_percent(self):
+        validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
+        return self
+
+    def invoke(self, context: InvocationContext) -> FluxControlNetOutput:
+        return FluxControlNetOutput(
+            control=FluxControlNetField(
+                image=self.image,
+                control_model=self.control_model,
+                control_weight=self.control_weight,
+                begin_step_percent=self.begin_step_percent,
+                end_step_percent=self.end_step_percent,
+                resize_mode=self.resize_mode,
+                instantx_control_mode=self.instantx_control_mode,
+            ),
+        )

invokeai/app/invocations/flux_denoise.py

@@ -1,26 +1,38 @@
 from contextlib import ExitStack
 from typing import Callable, Iterator, Optional, Tuple
 
+import numpy as np
+import numpy.typing as npt
 import torch
 import torchvision.transforms as tv_transforms
 from torchvision.transforms.functional import resize as tv_resize
+from transformers import CLIPImageProcessor, CLIPVisionModelWithProjection
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
 from invokeai.app.invocations.fields import (
     DenoiseMaskField,
     FieldDescriptions,
     FluxConditioningField,
+    ImageField,
     Input,
     InputField,
     LatentsField,
     WithBoard,
     WithMetadata,
 )
-from invokeai.app.invocations.model import TransformerField
+from invokeai.app.invocations.flux_controlnet import FluxControlNetField
+from invokeai.app.invocations.ip_adapter import IPAdapterField
+from invokeai.app.invocations.model import TransformerField, VAEField
 from invokeai.app.invocations.primitives import LatentsOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.flux.controlnet.instantx_controlnet_flux import InstantXControlNetFlux
+from invokeai.backend.flux.controlnet.xlabs_controlnet_flux import XLabsControlNetFlux
 from invokeai.backend.flux.denoise import denoise
-from invokeai.backend.flux.inpaint_extension import InpaintExtension
+from invokeai.backend.flux.extensions.inpaint_extension import InpaintExtension
+from invokeai.backend.flux.extensions.instantx_controlnet_extension import InstantXControlNetExtension
+from invokeai.backend.flux.extensions.xlabs_controlnet_extension import XLabsControlNetExtension
+from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
+from invokeai.backend.flux.ip_adapter.xlabs_ip_adapter_flux import XlabsIpAdapterFlux
 from invokeai.backend.flux.model import Flux
 from invokeai.backend.flux.sampling_utils import (
     clip_timestep_schedule_fractional,
@@ -44,7 +56,7 @@ from invokeai.backend.util.devices import TorchDevice
     title="FLUX Denoise",
     tags=["image", "flux"],
     category="image",
-    version="3.0.0",
+    version="3.2.0",
     classification=Classification.Prototype,
 )
 class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
@@ -77,6 +89,24 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
     positive_text_conditioning: FluxConditioningField = InputField(
         description=FieldDescriptions.positive_cond, input=Input.Connection
     )
+    negative_text_conditioning: FluxConditioningField | None = InputField(
+        default=None,
+        description="Negative conditioning tensor. Can be None if cfg_scale is 1.0.",
+        input=Input.Connection,
+    )
+    cfg_scale: float | list[float] = InputField(default=1.0, description=FieldDescriptions.cfg_scale, title="CFG Scale")
+    cfg_scale_start_step: int = InputField(
+        default=0,
+        title="CFG Scale Start Step",
+        description="Index of the first step to apply cfg_scale. Negative indices count backwards from the "
+        + "the last step (e.g. a value of -1 refers to the final step).",
+    )
+    cfg_scale_end_step: int = InputField(
+        default=-1,
+        title="CFG Scale End Step",
+        description="Index of the last step to apply cfg_scale. Negative indices count backwards from the "
+        + "last step (e.g. a value of -1 refers to the final step).",
+    )
     width: int = InputField(default=1024, multiple_of=16, description="Width of the generated image.")
     height: int = InputField(default=1024, multiple_of=16, description="Height of the generated image.")
     num_steps: int = InputField(
@@ -87,6 +117,18 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         description="The guidance strength. Higher values adhere more strictly to the prompt, and will produce less diverse images. FLUX dev only, ignored for schnell.",
     )
     seed: int = InputField(default=0, description="Randomness seed for reproducibility.")
+    control: FluxControlNetField | list[FluxControlNetField] | None = InputField(
+        default=None, input=Input.Connection, description="ControlNet models."
+    )
+    controlnet_vae: VAEField | None = InputField(
+        default=None,
+        description=FieldDescriptions.vae,
+        input=Input.Connection,
+    )
+
+    ip_adapter: IPAdapterField | list[IPAdapterField] | None = InputField(
+        description=FieldDescriptions.ip_adapter, title="IP-Adapter", default=None, input=Input.Connection
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
@@ -96,6 +138,19 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         name = context.tensors.save(tensor=latents)
         return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
 
+    def _load_text_conditioning(
+        self, context: InvocationContext, conditioning_name: str, dtype: torch.dtype
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        # Load the conditioning data.
+        cond_data = context.conditioning.load(conditioning_name)
+        assert len(cond_data.conditionings) == 1
+        flux_conditioning = cond_data.conditionings[0]
+        assert isinstance(flux_conditioning, FLUXConditioningInfo)
+        flux_conditioning = flux_conditioning.to(dtype=dtype)
+        t5_embeddings = flux_conditioning.t5_embeds
+        clip_embeddings = flux_conditioning.clip_embeds
+        return t5_embeddings, clip_embeddings
+
     def _run_diffusion(
         self,
         context: InvocationContext,
@@ -103,13 +158,15 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         inference_dtype = torch.bfloat16
 
         # Load the conditioning data.
-        cond_data = context.conditioning.load(self.positive_text_conditioning.conditioning_name)
-        assert len(cond_data.conditionings) == 1
-        flux_conditioning = cond_data.conditionings[0]
-        assert isinstance(flux_conditioning, FLUXConditioningInfo)
-        flux_conditioning = flux_conditioning.to(dtype=inference_dtype)
-        t5_embeddings = flux_conditioning.t5_embeds
-        clip_embeddings = flux_conditioning.clip_embeds
+        pos_t5_embeddings, pos_clip_embeddings = self._load_text_conditioning(
+            context, self.positive_text_conditioning.conditioning_name, inference_dtype
+        )
+        neg_t5_embeddings: torch.Tensor | None = None
+        neg_clip_embeddings: torch.Tensor | None = None
+        if self.negative_text_conditioning is not None:
+            neg_t5_embeddings, neg_clip_embeddings = self._load_text_conditioning(
+                context, self.negative_text_conditioning.conditioning_name, inference_dtype
+            )
 
         # Load the input latents, if provided.
         init_latents = context.tensors.load(self.latents.latents_name) if self.latents else None
@@ -167,11 +224,19 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
 
         inpaint_mask = self._prep_inpaint_mask(context, x)
 
-        b, _c, h, w = x.shape
-        img_ids = generate_img_ids(h=h, w=w, batch_size=b, device=x.device, dtype=x.dtype)
+        b, _c, latent_h, latent_w = x.shape
+        img_ids = generate_img_ids(h=latent_h, w=latent_w, batch_size=b, device=x.device, dtype=x.dtype)
 
-        bs, t5_seq_len, _ = t5_embeddings.shape
-        txt_ids = torch.zeros(bs, t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device())
+        pos_bs, pos_t5_seq_len, _ = pos_t5_embeddings.shape
+        pos_txt_ids = torch.zeros(
+            pos_bs, pos_t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device()
+        )
+        neg_txt_ids: torch.Tensor | None = None
+        if neg_t5_embeddings is not None:
+            neg_bs, neg_t5_seq_len, _ = neg_t5_embeddings.shape
+            neg_txt_ids = torch.zeros(
+                neg_bs, neg_t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device()
+            )
 
         # Pack all latent tensors.
         init_latents = pack(init_latents) if init_latents is not None else None
@@ -192,12 +257,36 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                 noise=noise,
             )
 
-        with (
-            transformer_info.model_on_device() as (cached_weights, transformer),
-            ExitStack() as exit_stack,
-        ):
-            assert isinstance(transformer, Flux)
+        # Compute the IP-Adapter image prompt clip embeddings.
+        # We do this before loading other models to minimize peak memory.
+        # TODO(ryand): We should really do this in a separate invocation to benefit from caching.
+        ip_adapter_fields = self._normalize_ip_adapter_fields()
+        pos_image_prompt_clip_embeds, neg_image_prompt_clip_embeds = self._prep_ip_adapter_image_prompt_clip_embeds(
+            ip_adapter_fields, context
+        )
 
+        cfg_scale = self.prep_cfg_scale(
+            cfg_scale=self.cfg_scale,
+            timesteps=timesteps,
+            cfg_scale_start_step=self.cfg_scale_start_step,
+            cfg_scale_end_step=self.cfg_scale_end_step,
+        )
+
+        with ExitStack() as exit_stack:
+            # Prepare ControlNet extensions.
+            # Note: We do this before loading the transformer model to minimize peak memory (see implementation).
+            controlnet_extensions = self._prep_controlnet_extensions(
+                context=context,
+                exit_stack=exit_stack,
+                latent_height=latent_h,
+                latent_width=latent_w,
+                dtype=inference_dtype,
+                device=x.device,
+            )
+
+            # Load the transformer model.
+            (cached_weights, transformer) = exit_stack.enter_context(transformer_info.model_on_device())
+            assert isinstance(transformer, Flux)
             config = transformer_info.config
             assert config is not None
 
@@ -231,22 +320,88 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
             else:
                 raise ValueError(f"Unsupported model format: {config.format}")
 
+            # Prepare IP-Adapter extensions.
+            pos_ip_adapter_extensions, neg_ip_adapter_extensions = self._prep_ip_adapter_extensions(
+                pos_image_prompt_clip_embeds=pos_image_prompt_clip_embeds,
+                neg_image_prompt_clip_embeds=neg_image_prompt_clip_embeds,
+                ip_adapter_fields=ip_adapter_fields,
+                context=context,
+                exit_stack=exit_stack,
+                dtype=inference_dtype,
+            )
+
             x = denoise(
                 model=transformer,
                 img=x,
                 img_ids=img_ids,
-                txt=t5_embeddings,
-                txt_ids=txt_ids,
-                vec=clip_embeddings,
+                txt=pos_t5_embeddings,
+                txt_ids=pos_txt_ids,
+                vec=pos_clip_embeddings,
+                neg_txt=neg_t5_embeddings,
+                neg_txt_ids=neg_txt_ids,
+                neg_vec=neg_clip_embeddings,
                 timesteps=timesteps,
                 step_callback=self._build_step_callback(context),
                 guidance=self.guidance,
+                cfg_scale=cfg_scale,
                 inpaint_extension=inpaint_extension,
+                controlnet_extensions=controlnet_extensions,
+                pos_ip_adapter_extensions=pos_ip_adapter_extensions,
+                neg_ip_adapter_extensions=neg_ip_adapter_extensions,
             )
 
         x = unpack(x.float(), self.height, self.width)
         return x
 
+    @classmethod
+    def prep_cfg_scale(
+        cls, cfg_scale: float | list[float], timesteps: list[float], cfg_scale_start_step: int, cfg_scale_end_step: int
+    ) -> list[float]:
+        """Prepare the cfg_scale schedule.
+
+        - Clips the cfg_scale schedule based on cfg_scale_start_step and cfg_scale_end_step.
+        - If cfg_scale is a list, then it is assumed to be a schedule and is returned as-is.
+        - If cfg_scale is a scalar, then a linear schedule is created from cfg_scale_start_step to cfg_scale_end_step.
+        """
+        # num_steps is the number of denoising steps, which is one less than the number of timesteps.
+        num_steps = len(timesteps) - 1
+
+        # Normalize cfg_scale to a list if it is a scalar.
+        cfg_scale_list: list[float]
+        if isinstance(cfg_scale, float):
+            cfg_scale_list = [cfg_scale] * num_steps
+        elif isinstance(cfg_scale, list):
+            cfg_scale_list = cfg_scale
+        else:
+            raise ValueError(f"Unsupported cfg_scale type: {type(cfg_scale)}")
+        assert len(cfg_scale_list) == num_steps
+
+        # Handle negative indices for cfg_scale_start_step and cfg_scale_end_step.
+        start_step_index = cfg_scale_start_step
+        if start_step_index < 0:
+            start_step_index = num_steps + start_step_index
+        end_step_index = cfg_scale_end_step
+        if end_step_index < 0:
+            end_step_index = num_steps + end_step_index
+
+        # Validate the start and end step indices.
+        if not (0 <= start_step_index < num_steps):
+            raise ValueError(f"Invalid cfg_scale_start_step. Out of range: {cfg_scale_start_step}.")
+        if not (0 <= end_step_index < num_steps):
+            raise ValueError(f"Invalid cfg_scale_end_step. Out of range: {cfg_scale_end_step}.")
+        if start_step_index > end_step_index:
+            raise ValueError(
+                f"cfg_scale_start_step ({cfg_scale_start_step}) must be before cfg_scale_end_step "
+                + f"({cfg_scale_end_step})."
+            )
+
+        # Set values outside the start and end step indices to 1.0. This is equivalent to disabling cfg_scale for those
+        # steps.
+        clipped_cfg_scale = [1.0] * num_steps
+        clipped_cfg_scale[start_step_index : end_step_index + 1] = cfg_scale_list[start_step_index : end_step_index + 1]
+
+        return clipped_cfg_scale
+
     def _prep_inpaint_mask(self, context: InvocationContext, latents: torch.Tensor) -> torch.Tensor | None:
         """Prepare the inpaint mask.
 
@@ -288,6 +443,210 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         # `latents`.
         return mask.expand_as(latents)
 
+    def _prep_controlnet_extensions(
+        self,
+        context: InvocationContext,
+        exit_stack: ExitStack,
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+    ) -> list[XLabsControlNetExtension | InstantXControlNetExtension]:
+        # Normalize the controlnet input to list[ControlField].
+        controlnets: list[FluxControlNetField]
+        if self.control is None:
+            controlnets = []
+        elif isinstance(self.control, FluxControlNetField):
+            controlnets = [self.control]
+        elif isinstance(self.control, list):
+            controlnets = self.control
+        else:
+            raise ValueError(f"Unsupported controlnet type: {type(self.control)}")
+
+        # TODO(ryand): Add a field to the model config so that we can distinguish between XLabs and InstantX ControlNets
+        # before loading the models. Then make sure that all VAE encoding is done before loading the ControlNets to
+        # minimize peak memory.
+
+        # First, load the ControlNet models so that we can determine the ControlNet types.
+        controlnet_models = [context.models.load(controlnet.control_model) for controlnet in controlnets]
+
+        # Calculate the controlnet conditioning tensors.
+        # We do this before loading the ControlNet models because it may require running the VAE, and we are trying to
+        # keep peak memory down.
+        controlnet_conds: list[torch.Tensor] = []
+        for controlnet, controlnet_model in zip(controlnets, controlnet_models, strict=True):
+            image = context.images.get_pil(controlnet.image.image_name)
+            if isinstance(controlnet_model.model, InstantXControlNetFlux):
+                if self.controlnet_vae is None:
+                    raise ValueError("A ControlNet VAE is required when using an InstantX FLUX ControlNet.")
+                vae_info = context.models.load(self.controlnet_vae.vae)
+                controlnet_conds.append(
+                    InstantXControlNetExtension.prepare_controlnet_cond(
+                        controlnet_image=image,
+                        vae_info=vae_info,
+                        latent_height=latent_height,
+                        latent_width=latent_width,
+                        dtype=dtype,
+                        device=device,
+                        resize_mode=controlnet.resize_mode,
+                    )
+                )
+            elif isinstance(controlnet_model.model, XLabsControlNetFlux):
+                controlnet_conds.append(
+                    XLabsControlNetExtension.prepare_controlnet_cond(
+                        controlnet_image=image,
+                        latent_height=latent_height,
+                        latent_width=latent_width,
+                        dtype=dtype,
+                        device=device,
+                        resize_mode=controlnet.resize_mode,
+                    )
+                )
+
+        # Finally, load the ControlNet models and initialize the ControlNet extensions.
+        controlnet_extensions: list[XLabsControlNetExtension | InstantXControlNetExtension] = []
+        for controlnet, controlnet_cond, controlnet_model in zip(
+            controlnets, controlnet_conds, controlnet_models, strict=True
+        ):
+            model = exit_stack.enter_context(controlnet_model)
+
+            if isinstance(model, XLabsControlNetFlux):
+                controlnet_extensions.append(
+                    XLabsControlNetExtension(
+                        model=model,
+                        controlnet_cond=controlnet_cond,
+                        weight=controlnet.control_weight,
+                        begin_step_percent=controlnet.begin_step_percent,
+                        end_step_percent=controlnet.end_step_percent,
+                    )
+                )
+            elif isinstance(model, InstantXControlNetFlux):
+                instantx_control_mode: torch.Tensor | None = None
+                if controlnet.instantx_control_mode is not None and controlnet.instantx_control_mode >= 0:
+                    instantx_control_mode = torch.tensor(controlnet.instantx_control_mode, dtype=torch.long)
+                    instantx_control_mode = instantx_control_mode.reshape([-1, 1])
+
+                controlnet_extensions.append(
+                    InstantXControlNetExtension(
+                        model=model,
+                        controlnet_cond=controlnet_cond,
+                        instantx_control_mode=instantx_control_mode,
+                        weight=controlnet.control_weight,
+                        begin_step_percent=controlnet.begin_step_percent,
+                        end_step_percent=controlnet.end_step_percent,
+                    )
+                )
+            else:
+                raise ValueError(f"Unsupported ControlNet model type: {type(model)}")
+
+        return controlnet_extensions
+
+    def _normalize_ip_adapter_fields(self) -> list[IPAdapterField]:
+        if self.ip_adapter is None:
+            return []
+        elif isinstance(self.ip_adapter, IPAdapterField):
+            return [self.ip_adapter]
+        elif isinstance(self.ip_adapter, list):
+            return self.ip_adapter
+        else:
+            raise ValueError(f"Unsupported IP-Adapter type: {type(self.ip_adapter)}")
+
+    def _prep_ip_adapter_image_prompt_clip_embeds(
+        self,
+        ip_adapter_fields: list[IPAdapterField],
+        context: InvocationContext,
+    ) -> tuple[list[torch.Tensor], list[torch.Tensor]]:
+        """Run the IPAdapter CLIPVisionModel, returning image prompt embeddings."""
+        clip_image_processor = CLIPImageProcessor()
+
+        pos_image_prompt_clip_embeds: list[torch.Tensor] = []
+        neg_image_prompt_clip_embeds: list[torch.Tensor] = []
+        for ip_adapter_field in ip_adapter_fields:
+            # `ip_adapter_field.image` could be a list or a single ImageField. Normalize to a list here.
+            ipa_image_fields: list[ImageField]
+            if isinstance(ip_adapter_field.image, ImageField):
+                ipa_image_fields = [ip_adapter_field.image]
+            elif isinstance(ip_adapter_field.image, list):
+                ipa_image_fields = ip_adapter_field.image
+            else:
+                raise ValueError(f"Unsupported IP-Adapter image type: {type(ip_adapter_field.image)}")
+
+            if len(ipa_image_fields) != 1:
+                raise ValueError(
+                    f"FLUX IP-Adapter only supports a single image prompt (received {len(ipa_image_fields)})."
+                )
+
+            ipa_images = [context.images.get_pil(image.image_name, mode="RGB") for image in ipa_image_fields]
+
+            pos_images: list[npt.NDArray[np.uint8]] = []
+            neg_images: list[npt.NDArray[np.uint8]] = []
+            for ipa_image in ipa_images:
+                assert ipa_image.mode == "RGB"
+                pos_image = np.array(ipa_image)
+                # We use a black image as the negative image prompt for parity with
+                # https://github.com/XLabs-AI/x-flux-comfyui/blob/45c834727dd2141aebc505ae4b01f193a8414e38/nodes.py#L592-L593
+                # An alternative scheme would be to apply zeros_like() after calling the clip_image_processor.
+                neg_image = np.zeros_like(pos_image)
+                pos_images.append(pos_image)
+                neg_images.append(neg_image)
+
+            with context.models.load(ip_adapter_field.image_encoder_model) as image_encoder_model:
+                assert isinstance(image_encoder_model, CLIPVisionModelWithProjection)
+
+                clip_image: torch.Tensor = clip_image_processor(images=pos_images, return_tensors="pt").pixel_values
+                clip_image = clip_image.to(device=image_encoder_model.device, dtype=image_encoder_model.dtype)
+                pos_clip_image_embeds = image_encoder_model(clip_image).image_embeds
+
+                clip_image = clip_image_processor(images=neg_images, return_tensors="pt").pixel_values
+                clip_image = clip_image.to(device=image_encoder_model.device, dtype=image_encoder_model.dtype)
+                neg_clip_image_embeds = image_encoder_model(clip_image).image_embeds
+
+            pos_image_prompt_clip_embeds.append(pos_clip_image_embeds)
+            neg_image_prompt_clip_embeds.append(neg_clip_image_embeds)
+
+        return pos_image_prompt_clip_embeds, neg_image_prompt_clip_embeds
+
+    def _prep_ip_adapter_extensions(
+        self,
+        ip_adapter_fields: list[IPAdapterField],
+        pos_image_prompt_clip_embeds: list[torch.Tensor],
+        neg_image_prompt_clip_embeds: list[torch.Tensor],
+        context: InvocationContext,
+        exit_stack: ExitStack,
+        dtype: torch.dtype,
+    ) -> tuple[list[XLabsIPAdapterExtension], list[XLabsIPAdapterExtension]]:
+        pos_ip_adapter_extensions: list[XLabsIPAdapterExtension] = []
+        neg_ip_adapter_extensions: list[XLabsIPAdapterExtension] = []
+        for ip_adapter_field, pos_image_prompt_clip_embed, neg_image_prompt_clip_embed in zip(
+            ip_adapter_fields, pos_image_prompt_clip_embeds, neg_image_prompt_clip_embeds, strict=True
+        ):
+            ip_adapter_model = exit_stack.enter_context(context.models.load(ip_adapter_field.ip_adapter_model))
+            assert isinstance(ip_adapter_model, XlabsIpAdapterFlux)
+            ip_adapter_model = ip_adapter_model.to(dtype=dtype)
+            if ip_adapter_field.mask is not None:
+                raise ValueError("IP-Adapter masks are not yet supported in Flux.")
+            ip_adapter_extension = XLabsIPAdapterExtension(
+                model=ip_adapter_model,
+                image_prompt_clip_embed=pos_image_prompt_clip_embed,
+                weight=ip_adapter_field.weight,
+                begin_step_percent=ip_adapter_field.begin_step_percent,
+                end_step_percent=ip_adapter_field.end_step_percent,
+            )
+            ip_adapter_extension.run_image_proj(dtype=dtype)
+            pos_ip_adapter_extensions.append(ip_adapter_extension)
+
+            ip_adapter_extension = XLabsIPAdapterExtension(
+                model=ip_adapter_model,
+                image_prompt_clip_embed=neg_image_prompt_clip_embed,
+                weight=ip_adapter_field.weight,
+                begin_step_percent=ip_adapter_field.begin_step_percent,
+                end_step_percent=ip_adapter_field.end_step_percent,
+            )
+            ip_adapter_extension.run_image_proj(dtype=dtype)
+            neg_ip_adapter_extensions.append(ip_adapter_extension)
+
+        return pos_ip_adapter_extensions, neg_ip_adapter_extensions
+
     def _lora_iterator(self, context: InvocationContext) -> Iterator[Tuple[LoRAModelRaw, float]]:
         for lora in self.transformer.loras:
             lora_info = context.models.load(lora.lora)

invokeai/app/invocations/flux_ip_adapter.py

@@ -0,0 +1,89 @@
+from builtins import float
+from typing import List, Literal, Union
+
+from pydantic import field_validator, model_validator
+from typing_extensions import Self
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.fields import InputField, UIType
+from invokeai.app.invocations.ip_adapter import (
+    CLIP_VISION_MODEL_MAP,
+    IPAdapterField,
+    IPAdapterInvocation,
+    IPAdapterOutput,
+)
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.invocations.primitives import ImageField
+from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager.config import (
+    IPAdapterCheckpointConfig,
+    IPAdapterInvokeAIConfig,
+)
+
+
+@invocation(
+    "flux_ip_adapter",
+    title="FLUX IP-Adapter",
+    tags=["ip_adapter", "control"],
+    category="ip_adapter",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class FluxIPAdapterInvocation(BaseInvocation):
+    """Collects FLUX IP-Adapter info to pass to other nodes."""
+
+    # FLUXIPAdapterInvocation is based closely on IPAdapterInvocation, but with some unsupported features removed.
+
+    image: ImageField = InputField(description="The IP-Adapter image prompt(s).")
+    ip_adapter_model: ModelIdentifierField = InputField(
+        description="The IP-Adapter model.", title="IP-Adapter Model", ui_type=UIType.IPAdapterModel
+    )
+    # Currently, the only known ViT model used by FLUX IP-Adapters is ViT-L.
+    clip_vision_model: Literal["ViT-L"] = InputField(description="CLIP Vision model to use.", default="ViT-L")
+    weight: Union[float, List[float]] = InputField(
+        default=1, description="The weight given to the IP-Adapter", title="Weight"
+    )
+    begin_step_percent: float = InputField(
+        default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = InputField(
+        default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
+    )
+
+    @field_validator("weight")
+    @classmethod
+    def validate_ip_adapter_weight(cls, v: float) -> float:
+        validate_weights(v)
+        return v
+
+    @model_validator(mode="after")
+    def validate_begin_end_step_percent(self) -> Self:
+        validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
+        return self
+
+    def invoke(self, context: InvocationContext) -> IPAdapterOutput:
+        # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
+        ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
+        assert isinstance(ip_adapter_info, (IPAdapterInvokeAIConfig, IPAdapterCheckpointConfig))
+
+        # Note: There is a IPAdapterInvokeAIConfig.image_encoder_model_id field, but it isn't trustworthy.
+        image_encoder_starter_model = CLIP_VISION_MODEL_MAP[self.clip_vision_model]
+        image_encoder_model_id = image_encoder_starter_model.source
+        image_encoder_model_name = image_encoder_starter_model.name
+        image_encoder_model = IPAdapterInvocation.get_clip_image_encoder(
+            context, image_encoder_model_id, image_encoder_model_name
+        )
+
+        return IPAdapterOutput(
+            ip_adapter=IPAdapterField(
+                image=self.image,
+                ip_adapter_model=self.ip_adapter_model,
+                image_encoder_model=ModelIdentifierField.from_config(image_encoder_model),
+                weight=self.weight,
+                target_blocks=[],  # target_blocks is currently unused for FLUX IP-Adapters.
+                begin_step_percent=self.begin_step_percent,
+                end_step_percent=self.end_step_percent,
+                mask=None,  # mask is currently unused for FLUX IP-Adapters.
+            ),
+        )

invokeai/app/invocations/ip_adapter.py

@@ -9,6 +9,7 @@ from invokeai.app.invocations.fields import FieldDescriptions, InputField, Outpu
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
+from invokeai.app.services.model_records.model_records_base import ModelRecordChanges
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
@@ -17,6 +18,12 @@ from invokeai.backend.model_manager.config import (
     IPAdapterInvokeAIConfig,
     ModelType,
 )
+from invokeai.backend.model_manager.starter_models import (
+    StarterModel,
+    clip_vit_l_image_encoder,
+    ip_adapter_sd_image_encoder,
+    ip_adapter_sdxl_image_encoder,
+)
 
 
 class IPAdapterField(BaseModel):
@@ -55,10 +62,14 @@ class IPAdapterOutput(BaseInvocationOutput):
     ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
 
 
-CLIP_VISION_MODEL_MAP = {"ViT-H": "ip_adapter_sd_image_encoder", "ViT-G": "ip_adapter_sdxl_image_encoder"}
+CLIP_VISION_MODEL_MAP: dict[Literal["ViT-L", "ViT-H", "ViT-G"], StarterModel] = {
+    "ViT-L": clip_vit_l_image_encoder,
+    "ViT-H": ip_adapter_sd_image_encoder,
+    "ViT-G": ip_adapter_sdxl_image_encoder,
+}
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.4.1")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.5.0")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
@@ -70,7 +81,7 @@ class IPAdapterInvocation(BaseInvocation):
         ui_order=-1,
         ui_type=UIType.IPAdapterModel,
     )
-    clip_vision_model: Literal["ViT-H", "ViT-G"] = InputField(
+    clip_vision_model: Literal["ViT-H", "ViT-G", "ViT-L"] = InputField(
         description="CLIP Vision model to use. Overrides model settings. Mandatory for checkpoint models.",
         default="ViT-H",
         ui_order=2,
@@ -111,9 +122,11 @@ class IPAdapterInvocation(BaseInvocation):
             image_encoder_model_id = ip_adapter_info.image_encoder_model_id
             image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
         else:
-            image_encoder_model_name = CLIP_VISION_MODEL_MAP[self.clip_vision_model]
+            image_encoder_starter_model = CLIP_VISION_MODEL_MAP[self.clip_vision_model]
+            image_encoder_model_id = image_encoder_starter_model.source
+            image_encoder_model_name = image_encoder_starter_model.name
 
-        image_encoder_model = self._get_image_encoder(context, image_encoder_model_name)
+        image_encoder_model = self.get_clip_image_encoder(context, image_encoder_model_id, image_encoder_model_name)
 
         if self.method == "style":
             if ip_adapter_info.base == "sd-1":
@@ -147,7 +160,10 @@ class IPAdapterInvocation(BaseInvocation):
             ),
         )
 
-    def _get_image_encoder(self, context: InvocationContext, image_encoder_model_name: str) -> AnyModelConfig:
+    @classmethod
+    def get_clip_image_encoder(
+        cls, context: InvocationContext, image_encoder_model_id: str, image_encoder_model_name: str
+    ) -> AnyModelConfig:
         image_encoder_models = context.models.search_by_attrs(
             name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
         )
@@ -159,7 +175,11 @@ class IPAdapterInvocation(BaseInvocation):
             )
 
             installer = context._services.model_manager.install
-            job = installer.heuristic_import(f"InvokeAI/{image_encoder_model_name}")
+            # Note: We hard-code the type to CLIPVision here because if the model contains both a CLIPVision and a
+            # CLIPText model, the probe may treat it as a CLIPText model.
+            job = installer.heuristic_import(
+                image_encoder_model_id, ModelRecordChanges(name=image_encoder_model_name, type=ModelType.CLIPVision)
+            )
             installer.wait_for_job(job, timeout=600)  # Wait for up to 10 minutes
             image_encoder_models = context.models.search_by_attrs(
                 name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision

invokeai/app/invocations/mask.py

@@ -5,6 +5,7 @@ from PIL import Image
 from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, InvocationContext, invocation
 from invokeai.app.invocations.fields import ImageField, InputField, TensorField, WithBoard, WithMetadata
 from invokeai.app.invocations.primitives import ImageOutput, MaskOutput
+from invokeai.backend.image_util.util import pil_to_np
 
 
 @invocation(
@@ -148,3 +149,55 @@ class MaskTensorToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
         mask_pil = Image.fromarray(mask_np, mode="L")
         image_dto = context.images.save(image=mask_pil)
         return ImageOutput.build(image_dto)
+
+
+@invocation(
+    "apply_tensor_mask_to_image",
+    title="Apply Tensor Mask to Image",
+    tags=["mask"],
+    category="mask",
+    version="1.0.0",
+)
+class ApplyMaskTensorToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Applies a tensor mask to an image.
+
+    The image is converted to RGBA and the mask is applied to the alpha channel."""
+
+    mask: TensorField = InputField(description="The mask tensor to apply.")
+    image: ImageField = InputField(description="The image to apply the mask to.")
+    invert: bool = InputField(default=False, description="Whether to invert the mask.")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.images.get_pil(self.image.image_name, mode="RGBA")
+        mask = context.tensors.load(self.mask.tensor_name)
+
+        # Squeeze the channel dimension if it exists.
+        if mask.dim() == 3:
+            mask = mask.squeeze(0)
+
+        # Ensure that the mask is binary.
+        if mask.dtype != torch.bool:
+            mask = mask > 0.5
+        mask_np = (mask.float() * 255).byte().cpu().numpy().astype(np.uint8)
+
+        if self.invert:
+            mask_np = 255 - mask_np
+
+        # Apply the mask only to the alpha channel where the original alpha is non-zero. This preserves the original
+        # image's transparency - else the transparent regions would end up as opaque black.
+
+        # Separate the image into R, G, B, and A channels
+        image_np = pil_to_np(image)
+        r, g, b, a = np.split(image_np, 4, axis=-1)
+
+        # Apply the mask to the alpha channel
+        new_alpha = np.where(a.squeeze() > 0, mask_np, a.squeeze())
+
+        # Stack the RGB channels with the modified alpha
+        masked_image_np = np.dstack([r.squeeze(), g.squeeze(), b.squeeze(), new_alpha])
+
+        # Convert back to an image (RGBA)
+        masked_image = Image.fromarray(masked_image_np.astype(np.uint8), "RGBA")
+        image_dto = context.images.save(image=masked_image)
+
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/metadata.py

@@ -40,7 +40,7 @@ class IPAdapterMetadataField(BaseModel):
 
     image: ImageField = Field(description="The IP-Adapter image prompt.")
     ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model.")
-    clip_vision_model: Literal["ViT-H", "ViT-G"] = Field(description="The CLIP Vision model")
+    clip_vision_model: Literal["ViT-L", "ViT-H", "ViT-G"] = Field(description="The CLIP Vision model")
     method: Literal["full", "style", "composition"] = Field(description="Method to apply IP Weights with")
     weight: Union[float, list[float]] = Field(description="The weight given to the IP-Adapter")
     begin_step_percent: float = Field(description="When the IP-Adapter is first applied (% of total steps)")

invokeai/app/invocations/segment_anything.py

@@ -1,9 +1,11 @@
+from enum import Enum
 from pathlib import Path
 from typing import Literal
 
 import numpy as np
 import torch
 from PIL import Image
+from pydantic import BaseModel, Field, model_validator
 from transformers import AutoModelForMaskGeneration, AutoProcessor
 from transformers.models.sam import SamModel
 from transformers.models.sam.processing_sam import SamProcessor
@@ -23,12 +25,31 @@ SEGMENT_ANYTHING_MODEL_IDS: dict[SegmentAnythingModelKey, str] = {
 }
 
 
+class SAMPointLabel(Enum):
+    negative = -1
+    neutral = 0
+    positive = 1
+
+
+class SAMPoint(BaseModel):
+    x: int = Field(..., description="The x-coordinate of the point")
+    y: int = Field(..., description="The y-coordinate of the point")
+    label: SAMPointLabel = Field(..., description="The label of the point")
+
+
+class SAMPointsField(BaseModel):
+    points: list[SAMPoint] = Field(..., description="The points of the object")
+
+    def to_list(self) -> list[list[int]]:
+        return [[point.x, point.y, point.label.value] for point in self.points]
+
+
 @invocation(
     "segment_anything",
     title="Segment Anything",
     tags=["prompt", "segmentation"],
     category="segmentation",
-    version="1.0.0",
+    version="1.1.0",
 )
 class SegmentAnythingInvocation(BaseInvocation):
     """Runs a Segment Anything Model."""
@@ -40,7 +61,13 @@ class SegmentAnythingInvocation(BaseInvocation):
 
     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.")
+    bounding_boxes: list[BoundingBoxField] | None = InputField(
+        default=None, description="The bounding boxes to prompt the SAM model with."
+    )
+    point_lists: list[SAMPointsField] | None = InputField(
+        default=None,
+        description="The list of point lists to prompt the SAM model with. Each list of points represents a single object.",
+    )
     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,
@@ -50,12 +77,22 @@ class SegmentAnythingInvocation(BaseInvocation):
         default="all",
     )
 
+    @model_validator(mode="after")
+    def check_point_lists_or_bounding_box(self):
+        if self.point_lists is None and self.bounding_boxes is None:
+            raise ValueError("Either point_lists or bounding_box must be provided.")
+        elif self.point_lists is not None and self.bounding_boxes is not None:
+            raise ValueError("Only one of point_lists or bounding_box can be provided.")
+        return self
+
     @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:
+        if (not self.bounding_boxes or len(self.bounding_boxes) == 0) and (
+            not self.point_lists or len(self.point_lists) == 0
+        ):
             combined_mask = torch.zeros(image_pil.size[::-1], dtype=torch.bool)
         else:
             masks = self._segment(context=context, image=image_pil)
@@ -83,14 +120,13 @@ class SegmentAnythingInvocation(BaseInvocation):
         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]:
+    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]
+        sam_bounding_boxes = (
+            [[bb.x_min, bb.y_min, bb.x_max, bb.y_max] for bb in self.bounding_boxes] if self.bounding_boxes else None
+        )
+        sam_points = [p.to_list() for p in self.point_lists] if self.point_lists else None
 
         with (
             context.models.load_remote_model(
@@ -98,7 +134,7 @@ class SegmentAnythingInvocation(BaseInvocation):
             ) as sam_pipeline,
         ):
             assert isinstance(sam_pipeline, SegmentAnythingPipeline)
-            masks = sam_pipeline.segment(image=image, bounding_boxes=sam_bounding_boxes)
+            masks = sam_pipeline.segment(image=image, bounding_boxes=sam_bounding_boxes, point_lists=sam_points)
 
         masks = self._process_masks(masks)
         if self.apply_polygon_refinement:
@@ -141,9 +177,10 @@ class SegmentAnythingInvocation(BaseInvocation):
 
         return masks
 
-    def _filter_masks(self, masks: list[torch.Tensor], bounding_boxes: list[BoundingBoxField]) -> list[torch.Tensor]:
+    def _filter_masks(
+        self, masks: list[torch.Tensor], bounding_boxes: list[BoundingBoxField] | None
+    ) -> 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
@@ -151,6 +188,10 @@ class SegmentAnythingInvocation(BaseInvocation):
             # Find the largest mask.
             return [max(masks, key=lambda x: float(x.sum()))]
         elif self.mask_filter == "highest_box_score":
+            assert (
+                bounding_boxes is not None
+            ), "Bounding boxes must be provided to use the 'highest_box_score' mask filter."
+            assert len(masks) == len(bounding_boxes)
             # 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

invokeai/app/services/board_records/board_records_base.py

@@ -1,7 +1,8 @@
 from abc import ABC, abstractmethod
 
-from invokeai.app.services.board_records.board_records_common import BoardChanges, BoardRecord
+from invokeai.app.services.board_records.board_records_common import BoardChanges, BoardRecord, BoardRecordOrderBy
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+from invokeai.app.services.shared.sqlite.sqlite_common import SQLiteDirection
 
 
 class BoardRecordStorageBase(ABC):
@@ -39,12 +40,19 @@ class BoardRecordStorageBase(ABC):
 
     @abstractmethod
     def get_many(
-        self, offset: int = 0, limit: int = 10, include_archived: bool = False
+        self,
+        order_by: BoardRecordOrderBy,
+        direction: SQLiteDirection,
+        offset: int = 0,
+        limit: int = 10,
+        include_archived: bool = False,
     ) -> OffsetPaginatedResults[BoardRecord]:
         """Gets many board records."""
         pass
 
     @abstractmethod
-    def get_all(self, include_archived: bool = False) -> list[BoardRecord]:
+    def get_all(
+        self, order_by: BoardRecordOrderBy, direction: SQLiteDirection, include_archived: bool = False
+    ) -> list[BoardRecord]:
         """Gets all board records."""
         pass

invokeai/app/services/board_records/board_records_common.py

@@ -1,8 +1,10 @@
 from datetime import datetime
+from enum import Enum
 from typing import Optional, Union
 
 from pydantic import BaseModel, Field
 
+from invokeai.app.util.metaenum import MetaEnum
 from invokeai.app.util.misc import get_iso_timestamp
 from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
 
@@ -60,6 +62,13 @@ class BoardChanges(BaseModel, extra="forbid"):
     archived: Optional[bool] = Field(default=None, description="Whether or not the board is archived")
 
 
+class BoardRecordOrderBy(str, Enum, metaclass=MetaEnum):
+    """The order by options for board records"""
+
+    CreatedAt = "created_at"
+    Name = "board_name"
+
+
 class BoardRecordNotFoundException(Exception):
     """Raised when an board record is not found."""
 

invokeai/app/services/board_records/board_records_sqlite.py

@@ -8,10 +8,12 @@ from invokeai.app.services.board_records.board_records_common import (
     BoardRecord,
     BoardRecordDeleteException,
     BoardRecordNotFoundException,
+    BoardRecordOrderBy,
     BoardRecordSaveException,
     deserialize_board_record,
 )
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+from invokeai.app.services.shared.sqlite.sqlite_common import SQLiteDirection
 from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
 from invokeai.app.util.misc import uuid_string
 
@@ -144,7 +146,12 @@ class SqliteBoardRecordStorage(BoardRecordStorageBase):
         return self.get(board_id)
 
     def get_many(
-        self, offset: int = 0, limit: int = 10, include_archived: bool = False
+        self,
+        order_by: BoardRecordOrderBy,
+        direction: SQLiteDirection,
+        offset: int = 0,
+        limit: int = 10,
+        include_archived: bool = False,
     ) -> OffsetPaginatedResults[BoardRecord]:
         try:
             self._lock.acquire()
@@ -154,17 +161,16 @@ class SqliteBoardRecordStorage(BoardRecordStorageBase):
                 SELECT *
                 FROM boards
                 {archived_filter}
-                ORDER BY created_at DESC
+                ORDER BY {order_by} {direction}
                 LIMIT ? OFFSET ?;
             """
 
             # Determine archived filter condition
-            if include_archived:
-                archived_filter = ""
-            else:
-                archived_filter = "WHERE archived = 0"
+            archived_filter = "" if include_archived else "WHERE archived = 0"
 
-            final_query = base_query.format(archived_filter=archived_filter)
+            final_query = base_query.format(
+                archived_filter=archived_filter, order_by=order_by.value, direction=direction.value
+            )
 
             # Execute query to fetch boards
             self._cursor.execute(final_query, (limit, offset))
@@ -198,23 +204,32 @@ class SqliteBoardRecordStorage(BoardRecordStorageBase):
         finally:
             self._lock.release()
 
-    def get_all(self, include_archived: bool = False) -> list[BoardRecord]:
+    def get_all(
+        self, order_by: BoardRecordOrderBy, direction: SQLiteDirection, include_archived: bool = False
+    ) -> list[BoardRecord]:
         try:
             self._lock.acquire()
 
-            base_query = """
-                SELECT *
-                FROM boards
-                {archived_filter}
-                ORDER BY created_at DESC
-            """
-
-            if include_archived:
-                archived_filter = ""
+            if order_by == BoardRecordOrderBy.Name:
+                base_query = """
+                    SELECT *
+                    FROM boards
+                    {archived_filter}
+                    ORDER BY LOWER(board_name) {direction}
+                """
             else:
-                archived_filter = "WHERE archived = 0"
+                base_query = """
+                    SELECT *
+                    FROM boards
+                    {archived_filter}
+                    ORDER BY {order_by} {direction}
+                """
 
-            final_query = base_query.format(archived_filter=archived_filter)
+            archived_filter = "" if include_archived else "WHERE archived = 0"
+
+            final_query = base_query.format(
+                archived_filter=archived_filter, order_by=order_by.value, direction=direction.value
+            )
 
             self._cursor.execute(final_query)
 

invokeai/app/services/boards/boards_base.py

@@ -1,8 +1,9 @@
 from abc import ABC, abstractmethod
 
-from invokeai.app.services.board_records.board_records_common import BoardChanges
+from invokeai.app.services.board_records.board_records_common import BoardChanges, BoardRecordOrderBy
 from invokeai.app.services.boards.boards_common import BoardDTO
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+from invokeai.app.services.shared.sqlite.sqlite_common import SQLiteDirection
 
 
 class BoardServiceABC(ABC):
@@ -43,12 +44,19 @@ class BoardServiceABC(ABC):
 
     @abstractmethod
     def get_many(
-        self, offset: int = 0, limit: int = 10, include_archived: bool = False
+        self,
+        order_by: BoardRecordOrderBy,
+        direction: SQLiteDirection,
+        offset: int = 0,
+        limit: int = 10,
+        include_archived: bool = False,
     ) -> OffsetPaginatedResults[BoardDTO]:
         """Gets many boards."""
         pass
 
     @abstractmethod
-    def get_all(self, include_archived: bool = False) -> list[BoardDTO]:
+    def get_all(
+        self, order_by: BoardRecordOrderBy, direction: SQLiteDirection, include_archived: bool = False
+    ) -> list[BoardDTO]:
         """Gets all boards."""
         pass

invokeai/app/services/boards/boards_default.py

@@ -1,8 +1,9 @@
-from invokeai.app.services.board_records.board_records_common import BoardChanges
+from invokeai.app.services.board_records.board_records_common import BoardChanges, BoardRecordOrderBy
 from invokeai.app.services.boards.boards_base import BoardServiceABC
 from invokeai.app.services.boards.boards_common import BoardDTO, board_record_to_dto
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
+from invokeai.app.services.shared.sqlite.sqlite_common import SQLiteDirection
 
 
 class BoardService(BoardServiceABC):
@@ -47,9 +48,16 @@ class BoardService(BoardServiceABC):
         self.__invoker.services.board_records.delete(board_id)
 
     def get_many(
-        self, offset: int = 0, limit: int = 10, include_archived: bool = False
+        self,
+        order_by: BoardRecordOrderBy,
+        direction: SQLiteDirection,
+        offset: int = 0,
+        limit: int = 10,
+        include_archived: bool = False,
     ) -> OffsetPaginatedResults[BoardDTO]:
-        board_records = self.__invoker.services.board_records.get_many(offset, limit, include_archived)
+        board_records = self.__invoker.services.board_records.get_many(
+            order_by, direction, offset, limit, include_archived
+        )
         board_dtos = []
         for r in board_records.items:
             cover_image = self.__invoker.services.image_records.get_most_recent_image_for_board(r.board_id)
@@ -63,8 +71,10 @@ class BoardService(BoardServiceABC):
 
         return OffsetPaginatedResults[BoardDTO](items=board_dtos, offset=offset, limit=limit, total=len(board_dtos))
 
-    def get_all(self, include_archived: bool = False) -> list[BoardDTO]:
-        board_records = self.__invoker.services.board_records.get_all(include_archived)
+    def get_all(
+        self, order_by: BoardRecordOrderBy, direction: SQLiteDirection, include_archived: bool = False
+    ) -> list[BoardDTO]:
+        board_records = self.__invoker.services.board_records.get_all(order_by, direction, include_archived)
         board_dtos = []
         for r in board_records:
             cover_image = self.__invoker.services.image_records.get_most_recent_image_for_board(r.board_id)

invokeai/app/services/image_files/image_files_disk.py

@@ -110,15 +110,26 @@ class DiskImageFileStorage(ImageFileStorageBase):
         except Exception as e:
             raise ImageFileDeleteException from e
 
-    # TODO: make this a bit more flexible for e.g. cloud storage
     def get_path(self, image_name: str, thumbnail: bool = False) -> Path:
-        path = self.__output_folder / image_name
+        base_folder = self.__thumbnails_folder if thumbnail else self.__output_folder
+        filename = get_thumbnail_name(image_name) if thumbnail else image_name
 
-        if thumbnail:
-            thumbnail_name = get_thumbnail_name(image_name)
-            path = self.__thumbnails_folder / thumbnail_name
+        # Strip any path information from the filename
+        basename = Path(filename).name
 
-        return path
+        if basename != filename:
+            raise ValueError("Invalid image name, potential directory traversal detected")
+
+        image_path = base_folder / basename
+
+        # Ensure the image path is within the base folder to prevent directory traversal
+        resolved_base = base_folder.resolve()
+        resolved_image_path = image_path.resolve()
+
+        if not resolved_image_path.is_relative_to(resolved_base):
+            raise ValueError("Image path outside outputs folder, potential directory traversal detected")
+
+        return resolved_image_path
 
     def validate_path(self, path: Union[str, Path]) -> bool:
         """Validates the path given for an image or thumbnail."""

invokeai/app/services/shared/invocation_context.py

@@ -1,3 +1,4 @@
+from copy import deepcopy
 from dataclasses import dataclass
 from pathlib import Path
 from typing import TYPE_CHECKING, Callable, Optional, Union
@@ -221,7 +222,7 @@ class ImagesInterface(InvocationContextInterface):
         )
 
     def get_pil(self, image_name: str, mode: IMAGE_MODES | None = None) -> Image:
-        """Gets an image as a PIL Image object.
+        """Gets an image as a PIL Image object. This method returns a copy of the image.
 
         Args:
             image_name: The name of the image to get.
@@ -233,11 +234,15 @@ class ImagesInterface(InvocationContextInterface):
         image = self._services.images.get_pil_image(image_name)
         if mode and mode != image.mode:
             try:
+                # convert makes a copy!
                 image = image.convert(mode)
             except ValueError:
                 self._services.logger.warning(
                     f"Could not convert image from {image.mode} to {mode}. Using original mode instead."
                 )
+        else:
+            # copy the image to prevent the user from modifying the original
+            image = image.copy()
         return image
 
     def get_metadata(self, image_name: str) -> Optional[MetadataField]:
@@ -290,15 +295,15 @@ class TensorsInterface(InvocationContextInterface):
         return name
 
     def load(self, name: str) -> Tensor:
-        """Loads a tensor by name.
+        """Loads a tensor by name. This method returns a copy of the tensor.
 
         Args:
             name: The name of the tensor to load.
 
         Returns:
-            The loaded tensor.
+            The tensor.
         """
-        return self._services.tensors.load(name)
+        return self._services.tensors.load(name).clone()
 
 
 class ConditioningInterface(InvocationContextInterface):
@@ -316,16 +321,16 @@ class ConditioningInterface(InvocationContextInterface):
         return name
 
     def load(self, name: str) -> ConditioningFieldData:
-        """Loads conditioning data by name.
+        """Loads conditioning data by name. This method returns a copy of the conditioning data.
 
         Args:
             name: The name of the conditioning data to load.
 
         Returns:
-            The loaded conditioning data.
+            The conditioning data.
         """
 
-        return self._services.conditioning.load(name)
+        return deepcopy(self._services.conditioning.load(name))
 
 
 class ModelsInterface(InvocationContextInterface):

invokeai/app/services/workflow_records/workflow_records_base.py

@@ -41,9 +41,9 @@ class WorkflowRecordsStorageBase(ABC):
         self,
         order_by: WorkflowRecordOrderBy,
         direction: SQLiteDirection,
+        category: WorkflowCategory,
         page: int,
         per_page: Optional[int],
-        category: Optional[WorkflowCategory],
         query: Optional[str],
     ) -> PaginatedResults[WorkflowRecordListItemDTO]:
         """Gets many workflows."""

invokeai/app/services/workflow_records/workflow_records_sqlite.py

@@ -127,9 +127,9 @@ class SqliteWorkflowRecordsStorage(WorkflowRecordsStorageBase):
         self,
         order_by: WorkflowRecordOrderBy,
         direction: SQLiteDirection,
+        category: WorkflowCategory,
         page: int = 0,
         per_page: Optional[int] = None,
-        category: Optional[WorkflowCategory] = None,
         query: Optional[str] = None,
     ) -> PaginatedResults[WorkflowRecordListItemDTO]:
         try:
@@ -137,7 +137,8 @@ class SqliteWorkflowRecordsStorage(WorkflowRecordsStorageBase):
             # sanitize!
             assert order_by in WorkflowRecordOrderBy
             assert direction in SQLiteDirection
-            count_query = "SELECT COUNT(*) FROM workflow_library"
+            assert category in WorkflowCategory
+            count_query = "SELECT COUNT(*) FROM workflow_library WHERE category = ?"
             main_query = """
                 SELECT
                     workflow_id,
@@ -148,26 +149,16 @@ class SqliteWorkflowRecordsStorage(WorkflowRecordsStorageBase):
                     updated_at,
                     opened_at
                 FROM workflow_library
+                WHERE category = ?
                 """
-            main_params: list[int | str] = []
-            count_params: list[int | str] = []
-
-            if category:
-                assert category in WorkflowCategory
-                main_query += " WHERE category = ?"
-                count_query += " WHERE category = ?"
-                main_params.append(category.value)
-                count_params.append(category.value)
+            main_params: list[int | str] = [category.value]
+            count_params: list[int | str] = [category.value]
 
             stripped_query = query.strip() if query else None
             if stripped_query:
                 wildcard_query = "%" + stripped_query + "%"
-                if "WHERE" in main_query:
-                    main_query += " AND (name LIKE ? OR description LIKE ?)"
-                    count_query += " AND (name LIKE ? OR description LIKE ?)"
-                else:
-                    main_query += " WHERE name LIKE ? OR description LIKE ?"
-                    count_query += " WHERE name LIKE ? OR description LIKE ?"
+                main_query += " AND name LIKE ? OR description LIKE ? "
+                count_query += " AND name LIKE ? OR description LIKE ?;"
                 main_params.extend([wildcard_query, wildcard_query])
                 count_params.extend([wildcard_query, wildcard_query])
 

invokeai/backend/flux/controlnet/controlnet_flux_output.py

@@ -0,0 +1,58 @@
+from dataclasses import dataclass
+
+import torch
+
+
+@dataclass
+class ControlNetFluxOutput:
+    single_block_residuals: list[torch.Tensor] | None
+    double_block_residuals: list[torch.Tensor] | None
+
+    def apply_weight(self, weight: float):
+        if self.single_block_residuals is not None:
+            for i in range(len(self.single_block_residuals)):
+                self.single_block_residuals[i] = self.single_block_residuals[i] * weight
+        if self.double_block_residuals is not None:
+            for i in range(len(self.double_block_residuals)):
+                self.double_block_residuals[i] = self.double_block_residuals[i] * weight
+
+
+def add_tensor_lists_elementwise(
+    list1: list[torch.Tensor] | None, list2: list[torch.Tensor] | None
+) -> list[torch.Tensor] | None:
+    """Add two tensor lists elementwise that could be None."""
+    if list1 is None and list2 is None:
+        return None
+    if list1 is None:
+        return list2
+    if list2 is None:
+        return list1
+
+    new_list: list[torch.Tensor] = []
+    for list1_tensor, list2_tensor in zip(list1, list2, strict=True):
+        new_list.append(list1_tensor + list2_tensor)
+    return new_list
+
+
+def add_controlnet_flux_outputs(
+    controlnet_output_1: ControlNetFluxOutput, controlnet_output_2: ControlNetFluxOutput
+) -> ControlNetFluxOutput:
+    return ControlNetFluxOutput(
+        single_block_residuals=add_tensor_lists_elementwise(
+            controlnet_output_1.single_block_residuals, controlnet_output_2.single_block_residuals
+        ),
+        double_block_residuals=add_tensor_lists_elementwise(
+            controlnet_output_1.double_block_residuals, controlnet_output_2.double_block_residuals
+        ),
+    )
+
+
+def sum_controlnet_flux_outputs(
+    controlnet_outputs: list[ControlNetFluxOutput],
+) -> ControlNetFluxOutput:
+    controlnet_output_sum = ControlNetFluxOutput(single_block_residuals=None, double_block_residuals=None)
+
+    for controlnet_output in controlnet_outputs:
+        controlnet_output_sum = add_controlnet_flux_outputs(controlnet_output_sum, controlnet_output)
+
+    return controlnet_output_sum

invokeai/backend/flux/controlnet/instantx_controlnet_flux.py

@@ -0,0 +1,180 @@
+# This file was initially copied from:
+# https://github.com/huggingface/diffusers/blob/99f608218caa069a2f16dcf9efab46959b15aec0/src/diffusers/models/controlnet_flux.py
+
+
+from dataclasses import dataclass
+
+import torch
+import torch.nn as nn
+
+from invokeai.backend.flux.controlnet.zero_module import zero_module
+from invokeai.backend.flux.model import FluxParams
+from invokeai.backend.flux.modules.layers import (
+    DoubleStreamBlock,
+    EmbedND,
+    MLPEmbedder,
+    SingleStreamBlock,
+    timestep_embedding,
+)
+
+
+@dataclass
+class InstantXControlNetFluxOutput:
+    controlnet_block_samples: list[torch.Tensor] | None
+    controlnet_single_block_samples: list[torch.Tensor] | None
+
+
+# NOTE(ryand): Mapping between diffusers FLUX transformer params and BFL FLUX transformer params:
+# - Diffusers: BFL
+# - in_channels: in_channels
+# - num_layers: depth
+# - num_single_layers: depth_single_blocks
+# - attention_head_dim: hidden_size // num_heads
+# - num_attention_heads: num_heads
+# - joint_attention_dim: context_in_dim
+# - pooled_projection_dim: vec_in_dim
+# - guidance_embeds: guidance_embed
+# - axes_dims_rope: axes_dim
+
+
+class InstantXControlNetFlux(torch.nn.Module):
+    def __init__(self, params: FluxParams, num_control_modes: int | None = None):
+        """
+        Args:
+            params (FluxParams): The parameters for the FLUX model.
+            num_control_modes (int | None, optional): The number of controlnet modes. If non-None, then the model is a
+                'union controlnet' model and expects a mode conditioning input at runtime.
+        """
+        super().__init__()
+
+        # The following modules mirror the base FLUX transformer model.
+        # -------------------------------------------------------------
+        self.params = params
+        self.in_channels = params.in_channels
+        self.out_channels = self.in_channels
+        if params.hidden_size % params.num_heads != 0:
+            raise ValueError(f"Hidden size {params.hidden_size} must be divisible by num_heads {params.num_heads}")
+        pe_dim = params.hidden_size // params.num_heads
+        if sum(params.axes_dim) != pe_dim:
+            raise ValueError(f"Got {params.axes_dim} but expected positional dim {pe_dim}")
+        self.hidden_size = params.hidden_size
+        self.num_heads = params.num_heads
+        self.pe_embedder = EmbedND(dim=pe_dim, theta=params.theta, axes_dim=params.axes_dim)
+        self.img_in = nn.Linear(self.in_channels, self.hidden_size, bias=True)
+        self.time_in = MLPEmbedder(in_dim=256, hidden_dim=self.hidden_size)
+        self.vector_in = MLPEmbedder(params.vec_in_dim, self.hidden_size)
+        self.guidance_in = (
+            MLPEmbedder(in_dim=256, hidden_dim=self.hidden_size) if params.guidance_embed else nn.Identity()
+        )
+        self.txt_in = nn.Linear(params.context_in_dim, self.hidden_size)
+
+        self.double_blocks = nn.ModuleList(
+            [
+                DoubleStreamBlock(
+                    self.hidden_size,
+                    self.num_heads,
+                    mlp_ratio=params.mlp_ratio,
+                    qkv_bias=params.qkv_bias,
+                )
+                for _ in range(params.depth)
+            ]
+        )
+
+        self.single_blocks = nn.ModuleList(
+            [
+                SingleStreamBlock(self.hidden_size, self.num_heads, mlp_ratio=params.mlp_ratio)
+                for _ in range(params.depth_single_blocks)
+            ]
+        )
+
+        # The following modules are specific to the ControlNet model.
+        # -----------------------------------------------------------
+        self.controlnet_blocks = nn.ModuleList([])
+        for _ in range(len(self.double_blocks)):
+            self.controlnet_blocks.append(zero_module(nn.Linear(self.hidden_size, self.hidden_size)))
+
+        self.controlnet_single_blocks = nn.ModuleList([])
+        for _ in range(len(self.single_blocks)):
+            self.controlnet_single_blocks.append(zero_module(nn.Linear(self.hidden_size, self.hidden_size)))
+
+        self.is_union = False
+        if num_control_modes is not None:
+            self.is_union = True
+            self.controlnet_mode_embedder = nn.Embedding(num_control_modes, self.hidden_size)
+
+        self.controlnet_x_embedder = zero_module(torch.nn.Linear(self.in_channels, self.hidden_size))
+
+    def forward(
+        self,
+        controlnet_cond: torch.Tensor,
+        controlnet_mode: torch.Tensor | None,
+        img: torch.Tensor,
+        img_ids: torch.Tensor,
+        txt: torch.Tensor,
+        txt_ids: torch.Tensor,
+        timesteps: torch.Tensor,
+        y: torch.Tensor,
+        guidance: torch.Tensor | None = None,
+    ) -> InstantXControlNetFluxOutput:
+        if img.ndim != 3 or txt.ndim != 3:
+            raise ValueError("Input img and txt tensors must have 3 dimensions.")
+
+        img = self.img_in(img)
+
+        # Add controlnet_cond embedding.
+        img = img + self.controlnet_x_embedder(controlnet_cond)
+
+        vec = self.time_in(timestep_embedding(timesteps, 256))
+        if self.params.guidance_embed:
+            if guidance is None:
+                raise ValueError("Didn't get guidance strength for guidance distilled model.")
+            vec = vec + self.guidance_in(timestep_embedding(guidance, 256))
+        vec = vec + self.vector_in(y)
+        txt = self.txt_in(txt)
+
+        # If this is a union ControlNet, then concat the control mode embedding to the T5 text embedding.
+        if self.is_union:
+            if controlnet_mode is None:
+                # We allow users to enter 'None' as the controlnet_mode if they don't want to worry about this input.
+                # We've chosen to use a zero-embedding in this case.
+                zero_index = torch.zeros([1, 1], dtype=torch.long, device=txt.device)
+                controlnet_mode_emb = torch.zeros_like(self.controlnet_mode_embedder(zero_index))
+            else:
+                controlnet_mode_emb = self.controlnet_mode_embedder(controlnet_mode)
+            txt = torch.cat([controlnet_mode_emb, txt], dim=1)
+            txt_ids = torch.cat([txt_ids[:, :1, :], txt_ids], dim=1)
+        else:
+            assert controlnet_mode is None
+
+        ids = torch.cat((txt_ids, img_ids), dim=1)
+        pe = self.pe_embedder(ids)
+
+        double_block_samples: list[torch.Tensor] = []
+        for block in self.double_blocks:
+            img, txt = block(img=img, txt=txt, vec=vec, pe=pe)
+            double_block_samples.append(img)
+
+        img = torch.cat((txt, img), 1)
+
+        single_block_samples: list[torch.Tensor] = []
+        for block in self.single_blocks:
+            img = block(img, vec=vec, pe=pe)
+            single_block_samples.append(img[:, txt.shape[1] :])
+
+        # ControlNet Block
+        controlnet_double_block_samples: list[torch.Tensor] = []
+        for double_block_sample, controlnet_block in zip(double_block_samples, self.controlnet_blocks, strict=True):
+            double_block_sample = controlnet_block(double_block_sample)
+            controlnet_double_block_samples.append(double_block_sample)
+
+        controlnet_single_block_samples: list[torch.Tensor] = []
+        for single_block_sample, controlnet_block in zip(
+            single_block_samples, self.controlnet_single_blocks, strict=True
+        ):
+            single_block_sample = controlnet_block(single_block_sample)
+            controlnet_single_block_samples.append(single_block_sample)
+
+        return InstantXControlNetFluxOutput(
+            controlnet_block_samples=controlnet_double_block_samples or None,
+            controlnet_single_block_samples=controlnet_single_block_samples or None,
+        )

invokeai/backend/flux/controlnet/state_dict_utils.py

@@ -0,0 +1,295 @@
+from typing import Any, Dict
+
+import torch
+
+from invokeai.backend.flux.model import FluxParams
+
+
+def is_state_dict_xlabs_controlnet(sd: Dict[str, Any]) -> bool:
+    """Is the state dict for an XLabs ControlNet model?
+
+    This is intended to be a reasonably high-precision detector, but it is not guaranteed to have perfect precision.
+    """
+    # If all of the expected keys are present, then this is very likely an XLabs ControlNet model.
+    expected_keys = {
+        "controlnet_blocks.0.bias",
+        "controlnet_blocks.0.weight",
+        "input_hint_block.0.bias",
+        "input_hint_block.0.weight",
+        "pos_embed_input.bias",
+        "pos_embed_input.weight",
+    }
+
+    if expected_keys.issubset(sd.keys()):
+        return True
+    return False
+
+
+def is_state_dict_instantx_controlnet(sd: Dict[str, Any]) -> bool:
+    """Is the state dict for an InstantX ControlNet model?
+
+    This is intended to be a reasonably high-precision detector, but it is not guaranteed to have perfect precision.
+    """
+    # If all of the expected keys are present, then this is very likely an InstantX ControlNet model.
+    expected_keys = {
+        "controlnet_blocks.0.bias",
+        "controlnet_blocks.0.weight",
+        "controlnet_x_embedder.bias",
+        "controlnet_x_embedder.weight",
+    }
+
+    if expected_keys.issubset(sd.keys()):
+        return True
+    return False
+
+
+def _fuse_weights(*t: torch.Tensor) -> torch.Tensor:
+    """Fuse weights along dimension 0.
+
+    Used to fuse q, k, v attention weights into a single qkv tensor when converting from diffusers to BFL format.
+    """
+    # TODO(ryand): Double check dim=0 is correct.
+    return torch.cat(t, dim=0)
+
+
+def _convert_flux_double_block_sd_from_diffusers_to_bfl_format(
+    sd: Dict[str, torch.Tensor], double_block_index: int
+) -> Dict[str, torch.Tensor]:
+    """Convert the state dict for a double block from diffusers format to BFL format."""
+    to_prefix = f"double_blocks.{double_block_index}"
+    from_prefix = f"transformer_blocks.{double_block_index}"
+
+    new_sd: dict[str, torch.Tensor] = {}
+
+    # Check one key to determine if this block exists.
+    if f"{from_prefix}.attn.add_q_proj.bias" not in sd:
+        return new_sd
+
+    # txt_attn.qkv
+    new_sd[f"{to_prefix}.txt_attn.qkv.bias"] = _fuse_weights(
+        sd.pop(f"{from_prefix}.attn.add_q_proj.bias"),
+        sd.pop(f"{from_prefix}.attn.add_k_proj.bias"),
+        sd.pop(f"{from_prefix}.attn.add_v_proj.bias"),
+    )
+    new_sd[f"{to_prefix}.txt_attn.qkv.weight"] = _fuse_weights(
+        sd.pop(f"{from_prefix}.attn.add_q_proj.weight"),
+        sd.pop(f"{from_prefix}.attn.add_k_proj.weight"),
+        sd.pop(f"{from_prefix}.attn.add_v_proj.weight"),
+    )
+
+    # img_attn.qkv
+    new_sd[f"{to_prefix}.img_attn.qkv.bias"] = _fuse_weights(
+        sd.pop(f"{from_prefix}.attn.to_q.bias"),
+        sd.pop(f"{from_prefix}.attn.to_k.bias"),
+        sd.pop(f"{from_prefix}.attn.to_v.bias"),
+    )
+    new_sd[f"{to_prefix}.img_attn.qkv.weight"] = _fuse_weights(
+        sd.pop(f"{from_prefix}.attn.to_q.weight"),
+        sd.pop(f"{from_prefix}.attn.to_k.weight"),
+        sd.pop(f"{from_prefix}.attn.to_v.weight"),
+    )
+
+    # Handle basic 1-to-1 key conversions.
+    key_map = {
+        # img_attn
+        "attn.norm_k.weight": "img_attn.norm.key_norm.scale",
+        "attn.norm_q.weight": "img_attn.norm.query_norm.scale",
+        "attn.to_out.0.weight": "img_attn.proj.weight",
+        "attn.to_out.0.bias": "img_attn.proj.bias",
+        # img_mlp
+        "ff.net.0.proj.weight": "img_mlp.0.weight",
+        "ff.net.0.proj.bias": "img_mlp.0.bias",
+        "ff.net.2.weight": "img_mlp.2.weight",
+        "ff.net.2.bias": "img_mlp.2.bias",
+        # img_mod
+        "norm1.linear.weight": "img_mod.lin.weight",
+        "norm1.linear.bias": "img_mod.lin.bias",
+        # txt_attn
+        "attn.norm_added_q.weight": "txt_attn.norm.query_norm.scale",
+        "attn.norm_added_k.weight": "txt_attn.norm.key_norm.scale",
+        "attn.to_add_out.weight": "txt_attn.proj.weight",
+        "attn.to_add_out.bias": "txt_attn.proj.bias",
+        # txt_mlp
+        "ff_context.net.0.proj.weight": "txt_mlp.0.weight",
+        "ff_context.net.0.proj.bias": "txt_mlp.0.bias",
+        "ff_context.net.2.weight": "txt_mlp.2.weight",
+        "ff_context.net.2.bias": "txt_mlp.2.bias",
+        # txt_mod
+        "norm1_context.linear.weight": "txt_mod.lin.weight",
+        "norm1_context.linear.bias": "txt_mod.lin.bias",
+    }
+    for from_key, to_key in key_map.items():
+        new_sd[f"{to_prefix}.{to_key}"] = sd.pop(f"{from_prefix}.{from_key}")
+
+    return new_sd
+
+
+def _convert_flux_single_block_sd_from_diffusers_to_bfl_format(
+    sd: Dict[str, torch.Tensor], single_block_index: int
+) -> Dict[str, torch.Tensor]:
+    """Convert the state dict for a single block from diffusers format to BFL format."""
+    to_prefix = f"single_blocks.{single_block_index}"
+    from_prefix = f"single_transformer_blocks.{single_block_index}"
+
+    new_sd: dict[str, torch.Tensor] = {}
+
+    # Check one key to determine if this block exists.
+    if f"{from_prefix}.attn.to_q.bias" not in sd:
+        return new_sd
+
+    # linear1 (qkv)
+    new_sd[f"{to_prefix}.linear1.bias"] = _fuse_weights(
+        sd.pop(f"{from_prefix}.attn.to_q.bias"),
+        sd.pop(f"{from_prefix}.attn.to_k.bias"),
+        sd.pop(f"{from_prefix}.attn.to_v.bias"),
+        sd.pop(f"{from_prefix}.proj_mlp.bias"),
+    )
+    new_sd[f"{to_prefix}.linear1.weight"] = _fuse_weights(
+        sd.pop(f"{from_prefix}.attn.to_q.weight"),
+        sd.pop(f"{from_prefix}.attn.to_k.weight"),
+        sd.pop(f"{from_prefix}.attn.to_v.weight"),
+        sd.pop(f"{from_prefix}.proj_mlp.weight"),
+    )
+
+    # Handle basic 1-to-1 key conversions.
+    key_map = {
+        # linear2
+        "proj_out.weight": "linear2.weight",
+        "proj_out.bias": "linear2.bias",
+        # modulation
+        "norm.linear.weight": "modulation.lin.weight",
+        "norm.linear.bias": "modulation.lin.bias",
+        # norm
+        "attn.norm_k.weight": "norm.key_norm.scale",
+        "attn.norm_q.weight": "norm.query_norm.scale",
+    }
+    for from_key, to_key in key_map.items():
+        new_sd[f"{to_prefix}.{to_key}"] = sd.pop(f"{from_prefix}.{from_key}")
+
+    return new_sd
+
+
+def convert_diffusers_instantx_state_dict_to_bfl_format(sd: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+    """Convert an InstantX ControlNet state dict to the format that can be loaded by our internal
+    InstantXControlNetFlux model.
+
+    The original InstantX ControlNet model was developed to be used in diffusers. We have ported the original
+    implementation to InstantXControlNetFlux to make it compatible with BFL-style models. This function converts the
+    original state dict to the format expected by InstantXControlNetFlux.
+    """
+    # Shallow copy sd so that we can pop keys from it without modifying the original.
+    sd = sd.copy()
+
+    new_sd: dict[str, torch.Tensor] = {}
+
+    # Handle basic 1-to-1 key conversions.
+    basic_key_map = {
+        # Base model keys.
+        # ----------------
+        # txt_in keys.
+        "context_embedder.bias": "txt_in.bias",
+        "context_embedder.weight": "txt_in.weight",
+        # guidance_in MLPEmbedder keys.
+        "time_text_embed.guidance_embedder.linear_1.bias": "guidance_in.in_layer.bias",
+        "time_text_embed.guidance_embedder.linear_1.weight": "guidance_in.in_layer.weight",
+        "time_text_embed.guidance_embedder.linear_2.bias": "guidance_in.out_layer.bias",
+        "time_text_embed.guidance_embedder.linear_2.weight": "guidance_in.out_layer.weight",
+        # vector_in MLPEmbedder keys.
+        "time_text_embed.text_embedder.linear_1.bias": "vector_in.in_layer.bias",
+        "time_text_embed.text_embedder.linear_1.weight": "vector_in.in_layer.weight",
+        "time_text_embed.text_embedder.linear_2.bias": "vector_in.out_layer.bias",
+        "time_text_embed.text_embedder.linear_2.weight": "vector_in.out_layer.weight",
+        # time_in MLPEmbedder keys.
+        "time_text_embed.timestep_embedder.linear_1.bias": "time_in.in_layer.bias",
+        "time_text_embed.timestep_embedder.linear_1.weight": "time_in.in_layer.weight",
+        "time_text_embed.timestep_embedder.linear_2.bias": "time_in.out_layer.bias",
+        "time_text_embed.timestep_embedder.linear_2.weight": "time_in.out_layer.weight",
+        # img_in keys.
+        "x_embedder.bias": "img_in.bias",
+        "x_embedder.weight": "img_in.weight",
+    }
+    for old_key, new_key in basic_key_map.items():
+        v = sd.pop(old_key, None)
+        if v is not None:
+            new_sd[new_key] = v
+
+    # Handle the double_blocks.
+    block_index = 0
+    while True:
+        converted_double_block_sd = _convert_flux_double_block_sd_from_diffusers_to_bfl_format(sd, block_index)
+        if len(converted_double_block_sd) == 0:
+            break
+        new_sd.update(converted_double_block_sd)
+        block_index += 1
+
+    # Handle the single_blocks.
+    block_index = 0
+    while True:
+        converted_singe_block_sd = _convert_flux_single_block_sd_from_diffusers_to_bfl_format(sd, block_index)
+        if len(converted_singe_block_sd) == 0:
+            break
+        new_sd.update(converted_singe_block_sd)
+        block_index += 1
+
+    # Transfer controlnet keys as-is.
+    for k in list(sd.keys()):
+        if k.startswith("controlnet_"):
+            new_sd[k] = sd.pop(k)
+
+    # Assert that all keys have been handled.
+    assert len(sd) == 0
+    return new_sd
+
+
+def infer_flux_params_from_state_dict(sd: Dict[str, torch.Tensor]) -> FluxParams:
+    """Infer the FluxParams from the shape of a FLUX state dict. When a model is distributed in diffusers format, this
+    information is all contained in the config.json file that accompanies the model. However, being apple to infer the
+    params from the state dict enables us to load models (e.g. an InstantX ControlNet) from a single weight file.
+    """
+    hidden_size = sd["img_in.weight"].shape[0]
+    mlp_hidden_dim = sd["double_blocks.0.img_mlp.0.weight"].shape[0]
+    # mlp_ratio is a float, but we treat it as an int here to avoid having to think about possible float precision
+    # issues. In practice, mlp_ratio is usually 4.
+    mlp_ratio = mlp_hidden_dim // hidden_size
+
+    head_dim = sd["double_blocks.0.img_attn.norm.query_norm.scale"].shape[0]
+    num_heads = hidden_size // head_dim
+
+    # Count the number of double blocks.
+    double_block_index = 0
+    while f"double_blocks.{double_block_index}.img_attn.qkv.weight" in sd:
+        double_block_index += 1
+
+    # Count the number of single blocks.
+    single_block_index = 0
+    while f"single_blocks.{single_block_index}.linear1.weight" in sd:
+        single_block_index += 1
+
+    return FluxParams(
+        in_channels=sd["img_in.weight"].shape[1],
+        vec_in_dim=sd["vector_in.in_layer.weight"].shape[1],
+        context_in_dim=sd["txt_in.weight"].shape[1],
+        hidden_size=hidden_size,
+        mlp_ratio=mlp_ratio,
+        num_heads=num_heads,
+        depth=double_block_index,
+        depth_single_blocks=single_block_index,
+        # axes_dim cannot be inferred from the state dict. The hard-coded value is correct for dev/schnell models.
+        axes_dim=[16, 56, 56],
+        # theta cannot be inferred from the state dict. The hard-coded value is correct for dev/schnell models.
+        theta=10_000,
+        qkv_bias="double_blocks.0.img_attn.qkv.bias" in sd,
+        guidance_embed="guidance_in.in_layer.weight" in sd,
+    )
+
+
+def infer_instantx_num_control_modes_from_state_dict(sd: Dict[str, torch.Tensor]) -> int | None:
+    """Infer the number of ControlNet Union modes from the shape of a InstantX ControlNet state dict.
+
+    Returns None if the model is not a ControlNet Union model. Otherwise returns the number of modes.
+    """
+    mode_embedder_key = "controlnet_mode_embedder.weight"
+    if mode_embedder_key not in sd:
+        return None
+
+    return sd[mode_embedder_key].shape[0]

invokeai/backend/flux/controlnet/xlabs_controlnet_flux.py

@@ -0,0 +1,130 @@
+# This file was initially based on:
+# https://github.com/XLabs-AI/x-flux/blob/47495425dbed499be1e8e5a6e52628b07349cba2/src/flux/controlnet.py
+
+
+from dataclasses import dataclass
+
+import torch
+from einops import rearrange
+
+from invokeai.backend.flux.controlnet.zero_module import zero_module
+from invokeai.backend.flux.model import FluxParams
+from invokeai.backend.flux.modules.layers import DoubleStreamBlock, EmbedND, MLPEmbedder, timestep_embedding
+
+
+@dataclass
+class XLabsControlNetFluxOutput:
+    controlnet_double_block_residuals: list[torch.Tensor] | None
+
+
+class XLabsControlNetFlux(torch.nn.Module):
+    """A ControlNet model for FLUX.
+
+    The architecture is very similar to the base FLUX model, with the following differences:
+    - A `controlnet_depth` parameter is passed to control the number of double_blocks that the ControlNet is applied to.
+      In order to keep the ControlNet small, this is typically much less than the depth of the base FLUX model.
+    - There is a set of `controlnet_blocks` that are applied to the output of each double_block.
+    """
+
+    def __init__(self, params: FluxParams, controlnet_depth: int = 2):
+        super().__init__()
+
+        self.params = params
+        self.in_channels = params.in_channels
+        self.out_channels = self.in_channels
+        if params.hidden_size % params.num_heads != 0:
+            raise ValueError(f"Hidden size {params.hidden_size} must be divisible by num_heads {params.num_heads}")
+        pe_dim = params.hidden_size // params.num_heads
+        if sum(params.axes_dim) != pe_dim:
+            raise ValueError(f"Got {params.axes_dim} but expected positional dim {pe_dim}")
+        self.hidden_size = params.hidden_size
+        self.num_heads = params.num_heads
+        self.pe_embedder = EmbedND(dim=pe_dim, theta=params.theta, axes_dim=params.axes_dim)
+        self.img_in = torch.nn.Linear(self.in_channels, self.hidden_size, bias=True)
+        self.time_in = MLPEmbedder(in_dim=256, hidden_dim=self.hidden_size)
+        self.vector_in = MLPEmbedder(params.vec_in_dim, self.hidden_size)
+        self.guidance_in = (
+            MLPEmbedder(in_dim=256, hidden_dim=self.hidden_size) if params.guidance_embed else torch.nn.Identity()
+        )
+        self.txt_in = torch.nn.Linear(params.context_in_dim, self.hidden_size)
+
+        self.double_blocks = torch.nn.ModuleList(
+            [
+                DoubleStreamBlock(
+                    self.hidden_size,
+                    self.num_heads,
+                    mlp_ratio=params.mlp_ratio,
+                    qkv_bias=params.qkv_bias,
+                )
+                for _ in range(controlnet_depth)
+            ]
+        )
+
+        # Add ControlNet blocks.
+        self.controlnet_blocks = torch.nn.ModuleList([])
+        for _ in range(controlnet_depth):
+            controlnet_block = torch.nn.Linear(self.hidden_size, self.hidden_size)
+            controlnet_block = zero_module(controlnet_block)
+            self.controlnet_blocks.append(controlnet_block)
+        self.pos_embed_input = torch.nn.Linear(self.in_channels, self.hidden_size, bias=True)
+        self.input_hint_block = torch.nn.Sequential(
+            torch.nn.Conv2d(3, 16, 3, padding=1),
+            torch.nn.SiLU(),
+            torch.nn.Conv2d(16, 16, 3, padding=1),
+            torch.nn.SiLU(),
+            torch.nn.Conv2d(16, 16, 3, padding=1, stride=2),
+            torch.nn.SiLU(),
+            torch.nn.Conv2d(16, 16, 3, padding=1),
+            torch.nn.SiLU(),
+            torch.nn.Conv2d(16, 16, 3, padding=1, stride=2),
+            torch.nn.SiLU(),
+            torch.nn.Conv2d(16, 16, 3, padding=1),
+            torch.nn.SiLU(),
+            torch.nn.Conv2d(16, 16, 3, padding=1, stride=2),
+            torch.nn.SiLU(),
+            zero_module(torch.nn.Conv2d(16, 16, 3, padding=1)),
+        )
+
+    def forward(
+        self,
+        img: torch.Tensor,
+        img_ids: torch.Tensor,
+        controlnet_cond: torch.Tensor,
+        txt: torch.Tensor,
+        txt_ids: torch.Tensor,
+        timesteps: torch.Tensor,
+        y: torch.Tensor,
+        guidance: torch.Tensor | None = None,
+    ) -> XLabsControlNetFluxOutput:
+        if img.ndim != 3 or txt.ndim != 3:
+            raise ValueError("Input img and txt tensors must have 3 dimensions.")
+
+        # running on sequences img
+        img = self.img_in(img)
+        controlnet_cond = self.input_hint_block(controlnet_cond)
+        controlnet_cond = rearrange(controlnet_cond, "b c (h ph) (w pw) -> b (h w) (c ph pw)", ph=2, pw=2)
+        controlnet_cond = self.pos_embed_input(controlnet_cond)
+        img = img + controlnet_cond
+        vec = self.time_in(timestep_embedding(timesteps, 256))
+        if self.params.guidance_embed:
+            if guidance is None:
+                raise ValueError("Didn't get guidance strength for guidance distilled model.")
+            vec = vec + self.guidance_in(timestep_embedding(guidance, 256))
+        vec = vec + self.vector_in(y)
+        txt = self.txt_in(txt)
+
+        ids = torch.cat((txt_ids, img_ids), dim=1)
+        pe = self.pe_embedder(ids)
+
+        block_res_samples: list[torch.Tensor] = []
+
+        for block in self.double_blocks:
+            img, txt = block(img=img, txt=txt, vec=vec, pe=pe)
+            block_res_samples.append(img)
+
+        controlnet_block_res_samples: list[torch.Tensor] = []
+        for block_res_sample, controlnet_block in zip(block_res_samples, self.controlnet_blocks, strict=True):
+            block_res_sample = controlnet_block(block_res_sample)
+            controlnet_block_res_samples.append(block_res_sample)
+
+        return XLabsControlNetFluxOutput(controlnet_double_block_residuals=controlnet_block_res_samples)

invokeai/backend/flux/controlnet/zero_module.py

@@ -0,0 +1,12 @@
+from typing import TypeVar
+
+import torch
+
+T = TypeVar("T", bound=torch.nn.Module)
+
+
+def zero_module(module: T) -> T:
+    """Initialize the parameters of a module to zero."""
+    for p in module.parameters():
+        torch.nn.init.zeros_(p)
+    return module

invokeai/backend/flux/custom_block_processor.py

@@ -0,0 +1,83 @@
+import einops
+import torch
+
+from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
+from invokeai.backend.flux.math import attention
+from invokeai.backend.flux.modules.layers import DoubleStreamBlock
+
+
+class CustomDoubleStreamBlockProcessor:
+    """A class containing a custom implementation of DoubleStreamBlock.forward() with additional features
+    (IP-Adapter, etc.).
+    """
+
+    @staticmethod
+    def _double_stream_block_forward(
+        block: DoubleStreamBlock, img: torch.Tensor, txt: torch.Tensor, vec: torch.Tensor, pe: torch.Tensor
+    ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        """This function is a direct copy of DoubleStreamBlock.forward(), but it returns some of the intermediate
+        values.
+        """
+        img_mod1, img_mod2 = block.img_mod(vec)
+        txt_mod1, txt_mod2 = block.txt_mod(vec)
+
+        # prepare image for attention
+        img_modulated = block.img_norm1(img)
+        img_modulated = (1 + img_mod1.scale) * img_modulated + img_mod1.shift
+        img_qkv = block.img_attn.qkv(img_modulated)
+        img_q, img_k, img_v = einops.rearrange(img_qkv, "B L (K H D) -> K B H L D", K=3, H=block.num_heads)
+        img_q, img_k = block.img_attn.norm(img_q, img_k, img_v)
+
+        # prepare txt for attention
+        txt_modulated = block.txt_norm1(txt)
+        txt_modulated = (1 + txt_mod1.scale) * txt_modulated + txt_mod1.shift
+        txt_qkv = block.txt_attn.qkv(txt_modulated)
+        txt_q, txt_k, txt_v = einops.rearrange(txt_qkv, "B L (K H D) -> K B H L D", K=3, H=block.num_heads)
+        txt_q, txt_k = block.txt_attn.norm(txt_q, txt_k, txt_v)
+
+        # run actual attention
+        q = torch.cat((txt_q, img_q), dim=2)
+        k = torch.cat((txt_k, img_k), dim=2)
+        v = torch.cat((txt_v, img_v), dim=2)
+
+        attn = attention(q, k, v, pe=pe)
+        txt_attn, img_attn = attn[:, : txt.shape[1]], attn[:, txt.shape[1] :]
+
+        # calculate the img bloks
+        img = img + img_mod1.gate * block.img_attn.proj(img_attn)
+        img = img + img_mod2.gate * block.img_mlp((1 + img_mod2.scale) * block.img_norm2(img) + img_mod2.shift)
+
+        # calculate the txt bloks
+        txt = txt + txt_mod1.gate * block.txt_attn.proj(txt_attn)
+        txt = txt + txt_mod2.gate * block.txt_mlp((1 + txt_mod2.scale) * block.txt_norm2(txt) + txt_mod2.shift)
+        return img, txt, img_q
+
+    @staticmethod
+    def custom_double_block_forward(
+        timestep_index: int,
+        total_num_timesteps: int,
+        block_index: int,
+        block: DoubleStreamBlock,
+        img: torch.Tensor,
+        txt: torch.Tensor,
+        vec: torch.Tensor,
+        pe: torch.Tensor,
+        ip_adapter_extensions: list[XLabsIPAdapterExtension],
+    ) -> tuple[torch.Tensor, torch.Tensor]:
+        """A custom implementation of DoubleStreamBlock.forward() with additional features:
+        - IP-Adapter support
+        """
+        img, txt, img_q = CustomDoubleStreamBlockProcessor._double_stream_block_forward(block, img, txt, vec, pe)
+
+        # Apply IP-Adapter conditioning.
+        for ip_adapter_extension in ip_adapter_extensions:
+            img = ip_adapter_extension.run_ip_adapter(
+                timestep_index=timestep_index,
+                total_num_timesteps=total_num_timesteps,
+                block_index=block_index,
+                block=block,
+                img_q=img_q,
+                img=img,
+            )
+
+        return img, txt

invokeai/backend/flux/denoise.py

@@ -1,9 +1,14 @@
+import math
 from typing import Callable
 
 import torch
 from tqdm import tqdm
 
-from invokeai.backend.flux.inpaint_extension import InpaintExtension
+from invokeai.backend.flux.controlnet.controlnet_flux_output import ControlNetFluxOutput, sum_controlnet_flux_outputs
+from invokeai.backend.flux.extensions.inpaint_extension import InpaintExtension
+from invokeai.backend.flux.extensions.instantx_controlnet_extension import InstantXControlNetExtension
+from invokeai.backend.flux.extensions.xlabs_controlnet_extension import XLabsControlNetExtension
+from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
 from invokeai.backend.flux.model import Flux
 from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineIntermediateState
 
@@ -13,14 +18,23 @@ def denoise(
     # model input
     img: torch.Tensor,
     img_ids: torch.Tensor,
+    # positive text conditioning
     txt: torch.Tensor,
     txt_ids: torch.Tensor,
     vec: torch.Tensor,
+    # negative text conditioning
+    neg_txt: torch.Tensor | None,
+    neg_txt_ids: torch.Tensor | None,
+    neg_vec: torch.Tensor | None,
     # sampling parameters
     timesteps: list[float],
     step_callback: Callable[[PipelineIntermediateState], None],
     guidance: float,
+    cfg_scale: list[float],
     inpaint_extension: InpaintExtension | None,
+    controlnet_extensions: list[XLabsControlNetExtension | InstantXControlNetExtension],
+    pos_ip_adapter_extensions: list[XLabsIPAdapterExtension],
+    neg_ip_adapter_extensions: list[XLabsIPAdapterExtension],
 ):
     # step 0 is the initial state
     total_steps = len(timesteps) - 1
@@ -33,11 +47,34 @@ def denoise(
             latents=img,
         ),
     )
-    step = 1
     # guidance_vec is ignored for schnell.
     guidance_vec = torch.full((img.shape[0],), guidance, device=img.device, dtype=img.dtype)
-    for t_curr, t_prev in tqdm(list(zip(timesteps[:-1], timesteps[1:], strict=True))):
+    for step_index, (t_curr, t_prev) in tqdm(list(enumerate(zip(timesteps[:-1], timesteps[1:], strict=True)))):
         t_vec = torch.full((img.shape[0],), t_curr, dtype=img.dtype, device=img.device)
+
+        # Run ControlNet models.
+        controlnet_residuals: list[ControlNetFluxOutput] = []
+        for controlnet_extension in controlnet_extensions:
+            controlnet_residuals.append(
+                controlnet_extension.run_controlnet(
+                    timestep_index=step_index,
+                    total_num_timesteps=total_steps,
+                    img=img,
+                    img_ids=img_ids,
+                    txt=txt,
+                    txt_ids=txt_ids,
+                    y=vec,
+                    timesteps=t_vec,
+                    guidance=guidance_vec,
+                )
+            )
+
+        # Merge the ControlNet residuals from multiple ControlNets.
+        # TODO(ryand): We may want to calculate the sum just-in-time to keep peak memory low. Keep in mind, that the
+        # controlnet_residuals datastructure is efficient in that it likely contains multiple references to the same
+        # tensors. Calculating the sum materializes each tensor into its own instance.
+        merged_controlnet_residuals = sum_controlnet_flux_outputs(controlnet_residuals)
+
         pred = model(
             img=img,
             img_ids=img_ids,
@@ -46,8 +83,39 @@ def denoise(
             y=vec,
             timesteps=t_vec,
             guidance=guidance_vec,
+            timestep_index=step_index,
+            total_num_timesteps=total_steps,
+            controlnet_double_block_residuals=merged_controlnet_residuals.double_block_residuals,
+            controlnet_single_block_residuals=merged_controlnet_residuals.single_block_residuals,
+            ip_adapter_extensions=pos_ip_adapter_extensions,
         )
 
+        step_cfg_scale = cfg_scale[step_index]
+
+        # If step_cfg_scale, is 1.0, then we don't need to run the negative prediction.
+        if not math.isclose(step_cfg_scale, 1.0):
+            # TODO(ryand): Add option to run positive and negative predictions in a single batch for better performance
+            # on systems with sufficient VRAM.
+
+            if neg_txt is None or neg_txt_ids is None or neg_vec is None:
+                raise ValueError("Negative text conditioning is required when cfg_scale is not 1.0.")
+
+            neg_pred = model(
+                img=img,
+                img_ids=img_ids,
+                txt=neg_txt,
+                txt_ids=neg_txt_ids,
+                y=neg_vec,
+                timesteps=t_vec,
+                guidance=guidance_vec,
+                timestep_index=step_index,
+                total_num_timesteps=total_steps,
+                controlnet_double_block_residuals=None,
+                controlnet_single_block_residuals=None,
+                ip_adapter_extensions=neg_ip_adapter_extensions,
+            )
+            pred = neg_pred + step_cfg_scale * (pred - neg_pred)
+
         preview_img = img - t_curr * pred
         img = img + (t_prev - t_curr) * pred
 
@@ -57,13 +125,12 @@ def denoise(
 
         step_callback(
             PipelineIntermediateState(
-                step=step,
+                step=step_index + 1,
                 order=1,
                 total_steps=total_steps,
                 timestep=int(t_curr),
                 latents=preview_img,
             ),
         )
-        step += 1
 
     return img

invokeai/backend/flux/extensions/base_controlnet_extension.py

@@ -0,0 +1,45 @@
+import math
+from abc import ABC, abstractmethod
+from typing import List, Union
+
+import torch
+
+from invokeai.backend.flux.controlnet.controlnet_flux_output import ControlNetFluxOutput
+
+
+class BaseControlNetExtension(ABC):
+    def __init__(
+        self,
+        weight: Union[float, List[float]],
+        begin_step_percent: float,
+        end_step_percent: float,
+    ):
+        self._weight = weight
+        self._begin_step_percent = begin_step_percent
+        self._end_step_percent = end_step_percent
+
+    def _get_weight(self, timestep_index: int, total_num_timesteps: int) -> float:
+        first_step = math.floor(self._begin_step_percent * total_num_timesteps)
+        last_step = math.ceil(self._end_step_percent * total_num_timesteps)
+
+        if timestep_index < first_step or timestep_index > last_step:
+            return 0.0
+
+        if isinstance(self._weight, list):
+            return self._weight[timestep_index]
+
+        return self._weight
+
+    @abstractmethod
+    def run_controlnet(
+        self,
+        timestep_index: int,
+        total_num_timesteps: int,
+        img: torch.Tensor,
+        img_ids: torch.Tensor,
+        txt: torch.Tensor,
+        txt_ids: torch.Tensor,
+        y: torch.Tensor,
+        timesteps: torch.Tensor,
+        guidance: torch.Tensor | None,
+    ) -> ControlNetFluxOutput: ...

invokeai/backend/flux/extensions/instantx_controlnet_extension.py

@@ -0,0 +1,194 @@
+import math
+from typing import List, Union
+
+import torch
+from PIL.Image import Image
+
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.flux_vae_encode import FluxVaeEncodeInvocation
+from invokeai.app.util.controlnet_utils import CONTROLNET_RESIZE_VALUES, prepare_control_image
+from invokeai.backend.flux.controlnet.controlnet_flux_output import ControlNetFluxOutput
+from invokeai.backend.flux.controlnet.instantx_controlnet_flux import (
+    InstantXControlNetFlux,
+    InstantXControlNetFluxOutput,
+)
+from invokeai.backend.flux.extensions.base_controlnet_extension import BaseControlNetExtension
+from invokeai.backend.flux.sampling_utils import pack
+from invokeai.backend.model_manager.load.load_base import LoadedModel
+
+
+class InstantXControlNetExtension(BaseControlNetExtension):
+    def __init__(
+        self,
+        model: InstantXControlNetFlux,
+        controlnet_cond: torch.Tensor,
+        instantx_control_mode: torch.Tensor | None,
+        weight: Union[float, List[float]],
+        begin_step_percent: float,
+        end_step_percent: float,
+    ):
+        super().__init__(
+            weight=weight,
+            begin_step_percent=begin_step_percent,
+            end_step_percent=end_step_percent,
+        )
+        self._model = model
+        # The VAE-encoded and 'packed' control image to pass to the ControlNet model.
+        self._controlnet_cond = controlnet_cond
+        # TODO(ryand): Should we define an enum for the instantx_control_mode? Is it likely to change for future models?
+        # The control mode for InstantX ControlNet union models.
+        # See the values defined here: https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union#control-mode
+        # Expected shape: (batch_size, 1), Expected dtype: torch.long
+        # If None, a zero-embedding will be used.
+        self._instantx_control_mode = instantx_control_mode
+
+        # TODO(ryand): Pass in these params if a new base transformer / InstantX ControlNet pair get released.
+        self._flux_transformer_num_double_blocks = 19
+        self._flux_transformer_num_single_blocks = 38
+
+    @classmethod
+    def prepare_controlnet_cond(
+        cls,
+        controlnet_image: Image,
+        vae_info: LoadedModel,
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        resize_mode: CONTROLNET_RESIZE_VALUES,
+    ):
+        image_height = latent_height * LATENT_SCALE_FACTOR
+        image_width = latent_width * LATENT_SCALE_FACTOR
+
+        resized_controlnet_image = prepare_control_image(
+            image=controlnet_image,
+            do_classifier_free_guidance=False,
+            width=image_width,
+            height=image_height,
+            device=device,
+            dtype=dtype,
+            control_mode="balanced",
+            resize_mode=resize_mode,
+        )
+
+        # Shift the image from [0, 1] to [-1, 1].
+        resized_controlnet_image = resized_controlnet_image * 2 - 1
+
+        # Run VAE encoder.
+        controlnet_cond = FluxVaeEncodeInvocation.vae_encode(vae_info=vae_info, image_tensor=resized_controlnet_image)
+        controlnet_cond = pack(controlnet_cond)
+
+        return controlnet_cond
+
+    @classmethod
+    def from_controlnet_image(
+        cls,
+        model: InstantXControlNetFlux,
+        controlnet_image: Image,
+        instantx_control_mode: torch.Tensor | None,
+        vae_info: LoadedModel,
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        resize_mode: CONTROLNET_RESIZE_VALUES,
+        weight: Union[float, List[float]],
+        begin_step_percent: float,
+        end_step_percent: float,
+    ):
+        image_height = latent_height * LATENT_SCALE_FACTOR
+        image_width = latent_width * LATENT_SCALE_FACTOR
+
+        resized_controlnet_image = prepare_control_image(
+            image=controlnet_image,
+            do_classifier_free_guidance=False,
+            width=image_width,
+            height=image_height,
+            device=device,
+            dtype=dtype,
+            control_mode="balanced",
+            resize_mode=resize_mode,
+        )
+
+        # Shift the image from [0, 1] to [-1, 1].
+        resized_controlnet_image = resized_controlnet_image * 2 - 1
+
+        # Run VAE encoder.
+        controlnet_cond = FluxVaeEncodeInvocation.vae_encode(vae_info=vae_info, image_tensor=resized_controlnet_image)
+        controlnet_cond = pack(controlnet_cond)
+
+        return cls(
+            model=model,
+            controlnet_cond=controlnet_cond,
+            instantx_control_mode=instantx_control_mode,
+            weight=weight,
+            begin_step_percent=begin_step_percent,
+            end_step_percent=end_step_percent,
+        )
+
+    def _instantx_output_to_controlnet_output(
+        self, instantx_output: InstantXControlNetFluxOutput
+    ) -> ControlNetFluxOutput:
+        # The `interval_control` logic here is based on
+        # https://github.com/huggingface/diffusers/blob/31058cdaef63ca660a1a045281d156239fba8192/src/diffusers/models/transformers/transformer_flux.py#L507-L511
+
+        # Handle double block residuals.
+        double_block_residuals: list[torch.Tensor] = []
+        double_block_samples = instantx_output.controlnet_block_samples
+        if double_block_samples:
+            interval_control = self._flux_transformer_num_double_blocks / len(double_block_samples)
+            interval_control = int(math.ceil(interval_control))
+            for i in range(self._flux_transformer_num_double_blocks):
+                double_block_residuals.append(double_block_samples[i // interval_control])
+
+        # Handle single block residuals.
+        single_block_residuals: list[torch.Tensor] = []
+        single_block_samples = instantx_output.controlnet_single_block_samples
+        if single_block_samples:
+            interval_control = self._flux_transformer_num_single_blocks / len(single_block_samples)
+            interval_control = int(math.ceil(interval_control))
+            for i in range(self._flux_transformer_num_single_blocks):
+                single_block_residuals.append(single_block_samples[i // interval_control])
+
+        return ControlNetFluxOutput(
+            double_block_residuals=double_block_residuals or None,
+            single_block_residuals=single_block_residuals or None,
+        )
+
+    def run_controlnet(
+        self,
+        timestep_index: int,
+        total_num_timesteps: int,
+        img: torch.Tensor,
+        img_ids: torch.Tensor,
+        txt: torch.Tensor,
+        txt_ids: torch.Tensor,
+        y: torch.Tensor,
+        timesteps: torch.Tensor,
+        guidance: torch.Tensor | None,
+    ) -> ControlNetFluxOutput:
+        weight = self._get_weight(timestep_index=timestep_index, total_num_timesteps=total_num_timesteps)
+        if weight < 1e-6:
+            return ControlNetFluxOutput(single_block_residuals=None, double_block_residuals=None)
+
+        # Make sure inputs have correct device and dtype.
+        self._controlnet_cond = self._controlnet_cond.to(device=img.device, dtype=img.dtype)
+        self._instantx_control_mode = (
+            self._instantx_control_mode.to(device=img.device) if self._instantx_control_mode is not None else None
+        )
+
+        instantx_output: InstantXControlNetFluxOutput = self._model(
+            controlnet_cond=self._controlnet_cond,
+            controlnet_mode=self._instantx_control_mode,
+            img=img,
+            img_ids=img_ids,
+            txt=txt,
+            txt_ids=txt_ids,
+            timesteps=timesteps,
+            y=y,
+            guidance=guidance,
+        )
+
+        controlnet_output = self._instantx_output_to_controlnet_output(instantx_output)
+        controlnet_output.apply_weight(weight)
+        return controlnet_output

invokeai/backend/flux/extensions/xlabs_controlnet_extension.py

@@ -0,0 +1,150 @@
+from typing import List, Union
+
+import torch
+from PIL.Image import Image
+
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.util.controlnet_utils import CONTROLNET_RESIZE_VALUES, prepare_control_image
+from invokeai.backend.flux.controlnet.controlnet_flux_output import ControlNetFluxOutput
+from invokeai.backend.flux.controlnet.xlabs_controlnet_flux import XLabsControlNetFlux, XLabsControlNetFluxOutput
+from invokeai.backend.flux.extensions.base_controlnet_extension import BaseControlNetExtension
+
+
+class XLabsControlNetExtension(BaseControlNetExtension):
+    def __init__(
+        self,
+        model: XLabsControlNetFlux,
+        controlnet_cond: torch.Tensor,
+        weight: Union[float, List[float]],
+        begin_step_percent: float,
+        end_step_percent: float,
+    ):
+        super().__init__(
+            weight=weight,
+            begin_step_percent=begin_step_percent,
+            end_step_percent=end_step_percent,
+        )
+
+        self._model = model
+        # _controlnet_cond is the control image passed to the ControlNet model.
+        # Pixel values are in the range [-1, 1]. Shape: (batch_size, 3, height, width).
+        self._controlnet_cond = controlnet_cond
+
+        # TODO(ryand): Pass in these params if a new base transformer / XLabs ControlNet pair get released.
+        self._flux_transformer_num_double_blocks = 19
+        self._flux_transformer_num_single_blocks = 38
+
+    @classmethod
+    def prepare_controlnet_cond(
+        cls,
+        controlnet_image: Image,
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        resize_mode: CONTROLNET_RESIZE_VALUES,
+    ):
+        image_height = latent_height * LATENT_SCALE_FACTOR
+        image_width = latent_width * LATENT_SCALE_FACTOR
+
+        controlnet_cond = prepare_control_image(
+            image=controlnet_image,
+            do_classifier_free_guidance=False,
+            width=image_width,
+            height=image_height,
+            device=device,
+            dtype=dtype,
+            control_mode="balanced",
+            resize_mode=resize_mode,
+        )
+
+        # Map pixel values from [0, 1] to [-1, 1].
+        controlnet_cond = controlnet_cond * 2 - 1
+
+        return controlnet_cond
+
+    @classmethod
+    def from_controlnet_image(
+        cls,
+        model: XLabsControlNetFlux,
+        controlnet_image: Image,
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        resize_mode: CONTROLNET_RESIZE_VALUES,
+        weight: Union[float, List[float]],
+        begin_step_percent: float,
+        end_step_percent: float,
+    ):
+        image_height = latent_height * LATENT_SCALE_FACTOR
+        image_width = latent_width * LATENT_SCALE_FACTOR
+
+        controlnet_cond = prepare_control_image(
+            image=controlnet_image,
+            do_classifier_free_guidance=False,
+            width=image_width,
+            height=image_height,
+            device=device,
+            dtype=dtype,
+            control_mode="balanced",
+            resize_mode=resize_mode,
+        )
+
+        # Map pixel values from [0, 1] to [-1, 1].
+        controlnet_cond = controlnet_cond * 2 - 1
+
+        return cls(
+            model=model,
+            controlnet_cond=controlnet_cond,
+            weight=weight,
+            begin_step_percent=begin_step_percent,
+            end_step_percent=end_step_percent,
+        )
+
+    def _xlabs_output_to_controlnet_output(self, xlabs_output: XLabsControlNetFluxOutput) -> ControlNetFluxOutput:
+        # The modulo index logic used here is based on:
+        # https://github.com/XLabs-AI/x-flux/blob/47495425dbed499be1e8e5a6e52628b07349cba2/src/flux/model.py#L198-L200
+
+        # Handle double block residuals.
+        double_block_residuals: list[torch.Tensor] = []
+        xlabs_double_block_residuals = xlabs_output.controlnet_double_block_residuals
+        if xlabs_double_block_residuals is not None:
+            for i in range(self._flux_transformer_num_double_blocks):
+                double_block_residuals.append(xlabs_double_block_residuals[i % len(xlabs_double_block_residuals)])
+
+        return ControlNetFluxOutput(
+            double_block_residuals=double_block_residuals,
+            single_block_residuals=None,
+        )
+
+    def run_controlnet(
+        self,
+        timestep_index: int,
+        total_num_timesteps: int,
+        img: torch.Tensor,
+        img_ids: torch.Tensor,
+        txt: torch.Tensor,
+        txt_ids: torch.Tensor,
+        y: torch.Tensor,
+        timesteps: torch.Tensor,
+        guidance: torch.Tensor | None,
+    ) -> ControlNetFluxOutput:
+        weight = self._get_weight(timestep_index=timestep_index, total_num_timesteps=total_num_timesteps)
+        if weight < 1e-6:
+            return ControlNetFluxOutput(single_block_residuals=None, double_block_residuals=None)
+
+        xlabs_output: XLabsControlNetFluxOutput = self._model(
+            img=img,
+            img_ids=img_ids,
+            controlnet_cond=self._controlnet_cond,
+            txt=txt,
+            txt_ids=txt_ids,
+            timesteps=timesteps,
+            y=y,
+            guidance=guidance,
+        )
+
+        controlnet_output = self._xlabs_output_to_controlnet_output(xlabs_output)
+        controlnet_output.apply_weight(weight)
+        return controlnet_output

invokeai/backend/flux/extensions/xlabs_ip_adapter_extension.py

@@ -0,0 +1,89 @@
+import math
+from typing import List, Union
+
+import einops
+import torch
+from PIL import Image
+from transformers import CLIPImageProcessor, CLIPVisionModelWithProjection
+
+from invokeai.backend.flux.ip_adapter.xlabs_ip_adapter_flux import XlabsIpAdapterFlux
+from invokeai.backend.flux.modules.layers import DoubleStreamBlock
+
+
+class XLabsIPAdapterExtension:
+    def __init__(
+        self,
+        model: XlabsIpAdapterFlux,
+        image_prompt_clip_embed: torch.Tensor,
+        weight: Union[float, List[float]],
+        begin_step_percent: float,
+        end_step_percent: float,
+    ):
+        self._model = model
+        self._image_prompt_clip_embed = image_prompt_clip_embed
+        self._weight = weight
+        self._begin_step_percent = begin_step_percent
+        self._end_step_percent = end_step_percent
+
+        self._image_proj: torch.Tensor | None = None
+
+    def _get_weight(self, timestep_index: int, total_num_timesteps: int) -> float:
+        first_step = math.floor(self._begin_step_percent * total_num_timesteps)
+        last_step = math.ceil(self._end_step_percent * total_num_timesteps)
+
+        if timestep_index < first_step or timestep_index > last_step:
+            return 0.0
+
+        if isinstance(self._weight, list):
+            return self._weight[timestep_index]
+
+        return self._weight
+
+    @staticmethod
+    def run_clip_image_encoder(
+        pil_image: List[Image.Image], image_encoder: CLIPVisionModelWithProjection
+    ) -> torch.Tensor:
+        clip_image_processor = CLIPImageProcessor()
+        clip_image: torch.Tensor = clip_image_processor(images=pil_image, return_tensors="pt").pixel_values
+        clip_image = clip_image.to(device=image_encoder.device, dtype=image_encoder.dtype)
+        clip_image_embeds = image_encoder(clip_image).image_embeds
+        return clip_image_embeds
+
+    def run_image_proj(self, dtype: torch.dtype):
+        image_prompt_clip_embed = self._image_prompt_clip_embed.to(dtype=dtype)
+        self._image_proj = self._model.image_proj(image_prompt_clip_embed)
+
+    def run_ip_adapter(
+        self,
+        timestep_index: int,
+        total_num_timesteps: int,
+        block_index: int,
+        block: DoubleStreamBlock,
+        img_q: torch.Tensor,
+        img: torch.Tensor,
+    ) -> torch.Tensor:
+        """The logic in this function is based on:
+        https://github.com/XLabs-AI/x-flux/blob/47495425dbed499be1e8e5a6e52628b07349cba2/src/flux/modules/layers.py#L245-L301
+        """
+        weight = self._get_weight(timestep_index=timestep_index, total_num_timesteps=total_num_timesteps)
+        if weight < 1e-6:
+            return img
+
+        ip_adapter_block = self._model.ip_adapter_double_blocks.double_blocks[block_index]
+
+        ip_key = ip_adapter_block.ip_adapter_double_stream_k_proj(self._image_proj)
+        ip_value = ip_adapter_block.ip_adapter_double_stream_v_proj(self._image_proj)
+
+        # Reshape projections for multi-head attention.
+        ip_key = einops.rearrange(ip_key, "B L (H D) -> B H L D", H=block.num_heads)
+        ip_value = einops.rearrange(ip_value, "B L (H D) -> B H L D", H=block.num_heads)
+
+        # Compute attention between IP projections and the latent query.
+        ip_attn = torch.nn.functional.scaled_dot_product_attention(
+            img_q, ip_key, ip_value, dropout_p=0.0, is_causal=False
+        )
+        ip_attn = einops.rearrange(ip_attn, "B H L D -> B L (H D)", H=block.num_heads)
+
+        img = img + weight * ip_attn
+
+        return img

invokeai/backend/flux/ip_adapter/ip_double_stream_block_processor.py

@@ -0,0 +1,93 @@
+# This file is based on:
+# https://github.com/XLabs-AI/x-flux/blob/47495425dbed499be1e8e5a6e52628b07349cba2/src/flux/modules/layers.py#L221
+import einops
+import torch
+
+from invokeai.backend.flux.math import attention
+from invokeai.backend.flux.modules.layers import DoubleStreamBlock
+
+
+class IPDoubleStreamBlockProcessor(torch.nn.Module):
+    """Attention processor for handling IP-adapter with double stream block."""
+
+    def __init__(self, context_dim: int, hidden_dim: int):
+        super().__init__()
+
+        # Ensure context_dim matches the dimension of image_proj
+        self.context_dim = context_dim
+        self.hidden_dim = hidden_dim
+
+        # Initialize projections for IP-adapter
+        self.ip_adapter_double_stream_k_proj = torch.nn.Linear(context_dim, hidden_dim, bias=True)
+        self.ip_adapter_double_stream_v_proj = torch.nn.Linear(context_dim, hidden_dim, bias=True)
+
+        torch.nn.init.zeros_(self.ip_adapter_double_stream_k_proj.weight)
+        torch.nn.init.zeros_(self.ip_adapter_double_stream_k_proj.bias)
+
+        torch.nn.init.zeros_(self.ip_adapter_double_stream_v_proj.weight)
+        torch.nn.init.zeros_(self.ip_adapter_double_stream_v_proj.bias)
+
+    def __call__(
+        self,
+        attn: DoubleStreamBlock,
+        img: torch.Tensor,
+        txt: torch.Tensor,
+        vec: torch.Tensor,
+        pe: torch.Tensor,
+        image_proj: torch.Tensor,
+        ip_scale: float = 1.0,
+    ):
+        # Prepare image for attention
+        img_mod1, img_mod2 = attn.img_mod(vec)
+        txt_mod1, txt_mod2 = attn.txt_mod(vec)
+
+        img_modulated = attn.img_norm1(img)
+        img_modulated = (1 + img_mod1.scale) * img_modulated + img_mod1.shift
+        img_qkv = attn.img_attn.qkv(img_modulated)
+        img_q, img_k, img_v = einops.rearrange(
+            img_qkv, "B L (K H D) -> K B H L D", K=3, H=attn.num_heads, D=attn.head_dim
+        )
+        img_q, img_k = attn.img_attn.norm(img_q, img_k, img_v)
+
+        txt_modulated = attn.txt_norm1(txt)
+        txt_modulated = (1 + txt_mod1.scale) * txt_modulated + txt_mod1.shift
+        txt_qkv = attn.txt_attn.qkv(txt_modulated)
+        txt_q, txt_k, txt_v = einops.rearrange(
+            txt_qkv, "B L (K H D) -> K B H L D", K=3, H=attn.num_heads, D=attn.head_dim
+        )
+        txt_q, txt_k = attn.txt_attn.norm(txt_q, txt_k, txt_v)
+
+        q = torch.cat((txt_q, img_q), dim=2)
+        k = torch.cat((txt_k, img_k), dim=2)
+        v = torch.cat((txt_v, img_v), dim=2)
+
+        attn1 = attention(q, k, v, pe=pe)
+        txt_attn, img_attn = attn1[:, : txt.shape[1]], attn1[:, txt.shape[1] :]
+
+        # print(f"txt_attn shape: {txt_attn.size()}")
+        # print(f"img_attn shape: {img_attn.size()}")
+
+        img = img + img_mod1.gate * attn.img_attn.proj(img_attn)
+        img = img + img_mod2.gate * attn.img_mlp((1 + img_mod2.scale) * attn.img_norm2(img) + img_mod2.shift)
+
+        txt = txt + txt_mod1.gate * attn.txt_attn.proj(txt_attn)
+        txt = txt + txt_mod2.gate * attn.txt_mlp((1 + txt_mod2.scale) * attn.txt_norm2(txt) + txt_mod2.shift)
+
+        # IP-adapter processing
+        ip_query = img_q  # latent sample query
+        ip_key = self.ip_adapter_double_stream_k_proj(image_proj)
+        ip_value = self.ip_adapter_double_stream_v_proj(image_proj)
+
+        # Reshape projections for multi-head attention
+        ip_key = einops.rearrange(ip_key, "B L (H D) -> B H L D", H=attn.num_heads, D=attn.head_dim)
+        ip_value = einops.rearrange(ip_value, "B L (H D) -> B H L D", H=attn.num_heads, D=attn.head_dim)
+
+        # Compute attention between IP projections and the latent query
+        ip_attention = torch.nn.functional.scaled_dot_product_attention(
+            ip_query, ip_key, ip_value, dropout_p=0.0, is_causal=False
+        )
+        ip_attention = einops.rearrange(ip_attention, "B H L D -> B L (H D)", H=attn.num_heads, D=attn.head_dim)
+
+        img = img + ip_scale * ip_attention
+
+        return img, txt

invokeai/backend/flux/ip_adapter/state_dict_utils.py

@@ -0,0 +1,50 @@
+from typing import Any, Dict
+
+import torch
+
+from invokeai.backend.flux.ip_adapter.xlabs_ip_adapter_flux import XlabsIpAdapterParams
+
+
+def is_state_dict_xlabs_ip_adapter(sd: Dict[str, Any]) -> bool:
+    """Is the state dict for an XLabs FLUX IP-Adapter model?
+
+    This is intended to be a reasonably high-precision detector, but it is not guaranteed to have perfect precision.
+    """
+    # If all of the expected keys are present, then this is very likely an XLabs IP-Adapter model.
+    expected_keys = {
+        "double_blocks.0.processor.ip_adapter_double_stream_k_proj.bias",
+        "double_blocks.0.processor.ip_adapter_double_stream_k_proj.weight",
+        "double_blocks.0.processor.ip_adapter_double_stream_v_proj.bias",
+        "double_blocks.0.processor.ip_adapter_double_stream_v_proj.weight",
+        "ip_adapter_proj_model.norm.bias",
+        "ip_adapter_proj_model.norm.weight",
+        "ip_adapter_proj_model.proj.bias",
+        "ip_adapter_proj_model.proj.weight",
+    }
+
+    if expected_keys.issubset(sd.keys()):
+        return True
+    return False
+
+
+def infer_xlabs_ip_adapter_params_from_state_dict(state_dict: dict[str, torch.Tensor]) -> XlabsIpAdapterParams:
+    num_double_blocks = 0
+    context_dim = 0
+    hidden_dim = 0
+
+    # Count the number of double blocks.
+    double_block_index = 0
+    while f"double_blocks.{double_block_index}.processor.ip_adapter_double_stream_k_proj.weight" in state_dict:
+        double_block_index += 1
+    num_double_blocks = double_block_index
+
+    hidden_dim = state_dict["double_blocks.0.processor.ip_adapter_double_stream_k_proj.weight"].shape[0]
+    context_dim = state_dict["double_blocks.0.processor.ip_adapter_double_stream_k_proj.weight"].shape[1]
+    clip_embeddings_dim = state_dict["ip_adapter_proj_model.proj.weight"].shape[1]
+
+    return XlabsIpAdapterParams(
+        num_double_blocks=num_double_blocks,
+        context_dim=context_dim,
+        hidden_dim=hidden_dim,
+        clip_embeddings_dim=clip_embeddings_dim,
+    )

invokeai/backend/flux/ip_adapter/xlabs_ip_adapter_flux.py

@@ -0,0 +1,67 @@
+from dataclasses import dataclass
+
+import torch
+
+from invokeai.backend.ip_adapter.ip_adapter import ImageProjModel
+
+
+class IPDoubleStreamBlock(torch.nn.Module):
+    def __init__(self, context_dim: int, hidden_dim: int):
+        super().__init__()
+
+        self.context_dim = context_dim
+        self.hidden_dim = hidden_dim
+
+        self.ip_adapter_double_stream_k_proj = torch.nn.Linear(context_dim, hidden_dim, bias=True)
+        self.ip_adapter_double_stream_v_proj = torch.nn.Linear(context_dim, hidden_dim, bias=True)
+
+
+class IPAdapterDoubleBlocks(torch.nn.Module):
+    def __init__(self, num_double_blocks: int, context_dim: int, hidden_dim: int):
+        super().__init__()
+        self.double_blocks = torch.nn.ModuleList(
+            [IPDoubleStreamBlock(context_dim, hidden_dim) for _ in range(num_double_blocks)]
+        )
+
+
+@dataclass
+class XlabsIpAdapterParams:
+    num_double_blocks: int
+    context_dim: int
+    hidden_dim: int
+
+    clip_embeddings_dim: int
+
+
+class XlabsIpAdapterFlux(torch.nn.Module):
+    def __init__(self, params: XlabsIpAdapterParams):
+        super().__init__()
+        self.image_proj = ImageProjModel(
+            cross_attention_dim=params.context_dim, clip_embeddings_dim=params.clip_embeddings_dim
+        )
+        self.ip_adapter_double_blocks = IPAdapterDoubleBlocks(
+            num_double_blocks=params.num_double_blocks, context_dim=params.context_dim, hidden_dim=params.hidden_dim
+        )
+
+    def load_xlabs_state_dict(self, state_dict: dict[str, torch.Tensor], assign: bool = False):
+        """We need this custom function to load state dicts rather than using .load_state_dict(...) because the model
+        structure does not match the state_dict structure.
+        """
+        # Split the state_dict into the image projection model and the double blocks.
+        image_proj_sd: dict[str, torch.Tensor] = {}
+        double_blocks_sd: dict[str, torch.Tensor] = {}
+        for k, v in state_dict.items():
+            if k.startswith("ip_adapter_proj_model."):
+                image_proj_sd[k] = v
+            elif k.startswith("double_blocks."):
+                double_blocks_sd[k] = v
+            else:
+                raise ValueError(f"Unexpected key: {k}")
+
+        # Initialize the image projection model.
+        image_proj_sd = {k.replace("ip_adapter_proj_model.", ""): v for k, v in image_proj_sd.items()}
+        self.image_proj.load_state_dict(image_proj_sd, assign=assign)
+
+        # Initialize the double blocks.
+        double_blocks_sd = {k.replace("processor.", ""): v for k, v in double_blocks_sd.items()}
+        self.ip_adapter_double_blocks.load_state_dict(double_blocks_sd, assign=assign)

invokeai/backend/flux/model.py

@@ -5,6 +5,8 @@ from dataclasses import dataclass
 import torch
 from torch import Tensor, nn
 
+from invokeai.backend.flux.custom_block_processor import CustomDoubleStreamBlockProcessor
+from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
 from invokeai.backend.flux.modules.layers import (
     DoubleStreamBlock,
     EmbedND,
@@ -87,7 +89,12 @@ class Flux(nn.Module):
         txt_ids: Tensor,
         timesteps: Tensor,
         y: Tensor,
-        guidance: Tensor | None = None,
+        guidance: Tensor | None,
+        timestep_index: int,
+        total_num_timesteps: int,
+        controlnet_double_block_residuals: list[Tensor] | None,
+        controlnet_single_block_residuals: list[Tensor] | None,
+        ip_adapter_extensions: list[XLabsIPAdapterExtension],
     ) -> Tensor:
         if img.ndim != 3 or txt.ndim != 3:
             raise ValueError("Input img and txt tensors must have 3 dimensions.")
@@ -105,12 +112,39 @@ class Flux(nn.Module):
         ids = torch.cat((txt_ids, img_ids), dim=1)
         pe = self.pe_embedder(ids)
 
-        for block in self.double_blocks:
-            img, txt = block(img=img, txt=txt, vec=vec, pe=pe)
+        # Validate double_block_residuals shape.
+        if controlnet_double_block_residuals is not None:
+            assert len(controlnet_double_block_residuals) == len(self.double_blocks)
+        for block_index, block in enumerate(self.double_blocks):
+            assert isinstance(block, DoubleStreamBlock)
+
+            img, txt = CustomDoubleStreamBlockProcessor.custom_double_block_forward(
+                timestep_index=timestep_index,
+                total_num_timesteps=total_num_timesteps,
+                block_index=block_index,
+                block=block,
+                img=img,
+                txt=txt,
+                vec=vec,
+                pe=pe,
+                ip_adapter_extensions=ip_adapter_extensions,
+            )
+
+            if controlnet_double_block_residuals is not None:
+                img += controlnet_double_block_residuals[block_index]
 
         img = torch.cat((txt, img), 1)
-        for block in self.single_blocks:
+
+        # Validate single_block_residuals shape.
+        if controlnet_single_block_residuals is not None:
+            assert len(controlnet_single_block_residuals) == len(self.single_blocks)
+
+        for block_index, block in enumerate(self.single_blocks):
             img = block(img, vec=vec, pe=pe)
+
+            if controlnet_single_block_residuals is not None:
+                img[:, txt.shape[1] :, ...] += controlnet_single_block_residuals[block_index]
+
         img = img[:, txt.shape[1] :, ...]
 
         img = self.final_layer(img, vec)  # (N, T, patch_size ** 2 * out_channels)

invokeai/backend/flux/sampling_utils.py

@@ -168,8 +168,17 @@ def generate_img_ids(h: int, w: int, batch_size: int, device: torch.device, dtyp
     Returns:
         torch.Tensor: Image position ids.
     """
+
+    if device.type == "mps":
+        orig_dtype = dtype
+        dtype = torch.float16
+
     img_ids = torch.zeros(h // 2, w // 2, 3, device=device, dtype=dtype)
     img_ids[..., 1] = img_ids[..., 1] + torch.arange(h // 2, device=device, dtype=dtype)[:, None]
     img_ids[..., 2] = img_ids[..., 2] + torch.arange(w // 2, device=device, dtype=dtype)[None, :]
     img_ids = repeat(img_ids, "h w c -> b (h w) c", b=batch_size)
+
+    if device.type == "mps":
+        img_ids.to(orig_dtype)
+
     return img_ids

invokeai/backend/image_util/segment_anything/segment_anything_pipeline.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Optional, TypeAlias
 
 import torch
 from PIL import Image
@@ -7,6 +7,14 @@ from transformers.models.sam.processing_sam import SamProcessor
 
 from invokeai.backend.raw_model import RawModel
 
+# Type aliases for the inputs to the SAM model.
+ListOfBoundingBoxes: TypeAlias = list[list[int]]
+"""A list of bounding boxes. Each bounding box is in the format [xmin, ymin, xmax, ymax]."""
+ListOfPoints: TypeAlias = list[list[int]]
+"""A list of points. Each point is in the format [x, y]."""
+ListOfPointLabels: TypeAlias = list[int]
+"""A list of SAM point labels. Each label is an integer where -1 is background, 0 is neutral, and 1 is foreground."""
+
 
 class SegmentAnythingPipeline(RawModel):
     """A wrapper class for the transformers SAM model and processor that makes it compatible with the model manager."""
@@ -27,20 +35,53 @@ class SegmentAnythingPipeline(RawModel):
 
         return calc_module_size(self._sam_model)
 
-    def segment(self, image: Image.Image, bounding_boxes: list[list[int]]) -> torch.Tensor:
+    def segment(
+        self,
+        image: Image.Image,
+        bounding_boxes: list[list[int]] | None = None,
+        point_lists: list[list[list[int]]] | None = None,
+    ) -> torch.Tensor:
         """Run the SAM model.
 
+        Either bounding_boxes or point_lists must be provided. If both are provided, bounding_boxes will be used and
+        point_lists will be ignored.
+
         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].
+            point_lists (list[list[list[int]]]): The points prompts. Each point is in the format [x, y, label].
+                `label` is an integer where -1 is background, 0 is neutral, and 1 is foreground.
 
         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)
+
+        # Prep the inputs:
+        # - Create a list of bounding boxes or points and labels.
+        # - Add a batch dimension of 1 to the inputs.
+        if bounding_boxes:
+            input_boxes: list[ListOfBoundingBoxes] | None = [bounding_boxes]
+            input_points: list[ListOfPoints] | None = None
+            input_labels: list[ListOfPointLabels] | None = None
+        elif point_lists:
+            input_boxes: list[ListOfBoundingBoxes] | None = None
+            input_points: list[ListOfPoints] | None = []
+            input_labels: list[ListOfPointLabels] | None = []
+            for point_list in point_lists:
+                input_points.append([[p[0], p[1]] for p in point_list])
+                input_labels.append([p[2] for p in point_list])
+
+        else:
+            raise ValueError("Either bounding_boxes or points and labels must be provided.")
+
+        inputs = self._sam_processor(
+            images=image,
+            input_boxes=input_boxes,
+            input_points=input_points,
+            input_labels=input_labels,
+            return_tensors="pt",
+        ).to(self._sam_model.device)
         outputs = self._sam_model(**inputs)
         masks = self._sam_processor.post_process_masks(
             masks=outputs.pred_masks,

invokeai/backend/model_manager/config.py

@@ -394,6 +394,8 @@ class IPAdapterBaseConfig(ModelConfigBase):
 class IPAdapterInvokeAIConfig(IPAdapterBaseConfig):
     """Model config for IP Adapter diffusers format models."""
 
+    # TODO(ryand): Should we deprecate this field? From what I can tell, it hasn't been probed correctly for a long
+    # time. Need to go through the history to make sure I'm understanding this fully.
     image_encoder_model_id: str
     format: Literal[ModelFormat.InvokeAI]
 

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

@@ -0,0 +1,41 @@
+from pathlib import Path
+from typing import Optional
+
+from transformers import CLIPVisionModelWithProjection
+
+from invokeai.backend.model_manager.config import (
+    AnyModel,
+    AnyModelConfig,
+    BaseModelType,
+    DiffusersConfigBase,
+    ModelFormat,
+    ModelType,
+    SubModelType,
+)
+from invokeai.backend.model_manager.load.load_default import ModelLoader
+from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry
+
+
+@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.CLIPVision, format=ModelFormat.Diffusers)
+class ClipVisionLoader(ModelLoader):
+    """Class to load CLIPVision models."""
+
+    def _load_model(
+        self,
+        config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+    ) -> AnyModel:
+        if not isinstance(config, DiffusersConfigBase):
+            raise ValueError("Only DiffusersConfigBase models are currently supported here.")
+
+        if submodel_type is not None:
+            raise Exception("There are no submodels in CLIP Vision models.")
+
+        model_path = Path(config.path)
+
+        model = CLIPVisionModelWithProjection.from_pretrained(
+            model_path, torch_dtype=self._torch_dtype, local_files_only=True
+        )
+        assert isinstance(model, CLIPVisionModelWithProjection)
+
+        return model

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

@@ -8,17 +8,36 @@ from diffusers import ControlNetModel
 from invokeai.backend.model_manager import (
     AnyModel,
     AnyModelConfig,
+)
+from invokeai.backend.model_manager.config import (
     BaseModelType,
+    ControlNetCheckpointConfig,
     ModelFormat,
     ModelType,
+    SubModelType,
 )
-from invokeai.backend.model_manager.config import ControlNetCheckpointConfig, SubModelType
 from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry
 from invokeai.backend.model_manager.load.model_loaders.generic_diffusers import GenericDiffusersLoader
 
 
-@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.ControlNet, format=ModelFormat.Diffusers)
-@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.ControlNet, format=ModelFormat.Checkpoint)
+@ModelLoaderRegistry.register(
+    base=BaseModelType.StableDiffusion1, type=ModelType.ControlNet, format=ModelFormat.Diffusers
+)
+@ModelLoaderRegistry.register(
+    base=BaseModelType.StableDiffusion1, type=ModelType.ControlNet, format=ModelFormat.Checkpoint
+)
+@ModelLoaderRegistry.register(
+    base=BaseModelType.StableDiffusion2, type=ModelType.ControlNet, format=ModelFormat.Diffusers
+)
+@ModelLoaderRegistry.register(
+    base=BaseModelType.StableDiffusion2, type=ModelType.ControlNet, format=ModelFormat.Checkpoint
+)
+@ModelLoaderRegistry.register(
+    base=BaseModelType.StableDiffusionXL, type=ModelType.ControlNet, format=ModelFormat.Diffusers
+)
+@ModelLoaderRegistry.register(
+    base=BaseModelType.StableDiffusionXL, type=ModelType.ControlNet, format=ModelFormat.Checkpoint
+)
 class ControlNetLoader(GenericDiffusersLoader):
     """Class to load ControlNet models."""
 

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

@@ -10,6 +10,19 @@ from safetensors.torch import load_file
 from transformers import AutoConfig, AutoModelForTextEncoding, CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokenizer
 
 from invokeai.app.services.config.config_default import get_config
+from invokeai.backend.flux.controlnet.instantx_controlnet_flux import InstantXControlNetFlux
+from invokeai.backend.flux.controlnet.state_dict_utils import (
+    convert_diffusers_instantx_state_dict_to_bfl_format,
+    infer_flux_params_from_state_dict,
+    infer_instantx_num_control_modes_from_state_dict,
+    is_state_dict_instantx_controlnet,
+    is_state_dict_xlabs_controlnet,
+)
+from invokeai.backend.flux.controlnet.xlabs_controlnet_flux import XLabsControlNetFlux
+from invokeai.backend.flux.ip_adapter.state_dict_utils import infer_xlabs_ip_adapter_params_from_state_dict
+from invokeai.backend.flux.ip_adapter.xlabs_ip_adapter_flux import (
+    XlabsIpAdapterFlux,
+)
 from invokeai.backend.flux.model import Flux
 from invokeai.backend.flux.modules.autoencoder import AutoEncoder
 from invokeai.backend.flux.util import ae_params, params
@@ -24,6 +37,9 @@ from invokeai.backend.model_manager import (
 from invokeai.backend.model_manager.config import (
     CheckpointConfigBase,
     CLIPEmbedDiffusersConfig,
+    ControlNetCheckpointConfig,
+    ControlNetDiffusersConfig,
+    IPAdapterCheckpointConfig,
     MainBnbQuantized4bCheckpointConfig,
     MainCheckpointConfig,
     MainGGUFCheckpointConfig,
@@ -159,7 +175,7 @@ class T5EncoderCheckpointModel(ModelLoader):
             case SubModelType.Tokenizer2:
                 return T5Tokenizer.from_pretrained(Path(config.path) / "tokenizer_2", max_length=512)
             case SubModelType.TextEncoder2:
-                return T5EncoderModel.from_pretrained(Path(config.path) / "text_encoder_2")
+                return T5EncoderModel.from_pretrained(Path(config.path) / "text_encoder_2", torch_dtype="auto")
 
         raise ValueError(
             f"Only Tokenizer and TextEncoder submodels are currently supported. Received: {submodel_type.value if submodel_type else 'None'}"
@@ -293,3 +309,74 @@ class FluxBnbQuantizednf4bCheckpointModel(ModelLoader):
                 sd = convert_bundle_to_flux_transformer_checkpoint(sd)
             model.load_state_dict(sd, assign=True)
         return model
+
+
+@ModelLoaderRegistry.register(base=BaseModelType.Flux, type=ModelType.ControlNet, format=ModelFormat.Checkpoint)
+@ModelLoaderRegistry.register(base=BaseModelType.Flux, type=ModelType.ControlNet, format=ModelFormat.Diffusers)
+class FluxControlnetModel(ModelLoader):
+    """Class to load FLUX ControlNet models."""
+
+    def _load_model(
+        self,
+        config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+    ) -> AnyModel:
+        if isinstance(config, ControlNetCheckpointConfig):
+            model_path = Path(config.path)
+        elif isinstance(config, ControlNetDiffusersConfig):
+            # If this is a diffusers directory, we simply ignore the config file and load from the weight file.
+            model_path = Path(config.path) / "diffusion_pytorch_model.safetensors"
+        else:
+            raise ValueError(f"Unexpected ControlNet model config type: {type(config)}")
+
+        sd = load_file(model_path)
+
+        # Detect the FLUX ControlNet model type from the state dict.
+        if is_state_dict_xlabs_controlnet(sd):
+            return self._load_xlabs_controlnet(sd)
+        elif is_state_dict_instantx_controlnet(sd):
+            return self._load_instantx_controlnet(sd)
+        else:
+            raise ValueError("Do not recognize the state dict as an XLabs or InstantX ControlNet model.")
+
+    def _load_xlabs_controlnet(self, sd: dict[str, torch.Tensor]) -> AnyModel:
+        with accelerate.init_empty_weights():
+            # HACK(ryand): Is it safe to assume dev here?
+            model = XLabsControlNetFlux(params["flux-dev"])
+
+        model.load_state_dict(sd, assign=True)
+        return model
+
+    def _load_instantx_controlnet(self, sd: dict[str, torch.Tensor]) -> AnyModel:
+        sd = convert_diffusers_instantx_state_dict_to_bfl_format(sd)
+        flux_params = infer_flux_params_from_state_dict(sd)
+        num_control_modes = infer_instantx_num_control_modes_from_state_dict(sd)
+
+        with accelerate.init_empty_weights():
+            model = InstantXControlNetFlux(flux_params, num_control_modes)
+
+        model.load_state_dict(sd, assign=True)
+        return model
+
+
+@ModelLoaderRegistry.register(base=BaseModelType.Flux, type=ModelType.IPAdapter, format=ModelFormat.Checkpoint)
+class FluxIpAdapterModel(ModelLoader):
+    """Class to load FLUX IP-Adapter models."""
+
+    def _load_model(
+        self,
+        config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+    ) -> AnyModel:
+        if not isinstance(config, IPAdapterCheckpointConfig):
+            raise ValueError(f"Unexpected model config type: {type(config)}.")
+
+        sd = load_file(Path(config.path))
+
+        params = infer_xlabs_ip_adapter_params_from_state_dict(sd)
+
+        with accelerate.init_empty_weights():
+            model = XlabsIpAdapterFlux(params=params)
+
+        model.load_xlabs_state_dict(sd, assign=True)
+        return model

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

@@ -22,7 +22,6 @@ from invokeai.backend.model_manager.load.load_default import ModelLoader
 from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry
 
 
-@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.CLIPVision, format=ModelFormat.Diffusers)
 @ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.T2IAdapter, format=ModelFormat.Diffusers)
 class GenericDiffusersLoader(ModelLoader):
     """Class to load simple diffusers models."""

invokeai/backend/model_manager/probe.py

@@ -10,6 +10,11 @@ from picklescan.scanner import scan_file_path
 
 import invokeai.backend.util.logging as logger
 from invokeai.app.util.misc import uuid_string
+from invokeai.backend.flux.controlnet.state_dict_utils import (
+    is_state_dict_instantx_controlnet,
+    is_state_dict_xlabs_controlnet,
+)
+from invokeai.backend.flux.ip_adapter.state_dict_utils import is_state_dict_xlabs_ip_adapter
 from invokeai.backend.lora.conversions.flux_diffusers_lora_conversion_utils import (
     is_state_dict_likely_in_flux_diffusers_format,
 )
@@ -116,6 +121,7 @@ class ModelProbe(object):
         "CLIPModel": ModelType.CLIPEmbed,
         "CLIPTextModel": ModelType.CLIPEmbed,
         "T5EncoderModel": ModelType.T5Encoder,
+        "FluxControlNetModel": ModelType.ControlNet,
     }
 
     @classmethod
@@ -238,8 +244,6 @@ class ModelProbe(object):
                     "cond_stage_model.",
                     "first_stage_model.",
                     "model.diffusion_model.",
-                    # FLUX models in the official BFL format contain keys with the "double_blocks." prefix.
-                    "double_blocks.",
                     # Some FLUX checkpoint files contain transformer keys prefixed with "model.diffusion_model".
                     # This prefix is typically used to distinguish between multiple models bundled in a single file.
                     "model.diffusion_model.double_blocks.",
@@ -247,6 +251,10 @@ class ModelProbe(object):
             ):
                 # Keys starting with double_blocks are associated with Flux models
                 return ModelType.Main
+            # FLUX models in the official BFL format contain keys with the "double_blocks." prefix, but we must be
+            # careful to avoid false positives on XLabs FLUX IP-Adapter models.
+            elif key.startswith("double_blocks.") and "ip_adapter" not in key:
+                return ModelType.Main
             elif key.startswith(("encoder.conv_in", "decoder.conv_in")):
                 return ModelType.VAE
             elif key.startswith(("lora_te_", "lora_unet_")):
@@ -255,9 +263,28 @@ class ModelProbe(object):
             # LoRA models, but as of the time of writing, we support Diffusers FLUX PEFT LoRA models.
             elif key.endswith(("to_k_lora.up.weight", "to_q_lora.down.weight", "lora_A.weight", "lora_B.weight")):
                 return ModelType.LoRA
-            elif key.startswith(("controlnet", "control_model", "input_blocks")):
+            elif key.startswith(
+                (
+                    "controlnet",
+                    "control_model",
+                    "input_blocks",
+                    # XLabs FLUX ControlNet models have keys starting with "controlnet_blocks."
+                    # For example: https://huggingface.co/XLabs-AI/flux-controlnet-collections/blob/86ab1e915a389d5857135c00e0d350e9e38a9048/flux-canny-controlnet_v2.safetensors
+                    # TODO(ryand): This is very fragile. XLabs FLUX ControlNet models also contain keys starting with
+                    # "double_blocks.", which we check for above. But, I'm afraid to modify this logic because it is so
+                    # delicate.
+                    "controlnet_blocks",
+                )
+            ):
                 return ModelType.ControlNet
-            elif key.startswith(("image_proj.", "ip_adapter.")):
+            elif key.startswith(
+                (
+                    "image_proj.",
+                    "ip_adapter.",
+                    # XLabs FLUX IP-Adapter models have keys startinh with "ip_adapter_proj_model.".
+                    "ip_adapter_proj_model.",
+                )
+            ):
                 return ModelType.IPAdapter
             elif key in {"emb_params", "string_to_param"}:
                 return ModelType.TextualInversion
@@ -435,9 +462,11 @@ MODEL_NAME_TO_PREPROCESSOR = {
     "normal": "normalbae_image_processor",
     "sketch": "pidi_image_processor",
     "scribble": "lineart_image_processor",
-    "lineart": "lineart_image_processor",
+    "lineart anime": "lineart_anime_image_processor",
     "lineart_anime": "lineart_anime_image_processor",
+    "lineart": "lineart_image_processor",
     "softedge": "hed_image_processor",
+    "hed": "hed_image_processor",
     "shuffle": "content_shuffle_image_processor",
     "pose": "dw_openpose_image_processor",
     "mediapipe": "mediapipe_face_processor",
@@ -449,7 +478,8 @@ MODEL_NAME_TO_PREPROCESSOR = {
 
 def get_default_settings_controlnet_t2i_adapter(model_name: str) -> Optional[ControlAdapterDefaultSettings]:
     for k, v in MODEL_NAME_TO_PREPROCESSOR.items():
-        if k in model_name:
+        model_name_lower = model_name.lower()
+        if k in model_name_lower:
             return ControlAdapterDefaultSettings(preprocessor=v)
     return None
 
@@ -623,6 +653,11 @@ class ControlNetCheckpointProbe(CheckpointProbeBase):
 
     def get_base_type(self) -> BaseModelType:
         checkpoint = self.checkpoint
+        if is_state_dict_xlabs_controlnet(checkpoint) or is_state_dict_instantx_controlnet(checkpoint):
+            # TODO(ryand): Should I distinguish between XLabs, InstantX and other ControlNet models by implementing
+            # get_format()?
+            return BaseModelType.Flux
+
         for key_name in (
             "control_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight",
             "controlnet_mid_block.bias",
@@ -648,6 +683,10 @@ class IPAdapterCheckpointProbe(CheckpointProbeBase):
 
     def get_base_type(self) -> BaseModelType:
         checkpoint = self.checkpoint
+
+        if is_state_dict_xlabs_ip_adapter(checkpoint):
+            return BaseModelType.Flux
+
         for key in checkpoint.keys():
             if not key.startswith(("image_proj.", "ip_adapter.")):
                 continue
@@ -844,22 +883,19 @@ class ControlNetFolderProbe(FolderProbeBase):
             raise InvalidModelConfigException(f"Cannot determine base type for {self.model_path}")
         with open(config_file, "r") as file:
             config = json.load(file)
+
+        if config.get("_class_name", None) == "FluxControlNetModel":
+            return BaseModelType.Flux
+
         # no obvious way to distinguish between sd2-base and sd2-768
         dimension = config["cross_attention_dim"]
-        base_model = (
-            BaseModelType.StableDiffusion1
-            if dimension == 768
-            else (
-                BaseModelType.StableDiffusion2
-                if dimension == 1024
-                else BaseModelType.StableDiffusionXL
-                if dimension == 2048
-                else None
-            )
-        )
-        if not base_model:
-            raise InvalidModelConfigException(f"Unable to determine model base for {self.model_path}")
-        return base_model
+        if dimension == 768:
+            return BaseModelType.StableDiffusion1
+        if dimension == 1024:
+            return BaseModelType.StableDiffusion2
+        if dimension == 2048:
+            return BaseModelType.StableDiffusionXL
+        raise InvalidModelConfigException(f"Unable to determine model base for {self.model_path}")
 
 
 class LoRAFolderProbe(FolderProbeBase):

invokeai/backend/quantization/gguf/ggml_tensor.py

@@ -54,6 +54,11 @@ GGML_TENSOR_OP_TABLE = {
     torch.ops.aten.mul.Tensor: dequantize_and_run,  # pyright: ignore
 }
 
+if torch.backends.mps.is_available():
+    GGML_TENSOR_OP_TABLE.update(
+        {torch.ops.aten.linear.default: dequantize_and_run}  # pyright: ignore
+    )
+
 
 class GGMLTensor(torch.Tensor):
     """A torch.Tensor sub-class holding a quantized GGML tensor.

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -171,8 +171,19 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         """
         if xformers is available, use it, otherwise use sliced attention.
         """
+
+        # On 30xx and 40xx series GPUs, `torch-sdp` is faster than `xformers`. This corresponds to a CUDA major
+        # version of 8 or higher. So, for major version 7 or below, we prefer `xformers`.
+        # See:
+        # - https://developer.nvidia.com/cuda-gpus
+        # - https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#compute-capabilities
+        try:
+            prefer_xformers = torch.cuda.is_available() and torch.cuda.get_device_properties("cuda").major <= 7  # type: ignore # Type of "get_device_properties" is partially unknown
+        except Exception:
+            prefer_xformers = False
+
         config = get_config()
-        if config.attention_type == "xformers":
+        if config.attention_type == "xformers" and is_xformers_available() and prefer_xformers:
             self.enable_xformers_memory_efficient_attention()
             return
         elif config.attention_type == "sliced":
@@ -187,20 +198,24 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
             self.disable_attention_slicing()
             return
         elif config.attention_type == "torch-sdp":
-            if hasattr(torch.nn.functional, "scaled_dot_product_attention"):
-                # diffusers enables sdp automatically
-                return
-            else:
-                raise Exception("torch-sdp attention slicing not available")
+            # torch-sdp is the default in diffusers.
+            return
 
-        # the remainder if this code is called when attention_type=='auto'
+        # See https://github.com/invoke-ai/InvokeAI/issues/7049 for context.
+        # Bumping torch from 2.2.2 to 2.4.1 caused the sliced attention implementation to produce incorrect results.
+        # For now, if a user is on an MPS device and has not explicitly set the attention_type, then we select the
+        # non-sliced torch-sdp implementation. This keeps things working on MPS at the cost of increased peak memory
+        # utilization.
+        if torch.backends.mps.is_available():
+            return
+
+        # The remainder if this code is called when attention_type=='auto'.
         if self.unet.device.type == "cuda":
-            if is_xformers_available():
+            if is_xformers_available() and prefer_xformers:
                 self.enable_xformers_memory_efficient_attention()
                 return
-            elif hasattr(torch.nn.functional, "scaled_dot_product_attention"):
-                # diffusers enables sdp automatically
-                return
+            # torch-sdp is the default in diffusers.
+            return
 
         if self.unet.device.type == "cpu" or self.unet.device.type == "mps":
             mem_free = psutil.virtual_memory().free

invokeai/frontend/web/package.json

@@ -58,7 +58,7 @@
     "@dnd-kit/sortable": "^8.0.0",
     "@dnd-kit/utilities": "^3.2.2",
     "@fontsource-variable/inter": "^5.1.0",
-    "@invoke-ai/ui-library": "^0.0.41",
+    "@invoke-ai/ui-library": "^0.0.43",
     "@nanostores/react": "^0.7.3",
     "@reduxjs/toolkit": "2.2.3",
     "@roarr/browser-log-writer": "^1.3.0",
@@ -114,8 +114,7 @@
   },
   "peerDependencies": {
     "react": "^18.2.0",
-    "react-dom": "^18.2.0",
-    "ts-toolbelt": "^9.6.0"
+    "react-dom": "^18.2.0"
   },
   "devDependencies": {
     "@invoke-ai/eslint-config-react": "^0.0.14",
@@ -149,8 +148,8 @@
     "prettier": "^3.3.3",
     "rollup-plugin-visualizer": "^5.12.0",
     "storybook": "^8.3.4",
-    "ts-toolbelt": "^9.6.0",
     "tsafe": "^1.7.5",
+    "type-fest": "^4.26.1",
     "typescript": "^5.6.2",
     "vite": "^5.4.8",
     "vite-plugin-css-injected-by-js": "^3.5.2",

invokeai/frontend/web/pnpm-lock.yaml

@@ -24,8 +24,8 @@ dependencies:
     specifier: ^5.1.0
     version: 5.1.0
   '@invoke-ai/ui-library':
-    specifier: ^0.0.41
-    version: 0.0.41(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1)
+    specifier: ^0.0.43
+    version: 0.0.43(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1)
   '@nanostores/react':
     specifier: ^0.7.3
     version: 0.7.3(nanostores@0.11.3)(react@18.3.1)
@@ -277,12 +277,12 @@ devDependencies:
   storybook:
     specifier: ^8.3.4
     version: 8.3.4
-  ts-toolbelt:
-    specifier: ^9.6.0
-    version: 9.6.0
   tsafe:
     specifier: ^1.7.5
     version: 1.7.5
+  type-fest:
+    specifier: ^4.26.1
+    version: 4.26.1
   typescript:
     specifier: ^5.6.2
     version: 5.6.2
@@ -551,12 +551,12 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/hooks@2.4.1(react@18.3.1):
-    resolution: {integrity: sha512-f81S0TiSh14LjiXBAvdezmIQLKGR7pckQ8kLMIxjngNW4VV92dhznOP+VcQmDOyXslfWsaWNFswlASE6clVw1g==}
+  /@chakra-ui/hooks@2.4.2(react@18.3.1):
+    resolution: {integrity: sha512-LRKiVE1oA7afT5tbbSKAy7Uas2xFHE6IkrQdbhWCHmkHBUtPvjQQDgwtnd4IRZPmoEfNGwoJ/MQpwOM/NRTTwA==}
     peerDependencies:
       react: '>=18'
     dependencies:
-      '@chakra-ui/utils': 2.2.1(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       '@zag-js/element-size': 0.31.1
       copy-to-clipboard: 3.3.3
       framesync: 6.1.2
@@ -574,13 +574,13 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/icons@2.2.4(@chakra-ui/react@2.10.1)(react@18.3.1):
+  /@chakra-ui/icons@2.2.4(@chakra-ui/react@2.10.2)(react@18.3.1):
     resolution: {integrity: sha512-l5QdBgwrAg3Sc2BRqtNkJpfuLw/pWRDwwT58J6c4PqQT6wzXxyNa8Q0PForu1ltB5qEiFb1kxr/F/HO1EwNa6g==}
     peerDependencies:
       '@chakra-ui/react': '>=2.0.0'
       react: '>=18'
     dependencies:
-      '@chakra-ui/react': 2.10.1(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
+      '@chakra-ui/react': 2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
       react: 18.3.1
     dev: false
 
@@ -803,8 +803,8 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/react@2.10.1(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1):
-    resolution: {integrity: sha512-YUOPyuq6Z0P1TSURNQRccwV/YbiWlkHlRLEMqNMwFQeQe7lyXfkPHn8GZyxvaiu+S02iopG9xg+wl68K4G3FSQ==}
+  /@chakra-ui/react@2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1):
+    resolution: {integrity: sha512-TfIHTqTlxTHYJZBtpiR5EZasPUrLYKJxdbHkdOJb5G1OQ+2c5kKl5XA7c2pMtsEptzb7KxAAIB62t3hxdfWp1w==}
     peerDependencies:
       '@emotion/react': '>=11'
       '@emotion/styled': '>=11'
@@ -812,10 +812,10 @@ packages:
       react: '>=18'
       react-dom: '>=18'
     dependencies:
-      '@chakra-ui/hooks': 2.4.1(react@18.3.1)
-      '@chakra-ui/styled-system': 2.11.1(react@18.3.1)
-      '@chakra-ui/theme': 3.4.5(@chakra-ui/styled-system@2.11.1)(react@18.3.1)
-      '@chakra-ui/utils': 2.2.1(react@18.3.1)
+      '@chakra-ui/hooks': 2.4.2(react@18.3.1)
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme': 3.4.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       '@emotion/react': 11.13.3(@types/react@18.3.11)(react@18.3.1)
       '@emotion/styled': 11.13.0(@emotion/react@11.13.3)(@types/react@18.3.11)(react@18.3.1)
       '@popperjs/core': 2.11.8
@@ -826,7 +826,6 @@ packages:
       react-dom: 18.3.1(react@18.3.1)
       react-fast-compare: 3.2.2
       react-focus-lock: 2.13.2(@types/react@18.3.11)(react@18.3.1)
-      react-lorem-component: 0.13.0(react@18.3.1)
       react-remove-scroll: 2.6.0(@types/react@18.3.11)(react@18.3.1)
     transitivePeerDependencies:
       - '@types/react'
@@ -847,10 +846,10 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/styled-system@2.11.1(react@18.3.1):
-    resolution: {integrity: sha512-1O4vQSSJqDYl+xkQLgNLVsBhEUkFd5BKQAIBEZC5ppppvCXAt+BPqrOLFAkNyo7piKYp5mf6fdYBAW/ESurqeg==}
+  /@chakra-ui/styled-system@2.11.2(react@18.3.1):
+    resolution: {integrity: sha512-y++z2Uop+hjfZX9mbH88F1ikazPv32asD2er56zMJBemUAzweXnHTpiCQbluEDSUDhqmghVZAdb+5L4XLbsRxA==}
     dependencies:
-      '@chakra-ui/utils': 2.2.1(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       csstype: 3.1.3
     transitivePeerDependencies:
       - react
@@ -894,14 +893,14 @@ packages:
       color2k: 2.0.3
     dev: false
 
-  /@chakra-ui/theme-tools@2.2.5(@chakra-ui/styled-system@2.11.1)(react@18.3.1):
-    resolution: {integrity: sha512-tUIv04Pzm2W8v5Iugei15qREIFX2mslI3fEouIVih8vHzwY821neCfspxOsAhvYSLNX+1kzk6ArBo9WzUpqn+Q==}
+  /@chakra-ui/theme-tools@2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1):
+    resolution: {integrity: sha512-3UhKPyzKbV3l/bg1iQN9PBvffYp+EBOoYMUaeTUdieQRPFzo2jbYR0lNCxqv8h5aGM/k54nCHU2M/GStyi9F2A==}
     peerDependencies:
       '@chakra-ui/styled-system': '>=2.0.0'
     dependencies:
       '@chakra-ui/anatomy': 2.3.4
-      '@chakra-ui/styled-system': 2.11.1(react@18.3.1)
-      '@chakra-ui/utils': 2.2.1(react@18.3.1)
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       color2k: 2.0.3
     transitivePeerDependencies:
       - react
@@ -927,15 +926,15 @@ packages:
       '@chakra-ui/theme-tools': 2.1.2(@chakra-ui/styled-system@2.9.2)
     dev: false
 
-  /@chakra-ui/theme@3.4.5(@chakra-ui/styled-system@2.11.1)(react@18.3.1):
-    resolution: {integrity: sha512-h/00W3xFCrUnsosVdh/SNMKfaez9jo1MMz2ruZAcpg/b1Jk0WnYa/ONhUwN89DR3UrPHSR+/vigZBxaA1+3QUQ==}
+  /@chakra-ui/theme@3.4.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1):
+    resolution: {integrity: sha512-ZwFBLfiMC3URwaO31ONXoKH9k0TX0OW3UjdPF3EQkQpYyrk/fm36GkkzajjtdpWEd7rzDLRsQjPmvwNaSoNDtg==}
     peerDependencies:
       '@chakra-ui/styled-system': '>=2.8.0'
     dependencies:
       '@chakra-ui/anatomy': 2.3.4
-      '@chakra-ui/styled-system': 2.11.1(react@18.3.1)
-      '@chakra-ui/theme-tools': 2.2.5(@chakra-ui/styled-system@2.11.1)(react@18.3.1)
-      '@chakra-ui/utils': 2.2.1(react@18.3.1)
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme-tools': 2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
     transitivePeerDependencies:
       - react
     dev: false
@@ -960,8 +959,8 @@ packages:
       lodash.mergewith: 4.6.2
     dev: false
 
-  /@chakra-ui/utils@2.2.1(react@18.3.1):
-    resolution: {integrity: sha512-e9D6CDtQZWBx+rq7yW13mAeI3Vod4cWfUIip+XFNjPWQSJGOJb1MiXocoiJqaZ1S+jsN+mod4uCZmGcukv0iSg==}
+  /@chakra-ui/utils@2.2.2(react@18.3.1):
+    resolution: {integrity: sha512-jUPLT0JzRMWxpdzH6c+t0YMJYrvc5CLericgITV3zDSXblkfx3DsYXqU11DJTSGZI9dUKzM1Wd0Wswn4eJwvFQ==}
     peerDependencies:
       react: '>=16.8.0'
     dependencies:
@@ -1697,20 +1696,20 @@ packages:
       prettier: 3.3.3
     dev: true
 
-  /@invoke-ai/ui-library@0.0.41(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1):
-    resolution: {integrity: sha512-bV83fXxqSuEMghQ68nF6uFkPE/DXtbnY2ZiXcoXXhOvv9X32/uKWSrcaeka9lZxrr10GFvV5a5LRORDornDaGg==}
+  /@invoke-ai/ui-library@0.0.43(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1):
+    resolution: {integrity: sha512-t3fPYyks07ue3dEBPJuTHbeDLnDckDCOrtvc07mMDbLOnlPEZ0StaeiNGH+oO8qLzAuMAlSTdswgHfzTc2MmPw==}
     peerDependencies:
       '@fontsource-variable/inter': ^5.0.16
       react: ^18.2.0
       react-dom: ^18.2.0
     dependencies:
-      '@chakra-ui/anatomy': 2.2.2
-      '@chakra-ui/icons': 2.2.4(@chakra-ui/react@2.10.1)(react@18.3.1)
+      '@chakra-ui/anatomy': 2.3.4
+      '@chakra-ui/icons': 2.2.4(@chakra-ui/react@2.10.2)(react@18.3.1)
       '@chakra-ui/layout': 2.3.1(@chakra-ui/system@2.6.2)(react@18.3.1)
       '@chakra-ui/portal': 2.1.0(react-dom@18.3.1)(react@18.3.1)
-      '@chakra-ui/react': 2.10.1(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
-      '@chakra-ui/styled-system': 2.9.2
-      '@chakra-ui/theme-tools': 2.1.2(@chakra-ui/styled-system@2.9.2)
+      '@chakra-ui/react': 2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme-tools': 2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
       '@emotion/react': 11.13.3(@types/react@18.3.11)(react@18.3.1)
       '@emotion/styled': 11.13.0(@emotion/react@11.13.3)(@types/react@18.3.11)(react@18.3.1)
       '@fontsource-variable/inter': 5.1.0
@@ -4691,14 +4690,6 @@ packages:
       yaml: 1.10.2
     dev: false
 
-  /create-react-class@15.7.0:
-    resolution: {integrity: sha512-QZv4sFWG9S5RUvkTYWbflxeZX+JG7Cz0Tn33rQBJ+WFQTqTfUTjMjiv9tnfXazjsO5r0KhPs+AqCjyrQX6h2ng==}
-    dependencies:
-      loose-envify: 1.4.0
-      object-assign: 4.1.1
-    dev: false
-    bundledDependencies: false
-
   /cross-fetch@4.0.0:
     resolution: {integrity: sha512-e4a5N8lVvuLgAWgnCrLr2PP0YyDOTHa9H/Rj54dirp61qXnNq46m82bRhNqIA5VccJtWBvPTFRV3TtvHUKPB1g==}
     dependencies:
@@ -6817,13 +6808,6 @@ packages:
     dependencies:
       js-tokens: 4.0.0
 
-  /lorem-ipsum@1.0.6:
-    resolution: {integrity: sha512-Rx4XH8X4KSDCKAVvWGYlhAfNqdUP5ZdT4rRyf0jjrvWgtViZimDIlopWNfn/y3lGM5K4uuiAoY28TaD+7YKFrQ==}
-    hasBin: true
-    dependencies:
-      minimist: 1.2.8
-    dev: false
-
   /loupe@2.3.7:
     resolution: {integrity: sha512-zSMINGVYkdpYSOBmLi0D1Uo7JU9nVdQKrHxC8eYlV+9YKK9WePqAlL7lSlorG/U2Fw1w0hTBmaa/jrQ3UbPHtA==}
     dependencies:
@@ -7017,6 +7001,7 @@ packages:
 
   /minimist@1.2.8:
     resolution: {integrity: sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==}
+    dev: true
 
   /minipass@7.1.2:
     resolution: {integrity: sha512-qOOzS1cBTWYF4BH8fVePDBOO9iptMnGUEZwNc/cMWnTV2nVLZ7VoNWEPHkYczZA0pdoA7dl6e7FL659nX9S2aw==}
@@ -7775,18 +7760,6 @@ packages:
     resolution: {integrity: sha512-/LLMVyas0ljjAtoYiPqYiL8VWXzUUdThrmU5+n20DZv+a+ClRoevUzw5JxU+Ieh5/c87ytoTBV9G1FiKfNJdmg==}
     dev: true
 
-  /react-lorem-component@0.13.0(react@18.3.1):
-    resolution: {integrity: sha512-4mWjxmcG/DJJwdxdKwXWyP2N9zohbJg/yYaC+7JffQNrKj3LYDpA/A4u/Dju1v1ZF6Jew2gbFKGb5Z6CL+UNTw==}
-    peerDependencies:
-      react: 16.x
-    dependencies:
-      create-react-class: 15.7.0
-      lorem-ipsum: 1.0.6
-      object-assign: 4.1.1
-      react: 18.3.1
-      seedable-random: 0.0.1
-    dev: false
-
   /react-redux@9.1.2(@types/react@18.3.11)(react@18.3.1)(redux@5.0.1):
     resolution: {integrity: sha512-0OA4dhM1W48l3uzmv6B7TXPCGmokUU4p1M44DGN2/D9a1FjVPukVjER1PcPX97jIg6aUeLq1XJo1IpfbgULn0w==}
     peerDependencies:
@@ -8301,10 +8274,6 @@ packages:
     engines: {node: '>=0.10.0'}
     dev: false
 
-  /seedable-random@0.0.1:
-    resolution: {integrity: sha512-uZWbEfz3BQdBl4QlUPELPqhInGEO1Q6zjzqrTDkd3j7mHaWWJo7h4ydr2g24a2WtTLk3imTLc8mPbBdQqdsbGw==}
-    dev: false
-
   /semver-compare@1.0.0:
     resolution: {integrity: sha512-YM3/ITh2MJ5MtzaM429anh+x2jiLVjqILF4m4oyQB18W7Ggea7BfqdH/wGMK7dDiMghv/6WG7znWMwUDzJiXow==}
     dev: false
@@ -8861,10 +8830,6 @@ packages:
     resolution: {integrity: sha512-tLJxacIQUM82IR7JO1UUkKlYuUTmoY9HBJAmNWFzheSlDS5SPMcNIepejHJa4BpPQLAcbRhRf3GDJzyj6rbKvA==}
     dev: false
 
-  /ts-toolbelt@9.6.0:
-    resolution: {integrity: sha512-nsZd8ZeNUzukXPlJmTBwUAuABDe/9qtVDelJeT/qW0ow3ZS3BsQJtNkan1802aM9Uf68/Y8ljw86Hu0h5IUW3w==}
-    dev: true
-
   /tsafe@1.7.5:
     resolution: {integrity: sha512-tbNyyBSbwfbilFfiuXkSOj82a6++ovgANwcoqBAcO9/REPoZMEQoE8kWPeO0dy5A2D/2Lajr8Ohue5T0ifIvLQ==}
     dev: true

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

@@ -93,7 +93,9 @@
         "placeholderSelectAModel": "Modell auswählen",
         "reset": "Zurücksetzen",
         "none": "Keine",
-        "new": "Neu"
+        "new": "Neu",
+        "ok": "OK",
+        "close": "Schließen"
     },
     "gallery": {
         "galleryImageSize": "Bildgröße",
@@ -156,7 +158,11 @@
         "displayBoardSearch": "Board durchsuchen",
         "displaySearch": "Bild suchen",
         "go": "Los",
-        "jump": "Springen"
+        "jump": "Springen",
+        "assetsTab": "Dateien, die Sie zur Verwendung in Ihren Projekten hochgeladen haben.",
+        "imagesTab": "Bilder, die Sie in Invoke erstellt und gespeichert haben.",
+        "boardsSettings": "Ordnereinstellungen",
+        "imagesSettings": "Galeriebildereinstellungen"
     },
     "hotkeys": {
         "noHotkeysFound": "Kein Hotkey gefunden",
@@ -267,6 +273,18 @@
             "applyFilter": {
                 "title": "Filter anwenden",
                 "desc": "Wende den ausstehenden Filter auf die ausgewählte Ebene an."
+            },
+            "cancelFilter": {
+                "title": "Filter abbrechen",
+                "desc": "Den ausstehenden Filter abbrechen."
+            },
+            "applyTransform": {
+                "desc": "Die ausstehende Transformation auf die ausgewählte Ebene anwenden.",
+                "title": "Transformation anwenden"
+            },
+            "cancelTransform": {
+                "title": "Transformation abbrechen",
+                "desc": "Die ausstehende Transformation abbrechen."
             }
         },
         "viewer": {
@@ -563,7 +581,18 @@
         "scanResults": "Ergebnisse des Scans",
         "urlOrLocalPathHelper": "URLs sollten auf eine einzelne Datei deuten. Lokale Pfade können zusätzlich auch auf einen Ordner für ein einzelnes Diffusers-Modell hinweisen.",
         "inplaceInstallDesc": "Installieren Sie Modelle, ohne die Dateien zu kopieren. Wenn Sie das Modell verwenden, wird es direkt von seinem Speicherort geladen. Wenn deaktiviert, werden die Dateien während der Installation in das von Invoke verwaltete Modellverzeichnis kopiert.",
-        "scanFolderHelper": "Der Ordner wird rekursiv nach Modellen durchsucht. Dies kann bei sehr großen Ordnern etwas dauern."
+        "scanFolderHelper": "Der Ordner wird rekursiv nach Modellen durchsucht. Dies kann bei sehr großen Ordnern etwas dauern.",
+        "includesNModels": "Enthält {{n}} Modelle und deren Abhängigkeiten",
+        "starterBundles": "Starterpakete",
+        "installingXModels_one": "{{count}} Modell wird installiert",
+        "installingXModels_other": "{{count}} Modelle werden installiert",
+        "skippingXDuplicates_one": ", überspringe {{count}} Duplikat",
+        "skippingXDuplicates_other": ", überspringe {{count}} Duplikate",
+        "installingModel": "Modell wird installiert",
+        "loraTriggerPhrases": "LoRA-Auslösephrasen",
+        "installingBundle": "Bündel wird installiert",
+        "triggerPhrases": "Auslösephrasen",
+        "mainModelTriggerPhrases": "Hauptmodell-Auslösephrasen"
     },
     "parameters": {
         "images": "Bilder",
@@ -667,7 +696,8 @@
         "about": "Über",
         "submitSupportTicket": "Support-Ticket senden",
         "toggleRightPanel": "Rechtes Bedienfeld umschalten (G)",
-        "toggleLeftPanel": "Linkes Bedienfeld umschalten (T)"
+        "toggleLeftPanel": "Linkes Bedienfeld umschalten (T)",
+        "uploadImages": "Bild(er) hochladen"
     },
     "boards": {
         "autoAddBoard": "Board automatisch erstellen",
@@ -702,7 +732,7 @@
         "shared": "Geteilte Ordner",
         "archiveBoard": "Ordner archivieren",
         "archived": "Archiviert",
-        "noBoards": "Kein {boardType}} Ordner",
+        "noBoards": "Kein {{boardType}} Ordner",
         "hideBoards": "Ordner verstecken",
         "viewBoards": "Ordner ansehen",
         "deletedPrivateBoardsCannotbeRestored": "Gelöschte Boards können nicht wiederhergestellt werden. Wenn Sie „Nur Board löschen“ wählen, werden die Bilder in einen privaten, nicht kategorisierten Status für den Ersteller des Bildes versetzt.",
@@ -811,7 +841,8 @@
         "parameterSet": "Parameter {{parameter}} setzen",
         "recallParameter": "{{label}} Abrufen",
         "parsingFailed": "Parsing Fehlgeschlagen",
-        "canvasV2Metadata": "Leinwand"
+        "canvasV2Metadata": "Leinwand",
+        "guidance": "Führung"
     },
     "popovers": {
         "noiseUseCPU": {
@@ -936,7 +967,8 @@
         },
         "paramScheduler": {
             "paragraphs": [
-                "\"Planer\" definiert, wie iterativ Rauschen zu einem Bild hinzugefügt wird, oder wie ein Sample bei der Ausgabe eines Modells aktualisiert wird."
+                "Verwendeter Planer währende des Generierungsprozesses.",
+                "Jeder Planer definiert, wie einem Bild iterativ Rauschen hinzugefügt wird, oder wie ein Sample basierend auf der Ausgabe eines Modells aktualisiert wird."
             ],
             "heading": "Planer"
         },
@@ -962,6 +994,61 @@
         },
         "ipAdapterMethod": {
             "heading": "Methode"
+        },
+        "refinerScheduler": {
+            "heading": "Planer",
+            "paragraphs": [
+                "Planer, der während der Veredelungsphase des Generierungsprozesses verwendet wird.",
+                "Ähnlich wie der Generierungsplaner."
+            ]
+        },
+        "compositingCoherenceMode": {
+            "paragraphs": [
+                "Verwendete Methode zur Erstellung eines kohärenten Bildes mit dem neu generierten maskierten Bereich."
+            ],
+            "heading": "Modus"
+        },
+        "compositingCoherencePass": {
+            "heading": "Kohärenzdurchlauf"
+        },
+        "controlNet": {
+            "heading": "ControlNet"
+        },
+        "compositingMaskAdjustments": {
+            "paragraphs": [
+                "Die Maske anpassen."
+            ],
+            "heading": "Maskenanpassungen"
+        },
+        "compositingMaskBlur": {
+            "paragraphs": [
+                "Der Unschärferadius der Maske."
+            ],
+            "heading": "Maskenunschärfe"
+        },
+        "compositingBlurMethod": {
+            "paragraphs": [
+                "Die auf den maskierten Bereich angewendete Unschärfemethode."
+            ],
+            "heading": "Unschärfemethode"
+        },
+        "controlNetResizeMode": {
+            "heading": "Größenänderungsmodus"
+        },
+        "paramWidth": {
+            "heading": "Breite",
+            "paragraphs": [
+                "Breite des generierten Bildes. Muss ein Vielfaches von 8 sein."
+            ]
+        },
+        "controlNetControlMode": {
+            "heading": "Kontrollmodus"
+        },
+        "controlNetProcessor": {
+            "heading": "Prozessor"
+        },
+        "patchmatchDownScaleSize": {
+            "heading": "Herunterskalieren"
         }
     },
     "invocationCache": {
@@ -1080,7 +1167,10 @@
         "workflowContact": "Kontaktdaten",
         "workflowNotes": "Notizen",
         "workflowTags": "Tags",
-        "workflowVersion": "Version"
+        "workflowVersion": "Version",
+        "saveToGallery": "In Galerie speichern",
+        "noWorkflows": "Keine Arbeitsabläufe",
+        "noMatchingWorkflows": "Keine passenden Arbeitsabläufe"
     },
     "hrf": {
         "enableHrf": "Korrektur für hohe Auflösungen",
@@ -1250,7 +1340,16 @@
         "searchByName": "Nach Name suchen",
         "promptTemplateCleared": "Promptvorlage gelöscht",
         "preview": "Vorschau",
-        "positivePrompt": "Positiv-Prompt"
+        "positivePrompt": "Positiv-Prompt",
+        "active": "Aktiv",
+        "deleteTemplate2": "Sind Sie sicher, dass Sie diese Vorlage löschen möchten? Dies kann nicht rückgängig gemacht werden.",
+        "deleteTemplate": "Vorlage löschen",
+        "copyTemplate": "Vorlage kopieren",
+        "editTemplate": "Vorlage bearbeiten",
+        "deleteImage": "Bild löschen",
+        "defaultTemplates": "Standardvorlagen",
+        "nameColumn": "'name'",
+        "exportDownloaded": "Export heruntergeladen"
     },
     "newUserExperience": {
         "gettingStartedSeries": "Wünschen Sie weitere Anleitungen? In unserer <LinkComponent>Einführungsserie</LinkComponent> finden Sie Tipps, wie Sie das Potenzial von Invoke Studio voll ausschöpfen können.",
@@ -1263,13 +1362,22 @@
             "bbox": "Bbox"
         },
         "transform": {
-            "fitToBbox": "An Bbox anpassen"
+            "fitToBbox": "An Bbox anpassen",
+            "reset": "Zurücksetzen",
+            "apply": "Anwenden",
+            "cancel": "Abbrechen"
         },
         "pullBboxIntoLayerError": "Problem, Bbox in die Ebene zu ziehen",
         "pullBboxIntoLayer": "Bbox in Ebene ziehen",
         "HUD": {
             "bbox": "Bbox",
-            "scaledBbox": "Skalierte Bbox"
+            "scaledBbox": "Skalierte Bbox",
+            "entityStatus": {
+                "isHidden": "{{title}} ist ausgeblendet",
+                "isDisabled": "{{title}} ist deaktiviert",
+                "isLocked": "{{title}} ist gesperrt",
+                "isEmpty": "{{title}} ist leer"
+            }
         },
         "fitBboxToLayers": "Bbox an Ebenen anpassen",
         "pullBboxIntoReferenceImage": "Bbox ins Referenzbild ziehen",
@@ -1279,7 +1387,12 @@
         "clipToBbox": "Pinselstriche auf Bbox beschränken",
         "canvasContextMenu": {
             "saveBboxToGallery": "Bbox in Galerie speichern",
-            "bboxGroup": "Aus Bbox erstellen"
+            "bboxGroup": "Aus Bbox erstellen",
+            "canvasGroup": "Leinwand",
+            "newGlobalReferenceImage": "Neues globales Referenzbild",
+            "newRegionalReferenceImage": "Neues regionales Referenzbild",
+            "newControlLayer": "Neue Kontroll-Ebene",
+            "newRasterLayer": "Neue Raster-Ebene"
         },
         "rectangle": "Rechteck",
         "saveCanvasToGallery": "Leinwand in Galerie speichern",
@@ -1310,7 +1423,7 @@
         "regional": "Regional",
         "newGlobalReferenceImageOk": "Globales Referenzbild erstellt",
         "savedToGalleryError": "Fehler beim Speichern in der Galerie",
-        "savedToGalleryOk": "In Galerie speichern",
+        "savedToGalleryOk": "In Galerie gespeichert",
         "newGlobalReferenceImageError": "Problem beim Erstellen eines globalen Referenzbilds",
         "newRegionalReferenceImageOk": "Regionales Referenzbild erstellt",
         "duplicate": "Duplizieren",
@@ -1343,12 +1456,39 @@
         "showProgressOnCanvas": "Fortschritt auf Leinwand anzeigen",
         "controlMode": {
             "balanced": "Ausgewogen"
-        }
+        },
+        "globalReferenceImages_withCount_hidden": "Globale Referenzbilder ({{count}} ausgeblendet)",
+        "sendToGallery": "An Galerie senden",
+        "stagingArea": {
+            "accept": "Annehmen",
+            "next": "Nächste",
+            "discardAll": "Alle verwerfen",
+            "discard": "Verwerfen",
+            "previous": "Vorherige"
+        },
+        "regionalGuidance_withCount_visible": "Regionale Führung ({{count}})",
+        "regionalGuidance_withCount_hidden": "Regionale Führung ({{count}} ausgeblendet)",
+        "settings": {
+            "snapToGrid": {
+                "on": "Ein",
+                "off": "Aus",
+                "label": "Am Raster ausrichten"
+            }
+        },
+        "layer_one": "Ebene",
+        "layer_other": "Ebenen",
+        "layer_withCount_one": "Ebene ({{count}})",
+        "layer_withCount_other": "Ebenen ({{count}})"
     },
     "upsell": {
         "shareAccess": "Zugang teilen",
         "professional": "Professionell",
         "inviteTeammates": "Teamkollegen einladen",
         "professionalUpsell": "Verfügbar in der Professional Edition von Invoke. Klicken Sie hier oder besuchen Sie invoke.com/pricing für weitere Details."
+    },
+    "upscaling": {
+        "creativity": "Kreativität",
+        "structure": "Struktur",
+        "scale": "Maßstab"
     }
 }

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

@@ -12,7 +12,8 @@
         "resetUI": "$t(accessibility.reset) UI",
         "toggleRightPanel": "Toggle Right Panel (G)",
         "toggleLeftPanel": "Toggle Left Panel (T)",
-        "uploadImage": "Upload Image"
+        "uploadImage": "Upload Image",
+        "uploadImages": "Upload Image(s)"
     },
     "boards": {
         "addBoard": "Add Board",
@@ -90,8 +91,10 @@
         "batch": "Batch Manager",
         "beta": "Beta",
         "cancel": "Cancel",
+        "close": "Close",
         "copy": "Copy",
         "copyError": "$t(gallery.copy) Error",
+        "clipboard": "Clipboard",
         "on": "On",
         "off": "Off",
         "or": "or",
@@ -284,6 +287,7 @@
         "assetsTab": "Files you’ve uploaded for use in your projects.",
         "autoAssignBoardOnClick": "Auto-Assign Board on Click",
         "autoSwitchNewImages": "Auto-Switch to New Images",
+        "boardsSettings": "Boards Settings",
         "copy": "Copy",
         "currentlyInUse": "This image is currently in use in the following features:",
         "drop": "Drop",
@@ -303,6 +307,7 @@
         "go": "Go",
         "image": "image",
         "imagesTab": "Images you’ve created and saved within Invoke.",
+        "imagesSettings": "Gallery Images Settings",
         "jump": "Jump",
         "loading": "Loading",
         "newestFirst": "Newest First",
@@ -661,6 +666,7 @@
         "cfgRescaleMultiplier": "$t(parameters.cfgRescaleMultiplier)",
         "createdBy": "Created By",
         "generationMode": "Generation Mode",
+        "guidance": "Guidance",
         "height": "Height",
         "imageDetails": "Image Details",
         "imageDimensions": "Image Dimensions",
@@ -707,8 +713,12 @@
         "convertToDiffusersHelpText4": "This is a one time process only. It might take around 30s-60s depending on the specifications of your computer.",
         "convertToDiffusersHelpText5": "Please make sure you have enough disk space. Models generally vary between 2GB-7GB in size.",
         "convertToDiffusersHelpText6": "Do you wish to convert this model?",
+        "noDefaultSettings": "No default settings configured for this model. Visit the Model Manager to add default settings.",
         "defaultSettings": "Default Settings",
         "defaultSettingsSaved": "Default Settings Saved",
+        "defaultSettingsOutOfSync": "Some settings do not match the model's defaults:",
+        "restoreDefaultSettings": "Click to use the model's default settings.",
+        "usingDefaultSettings": "Using model's default settings",
         "delete": "Delete",
         "deleteConfig": "Delete Config",
         "deleteModel": "Delete Model",
@@ -724,6 +734,7 @@
         "huggingFaceHelper": "If multiple models are found in this repo, you will be prompted to select one to install.",
         "hfToken": "HuggingFace Token",
         "imageEncoderModelId": "Image Encoder Model ID",
+        "includesNModels": "Includes {{n}} models and their dependencies",
         "installQueue": "Install Queue",
         "inplaceInstall": "In-place install",
         "inplaceInstallDesc": "Install models without copying the files. When using the model, it will be loaded from its this location. If disabled, the model file(s) will be copied into the Invoke-managed models directory during installation.",
@@ -777,6 +788,8 @@
         "simpleModelPlaceholder": "URL or path to a local file or diffusers folder",
         "source": "Source",
         "spandrelImageToImage": "Image to Image (Spandrel)",
+        "starterBundles": "Starter Bundles",
+        "starterBundleHelpText": "Easily install all models needed to get started with a base model, including a main model, controlnets, IP adapters, and more. Selecting a bundle will skip any models that you already have installed.",
         "starterModels": "Starter Models",
         "starterModelsInModelManager": "Starter Models can be found in Model Manager",
         "syncModels": "Sync Models",
@@ -790,11 +803,16 @@
         "uploadImage": "Upload Image",
         "urlOrLocalPath": "URL or Local Path",
         "urlOrLocalPathHelper": "URLs should point to a single file. Local paths can point to a single file or folder for a single diffusers model.",
-        "useDefaultSettings": "Use Default Settings",
         "vae": "VAE",
         "vaePrecision": "VAE Precision",
         "variant": "Variant",
-        "width": "Width"
+        "width": "Width",
+        "installingBundle": "Installing Bundle",
+        "installingModel": "Installing Model",
+        "installingXModels_one": "Installing {{count}} model",
+        "installingXModels_other": "Installing {{count}} models",
+        "skippingXDuplicates_one": ", skipping {{count}} duplicate",
+        "skippingXDuplicates_other": ", skipping {{count}} duplicates"
     },
     "models": {
         "addLora": "Add LoRA",
@@ -874,7 +892,7 @@
         "nodeType": "Node Type",
         "noFieldsLinearview": "No fields added to Linear View",
         "noFieldsViewMode": "This workflow has no selected fields to display. View the full workflow to configure values.",
-        "workflowHelpText": "Need Help? Check out our guide to <LinkComponent>Getting Started with Workflows</LinkComponent>",
+        "workflowHelpText": "Need Help? Check out our guide to <LinkComponent>Getting Started with Workflows</LinkComponent>.",
         "noNodeSelected": "No node selected",
         "nodeOpacity": "Node Opacity",
         "nodeVersion": "Node Version",
@@ -1094,6 +1112,9 @@
         "enableInformationalPopovers": "Enable Informational Popovers",
         "informationalPopoversDisabled": "Informational Popovers Disabled",
         "informationalPopoversDisabledDesc": "Informational popovers have been disabled. Enable them in Settings.",
+        "enableModelDescriptions": "Enable Model Descriptions in Dropdowns",
+        "modelDescriptionsDisabled": "Model Descriptions in Dropdowns Disabled",
+        "modelDescriptionsDisabledDesc": "Model descriptions in dropdowns have been disabled. Enable them in Settings.",
         "enableInvisibleWatermark": "Enable Invisible Watermark",
         "enableNSFWChecker": "Enable NSFW Checker",
         "general": "General",
@@ -1118,13 +1139,15 @@
         "reloadingIn": "Reloading in"
     },
     "toast": {
-        "addedToBoard": "Added to board",
+        "addedToBoard": "Added to board {{name}}'s assets",
+        "addedToUncategorized": "Added to board $t(boards.uncategorized)'s assets",
         "baseModelChanged": "Base Model Changed",
         "baseModelChangedCleared_one": "Cleared or disabled {{count}} incompatible submodel",
         "baseModelChangedCleared_other": "Cleared or disabled {{count}} incompatible submodels",
         "canceled": "Processing Canceled",
         "connected": "Connected to Server",
         "imageCopied": "Image Copied",
+        "linkCopied": "Link Copied",
         "unableToLoadImage": "Unable to Load Image",
         "unableToLoadImageMetadata": "Unable to Load Image Metadata",
         "unableToLoadStylePreset": "Unable to Load Style Preset",
@@ -1166,7 +1189,10 @@
         "setNodeField": "Set as node field",
         "somethingWentWrong": "Something Went Wrong",
         "uploadFailed": "Upload failed",
-        "uploadFailedInvalidUploadDesc": "Must be single PNG or JPEG image",
+        "imagesWillBeAddedTo": "Uploaded images will be added to board {{boardName}}'s assets.",
+        "uploadFailedInvalidUploadDesc_withCount_one": "Must be maximum of 1 PNG or JPEG image.",
+        "uploadFailedInvalidUploadDesc_withCount_other": "Must be maximum of {{count}} PNG or JPEG images.",
+        "uploadFailedInvalidUploadDesc": "Must be PNG or JPEG images.",
         "workflowLoaded": "Workflow Loaded",
         "problemRetrievingWorkflow": "Problem Retrieving Workflow",
         "workflowDeleted": "Workflow Deleted",
@@ -1232,6 +1258,33 @@
             "heading": "Mask Adjustments",
             "paragraphs": ["Adjust the mask."]
         },
+        "inpainting": {
+            "heading": "Inpainting",
+            "paragraphs": ["Controls which area is modified, guided by Denoising Strength."]
+        },
+        "rasterLayer": {
+            "heading": "Raster Layer",
+            "paragraphs": ["Pixel-based content of your canvas, used during image generation."]
+        },
+        "regionalGuidance": {
+            "heading": "Regional Guidance",
+            "paragraphs": ["Brush to guide where elements from global prompts should appear."]
+        },
+        "regionalGuidanceAndReferenceImage": {
+            "heading": "Regional Guidance and Regional Reference Image",
+            "paragraphs": [
+                "For Regional Guidance, brush to guide where elements from global prompts should appear.",
+                "For Regional Reference Image, brush to apply a reference image to specific areas."
+            ]
+        },
+        "globalReferenceImage": {
+            "heading": "Global Reference Image",
+            "paragraphs": ["Applies a reference image to influence the entire generation."]
+        },
+        "regionalReferenceImage": {
+            "heading": "Regional Reference Image",
+            "paragraphs": ["Brush to apply a reference image to specific areas."]
+        },
         "controlNet": {
             "heading": "ControlNet",
             "paragraphs": [
@@ -1559,7 +1612,12 @@
         "loadFromGraph": "Load Workflow from Graph",
         "convertGraph": "Convert Graph",
         "loadWorkflow": "$t(common.load) Workflow",
-        "autoLayout": "Auto Layout"
+        "autoLayout": "Auto Layout",
+        "edit": "Edit",
+        "download": "Download",
+        "copyShareLink": "Copy Share Link",
+        "copyShareLinkForWorkflow": "Copy Share Link for Workflow",
+        "delete": "Delete"
     },
     "controlLayers": {
         "regional": "Regional",
@@ -1624,6 +1682,8 @@
         "controlLayer": "Control Layer",
         "inpaintMask": "Inpaint Mask",
         "regionalGuidance": "Regional Guidance",
+        "canvasAsRasterLayer": "$t(controlLayers.canvas) as $t(controlLayers.rasterLayer)",
+        "canvasAsControlLayer": "$t(controlLayers.canvas) as $t(controlLayers.controlLayer)",
         "referenceImage": "Reference Image",
         "regionalReferenceImage": "Regional Reference Image",
         "globalReferenceImage": "Global Reference Image",
@@ -1634,6 +1694,7 @@
         "sendToCanvas": "Send To Canvas",
         "newLayerFromImage": "New Layer from Image",
         "newCanvasFromImage": "New Canvas from Image",
+        "newImg2ImgCanvasFromImage": "New Img2Img from Image",
         "copyToClipboard": "Copy to Clipboard",
         "sendToCanvasDesc": "Pressing Invoke stages your work in progress on the canvas.",
         "viewProgressInViewer": "View progress and outputs in the <Btn>Image Viewer</Btn>.",
@@ -1663,8 +1724,18 @@
         "layer_other": "Layers",
         "layer_withCount_one": "Layer ({{count}})",
         "layer_withCount_other": "Layers ({{count}})",
-        "convertToControlLayer": "Convert to Control Layer",
-        "convertToRasterLayer": "Convert to Raster Layer",
+        "convertRasterLayerTo": "Convert $t(controlLayers.rasterLayer) To",
+        "convertControlLayerTo": "Convert $t(controlLayers.controlLayer) To",
+        "convertInpaintMaskTo": "Convert $t(controlLayers.inpaintMask) To",
+        "convertRegionalGuidanceTo": "Convert $t(controlLayers.regionalGuidance) To",
+        "copyRasterLayerTo": "Copy $t(controlLayers.rasterLayer) To",
+        "copyControlLayerTo": "Copy $t(controlLayers.controlLayer) To",
+        "copyInpaintMaskTo": "Copy $t(controlLayers.inpaintMask) To",
+        "copyRegionalGuidanceTo": "Copy $t(controlLayers.regionalGuidance) To",
+        "newRasterLayer": "New $t(controlLayers.rasterLayer)",
+        "newControlLayer": "New $t(controlLayers.controlLayer)",
+        "newInpaintMask": "New $t(controlLayers.inpaintMask)",
+        "newRegionalGuidance": "New $t(controlLayers.regionalGuidance)",
         "transparency": "Transparency",
         "enableTransparencyEffect": "Enable Transparency Effect",
         "disableTransparencyEffect": "Disable Transparency Effect",
@@ -1688,6 +1759,7 @@
         "newGallerySessionDesc": "This will clear the canvas and all settings except for your model selection. Generations will be sent to the gallery.",
         "newCanvasSession": "New Canvas Session",
         "newCanvasSessionDesc": "This will clear the canvas and all settings except for your model selection. Generations will be staged on the canvas.",
+        "replaceCurrent": "Replace Current",
         "controlMode": {
             "controlMode": "Control Mode",
             "balanced": "Balanced",
@@ -1741,7 +1813,7 @@
                 "label": "Canny Edge Detection",
                 "description": "Generates an edge map from the selected layer using the Canny edge detection algorithm.",
                 "low_threshold": "Low Threshold",
-                "high_threshold": "Hight Threshold"
+                "high_threshold": "High Threshold"
             },
             "color_map": {
                 "label": "Color Map",
@@ -1809,10 +1881,33 @@
         "transform": {
             "transform": "Transform",
             "fitToBbox": "Fit to Bbox",
+            "fitMode": "Fit Mode",
+            "fitModeContain": "Contain",
+            "fitModeCover": "Cover",
+            "fitModeFill": "Fill",
             "reset": "Reset",
             "apply": "Apply",
             "cancel": "Cancel"
         },
+        "selectObject": {
+            "selectObject": "Select Object",
+            "pointType": "Point Type",
+            "invertSelection": "Invert Selection",
+            "include": "Include",
+            "exclude": "Exclude",
+            "neutral": "Neutral",
+            "apply": "Apply",
+            "reset": "Reset",
+            "saveAs": "Save As",
+            "cancel": "Cancel",
+            "process": "Process",
+            "help1": "Select a single target object. Add <Bold>Include</Bold> and <Bold>Exclude</Bold> points to indicate which parts of the layer are part of the target object.",
+            "help2": "Start with one <Bold>Include</Bold> point within the target object. Add more points to refine the selection. Fewer points typically produce better results.",
+            "help3": "Invert the selection to select everything except the target object.",
+            "clickToAdd": "Click on the layer to add a point",
+            "dragToMove": "Drag a point to move it",
+            "clickToRemove": "Click on a point to remove it"
+        },
         "settings": {
             "snapToGrid": {
                 "label": "Snap to Grid",
@@ -1823,10 +1918,10 @@
                 "label": "Preserve Masked Region",
                 "alert": "Preserving Masked Region"
             },
-            "isolatedPreview": "Isolated Preview",
             "isolatedStagingPreview": "Isolated Staging Preview",
-            "isolatedFilteringPreview": "Isolated Filtering Preview",
-            "isolatedTransformingPreview": "Isolated Transforming Preview",
+            "isolatedPreview": "Isolated Preview",
+            "isolatedLayerPreview": "Isolated Layer Preview",
+            "isolatedLayerPreviewDesc": "Whether to show only this layer when performing operations like filtering or transforming.",
             "invertBrushSizeScrollDirection": "Invert Scroll for Brush Size",
             "pressureSensitivity": "Pressure Sensitivity"
         },
@@ -1852,6 +1947,8 @@
             "newRegionalReferenceImage": "New Regional Reference Image",
             "newControlLayer": "New Control Layer",
             "newRasterLayer": "New Raster Layer",
+            "newInpaintMask": "New Inpaint Mask",
+            "newRegionalGuidance": "New Regional Guidance",
             "cropCanvasToBbox": "Crop Canvas to Bbox"
         },
         "stagingArea": {
@@ -1975,8 +2072,12 @@
         }
     },
     "newUserExperience": {
+        "toGetStartedLocal": "To get started, make sure to download or import models needed to run Invoke. Then, enter a prompt in the box and click <StrongComponent>Invoke</StrongComponent> to generate your first image. Select a prompt template to improve results. You can choose to save your images directly to the <StrongComponent>Gallery</StrongComponent> or edit them to the <StrongComponent>Canvas</StrongComponent>.",
         "toGetStarted": "To get started, enter a prompt in the box and click <StrongComponent>Invoke</StrongComponent> to generate your first image. Select a prompt template to improve results. You can choose to save your images directly to the <StrongComponent>Gallery</StrongComponent> or edit them to the <StrongComponent>Canvas</StrongComponent>.",
-        "gettingStartedSeries": "Want more guidance? Check out our <LinkComponent>Getting Started Series</LinkComponent> for tips on unlocking the full potential of the Invoke Studio."
+        "gettingStartedSeries": "Want more guidance? Check out our <LinkComponent>Getting Started Series</LinkComponent> for tips on unlocking the full potential of the Invoke Studio.",
+        "downloadStarterModels": "Download Starter Models",
+        "importModels": "Import Models",
+        "noModelsInstalled": "It looks like you don't have any models installed"
     },
     "whatsNew": {
         "whatsNewInInvoke": "What's New in Invoke",

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

@@ -224,7 +224,9 @@
         "createIssue": "Crear un problema",
         "resetUI": "Interfaz de usuario $t(accessibility.reset)",
         "mode": "Modo",
-        "submitSupportTicket": "Enviar Ticket de Soporte"
+        "submitSupportTicket": "Enviar Ticket de Soporte",
+        "toggleRightPanel": "Activar o desactivar el panel derecho (G)",
+        "toggleLeftPanel": "Activar o desactivar el panel izquierdo (T)"
     },
     "nodes": {
         "zoomInNodes": "Acercar",
@@ -273,7 +275,12 @@
         "addSharedBoard": "Agregar Panel Compartido",
         "boards": "Paneles",
         "archiveBoard": "Archivar Panel",
-        "archived": "Archivado"
+        "archived": "Archivado",
+        "selectedForAutoAdd": "Seleccionado para agregar automáticamente",
+        "unarchiveBoard": "Desarchivar el tablero",
+        "noBoards": "No hay tableros {{boardType}}",
+        "shared": "Carpetas compartidas",
+        "deletedPrivateBoardsCannotbeRestored": "Los tableros eliminados no se pueden restaurar. Al elegir \"Eliminar solo tablero\", las imágenes se colocan en un estado privado y sin categoría para el creador de la imagen."
     },
     "accordions": {
         "compositing": {
@@ -316,5 +323,13 @@
         "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."
+    },
+    "controlLayers": {
+        "layer_one": "Capa",
+        "layer_many": "Capas",
+        "layer_other": "Capas",
+        "layer_withCount_one": "({{count}}) capa",
+        "layer_withCount_many": "({{count}}) capas",
+        "layer_withCount_other": "({{count}}) capas"
     }
 }

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

@@ -91,7 +91,8 @@
         "reset": "Reimposta",
         "none": "Niente",
         "new": "Nuovo",
-        "view": "Vista"
+        "view": "Vista",
+        "close": "Chiudi"
     },
     "gallery": {
         "galleryImageSize": "Dimensione dell'immagine",
@@ -157,7 +158,9 @@
         "openViewer": "Apri visualizzatore",
         "closeViewer": "Chiudi visualizzatore",
         "imagesTab": "Immagini create e salvate in Invoke.",
-        "assetsTab": "File che hai caricato per usarli nei tuoi progetti."
+        "assetsTab": "File che hai caricato per usarli nei tuoi progetti.",
+        "boardsSettings": "Impostazioni Bacheche",
+        "imagesSettings": "Impostazioni Immagini Galleria"
     },
     "hotkeys": {
         "searchHotkeys": "Cerca tasti di scelta rapida",
@@ -574,7 +577,18 @@
         "noMatchingModels": "Nessun modello corrispondente",
         "starterModelsInModelManager": "I modelli iniziali possono essere trovati in Gestione Modelli",
         "spandrelImageToImage": "Immagine a immagine (Spandrel)",
-        "learnMoreAboutSupportedModels": "Scopri di più sui modelli che supportiamo"
+        "learnMoreAboutSupportedModels": "Scopri di più sui modelli che supportiamo",
+        "starterBundles": "Pacchetti per iniziare",
+        "installingBundle": "Installazione del pacchetto",
+        "skippingXDuplicates_one": ", saltando {{count}} duplicato",
+        "skippingXDuplicates_many": ", saltando {{count}} duplicati",
+        "skippingXDuplicates_other": ", saltando {{count}} duplicati",
+        "installingModel": "Installazione del modello",
+        "installingXModels_one": "Installazione di {{count}} modello",
+        "installingXModels_many": "Installazione di {{count}} modelli",
+        "installingXModels_other": "Installazione di {{count}} modelli",
+        "includesNModels": "Include {{n}} modelli e le loro dipendenze",
+        "starterBundleHelpText": "Installa facilmente tutti i modelli necessari per iniziare con un modello base, tra cui un modello principale, controlnet, adattatori IP e altro. Selezionando un pacchetto salterai tutti i modelli che hai già installato."
     },
     "parameters": {
         "images": "Immagini",
@@ -719,7 +733,7 @@
         "serverError": "Errore del Server",
         "connected": "Connesso al server",
         "canceled": "Elaborazione annullata",
-        "uploadFailedInvalidUploadDesc": "Deve essere una singola immagine PNG o JPEG",
+        "uploadFailedInvalidUploadDesc": "Devono essere immagini PNG o JPEG.",
         "parameterSet": "Parametro richiamato",
         "parameterNotSet": "Parametro non richiamato",
         "problemCopyingImage": "Impossibile copiare l'immagine",
@@ -728,7 +742,7 @@
         "baseModelChangedCleared_other": "Cancellati o disabilitati {{count}} sottomodelli incompatibili",
         "loadedWithWarnings": "Flusso di lavoro caricato con avvisi",
         "imageUploaded": "Immagine caricata",
-        "addedToBoard": "Aggiunto alla bacheca",
+        "addedToBoard": "Aggiunto alle risorse della bacheca {{name}}",
         "modelAddedSimple": "Modello aggiunto alla Coda",
         "imageUploadFailed": "Caricamento immagine non riuscito",
         "setControlImage": "Imposta come immagine di controllo",
@@ -766,7 +780,13 @@
         "imageSaved": "Immagine salvata",
         "imageSavingFailed": "Salvataggio dell'immagine non riuscito",
         "layerCopiedToClipboard": "Livello copiato negli appunti",
-        "imageNotLoadedDesc": "Impossibile trovare l'immagine"
+        "imageNotLoadedDesc": "Impossibile trovare l'immagine",
+        "linkCopied": "Collegamento copiato",
+        "addedToUncategorized": "Aggiunto alle risorse della bacheca $t(boards.uncategorized)",
+        "imagesWillBeAddedTo": "Le immagini caricate verranno aggiunte alle risorse della bacheca {{boardName}}.",
+        "uploadFailedInvalidUploadDesc_withCount_one": "Devi caricare al massimo 1 immagine PNG o JPEG.",
+        "uploadFailedInvalidUploadDesc_withCount_many": "Devi caricare al massimo {{count}} immagini PNG o JPEG.",
+        "uploadFailedInvalidUploadDesc_withCount_other": "Devi caricare al massimo {{count}} immagini PNG o JPEG."
     },
     "accessibility": {
         "invokeProgressBar": "Barra di avanzamento generazione",
@@ -781,7 +801,8 @@
         "about": "Informazioni",
         "submitSupportTicket": "Invia ticket di supporto",
         "toggleLeftPanel": "Attiva/disattiva il pannello sinistro (T)",
-        "toggleRightPanel": "Attiva/disattiva il pannello destro (G)"
+        "toggleRightPanel": "Attiva/disattiva il pannello destro (G)",
+        "uploadImages": "Carica immagine(i)"
     },
     "nodes": {
         "zoomOutNodes": "Rimpicciolire",
@@ -922,7 +943,7 @@
         "saveToGallery": "Salva nella Galleria",
         "noMatchingWorkflows": "Nessun flusso di lavoro corrispondente",
         "noWorkflows": "Nessun flusso di lavoro",
-        "workflowHelpText": "Hai bisogno di aiuto? Consulta la nostra guida <LinkComponent>Introduzione ai flussi di lavoro</LinkComponent>"
+        "workflowHelpText": "Hai bisogno di aiuto? Consulta la nostra guida <LinkComponent>Introduzione ai flussi di lavoro</LinkComponent>."
     },
     "boards": {
         "autoAddBoard": "Aggiungi automaticamente bacheca",
@@ -1519,7 +1540,8 @@
         "parameterSet": "Parametro {{parameter}} impostato",
         "parsingFailed": "Analisi non riuscita",
         "recallParameter": "Richiama {{label}}",
-        "canvasV2Metadata": "Tela"
+        "canvasV2Metadata": "Tela",
+        "guidance": "Guida"
     },
     "hrf": {
         "enableHrf": "Abilita Correzione Alta Risoluzione",
@@ -1570,7 +1592,12 @@
         "defaultWorkflows": "Flussi di lavoro predefiniti",
         "uploadAndSaveWorkflow": "Carica nella libreria",
         "chooseWorkflowFromLibrary": "Scegli il flusso di lavoro dalla libreria",
-        "deleteWorkflow2": "Vuoi davvero eliminare questo flusso di lavoro? Questa operazione non può essere annullata."
+        "deleteWorkflow2": "Vuoi davvero eliminare questo flusso di lavoro? Questa operazione non può essere annullata.",
+        "edit": "Modifica",
+        "download": "Scarica",
+        "copyShareLink": "Copia Condividi Link",
+        "copyShareLinkForWorkflow": "Copia Condividi Link del Flusso di lavoro",
+        "delete": "Elimina"
     },
     "accordions": {
         "compositing": {
@@ -1730,7 +1757,8 @@
             "mlsd_detection": {
                 "score_threshold": "Soglia di punteggio",
                 "distance_threshold": "Soglia di distanza",
-                "description": "Genera una mappa dei segmenti di linea dal livello selezionato utilizzando il modello di rilevamento dei segmenti di linea MLSD."
+                "description": "Genera una mappa dei segmenti di linea dal livello selezionato utilizzando il modello di rilevamento dei segmenti di linea MLSD.",
+                "label": "Rilevamento segmenti di linea"
             },
             "content_shuffle": {
                 "label": "Mescola contenuto",
@@ -1869,7 +1897,11 @@
             "fitToBbox": "Adatta al Riquadro",
             "transform": "Trasforma",
             "apply": "Applica",
-            "cancel": "Annulla"
+            "cancel": "Annulla",
+            "fitMode": "Adattamento",
+            "fitModeContain": "Contieni",
+            "fitModeFill": "Riempi",
+            "fitModeCover": "Copri"
         },
         "stagingArea": {
             "next": "Successiva",
@@ -1904,7 +1936,8 @@
             "newRasterLayer": "Nuovo Livello Raster",
             "saveCanvasToGallery": "Salva la Tela nella Galleria",
             "saveToGalleryGroup": "Salva nella Galleria"
-        }
+        },
+        "newImg2ImgCanvasFromImage": "Nuova Immagine da immagine"
     },
     "ui": {
         "tabs": {
@@ -1990,7 +2023,11 @@
     },
     "newUserExperience": {
         "gettingStartedSeries": "Desideri maggiori informazioni? Consulta la nostra <LinkComponent>Getting Started Series</LinkComponent> per suggerimenti su come sfruttare appieno il potenziale di Invoke Studio.",
-        "toGetStarted": "Per iniziare, inserisci un prompt nella casella e fai clic su <StrongComponent>Invoke</StrongComponent> per generare la tua prima immagine. Seleziona un modello di prompt per migliorare i risultati. Puoi scegliere di salvare le tue immagini direttamente nella <StrongComponent>Galleria</StrongComponent> o modificarle nella <StrongComponent>Tela</StrongComponent>."
+        "toGetStarted": "Per iniziare, inserisci un prompt nella casella e fai clic su <StrongComponent>Invoke</StrongComponent> per generare la tua prima immagine. Seleziona un modello di prompt per migliorare i risultati. Puoi scegliere di salvare le tue immagini direttamente nella <StrongComponent>Galleria</StrongComponent> o modificarle nella <StrongComponent>Tela</StrongComponent>.",
+        "importModels": "Importa modelli",
+        "downloadStarterModels": "Scarica i modelli per iniziare",
+        "noModelsInstalled": "Sembra che tu non abbia installato alcun modello",
+        "toGetStartedLocal": "Per iniziare, assicurati di scaricare o importare i modelli necessari per eseguire Invoke. Quindi, inserisci un prompt nella casella e fai clic su <StrongComponent>Invoke</StrongComponent> per generare la tua prima immagine. Seleziona un modello di prompt per migliorare i risultati. Puoi scegliere di salvare le tue immagini direttamente nella <StrongComponent>Galleria</StrongComponent> o modificarle nella <StrongComponent>Tela</StrongComponent>."
     },
     "whatsNew": {
         "canvasV2Announcement": {

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

@@ -94,7 +94,8 @@
         "reset": "Сброс",
         "none": "Ничего",
         "new": "Новый",
-        "ok": "Ok"
+        "ok": "Ok",
+        "close": "Закрыть"
     },
     "gallery": {
         "galleryImageSize": "Размер изображений",
@@ -158,7 +159,11 @@
         "move": "Двигать",
         "gallery": "Галерея",
         "openViewer": "Открыть просмотрщик",
-        "closeViewer": "Закрыть просмотрщик"
+        "closeViewer": "Закрыть просмотрщик",
+        "imagesTab": "Изображения, созданные и сохраненные в Invoke.",
+        "assetsTab": "Файлы, которые вы загрузили для использования в своих проектах.",
+        "boardsSettings": "Настройки доски",
+        "imagesSettings": "Настройки галереи изображений"
     },
     "hotkeys": {
         "searchHotkeys": "Поиск горячих клавиш",
@@ -581,7 +586,18 @@
         "learnMoreAboutSupportedModels": "Подробнее о поддерживаемых моделях",
         "t5Encoder": "T5 энкодер",
         "spandrelImageToImage": "Image to Image (Spandrel)",
-        "clipEmbed": "CLIP Embed"
+        "clipEmbed": "CLIP Embed",
+        "installingXModels_one": "Установка {{count}} модели",
+        "installingXModels_few": "Установка {{count}} моделей",
+        "installingXModels_many": "Установка {{count}} моделей",
+        "installingBundle": "Установка пакета",
+        "installingModel": "Установка модели",
+        "starterBundles": "Стартовые пакеты",
+        "skippingXDuplicates_one": ", пропуская {{count}} дубликат",
+        "skippingXDuplicates_few": ", пропуская {{count}} дубликата",
+        "skippingXDuplicates_many": ", пропуская {{count}} дубликатов",
+        "includesNModels": "Включает в себя {{n}} моделей и их зависимостей",
+        "starterBundleHelpText": "Легко установите все модели, необходимые для начала работы с базовой моделью, включая основную модель, сети управления, IP-адаптеры и многое другое. При выборе комплекта все уже установленные модели будут пропущены."
     },
     "parameters": {
         "images": "Изображения",
@@ -728,7 +744,7 @@
         "serverError": "Ошибка сервера",
         "connected": "Подключено к серверу",
         "canceled": "Обработка отменена",
-        "uploadFailedInvalidUploadDesc": "Должно быть одно изображение в формате PNG или JPEG",
+        "uploadFailedInvalidUploadDesc": "Это должны быть изображения PNG или JPEG.",
         "parameterNotSet": "Параметр не задан",
         "parameterSet": "Параметр задан",
         "problemCopyingImage": "Не удается скопировать изображение",
@@ -740,7 +756,7 @@
         "setNodeField": "Установить как поле узла",
         "invalidUpload": "Неверная загрузка",
         "imageUploaded": "Изображение загружено",
-        "addedToBoard": "Добавлено на доску",
+        "addedToBoard": "Добавлено в активы доски {{name}}",
         "workflowLoaded": "Рабочий процесс загружен",
         "problemDeletingWorkflow": "Проблема с удалением рабочего процесса",
         "modelAddedSimple": "Модель добавлена в очередь",
@@ -775,7 +791,13 @@
         "unableToLoadStylePreset": "Невозможно загрузить предустановку стиля",
         "layerCopiedToClipboard": "Слой скопирован в буфер обмена",
         "sentToUpscale": "Отправить на увеличение",
-        "layerSavedToAssets": "Слой сохранен в активах"
+        "layerSavedToAssets": "Слой сохранен в активах",
+        "linkCopied": "Ссылка скопирована",
+        "addedToUncategorized": "Добавлено в активы доски $t(boards.uncategorized)",
+        "imagesWillBeAddedTo": "Загруженные изображения будут добавлены в активы доски {{boardName}}.",
+        "uploadFailedInvalidUploadDesc_withCount_one": "Должно быть не более {{count}} изображения в формате PNG или JPEG.",
+        "uploadFailedInvalidUploadDesc_withCount_few": "Должно быть не более {{count}} изображений в формате PNG или JPEG.",
+        "uploadFailedInvalidUploadDesc_withCount_many": "Должно быть не более {{count}} изображений в формате PNG или JPEG."
     },
     "accessibility": {
         "uploadImage": "Загрузить изображение",
@@ -790,7 +812,8 @@
         "about": "Об этом",
         "submitSupportTicket": "Отправить тикет в службу поддержки",
         "toggleRightPanel": "Переключить правую панель (G)",
-        "toggleLeftPanel": "Переключить левую панель (T)"
+        "toggleLeftPanel": "Переключить левую панель (T)",
+        "uploadImages": "Загрузить изображения"
     },
     "nodes": {
         "zoomInNodes": "Увеличьте масштаб",
@@ -928,7 +951,10 @@
         "imageAccessError": "Невозможно найти изображение {{image_name}}, сбрасываем на значение по умолчанию",
         "boardAccessError": "Невозможно найти доску {{board_id}}, сбрасываем на значение по умолчанию",
         "modelAccessError": "Невозможно найти модель {{key}}, сброс на модель по умолчанию",
-        "saveToGallery": "Сохранить в галерею"
+        "saveToGallery": "Сохранить в галерею",
+        "noWorkflows": "Нет рабочих процессов",
+        "noMatchingWorkflows": "Нет совпадающих рабочих процессов",
+        "workflowHelpText": "Нужна помощь? Ознакомьтесь с нашим руководством <LinkComponent>Getting Started with Workflows</LinkComponent>."
     },
     "boards": {
         "autoAddBoard": "Авто добавление Доски",
@@ -1404,7 +1430,8 @@
         "recallParameter": "Отозвать {{label}}",
         "allPrompts": "Все запросы",
         "imageDimensions": "Размеры изображения",
-        "canvasV2Metadata": "Холст"
+        "canvasV2Metadata": "Холст",
+        "guidance": "Точность"
     },
     "queue": {
         "status": "Статус",
@@ -1553,7 +1580,15 @@
         "autoLayout": "Автоматическое расположение",
         "userWorkflows": "Пользовательские рабочие процессы",
         "projectWorkflows": "Рабочие процессы проекта",
-        "defaultWorkflows": "Стандартные рабочие процессы"
+        "defaultWorkflows": "Стандартные рабочие процессы",
+        "deleteWorkflow2": "Вы уверены, что хотите удалить этот рабочий процесс? Это нельзя отменить.",
+        "chooseWorkflowFromLibrary": "Выбрать рабочий процесс из библиотеки",
+        "uploadAndSaveWorkflow": "Загрузить в библиотеку",
+        "edit": "Редактировать",
+        "download": "Скачать",
+        "copyShareLink": "Скопировать ссылку на общий доступ",
+        "copyShareLinkForWorkflow": "Скопировать ссылку на общий доступ для рабочего процесса",
+        "delete": "Удалить"
     },
     "hrf": {
         "enableHrf": "Включить исправление высокого разрешения",
@@ -1872,8 +1907,8 @@
         "duplicate": "Дублировать",
         "inpaintMasks_withCount_visible": "Маски перерисовки ({{count}})",
         "layer_one": "Слой",
-        "layer_few": "",
-        "layer_many": "",
+        "layer_few": "Слоя",
+        "layer_many": "Слоев",
         "prompt": "Запрос",
         "negativePrompt": "Исключающий запрос",
         "beginEndStepPercentShort": "Начало/конец %",
@@ -1882,7 +1917,10 @@
             "fitToBbox": "Вместить в рамку",
             "reset": "Сбросить",
             "apply": "Применить",
-            "cancel": "Отменить"
+            "cancel": "Отменить",
+            "fitModeContain": "Уместить",
+            "fitMode": "Режим подгонки",
+            "fitModeFill": "Заполнить"
         },
         "disableAutoNegative": "Отключить авто негатив",
         "deleteReferenceImage": "Удалить эталонное изображение",
@@ -1912,7 +1950,8 @@
         "globalReferenceImage": "Глобальное эталонное изображение",
         "sendToGallery": "Отправить в галерею",
         "referenceImage": "Эталонное изображение",
-        "addGlobalReferenceImage": "Добавить $t(controlLayers.globalReferenceImage)"
+        "addGlobalReferenceImage": "Добавить $t(controlLayers.globalReferenceImage)",
+        "newImg2ImgCanvasFromImage": "Новое img2img из изображения"
     },
     "ui": {
         "tabs": {
@@ -2035,7 +2074,7 @@
         "whatsNewInInvoke": "Что нового в Invoke"
     },
     "newUserExperience": {
-        "toGetStarted": "Чтобы начать работу, введите в поле запрос и нажмите <StrongComponent>Invoke</StrongComponent>, чтобы сгенерировать первое изображение. Вы можете сохранить изображения непосредственно в <StrongComponent>Галерею</StrongComponent> или отредактировать их на <StrongComponent>Холсте</StrongComponent>.",
+        "toGetStarted": "Чтобы начать работу, введите в поле запрос и нажмите <StrongComponent>Invoke</StrongComponent>, чтобы сгенерировать первое изображение. Выберите шаблон запроса, чтобы улучшить результаты. Вы можете сохранить изображения непосредственно в <StrongComponent>Галерею</StrongComponent> или отредактировать их на <StrongComponent>Холсте</StrongComponent>.",
         "gettingStartedSeries": "Хотите получить больше рекомендаций? Ознакомьтесь с нашей серией <LinkComponent>Getting Started Series</LinkComponent> для получения советов по раскрытию всего потенциала Invoke Studio."
     }
 }

invokeai/frontend/web/src/app/components/App.tsx

@@ -4,6 +4,7 @@ import type { StudioInitAction } from 'app/hooks/useStudioInitAction';
 import { useStudioInitAction } from 'app/hooks/useStudioInitAction';
 import { useSyncQueueStatus } from 'app/hooks/useSyncQueueStatus';
 import { useLogger } from 'app/logging/useLogger';
+import { useSyncLoggingConfig } from 'app/logging/useSyncLoggingConfig';
 import { appStarted } from 'app/store/middleware/listenerMiddleware/listeners/appStarted';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
 import type { PartialAppConfig } from 'app/types/invokeai';
@@ -20,14 +21,18 @@ import {
 import DeleteImageModal from 'features/deleteImageModal/components/DeleteImageModal';
 import { DynamicPromptsModal } from 'features/dynamicPrompts/components/DynamicPromptsPreviewModal';
 import DeleteBoardModal from 'features/gallery/components/Boards/DeleteBoardModal';
+import { ImageContextMenu } from 'features/gallery/components/ImageContextMenu/ImageContextMenu';
 import { useStarterModelsToast } from 'features/modelManagerV2/hooks/useStarterModelsToast';
+import { ShareWorkflowModal } from 'features/nodes/components/sidePanel/WorkflowListMenu/ShareWorkflowModal';
 import { ClearQueueConfirmationsAlertDialog } from 'features/queue/components/ClearQueueConfirmationAlertDialog';
+import { DeleteStylePresetDialog } from 'features/stylePresets/components/DeleteStylePresetDialog';
 import { StylePresetModal } from 'features/stylePresets/components/StylePresetForm/StylePresetModal';
 import RefreshAfterResetModal from 'features/system/components/SettingsModal/RefreshAfterResetModal';
 import { configChanged } from 'features/system/store/configSlice';
 import { selectLanguage } from 'features/system/store/systemSelectors';
 import { AppContent } from 'features/ui/components/AppContent';
-import { AnimatePresence } from 'framer-motion';
+import { DeleteWorkflowDialog } from 'features/workflowLibrary/components/DeleteLibraryWorkflowConfirmationAlertDialog';
+import { NewWorkflowConfirmationAlertDialog } from 'features/workflowLibrary/components/NewWorkflowConfirmationAlertDialog';
 import i18n from 'i18n';
 import { size } from 'lodash-es';
 import { memo, useCallback, useEffect } from 'react';
@@ -55,6 +60,7 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
   useGlobalModifiersInit();
   useGlobalHotkeys();
   useGetOpenAPISchemaQuery();
+  useSyncLoggingConfig();
 
   const { dropzone, isHandlingUpload, setIsHandlingUpload } = useFullscreenDropzone();
 
@@ -96,22 +102,25 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
       >
         <input {...dropzone.getInputProps()} />
         <AppContent />
-        <AnimatePresence>
-          {dropzone.isDragActive && isHandlingUpload && (
-            <ImageUploadOverlay dropzone={dropzone} setIsHandlingUpload={setIsHandlingUpload} />
-          )}
-        </AnimatePresence>
+        {dropzone.isDragActive && isHandlingUpload && (
+          <ImageUploadOverlay dropzone={dropzone} setIsHandlingUpload={setIsHandlingUpload} />
+        )}
       </Box>
       <DeleteImageModal />
       <ChangeBoardModal />
       <DynamicPromptsModal />
       <StylePresetModal />
       <ClearQueueConfirmationsAlertDialog />
+      <NewWorkflowConfirmationAlertDialog />
+      <DeleteStylePresetDialog />
+      <DeleteWorkflowDialog />
+      <ShareWorkflowModal />
       <RefreshAfterResetModal />
       <DeleteBoardModal />
       <GlobalImageHotkeys />
       <NewGallerySessionDialog />
       <NewCanvasSessionDialog />
+      <ImageContextMenu />
     </ErrorBoundary>
   );
 };

invokeai/frontend/web/src/app/components/GlobalImageHotkeys.tsx

@@ -1,6 +1,7 @@
 import { skipToken } from '@reduxjs/toolkit/query';
 import { useAppSelector } from 'app/store/storeHooks';
 import { useIsRegionFocused } from 'common/hooks/focus';
+import { useAssertSingleton } from 'common/hooks/useAssertSingleton';
 import { selectIsStaging } from 'features/controlLayers/store/canvasStagingAreaSlice';
 import { useImageActions } from 'features/gallery/hooks/useImageActions';
 import { selectLastSelectedImage } from 'features/gallery/store/gallerySelectors';
@@ -11,6 +12,7 @@ import { useGetImageDTOQuery } from 'services/api/endpoints/images';
 import type { ImageDTO } from 'services/api/types';
 
 export const GlobalImageHotkeys = memo(() => {
+  useAssertSingleton('GlobalImageHotkeys');
   const lastSelectedImage = useAppSelector(selectLastSelectedImage);
   const { currentData: imageDTO } = useGetImageDTOQuery(lastSelectedImage?.image_name ?? skipToken);
 

invokeai/frontend/web/src/app/components/InvokeAIUI.tsx

@@ -2,6 +2,8 @@ import 'i18n';
 
 import type { Middleware } from '@reduxjs/toolkit';
 import type { StudioInitAction } from 'app/hooks/useStudioInitAction';
+import type { LoggingOverrides } from 'app/logging/logger';
+import { $loggingOverrides, configureLogging } from 'app/logging/logger';
 import { $authToken } from 'app/store/nanostores/authToken';
 import { $baseUrl } from 'app/store/nanostores/baseUrl';
 import { $customNavComponent } from 'app/store/nanostores/customNavComponent';
@@ -20,7 +22,7 @@ import Loading from 'common/components/Loading/Loading';
 import AppDndContext from 'features/dnd/components/AppDndContext';
 import type { WorkflowCategory } from 'features/nodes/types/workflow';
 import type { PropsWithChildren, ReactNode } from 'react';
-import React, { lazy, memo, useEffect, useMemo } from 'react';
+import React, { lazy, memo, useEffect, useLayoutEffect, useMemo } from 'react';
 import { Provider } from 'react-redux';
 import { addMiddleware, resetMiddlewares } from 'redux-dynamic-middlewares';
 import { $socketOptions } from 'services/events/stores';
@@ -46,6 +48,7 @@ interface Props extends PropsWithChildren {
   isDebugging?: boolean;
   logo?: ReactNode;
   workflowCategories?: WorkflowCategory[];
+  loggingOverrides?: LoggingOverrides;
 }
 
 const InvokeAIUI = ({
@@ -65,7 +68,26 @@ const InvokeAIUI = ({
   isDebugging = false,
   logo,
   workflowCategories,
+  loggingOverrides,
 }: Props) => {
+  useLayoutEffect(() => {
+    /*
+     * We need to configure logging before anything else happens - useLayoutEffect ensures we set this at the first
+     * possible opportunity.
+     *
+     * Once redux initializes, we will check the user's settings and update the logging config accordingly. See
+     * `useSyncLoggingConfig`.
+     */
+    $loggingOverrides.set(loggingOverrides);
+
+    // Until we get the user's settings, we will use the overrides OR default values.
+    configureLogging(
+      loggingOverrides?.logIsEnabled ?? true,
+      loggingOverrides?.logLevel ?? 'debug',
+      loggingOverrides?.logNamespaces ?? '*'
+    );
+  }, [loggingOverrides]);
+
   useEffect(() => {
     // configure API client token
     if (token) {

invokeai/frontend/web/src/app/hooks/useStudioInitAction.ts

@@ -12,7 +12,7 @@ import { parseAndRecallAllMetadata } from 'features/metadata/util/handlers';
 import { $isWorkflowListMenuIsOpen } from 'features/nodes/store/workflowListMenu';
 import { $isStylePresetsMenuOpen, activeStylePresetIdChanged } from 'features/stylePresets/store/stylePresetSlice';
 import { toast } from 'features/toast/toast';
-import { setActiveTab } from 'features/ui/store/uiSlice';
+import { activeTabCanvasRightPanelChanged, setActiveTab } from 'features/ui/store/uiSlice';
 import { useGetAndLoadLibraryWorkflow } from 'features/workflowLibrary/hooks/useGetAndLoadLibraryWorkflow';
 import { useCallback, useEffect, useRef } from 'react';
 import { useTranslation } from 'react-i18next';
@@ -140,6 +140,7 @@ export const useStudioInitAction = (action?: StudioInitAction) => {
         case 'generation':
           // Go to the canvas tab, open the image viewer, and enable send-to-gallery mode
           store.dispatch(setActiveTab('canvas'));
+          store.dispatch(activeTabCanvasRightPanelChanged('gallery'));
           store.dispatch(settingsSendToCanvasChanged(false));
           $imageViewer.set(true);
           break;

invokeai/frontend/web/src/app/logging/logger.ts

@@ -9,11 +9,10 @@ const serializeMessage: MessageSerializer = (message) => {
 };
 
 ROARR.serializeMessage = serializeMessage;
-ROARR.write = createLogWriter();
 
-export const BASE_CONTEXT = {};
+const BASE_CONTEXT = {};
 
-export const $logger = atom<Logger>(Roarr.child(BASE_CONTEXT));
+const $logger = atom<Logger>(Roarr.child(BASE_CONTEXT));
 
 export const zLogNamespace = z.enum([
   'canvas',
@@ -35,8 +34,22 @@ export const zLogLevel = z.enum(['trace', 'debug', 'info', 'warn', 'error', 'fat
 export type LogLevel = z.infer<typeof zLogLevel>;
 export const isLogLevel = (v: unknown): v is LogLevel => zLogLevel.safeParse(v).success;
 
+/**
+ * Override logging settings.
+ * @property logIsEnabled Override the enabled log state. Omit to use the user's settings.
+ * @property logNamespaces Override the enabled log namespaces. Use `"*"` for all namespaces. Omit to use the user's settings.
+ * @property logLevel Override the log level. Omit to use the user's settings.
+ */
+export type LoggingOverrides = {
+  logIsEnabled?: boolean;
+  logNamespaces?: LogNamespace[] | '*';
+  logLevel?: LogLevel;
+};
+
+export const $loggingOverrides = atom<LoggingOverrides | undefined>();
+
 // Translate human-readable log levels to numbers, used for log filtering
-export const LOG_LEVEL_MAP: Record<LogLevel, number> = {
+const LOG_LEVEL_MAP: Record<LogLevel, number> = {
   trace: 10,
   debug: 20,
   info: 30,
@@ -44,3 +57,40 @@ export const LOG_LEVEL_MAP: Record<LogLevel, number> = {
   error: 50,
   fatal: 60,
 };
+
+/**
+ * Configure logging, pushing settings to local storage.
+ *
+ * @param logIsEnabled Whether logging is enabled
+ * @param logLevel The log level
+ * @param logNamespaces A list of log namespaces to enable, or '*' to enable all
+ */
+export const configureLogging = (
+  logIsEnabled: boolean = true,
+  logLevel: LogLevel = 'warn',
+  logNamespaces: LogNamespace[] | '*'
+): void => {
+  if (!logIsEnabled) {
+    // Disable console log output
+    localStorage.setItem('ROARR_LOG', 'false');
+  } else {
+    // Enable console log output
+    localStorage.setItem('ROARR_LOG', 'true');
+
+    // Use a filter to show only logs of the given level
+    let filter = `context.logLevel:>=${LOG_LEVEL_MAP[logLevel]}`;
+
+    const namespaces = logNamespaces === '*' ? zLogNamespace.options : logNamespaces;
+
+    if (namespaces.length > 0) {
+      filter += ` AND (${namespaces.map((ns) => `context.namespace:${ns}`).join(' OR ')})`;
+    } else {
+      // This effectively hides all logs because we use namespaces for all logs
+      filter += ' AND context.namespace:undefined';
+    }
+
+    localStorage.setItem('ROARR_FILTER', filter);
+  }
+
+  ROARR.write = createLogWriter();
+};

invokeai/frontend/web/src/app/logging/useLogger.ts

@@ -1,53 +1,9 @@
-import { createLogWriter } from '@roarr/browser-log-writer';
-import { useAppSelector } from 'app/store/storeHooks';
-import {
-  selectSystemLogIsEnabled,
-  selectSystemLogLevel,
-  selectSystemLogNamespaces,
-} from 'features/system/store/systemSlice';
-import { useEffect, useMemo } from 'react';
-import { ROARR, Roarr } from 'roarr';
+import { useMemo } from 'react';
 
 import type { LogNamespace } from './logger';
-import { $logger, BASE_CONTEXT, LOG_LEVEL_MAP, logger } from './logger';
+import { logger } from './logger';
 
 export const useLogger = (namespace: LogNamespace) => {
-  const logLevel = useAppSelector(selectSystemLogLevel);
-  const logNamespaces = useAppSelector(selectSystemLogNamespaces);
-  const logIsEnabled = useAppSelector(selectSystemLogIsEnabled);
-
-  // The provided Roarr browser log writer uses localStorage to config logging to console
-  useEffect(() => {
-    if (logIsEnabled) {
-      // Enable console log output
-      localStorage.setItem('ROARR_LOG', 'true');
-
-      // Use a filter to show only logs of the given level
-      let filter = `context.logLevel:>=${LOG_LEVEL_MAP[logLevel]}`;
-      if (logNamespaces.length > 0) {
-        filter += ` AND (${logNamespaces.map((ns) => `context.namespace:${ns}`).join(' OR ')})`;
-      } else {
-        filter += ' AND context.namespace:undefined';
-      }
-      localStorage.setItem('ROARR_FILTER', filter);
-    } else {
-      // Disable console log output
-      localStorage.setItem('ROARR_LOG', 'false');
-    }
-    ROARR.write = createLogWriter();
-  }, [logLevel, logIsEnabled, logNamespaces]);
-
-  // Update the module-scoped logger context as needed
-  useEffect(() => {
-    // TODO: type this properly
-    //eslint-disable-next-line @typescript-eslint/no-explicit-any
-    const newContext: Record<string, any> = {
-      ...BASE_CONTEXT,
-    };
-
-    $logger.set(Roarr.child(newContext));
-  }, []);
-
   const log = useMemo(() => logger(namespace), [namespace]);
 
   return log;

invokeai/frontend/web/src/app/logging/useSyncLoggingConfig.ts

@@ -0,0 +1,43 @@
+import { useStore } from '@nanostores/react';
+import { $loggingOverrides, configureLogging } from 'app/logging/logger';
+import { useAppSelector } from 'app/store/storeHooks';
+import { useAssertSingleton } from 'common/hooks/useAssertSingleton';
+import {
+  selectSystemLogIsEnabled,
+  selectSystemLogLevel,
+  selectSystemLogNamespaces,
+} from 'features/system/store/systemSlice';
+import { useLayoutEffect } from 'react';
+
+/**
+ * This hook synchronizes the logging configuration stored in Redux with the logging system, which uses localstorage.
+ *
+ * The sync is one-way: from Redux to localstorage. This means that changes made in the UI will be reflected in the
+ * logging system, but changes made directly to localstorage will not be reflected in the UI.
+ *
+ * See {@link configureLogging}
+ */
+export const useSyncLoggingConfig = () => {
+  useAssertSingleton('useSyncLoggingConfig');
+
+  const loggingOverrides = useStore($loggingOverrides);
+
+  const logLevel = useAppSelector(selectSystemLogLevel);
+  const logNamespaces = useAppSelector(selectSystemLogNamespaces);
+  const logIsEnabled = useAppSelector(selectSystemLogIsEnabled);
+
+  useLayoutEffect(() => {
+    configureLogging(
+      loggingOverrides?.logIsEnabled ?? logIsEnabled,
+      loggingOverrides?.logLevel ?? logLevel,
+      loggingOverrides?.logNamespaces ?? logNamespaces
+    );
+  }, [
+    logIsEnabled,
+    logLevel,
+    logNamespaces,
+    loggingOverrides?.logIsEnabled,
+    loggingOverrides?.logLevel,
+    loggingOverrides?.logNamespaces,
+  ]);
+};

invokeai/frontend/web/src/app/store/constants.ts

@@ -1,3 +1,4 @@
 export const STORAGE_PREFIX = '@@invokeai-';
 export const EMPTY_ARRAY = [];
+/** @knipignore */
 export const EMPTY_OBJECT = {};

invokeai/frontend/web/src/app/store/middleware/debugLoggerMiddleware.ts

@@ -7,12 +7,20 @@ import { diff } from 'jsondiffpatch';
 /**
  * Super simple logger middleware. Useful for debugging when the redux devtools are awkward.
  */
-export const debugLoggerMiddleware: Middleware = (api: MiddlewareAPI) => (next) => (action) => {
-  const originalState = api.getState();
-  console.log('REDUX: dispatching', action);
-  const result = next(action);
-  const nextState = api.getState();
-  console.log('REDUX: next state', nextState);
-  console.log('REDUX: diff', diff(originalState, nextState));
-  return result;
-};
+export const getDebugLoggerMiddleware =
+  (options?: { withDiff?: boolean; withNextState?: boolean }): Middleware =>
+  (api: MiddlewareAPI) =>
+  (next) =>
+  (action) => {
+    const originalState = api.getState();
+    console.log('REDUX: dispatching', action);
+    const result = next(action);
+    const nextState = api.getState();
+    if (options?.withNextState) {
+      console.log('REDUX: next state', nextState);
+    }
+    if (options?.withDiff) {
+      console.log('REDUX: diff', diff(originalState, nextState));
+    }
+    return result;
+  };

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/addArchivedOrDeletedBoardListener.ts

@@ -29,13 +29,13 @@ export const addArchivedOrDeletedBoardListener = (startAppListening: AppStartLis
       const { autoAddBoardId, selectedBoardId } = state.gallery;
 
       // If the deleted board was currently selected, we should reset the selected board to uncategorized
-      if (deletedBoardId === selectedBoardId) {
+      if (selectedBoardId !== 'none' && deletedBoardId === selectedBoardId) {
         dispatch(boardIdSelected({ boardId: 'none' }));
         dispatch(galleryViewChanged('images'));
       }
 
       // If the deleted board was selected for auto-add, we should reset the auto-add board to uncategorized
-      if (deletedBoardId === autoAddBoardId) {
+      if (autoAddBoardId !== 'none' && deletedBoardId === autoAddBoardId) {
         dispatch(autoAddBoardIdChanged('none'));
       }
     },
@@ -46,11 +46,11 @@ export const addArchivedOrDeletedBoardListener = (startAppListening: AppStartLis
     matcher: boardsApi.endpoints.updateBoard.matchFulfilled,
     effect: (action, { dispatch, getState }) => {
       const state = getState();
-      const { shouldShowArchivedBoards } = state.gallery;
+      const { shouldShowArchivedBoards, selectedBoardId, autoAddBoardId } = state.gallery;
 
       const wasArchived = action.meta.arg.originalArgs.changes.archived === true;
 
-      if (wasArchived && !shouldShowArchivedBoards) {
+      if (selectedBoardId !== 'none' && autoAddBoardId !== 'none' && wasArchived && !shouldShowArchivedBoards) {
         dispatch(autoAddBoardIdChanged('none'));
         dispatch(boardIdSelected({ boardId: 'none' }));
         dispatch(galleryViewChanged('images'));
@@ -80,7 +80,7 @@ export const addArchivedOrDeletedBoardListener = (startAppListening: AppStartLis
 
       // Handle the case where selected board is archived
       const selectedBoard = queryResult.data.find((b) => b.board_id === selectedBoardId);
-      if (!selectedBoard || selectedBoard.archived) {
+      if (selectedBoardId !== 'none' && (!selectedBoard || selectedBoard.archived)) {
         // If we can't find the selected board or it's archived, we should reset the selected board to uncategorized
         dispatch(boardIdSelected({ boardId: 'none' }));
         dispatch(galleryViewChanged('images'));
@@ -88,7 +88,7 @@ export const addArchivedOrDeletedBoardListener = (startAppListening: AppStartLis
 
       // Handle the case where auto-add board is archived
       const autoAddBoard = queryResult.data.find((b) => b.board_id === autoAddBoardId);
-      if (!autoAddBoard || autoAddBoard.archived) {
+      if (autoAddBoardId !== 'none' && (!autoAddBoard || autoAddBoard.archived)) {
         // If we can't find the auto-add board or it's archived, we should reset the selected board to uncategorized
         dispatch(autoAddBoardIdChanged('none'));
       }
@@ -106,13 +106,13 @@ export const addArchivedOrDeletedBoardListener = (startAppListening: AppStartLis
       const { selectedBoardId, autoAddBoardId } = state.gallery;
 
       // Handle the case where selected board isn't in the list of boards
-      if (!boards.find((b) => b.board_id === selectedBoardId)) {
+      if (selectedBoardId !== 'none' && !boards.find((b) => b.board_id === selectedBoardId)) {
         dispatch(boardIdSelected({ boardId: 'none' }));
         dispatch(galleryViewChanged('images'));
       }
 
       // Handle the case where auto-add board isn't in the list of boards
-      if (!boards.find((b) => b.board_id === autoAddBoardId)) {
+      if (autoAddBoardId !== 'none' && !boards.find((b) => b.board_id === autoAddBoardId)) {
         dispatch(autoAddBoardIdChanged('none'));
       }
     },

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/imageDropped.ts

@@ -8,6 +8,7 @@ import {
   controlLayerAdded,
   entityRasterized,
   entitySelected,
+  inpaintMaskAdded,
   rasterLayerAdded,
   referenceImageAdded,
   referenceImageIPAdapterImageChanged,
@@ -17,6 +18,7 @@ import {
 import { selectCanvasSlice } from 'features/controlLayers/store/selectors';
 import type {
   CanvasControlLayerState,
+  CanvasInpaintMaskState,
   CanvasRasterLayerState,
   CanvasReferenceImageState,
   CanvasRegionalGuidanceState,
@@ -110,6 +112,46 @@ export const addImageDroppedListener = (startAppListening: AppStartListening) =>
         return;
       }
 
+      /**
+
+      /**
+       * Image dropped on Inpaint Mask
+       */
+      if (
+        overData.actionType === 'ADD_INPAINT_MASK_FROM_IMAGE' &&
+        activeData.payloadType === 'IMAGE_DTO' &&
+        activeData.payload.imageDTO
+      ) {
+        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
+        const { x, y } = selectCanvasSlice(getState()).bbox.rect;
+        const overrides: Partial<CanvasInpaintMaskState> = {
+          objects: [imageObject],
+          position: { x, y },
+        };
+        dispatch(inpaintMaskAdded({ overrides, isSelected: true }));
+        return;
+      }
+
+      /**
+
+      /**
+       * Image dropped on Regional Guidance
+       */
+      if (
+        overData.actionType === 'ADD_REGIONAL_GUIDANCE_FROM_IMAGE' &&
+        activeData.payloadType === 'IMAGE_DTO' &&
+        activeData.payload.imageDTO
+      ) {
+        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
+        const { x, y } = selectCanvasSlice(getState()).bbox.rect;
+        const overrides: Partial<CanvasRegionalGuidanceState> = {
+          objects: [imageObject],
+          position: { x, y },
+        };
+        dispatch(rgAdded({ overrides, isSelected: true }));
+        return;
+      }
+
       /**
        * Image dropped on Raster layer
        */

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/imageUploaded.ts

@@ -1,5 +1,6 @@
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
+import type { RootState } from 'app/store/store';
 import {
   entityRasterized,
   entitySelected,
@@ -20,24 +21,39 @@ import { imagesApi } from 'services/api/endpoints/images';
 
 const log = logger('gallery');
 
+/**
+ * Gets the description for the toast that is shown when an image is uploaded.
+ * @param boardId The board id of the uploaded image
+ * @param state The current state of the app
+ * @returns
+ */
+const getUploadedToastDescription = (boardId: string, state: RootState) => {
+  if (boardId === 'none') {
+    return t('toast.addedToUncategorized');
+  }
+  // Attempt to get the board's name for the toast
+  const queryArgs = selectListBoardsQueryArgs(state);
+  const { data } = boardsApi.endpoints.listAllBoards.select(queryArgs)(state);
+  // Fall back to just the board id if we can't find the board for some reason
+  const board = data?.find((b) => b.board_id === boardId);
+
+  return t('toast.addedToBoard', { name: board?.board_name ?? boardId });
+};
+
+let lastUploadedToastTimeout: number | null = null;
+
 export const addImageUploadedFulfilledListener = (startAppListening: AppStartListening) => {
   startAppListening({
     matcher: imagesApi.endpoints.uploadImage.matchFulfilled,
     effect: (action, { dispatch, getState }) => {
       const imageDTO = action.payload;
       const state = getState();
-      const { autoAddBoardId } = state.gallery;
 
       log.debug({ imageDTO }, 'Image uploaded');
 
       const { postUploadAction } = action.meta.arg.originalArgs;
 
-      if (
-        // No further actions needed for intermediate images,
-        action.payload.is_intermediate &&
-        // unless they have an explicit post-upload action
-        !postUploadAction
-      ) {
+      if (!postUploadAction) {
         return;
       }
 
@@ -48,42 +64,40 @@ export const addImageUploadedFulfilledListener = (startAppListening: AppStartLis
       } as const;
 
       // default action - just upload and alert user
-      if (postUploadAction?.type === 'TOAST') {
-        if (!autoAddBoardId || autoAddBoardId === 'none') {
-          const title = postUploadAction.title || DEFAULT_UPLOADED_TOAST.title;
-          toast({ ...DEFAULT_UPLOADED_TOAST, title });
-          dispatch(boardIdSelected({ boardId: 'none' }));
-          dispatch(galleryViewChanged('assets'));
-        } else {
-          // Add this image to the board
-          dispatch(
-            imagesApi.endpoints.addImageToBoard.initiate({
-              board_id: autoAddBoardId,
-              imageDTO,
-            })
-          );
-
-          // Attempt to get the board's name for the toast
-          const queryArgs = selectListBoardsQueryArgs(state);
-          const { data } = boardsApi.endpoints.listAllBoards.select(queryArgs)(state);
-
-          // Fall back to just the board id if we can't find the board for some reason
-          const board = data?.find((b) => b.board_id === autoAddBoardId);
-          const description = board
-            ? `${t('toast.addedToBoard')} ${board.board_name}`
-            : `${t('toast.addedToBoard')} ${autoAddBoardId}`;
-
-          toast({
-            ...DEFAULT_UPLOADED_TOAST,
-            description,
-          });
-          dispatch(boardIdSelected({ boardId: autoAddBoardId }));
+      if (postUploadAction.type === 'TOAST') {
+        const boardId = imageDTO.board_id ?? 'none';
+        if (lastUploadedToastTimeout !== null) {
+          window.clearTimeout(lastUploadedToastTimeout);
+        }
+        const toastApi = toast({
+          ...DEFAULT_UPLOADED_TOAST,
+          title: postUploadAction.title || DEFAULT_UPLOADED_TOAST.title,
+          description: getUploadedToastDescription(boardId, state),
+          duration: null, // we will close the toast manually
+        });
+        lastUploadedToastTimeout = window.setTimeout(() => {
+          toastApi.close();
+        }, 3000);
+        /**
+         * We only want to change the board and view if this is the first upload of a batch, else we end up hijacking
+         * the user's gallery board and view selection:
+         * - User uploads multiple images
+         * - A couple uploads finish, but others are pending still
+         * - User changes the board selection
+         * - Pending uploads finish and change the board back to the original board
+         * - User is confused as to why the board changed
+         *
+         * Default to true to not require _all_ image upload handlers to set this value
+         */
+        const isFirstUploadOfBatch = action.meta.arg.originalArgs.isFirstUploadOfBatch ?? true;
+        if (isFirstUploadOfBatch) {
+          dispatch(boardIdSelected({ boardId }));
           dispatch(galleryViewChanged('assets'));
         }
         return;
       }
 
-      if (postUploadAction?.type === 'SET_UPSCALE_INITIAL_IMAGE') {
+      if (postUploadAction.type === 'SET_UPSCALE_INITIAL_IMAGE') {
         dispatch(upscaleInitialImageChanged(imageDTO));
         toast({
           ...DEFAULT_UPLOADED_TOAST,
@@ -92,21 +106,14 @@ export const addImageUploadedFulfilledListener = (startAppListening: AppStartLis
         return;
       }
 
-      // if (postUploadAction?.type === 'SET_CA_IMAGE') {
-      //   const { id } = postUploadAction;
-      //   dispatch(caImageChanged({ id, imageDTO }));
-      //   toast({ ...DEFAULT_UPLOADED_TOAST, description: t('toast.setControlImage') });
-      //   return;
-      // }
-
-      if (postUploadAction?.type === 'SET_IPA_IMAGE') {
+      if (postUploadAction.type === 'SET_IPA_IMAGE') {
         const { id } = postUploadAction;
         dispatch(referenceImageIPAdapterImageChanged({ entityIdentifier: { id, type: 'reference_image' }, imageDTO }));
         toast({ ...DEFAULT_UPLOADED_TOAST, description: t('toast.setControlImage') });
         return;
       }
 
-      if (postUploadAction?.type === 'SET_RG_IP_ADAPTER_IMAGE') {
+      if (postUploadAction.type === 'SET_RG_IP_ADAPTER_IMAGE') {
         const { id, referenceImageId } = postUploadAction;
         dispatch(
           rgIPAdapterImageChanged({ entityIdentifier: { id, type: 'regional_guidance' }, referenceImageId, imageDTO })
@@ -115,14 +122,14 @@ export const addImageUploadedFulfilledListener = (startAppListening: AppStartLis
         return;
       }
 
-      if (postUploadAction?.type === 'SET_NODES_IMAGE') {
+      if (postUploadAction.type === 'SET_NODES_IMAGE') {
         const { nodeId, fieldName } = postUploadAction;
         dispatch(fieldImageValueChanged({ nodeId, fieldName, value: imageDTO }));
         toast({ ...DEFAULT_UPLOADED_TOAST, description: `${t('toast.setNodeField')} ${fieldName}` });
         return;
       }
 
-      if (postUploadAction?.type === 'REPLACE_LAYER_WITH_IMAGE') {
+      if (postUploadAction.type === 'REPLACE_LAYER_WITH_IMAGE') {
         const { entityIdentifier } = postUploadAction;
 
         const state = getState();

invokeai/frontend/web/src/app/types/invokeai.ts

@@ -1,7 +1,7 @@
 import type { FilterType } from 'features/controlLayers/store/filters';
 import type { ParameterPrecision, ParameterScheduler } from 'features/parameters/types/parameterSchemas';
 import type { TabName } from 'features/ui/store/uiTypes';
-import type { O } from 'ts-toolbelt';
+import type { PartialDeep } from 'type-fest';
 
 /**
  * A disable-able application feature
@@ -79,6 +79,7 @@ export type AppConfig = {
   metadataFetchDebounce?: number;
   workflowFetchDebounce?: number;
   isLocal?: boolean;
+  maxImageUploadCount?: number;
   sd: {
     defaultModel?: string;
     disabledControlNetModels: string[];
@@ -118,4 +119,4 @@ export type AppConfig = {
   };
 };
 
-export type PartialAppConfig = O.Partial<AppConfig, 'deep'>;
+export type PartialAppConfig = PartialDeep<AppConfig>;

invokeai/frontend/web/src/common/components/IAIDndImage.tsx

@@ -4,9 +4,9 @@ import { IAILoadingImageFallback, IAINoContentFallback } from 'common/components
 import ImageMetadataOverlay from 'common/components/ImageMetadataOverlay';
 import { useImageUploadButton } from 'common/hooks/useImageUploadButton';
 import type { TypesafeDraggableData, TypesafeDroppableData } from 'features/dnd/types';
-import ImageContextMenu from 'features/gallery/components/ImageContextMenu/ImageContextMenu';
+import { useImageContextMenu } from 'features/gallery/components/ImageContextMenu/ImageContextMenu';
 import type { MouseEvent, ReactElement, ReactNode, SyntheticEvent } from 'react';
-import { memo, useCallback, useMemo } from 'react';
+import { memo, useCallback, useMemo, useRef } from 'react';
 import { PiImageBold, PiUploadSimpleBold } from 'react-icons/pi';
 import type { ImageDTO, PostUploadAction } from 'services/api/types';
 
@@ -17,7 +17,14 @@ const defaultUploadElement = <Icon as={PiUploadSimpleBold} boxSize={16} />;
 
 const defaultNoContentFallback = <IAINoContentFallback icon={PiImageBold} />;
 
+const baseStyles: SystemStyleObject = {
+  touchAction: 'none',
+  userSelect: 'none',
+  webkitUserSelect: 'none',
+};
+
 const sx: SystemStyleObject = {
+  ...baseStyles,
   '.gallery-image-container::before': {
     content: '""',
     display: 'inline-block',
@@ -102,59 +109,10 @@ const IAIDndImage = (props: IAIDndImageProps) => {
     useThumbailFallback,
     withHoverOverlay = false,
     children,
-    onMouseOver,
-    onMouseOut,
     dataTestId,
     ...rest
   } = props;
 
-  const handleMouseOver = useCallback(
-    (e: MouseEvent<HTMLDivElement>) => {
-      if (onMouseOver) {
-        onMouseOver(e);
-      }
-    },
-    [onMouseOver]
-  );
-  const handleMouseOut = useCallback(
-    (e: MouseEvent<HTMLDivElement>) => {
-      if (onMouseOut) {
-        onMouseOut(e);
-      }
-    },
-    [onMouseOut]
-  );
-
-  const { getUploadButtonProps, getUploadInputProps } = useImageUploadButton({
-    postUploadAction,
-    isDisabled: isUploadDisabled,
-  });
-
-  const uploadButtonStyles = useMemo<SystemStyleObject>(() => {
-    const styles: SystemStyleObject = {
-      minH: minSize,
-      w: 'full',
-      h: 'full',
-      alignItems: 'center',
-      justifyContent: 'center',
-      borderRadius: 'base',
-      transitionProperty: 'common',
-      transitionDuration: '0.1s',
-      color: 'base.500',
-    };
-    if (!isUploadDisabled) {
-      Object.assign(styles, {
-        cursor: 'pointer',
-        bg: 'base.700',
-        _hover: {
-          bg: 'base.650',
-          color: 'base.300',
-        },
-      });
-    }
-    return styles;
-  }, [isUploadDisabled, minSize]);
-
   const openInNewTab = useCallback(
     (e: MouseEvent) => {
       if (!imageDTO) {
@@ -168,76 +126,126 @@ const IAIDndImage = (props: IAIDndImageProps) => {
     [imageDTO]
   );
 
+  const ref = useRef<HTMLDivElement>(null);
+  useImageContextMenu(imageDTO, ref);
+
   return (
-    <ImageContextMenu imageDTO={imageDTO}>
-      {(ref) => (
+    <Flex
+      ref={ref}
+      width="full"
+      height="full"
+      alignItems="center"
+      justifyContent="center"
+      position="relative"
+      minW={minSize ? minSize : undefined}
+      minH={minSize ? minSize : undefined}
+      userSelect="none"
+      cursor={isDragDisabled || !imageDTO ? 'default' : 'pointer'}
+      sx={withHoverOverlay ? sx : baseStyles}
+      data-selected={isSelectedForCompare ? 'selectedForCompare' : isSelected ? 'selected' : undefined}
+      {...rest}
+    >
+      {imageDTO && (
         <Flex
-          ref={ref}
-          onMouseOver={handleMouseOver}
-          onMouseOut={handleMouseOut}
-          width="full"
-          height="full"
+          className="gallery-image-container"
+          w="full"
+          h="full"
+          position={fitContainer ? 'absolute' : 'relative'}
           alignItems="center"
           justifyContent="center"
-          position="relative"
-          minW={minSize ? minSize : undefined}
-          minH={minSize ? minSize : undefined}
-          userSelect="none"
-          cursor={isDragDisabled || !imageDTO ? 'default' : 'pointer'}
-          sx={withHoverOverlay ? sx : undefined}
-          data-selected={isSelectedForCompare ? 'selectedForCompare' : isSelected ? 'selected' : undefined}
-          {...rest}
         >
-          {imageDTO && (
-            <Flex
-              className="gallery-image-container"
-              w="full"
-              h="full"
-              position={fitContainer ? 'absolute' : 'relative'}
-              alignItems="center"
-              justifyContent="center"
-            >
-              <Image
-                src={thumbnail ? imageDTO.thumbnail_url : imageDTO.image_url}
-                fallbackStrategy="beforeLoadOrError"
-                fallbackSrc={useThumbailFallback ? imageDTO.thumbnail_url : undefined}
-                fallback={useThumbailFallback ? undefined : <IAILoadingImageFallback image={imageDTO} />}
-                onError={onError}
-                draggable={false}
-                w={imageDTO.width}
-                objectFit="contain"
-                maxW="full"
-                maxH="full"
-                borderRadius="base"
-                sx={imageSx}
-                data-testid={dataTestId}
-              />
-              {withMetadataOverlay && <ImageMetadataOverlay imageDTO={imageDTO} />}
-            </Flex>
-          )}
-          {!imageDTO && !isUploadDisabled && (
-            <>
-              <Flex sx={uploadButtonStyles} {...getUploadButtonProps()}>
-                <input {...getUploadInputProps()} />
-                {uploadElement}
-              </Flex>
-            </>
-          )}
-          {!imageDTO && isUploadDisabled && noContentFallback}
-          {imageDTO && !isDragDisabled && (
-            <IAIDraggable
-              data={draggableData}
-              disabled={isDragDisabled || !imageDTO}
-              onClick={onClick}
-              onAuxClick={openInNewTab}
-            />
-          )}
-          {children}
-          {!isDropDisabled && <IAIDroppable data={droppableData} disabled={isDropDisabled} dropLabel={dropLabel} />}
+          <Image
+            src={thumbnail ? imageDTO.thumbnail_url : imageDTO.image_url}
+            fallbackStrategy="beforeLoadOrError"
+            fallbackSrc={useThumbailFallback ? imageDTO.thumbnail_url : undefined}
+            fallback={useThumbailFallback ? undefined : <IAILoadingImageFallback image={imageDTO} />}
+            onError={onError}
+            draggable={false}
+            w={imageDTO.width}
+            objectFit="contain"
+            maxW="full"
+            maxH="full"
+            borderRadius="base"
+            sx={imageSx}
+            data-testid={dataTestId}
+          />
+          {withMetadataOverlay && <ImageMetadataOverlay imageDTO={imageDTO} />}
         </Flex>
       )}
-    </ImageContextMenu>
+      {!imageDTO && !isUploadDisabled && (
+        <UploadButton
+          isUploadDisabled={isUploadDisabled}
+          postUploadAction={postUploadAction}
+          uploadElement={uploadElement}
+          minSize={minSize}
+        />
+      )}
+      {!imageDTO && isUploadDisabled && noContentFallback}
+      {imageDTO && !isDragDisabled && (
+        <IAIDraggable
+          data={draggableData}
+          disabled={isDragDisabled || !imageDTO}
+          onClick={onClick}
+          onAuxClick={openInNewTab}
+        />
+      )}
+      {children}
+      {!isDropDisabled && <IAIDroppable data={droppableData} disabled={isDropDisabled} dropLabel={dropLabel} />}
+    </Flex>
   );
 };
 
 export default memo(IAIDndImage);
+
+const UploadButton = memo(
+  ({
+    isUploadDisabled,
+    postUploadAction,
+    uploadElement,
+    minSize,
+  }: {
+    isUploadDisabled: boolean;
+    postUploadAction?: PostUploadAction;
+    uploadElement: ReactNode;
+    minSize: number;
+  }) => {
+    const { getUploadButtonProps, getUploadInputProps } = useImageUploadButton({
+      postUploadAction,
+      isDisabled: isUploadDisabled,
+    });
+
+    const uploadButtonStyles = useMemo<SystemStyleObject>(() => {
+      const styles: SystemStyleObject = {
+        minH: minSize,
+        w: 'full',
+        h: 'full',
+        alignItems: 'center',
+        justifyContent: 'center',
+        borderRadius: 'base',
+        transitionProperty: 'common',
+        transitionDuration: '0.1s',
+        color: 'base.500',
+      };
+      if (!isUploadDisabled) {
+        Object.assign(styles, {
+          cursor: 'pointer',
+          bg: 'base.700',
+          _hover: {
+            bg: 'base.650',
+            color: 'base.300',
+          },
+        });
+      }
+      return styles;
+    }, [isUploadDisabled, minSize]);
+
+    return (
+      <Flex sx={uploadButtonStyles} {...getUploadButtonProps()}>
+        <input {...getUploadInputProps()} />
+        {uploadElement}
+      </Flex>
+    );
+  }
+);
+
+UploadButton.displayName = 'UploadButton';

invokeai/frontend/web/src/common/components/IAIDropOverlay.tsx

@@ -1,15 +1,14 @@
 import { Flex, Text } from '@invoke-ai/ui-library';
 import { memo } from 'react';
-import { useTranslation } from 'react-i18next';
 
 type Props = {
   isOver: boolean;
   label?: string;
+  withBackdrop?: boolean;
 };
 
 const IAIDropOverlay = (props: Props) => {
-  const { t } = useTranslation();
-  const { isOver, label = t('gallery.drop') } = props;
+  const { isOver, label, withBackdrop = true } = props;
   return (
     <Flex position="absolute" top={0} right={0} bottom={0} left={0}>
       <Flex
@@ -20,7 +19,7 @@ const IAIDropOverlay = (props: Props) => {
         left={0}
         w="full"
         h="full"
-        bg="base.900"
+        bg={withBackdrop ? 'base.900' : 'transparent'}
         opacity={0.7}
         borderRadius="base"
         alignItems="center"
@@ -45,16 +44,18 @@ const IAIDropOverlay = (props: Props) => {
         alignItems="center"
         justifyContent="center"
       >
-        <Text
-          fontSize="lg"
-          fontWeight="semibold"
-          color={isOver ? 'invokeYellow.300' : 'base.500'}
-          transitionProperty="common"
-          transitionDuration="0.1s"
-          textAlign="center"
-        >
-          {label}
-        </Text>
+        {label && (
+          <Text
+            fontSize="lg"
+            fontWeight="semibold"
+            color={isOver ? 'invokeYellow.300' : 'base.500'}
+            transitionProperty="common"
+            transitionDuration="0.1s"
+            textAlign="center"
+          >
+            {label}
+          </Text>
+        )}
       </Flex>
     </Flex>
   );

invokeai/frontend/web/src/common/components/IconMenuItem.tsx

@@ -0,0 +1,34 @@
+import type { MenuItemProps } from '@invoke-ai/ui-library';
+import { Flex, MenuItem, Tooltip } from '@invoke-ai/ui-library';
+import type { ReactNode } from 'react';
+
+type Props = MenuItemProps & {
+  tooltip?: ReactNode;
+  icon: ReactNode;
+};
+
+export const IconMenuItem = ({ tooltip, icon, ...props }: Props) => {
+  return (
+    <Tooltip label={tooltip} placement="top" gutter={12}>
+      <MenuItem
+        display="flex"
+        alignItems="center"
+        justifyContent="center"
+        w="min-content"
+        aspectRatio="1"
+        borderRadius="base"
+        {...props}
+      >
+        {icon}
+      </MenuItem>
+    </Tooltip>
+  );
+};
+
+export const IconMenuItemGroup = ({ children }: { children: ReactNode }) => {
+  return (
+    <Flex gap={2} justifyContent="space-between">
+      {children}
+    </Flex>
+  );
+};

invokeai/frontend/web/src/common/components/ImageUploadOverlay.tsx

@@ -1,22 +1,12 @@
 import { Box, Flex, Heading } from '@invoke-ai/ui-library';
-import type { AnimationProps } from 'framer-motion';
-import { motion } from 'framer-motion';
+import { useAppSelector } from 'app/store/storeHooks';
+import { selectSelectedBoardId } from 'features/gallery/store/gallerySelectors';
+import { selectMaxImageUploadCount } from 'features/system/store/configSlice';
 import { memo } from 'react';
 import type { DropzoneState } from 'react-dropzone';
 import { useHotkeys } from 'react-hotkeys-hook';
 import { useTranslation } from 'react-i18next';
-
-const initial: AnimationProps['initial'] = {
-  opacity: 0,
-};
-const animate: AnimationProps['animate'] = {
-  opacity: 1,
-  transition: { duration: 0.1 },
-};
-const exit: AnimationProps['exit'] = {
-  opacity: 0,
-  transition: { duration: 0.1 },
-};
+import { useBoardName } from 'services/api/hooks/useBoardName';
 
 type ImageUploadOverlayProps = {
   dropzone: DropzoneState;
@@ -24,7 +14,6 @@ type ImageUploadOverlayProps = {
 };
 
 const ImageUploadOverlay = (props: ImageUploadOverlayProps) => {
-  const { t } = useTranslation();
   const { dropzone, setIsHandlingUpload } = props;
 
   useHotkeys(
@@ -36,67 +25,65 @@ const ImageUploadOverlay = (props: ImageUploadOverlayProps) => {
   );
 
   return (
-    <Box
-      key="image-upload-overlay"
-      initial={initial}
-      animate={animate}
-      exit={exit}
-      as={motion.div}
-      position="absolute"
-      top={0}
-      insetInlineStart={0}
-      width="100dvw"
-      height="100dvh"
-      zIndex={999}
-      backdropFilter="blur(20px)"
-    >
+    <Box position="absolute" top={0} right={0} bottom={0} left={0} zIndex={999} backdropFilter="blur(20px)">
+      <Flex position="absolute" top={0} right={0} bottom={0} left={0} bg="base.900" opacity={0.7} />
       <Flex
         position="absolute"
-        top={0}
-        insetInlineStart={0}
-        w="full"
-        h="full"
-        bg="base.900"
-        opacity={0.7}
-        alignItems="center"
-        justifyContent="center"
+        flexDir="column"
+        gap={4}
+        top={2}
+        right={2}
+        bottom={2}
+        left={2}
+        opacity={1}
+        borderWidth={2}
+        borderColor={dropzone.isDragAccept ? 'invokeYellow.300' : 'error.500'}
+        borderRadius="base"
+        borderStyle="dashed"
         transitionProperty="common"
         transitionDuration="0.1s"
-      />
-      <Flex
-        position="absolute"
-        top={0}
-        insetInlineStart={0}
-        width="full"
-        height="full"
         alignItems="center"
         justifyContent="center"
-        p={4}
+        color={dropzone.isDragReject ? 'error.300' : undefined}
       >
-        <Flex
-          width="full"
-          height="full"
-          alignItems="center"
-          justifyContent="center"
-          flexDir="column"
-          gap={4}
-          borderWidth={3}
-          borderRadius="xl"
-          borderStyle="dashed"
-          color="base.100"
-          borderColor="base.200"
-        >
-          {dropzone.isDragAccept ? (
-            <Heading size="lg">{t('gallery.dropToUpload')}</Heading>
-          ) : (
-            <>
-              <Heading size="lg">{t('toast.invalidUpload')}</Heading>
-              <Heading size="md">{t('toast.uploadFailedInvalidUploadDesc')}</Heading>
-            </>
-          )}
-        </Flex>
+        {dropzone.isDragAccept && <DragAcceptMessage />}
+        {!dropzone.isDragAccept && <DragRejectMessage />}
       </Flex>
     </Box>
   );
 };
 export default memo(ImageUploadOverlay);
+
+const DragAcceptMessage = () => {
+  const { t } = useTranslation();
+  const selectedBoardId = useAppSelector(selectSelectedBoardId);
+  const boardName = useBoardName(selectedBoardId);
+
+  return (
+    <>
+      <Heading size="lg">{t('gallery.dropToUpload')}</Heading>
+      <Heading size="md">{t('toast.imagesWillBeAddedTo', { boardName })}</Heading>
+    </>
+  );
+};
+
+const DragRejectMessage = () => {
+  const { t } = useTranslation();
+  const maxImageUploadCount = useAppSelector(selectMaxImageUploadCount);
+
+  if (maxImageUploadCount === undefined) {
+    return (
+      <>
+        <Heading size="lg">{t('toast.invalidUpload')}</Heading>
+        <Heading size="md">{t('toast.uploadFailedInvalidUploadDesc')}</Heading>
+      </>
+    );
+  }
+
+  return (
+    <>
+      <Heading size="lg">{t('toast.invalidUpload')}</Heading>
+      <Heading size="md">{t('toast.uploadFailedInvalidUploadDesc_withCount', { count: maxImageUploadCount })}</Heading>
+    </>
+  );
+};

invokeai/frontend/web/src/common/components/InformationalPopover/constants.ts

@@ -23,8 +23,10 @@ export type Feature =
   | 'dynamicPrompts'
   | 'dynamicPromptsMaxPrompts'
   | 'dynamicPromptsSeedBehaviour'
+  | 'globalReferenceImage'
   | 'imageFit'
   | 'infillMethod'
+  | 'inpainting'
   | 'ipAdapterMethod'
   | 'lora'
   | 'loraWeight'
@@ -46,6 +48,7 @@ export type Feature =
   | 'paramVAEPrecision'
   | 'paramWidth'
   | 'patchmatchDownScaleSize'
+  | 'rasterLayer'
   | 'refinerModel'
   | 'refinerNegativeAestheticScore'
   | 'refinerPositiveAestheticScore'
@@ -53,6 +56,9 @@ export type Feature =
   | 'refinerStart'
   | 'refinerSteps'
   | 'refinerCfgScale'
+  | 'regionalGuidance'
+  | 'regionalGuidanceAndReferenceImage'
+  | 'regionalReferenceImage'
   | 'scaleBeforeProcessing'
   | 'seamlessTilingXAxis'
   | 'seamlessTilingYAxis'
@@ -76,6 +82,24 @@ export const POPOVER_DATA: { [key in Feature]?: PopoverData } = {
   clipSkip: {
     href: 'https://support.invoke.ai/support/solutions/articles/151000178161-advanced-settings',
   },
+  inpainting: {
+    href: 'https://support.invoke.ai/support/solutions/articles/151000096702-inpainting-outpainting-and-bounding-box',
+  },
+  rasterLayer: {
+    href: 'https://support.invoke.ai/support/solutions/articles/151000094998-raster-layers-and-initial-images',
+  },
+  regionalGuidance: {
+    href: 'https://support.invoke.ai/support/solutions/articles/151000165024-regional-guidance-layers',
+  },
+  regionalGuidanceAndReferenceImage: {
+    href: 'https://support.invoke.ai/support/solutions/articles/151000165024-regional-guidance-layers',
+  },
+  globalReferenceImage: {
+    href: 'https://support.invoke.ai/support/solutions/articles/151000159340-global-and-regional-reference-images-ip-adapters-',
+  },
+  regionalReferenceImage: {
+    href: 'https://support.invoke.ai/support/solutions/articles/151000159340-global-and-regional-reference-images-ip-adapters-',
+  },
   controlNet: {
     href: 'https://support.invoke.ai/support/solutions/articles/151000105880',
   },

invokeai/frontend/web/src/common/hooks/useBoolean.ts

@@ -51,7 +51,7 @@ export const buildUseBoolean = (initialValue: boolean): [() => UseBoolean, Writa
  * Hook to manage a boolean state. Use this for a local boolean state.
  * @param initialValue Initial value of the boolean
  */
-export const useBoolean = (initialValue: boolean) => {
+export const useBoolean = (initialValue: boolean): UseBoolean => {
   const [isTrue, set] = useState(initialValue);
 
   const setTrue = useCallback(() => {
@@ -72,3 +72,80 @@ export const useBoolean = (initialValue: boolean) => {
     toggle,
   };
 };
+
+type UseDisclosure = {
+  isOpen: boolean;
+  open: () => void;
+  close: () => void;
+  set: (isOpen: boolean) => void;
+  toggle: () => void;
+};
+
+/**
+ * This is the same as `buildUseBoolean`, but the method names are more descriptive,
+ * serving the semantics of a disclosure state.
+ *
+ * Creates a hook to manage a boolean state. The boolean is stored in a nanostores atom.
+ * Returns a tuple containing the hook and the atom. Use this for global boolean state.
+ *
+ * @param defaultIsOpen Initial state of the disclosure
+ */
+export const buildUseDisclosure = (defaultIsOpen: boolean): [() => UseDisclosure, WritableAtom<boolean>] => {
+  const $isOpen = atom(defaultIsOpen);
+
+  const open = () => {
+    $isOpen.set(true);
+  };
+  const close = () => {
+    $isOpen.set(false);
+  };
+  const set = (isOpen: boolean) => {
+    $isOpen.set(isOpen);
+  };
+  const toggle = () => {
+    $isOpen.set(!$isOpen.get());
+  };
+
+  const useDisclosure = () => {
+    const isOpen = useStore($isOpen);
+
+    return {
+      isOpen,
+      open,
+      close,
+      set,
+      toggle,
+    };
+  };
+
+  return [useDisclosure, $isOpen] as const;
+};
+
+/**
+ * This is the same as `useBoolean`, but the method names are more descriptive,
+ * serving the semantics of a disclosure state.
+ *
+ * Hook to manage a boolean state. Use this for a local boolean state.
+ * @param defaultIsOpen Initial state of the disclosure
+ */
+export const useDisclosure = (defaultIsOpen: boolean): UseDisclosure => {
+  const [isOpen, set] = useState(defaultIsOpen);
+
+  const open = useCallback(() => {
+    set(true);
+  }, [set]);
+  const close = useCallback(() => {
+    set(false);
+  }, [set]);
+  const toggle = useCallback(() => {
+    set((val) => !val);
+  }, [set]);
+
+  return {
+    isOpen,
+    open,
+    close,
+    set,
+    toggle,
+  };
+};

invokeai/frontend/web/src/common/hooks/useFullscreenDropzone.ts

@@ -1,6 +1,8 @@
-import { createMemoizedSelector } from 'app/store/createMemoizedSelector';
+import { logger } from 'app/logging/logger';
 import { useAppSelector } from 'app/store/storeHooks';
+import { useAssertSingleton } from 'common/hooks/useAssertSingleton';
 import { selectAutoAddBoardId } from 'features/gallery/store/gallerySelectors';
+import { selectMaxImageUploadCount } from 'features/system/store/configSlice';
 import { toast } from 'features/toast/toast';
 import { selectActiveTab } from 'features/ui/store/uiSelectors';
 import { useCallback, useEffect, useState } from 'react';
@@ -10,89 +12,89 @@ import { useTranslation } from 'react-i18next';
 import { useUploadImageMutation } from 'services/api/endpoints/images';
 import type { PostUploadAction } from 'services/api/types';
 
+const log = logger('gallery');
+
 const accept: Accept = {
   'image/png': ['.png'],
   'image/jpeg': ['.jpg', '.jpeg', '.png'],
 };
 
-const selectPostUploadAction = createMemoizedSelector(selectActiveTab, (activeTabName) => {
-  let postUploadAction: PostUploadAction = { type: 'TOAST' };
-
-  if (activeTabName === 'upscaling') {
-    postUploadAction = { type: 'SET_UPSCALE_INITIAL_IMAGE' };
-  }
-
-  return postUploadAction;
-});
-
 export const useFullscreenDropzone = () => {
+  useAssertSingleton('useFullscreenDropzone');
   const { t } = useTranslation();
   const autoAddBoardId = useAppSelector(selectAutoAddBoardId);
   const [isHandlingUpload, setIsHandlingUpload] = useState<boolean>(false);
-  const postUploadAction = useAppSelector(selectPostUploadAction);
   const [uploadImage] = useUploadImageMutation();
+  const activeTabName = useAppSelector(selectActiveTab);
+  const maxImageUploadCount = useAppSelector(selectMaxImageUploadCount);
 
-  const fileRejectionCallback = useCallback(
-    (rejection: FileRejection) => {
-      setIsHandlingUpload(true);
-
-      toast({
-        id: 'UPLOAD_FAILED',
-        title: t('toast.uploadFailed'),
-        description: rejection.errors.map((error) => error.message).join('\n'),
-        status: 'error',
-      });
-    },
-    [t]
-  );
-
-  const fileAcceptedCallback = useCallback(
-    (file: File) => {
-      uploadImage({
-        file,
-        image_category: 'user',
-        is_intermediate: false,
-        postUploadAction,
-        board_id: autoAddBoardId === 'none' ? undefined : autoAddBoardId,
-      });
-    },
-    [autoAddBoardId, postUploadAction, uploadImage]
-  );
+  const getPostUploadAction = useCallback((): PostUploadAction => {
+    if (activeTabName === 'upscaling') {
+      return { type: 'SET_UPSCALE_INITIAL_IMAGE' };
+    } else {
+      return { type: 'TOAST' };
+    }
+  }, [activeTabName]);
 
   const onDrop = useCallback(
     (acceptedFiles: Array<File>, fileRejections: Array<FileRejection>) => {
-      if (fileRejections.length > 1) {
+      if (fileRejections.length > 0) {
+        const errors = fileRejections.map((rejection) => ({
+          errors: rejection.errors.map(({ message }) => message),
+          file: rejection.file.path,
+        }));
+        log.error({ errors }, 'Invalid upload');
+        const description =
+          maxImageUploadCount === undefined
+            ? t('toast.uploadFailedInvalidUploadDesc')
+            : t('toast.uploadFailedInvalidUploadDesc_withCount', { count: maxImageUploadCount });
+
         toast({
           id: 'UPLOAD_FAILED',
           title: t('toast.uploadFailed'),
-          description: t('toast.uploadFailedInvalidUploadDesc'),
+          description,
           status: 'error',
         });
+
+        setIsHandlingUpload(false);
         return;
       }
 
-      fileRejections.forEach((rejection: FileRejection) => {
-        fileRejectionCallback(rejection);
-      });
+      for (const [i, file] of acceptedFiles.entries()) {
+        uploadImage({
+          file,
+          image_category: 'user',
+          is_intermediate: false,
+          postUploadAction: getPostUploadAction(),
+          board_id: autoAddBoardId === 'none' ? undefined : autoAddBoardId,
+          // The `imageUploaded` listener does some extra logic, like switching to the asset view on upload on the
+          // first upload of a "batch".
+          isFirstUploadOfBatch: i === 0,
+        });
+      }
 
-      acceptedFiles.forEach((file: File) => {
-        fileAcceptedCallback(file);
-      });
+      setIsHandlingUpload(false);
     },
-    [t, fileAcceptedCallback, fileRejectionCallback]
+    [t, maxImageUploadCount, uploadImage, getPostUploadAction, autoAddBoardId]
   );
 
   const onDragOver = useCallback(() => {
     setIsHandlingUpload(true);
   }, []);
 
+  const onDragLeave = useCallback(() => {
+    setIsHandlingUpload(false);
+  }, []);
+
   const dropzone = useDropzone({
     accept,
     noClick: true,
     onDrop,
     onDragOver,
-    multiple: false,
+    onDragLeave,
     noKeyboard: true,
+    multiple: maxImageUploadCount === undefined || maxImageUploadCount > 1,
+    maxFiles: maxImageUploadCount,
   });
 
   useEffect(() => {

invokeai/frontend/web/src/common/hooks/useGroupedModelCombobox.ts

@@ -4,6 +4,7 @@ import { useAppSelector } from 'app/store/storeHooks';
 import type { GroupBase } from 'chakra-react-select';
 import { selectParamsSlice } from 'features/controlLayers/store/paramsSlice';
 import type { ModelIdentifierField } from 'features/nodes/types/common';
+import { selectSystemShouldEnableModelDescriptions } from 'features/system/store/systemSlice';
 import { groupBy, reduce } from 'lodash-es';
 import { useCallback, useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
@@ -37,6 +38,7 @@ export const useGroupedModelCombobox = <T extends AnyModelConfig>(
 ): UseGroupedModelComboboxReturn => {
   const { t } = useTranslation();
   const base = useAppSelector(selectBaseWithSDXLFallback);
+  const shouldShowModelDescriptions = useAppSelector(selectSystemShouldEnableModelDescriptions);
   const { modelConfigs, selectedModel, getIsDisabled, onChange, isLoading, groupByType = false } = arg;
   const options = useMemo<GroupBase<ComboboxOption>[]>(() => {
     if (!modelConfigs) {
@@ -51,6 +53,7 @@ export const useGroupedModelCombobox = <T extends AnyModelConfig>(
           options: val.map((model) => ({
             label: model.name,
             value: model.key,
+            description: (shouldShowModelDescriptions && model.description) || undefined,
             isDisabled: getIsDisabled ? getIsDisabled(model) : false,
           })),
         });
@@ -60,7 +63,7 @@ export const useGroupedModelCombobox = <T extends AnyModelConfig>(
     );
     _options.sort((a) => (a.label?.split('/')[0]?.toLowerCase().includes(base) ? -1 : 1));
     return _options;
-  }, [modelConfigs, groupByType, getIsDisabled, base]);
+  }, [modelConfigs, groupByType, getIsDisabled, base, shouldShowModelDescriptions]);
 
   const value = useMemo(
     () =>

invokeai/frontend/web/src/common/hooks/useImageUploadButton.tsx

@@ -1,15 +1,23 @@
+import { logger } from 'app/logging/logger';
 import { useAppSelector } from 'app/store/storeHooks';
 import { selectAutoAddBoardId } from 'features/gallery/store/gallerySelectors';
+import { selectMaxImageUploadCount } from 'features/system/store/configSlice';
+import { toast } from 'features/toast/toast';
 import { useCallback } from 'react';
+import type { FileRejection } from 'react-dropzone';
 import { useDropzone } from 'react-dropzone';
+import { useTranslation } from 'react-i18next';
 import { useUploadImageMutation } from 'services/api/endpoints/images';
 import type { PostUploadAction } from 'services/api/types';
 
 type UseImageUploadButtonArgs = {
   postUploadAction?: PostUploadAction;
   isDisabled?: boolean;
+  allowMultiple?: boolean;
 };
 
+const log = logger('gallery');
+
 /**
  * Provides image uploader functionality to any component.
  *
@@ -29,28 +37,58 @@ type UseImageUploadButtonArgs = {
  * <Button {...getUploadButtonProps()} /> // will open the file dialog on click
  * <input {...getUploadInputProps()} /> // hidden, handles native upload functionality
  */
-export const useImageUploadButton = ({ postUploadAction, isDisabled }: UseImageUploadButtonArgs) => {
+export const useImageUploadButton = ({
+  postUploadAction,
+  isDisabled,
+  allowMultiple = false,
+}: UseImageUploadButtonArgs) => {
   const autoAddBoardId = useAppSelector(selectAutoAddBoardId);
   const [uploadImage] = useUploadImageMutation();
+  const maxImageUploadCount = useAppSelector(selectMaxImageUploadCount);
+  const { t } = useTranslation();
+
   const onDropAccepted = useCallback(
     (files: File[]) => {
-      const file = files[0];
-
-      if (!file) {
-        return;
+      for (const [i, file] of files.entries()) {
+        uploadImage({
+          file,
+          image_category: 'user',
+          is_intermediate: false,
+          postUploadAction: postUploadAction ?? { type: 'TOAST' },
+          board_id: autoAddBoardId === 'none' ? undefined : autoAddBoardId,
+          isFirstUploadOfBatch: i === 0,
+        });
       }
-
-      uploadImage({
-        file,
-        image_category: 'user',
-        is_intermediate: false,
-        postUploadAction: postUploadAction ?? { type: 'TOAST' },
-        board_id: autoAddBoardId === 'none' ? undefined : autoAddBoardId,
-      });
     },
     [autoAddBoardId, postUploadAction, uploadImage]
   );
 
+  const onDropRejected = useCallback(
+    (fileRejections: FileRejection[]) => {
+      if (fileRejections.length > 0) {
+        const errors = fileRejections.map((rejection) => ({
+          errors: rejection.errors.map(({ message }) => message),
+          file: rejection.file.path,
+        }));
+        log.error({ errors }, 'Invalid upload');
+        const description =
+          maxImageUploadCount === undefined
+            ? t('toast.uploadFailedInvalidUploadDesc')
+            : t('toast.uploadFailedInvalidUploadDesc_withCount', { count: maxImageUploadCount });
+
+        toast({
+          id: 'UPLOAD_FAILED',
+          title: t('toast.uploadFailed'),
+          description,
+          status: 'error',
+        });
+
+        return;
+      }
+    },
+    [maxImageUploadCount, t]
+  );
+
   const {
     getRootProps: getUploadButtonProps,
     getInputProps: getUploadInputProps,
@@ -58,9 +96,11 @@ export const useImageUploadButton = ({ postUploadAction, isDisabled }: UseImageU
   } = useDropzone({
     accept: { 'image/png': ['.png'], 'image/jpeg': ['.jpg', '.jpeg', '.png'] },
     onDropAccepted,
+    onDropRejected,
     disabled: isDisabled,
     noDrag: true,
-    multiple: false,
+    multiple: allowMultiple && (maxImageUploadCount === undefined || maxImageUploadCount > 1),
+    maxFiles: maxImageUploadCount,
   });
 
   return { getUploadButtonProps, getUploadInputProps, openUploader };

invokeai/frontend/web/src/common/hooks/useModelCombobox.ts

@@ -1,5 +1,7 @@
 import type { ComboboxOnChange, ComboboxOption } from '@invoke-ai/ui-library';
+import { useAppSelector } from 'app/store/storeHooks';
 import type { ModelIdentifierField } from 'features/nodes/types/common';
+import { selectSystemShouldEnableModelDescriptions } from 'features/system/store/systemSlice';
 import { useCallback, useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
 import type { AnyModelConfig } from 'services/api/types';
@@ -24,13 +26,16 @@ type UseModelComboboxReturn = {
 export const useModelCombobox = <T extends AnyModelConfig>(arg: UseModelComboboxArg<T>): UseModelComboboxReturn => {
   const { t } = useTranslation();
   const { modelConfigs, selectedModel, getIsDisabled, onChange, isLoading, optionsFilter = () => true } = arg;
+  const shouldShowModelDescriptions = useAppSelector(selectSystemShouldEnableModelDescriptions);
+
   const options = useMemo<ComboboxOption[]>(() => {
     return modelConfigs.filter(optionsFilter).map((model) => ({
       label: model.name,
       value: model.key,
+      description: (shouldShowModelDescriptions && model.description) || undefined,
       isDisabled: getIsDisabled ? getIsDisabled(model) : false,
     }));
-  }, [optionsFilter, getIsDisabled, modelConfigs]);
+  }, [optionsFilter, getIsDisabled, modelConfigs, shouldShowModelDescriptions]);
 
   const value = useMemo(
     () => options.find((m) => (selectedModel ? m.value === selectedModel.key : false)),

invokeai/frontend/web/src/common/hooks/useSubMenu.tsx

@@ -0,0 +1,161 @@
+import type { MenuButtonProps, MenuItemProps, MenuListProps, MenuProps } from '@invoke-ai/ui-library';
+import { Box, Flex, Icon, Text } from '@invoke-ai/ui-library';
+import { useDisclosure } from 'common/hooks/useBoolean';
+import type { FocusEventHandler, PointerEvent, RefObject } from 'react';
+import { useCallback, useEffect, useRef } from 'react';
+import { PiCaretRightBold } from 'react-icons/pi';
+import { useDebouncedCallback } from 'use-debounce';
+
+const offset: [number, number] = [0, 8];
+
+type UseSubMenuReturn = {
+  parentMenuItemProps: Partial<MenuItemProps>;
+  menuProps: Partial<MenuProps>;
+  menuButtonProps: Partial<MenuButtonProps>;
+  menuListProps: Partial<MenuListProps> & { ref: RefObject<HTMLDivElement> };
+};
+
+/**
+ * A hook that provides the necessary props to create a sub-menu within a menu.
+ *
+ * The sub-menu should be wrapped inside a parent `MenuItem` component.
+ *
+ * Use SubMenuButtonContent to render a button with a label and a right caret icon.
+ *
+ * TODO(psyche): Add keyboard handling for sub-menu.
+ *
+ * @example
+ * ```tsx
+ * const SubMenuExample = () => {
+ *   const subMenu = useSubMenu();
+ *   return (
+ *     <Menu>
+ *       <MenuButton>Open Parent Menu</MenuButton>
+ *       <MenuList>
+ *         <MenuItem>Parent Item 1</MenuItem>
+ *         <MenuItem>Parent Item 2</MenuItem>
+ *         <MenuItem>Parent Item 3</MenuItem>
+ *         <MenuItem {...subMenu.parentMenuItemProps} icon={<PiImageBold />}>
+ *           <Menu {...subMenu.menuProps}>
+ *             <MenuButton {...subMenu.menuButtonProps}>
+ *               <SubMenuButtonContent label="Open Sub Menu" />
+ *             </MenuButton>
+ *             <MenuList {...subMenu.menuListProps}>
+ *               <MenuItem>Sub Item 1</MenuItem>
+ *               <MenuItem>Sub Item 2</MenuItem>
+ *               <MenuItem>Sub Item 3</MenuItem>
+ *             </MenuList>
+ *           </Menu>
+ *         </MenuItem>
+ *       </MenuList>
+ *     </Menu>
+ *   );
+ * };
+ * ```
+ */
+export const useSubMenu = (): UseSubMenuReturn => {
+  const subMenu = useDisclosure(false);
+  const menuListRef = useRef<HTMLDivElement>(null);
+  const closeDebounced = useDebouncedCallback(subMenu.close, 300);
+  const openAndCancelPendingClose = useCallback(() => {
+    closeDebounced.cancel();
+    subMenu.open();
+  }, [closeDebounced, subMenu]);
+  const toggleAndCancelPendingClose = useCallback(() => {
+    if (subMenu.isOpen) {
+      subMenu.close();
+      return;
+    } else {
+      closeDebounced.cancel();
+      subMenu.toggle();
+    }
+  }, [closeDebounced, subMenu]);
+  const onBlurMenuList = useCallback<FocusEventHandler<HTMLDivElement>>(
+    (e) => {
+      // Don't trigger blur if focus is moving to a child element - e.g. from a sub-menu item to another sub-menu item
+      if (e.currentTarget.contains(e.relatedTarget)) {
+        closeDebounced.cancel();
+        return;
+      }
+      subMenu.close();
+    },
+    [closeDebounced, subMenu]
+  );
+
+  const onParentMenuItemPointerLeave = useCallback(
+    (e: PointerEvent<HTMLButtonElement>) => {
+      /**
+       * The pointerleave event is triggered when the pen or touch device is lifted, which would close the sub-menu.
+       * However, we want to keep the sub-menu open until the pen or touch device pressed some other element. This
+       * will be handled in the useEffect below - just ignore the pointerleave event for pen and touch devices.
+       */
+      if (e.pointerType === 'pen' || e.pointerType === 'touch') {
+        return;
+      }
+      subMenu.close();
+    },
+    [subMenu]
+  );
+
+  /**
+   * When using a mouse, the pointerleave events close the menu. But when using a pen or touch device, we need to close
+   * the sub-menu when the user taps outside of the menu list. So we need to listen for clicks outside of the menu list
+   * and close the menu accordingly.
+   */
+  useEffect(() => {
+    const el = menuListRef.current;
+    if (!el) {
+      return;
+    }
+    const controller = new AbortController();
+    window.addEventListener(
+      'click',
+      (e) => {
+        if (menuListRef.current?.contains(e.target as Node)) {
+          return;
+        }
+        subMenu.close();
+      },
+      { signal: controller.signal }
+    );
+    return () => {
+      controller.abort();
+    };
+  }, [subMenu]);
+
+  return {
+    parentMenuItemProps: {
+      onClick: toggleAndCancelPendingClose,
+      onPointerEnter: openAndCancelPendingClose,
+      onPointerLeave: onParentMenuItemPointerLeave,
+      closeOnSelect: false,
+    },
+    menuProps: {
+      isOpen: subMenu.isOpen,
+      onClose: subMenu.close,
+      placement: 'right',
+      offset: offset,
+      closeOnBlur: false,
+    },
+    menuButtonProps: {
+      as: Box,
+      width: 'full',
+      height: 'full',
+    },
+    menuListProps: {
+      ref: menuListRef,
+      onPointerEnter: openAndCancelPendingClose,
+      onPointerLeave: closeDebounced,
+      onBlur: onBlurMenuList,
+    },
+  };
+};
+
+export const SubMenuButtonContent = ({ label }: { label: string }) => {
+  return (
+    <Flex w="full" h="full" flexDir="row" justifyContent="space-between" alignItems="center">
+      <Text>{label}</Text>
+      <Icon as={PiCaretRightBold} />
+    </Flex>
+  );
+};

invokeai/frontend/web/src/common/types.ts

@@ -1,4 +1,12 @@
-type SerializableValue = string | number | boolean | null | undefined | SerializableValue[] | SerializableObject;
+type SerializableValue =
+  | string
+  | number
+  | boolean
+  | null
+  | undefined
+  | SerializableValue[]
+  | readonly SerializableValue[]
+  | SerializableObject;
 export type SerializableObject = {
   [k: string | number]: SerializableValue;
 };

invokeai/frontend/web/src/features/changeBoardModal/components/ChangeBoardModal.tsx

@@ -3,12 +3,12 @@ import { Combobox, ConfirmationAlertDialog, Flex, FormControl, Text } from '@inv
 import { createSelector } from '@reduxjs/toolkit';
 import { createMemoizedSelector } from 'app/store/createMemoizedSelector';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import { useAssertSingleton } from 'common/hooks/useAssertSingleton';
 import {
   changeBoardReset,
   isModalOpenChanged,
   selectChangeBoardModalSlice,
 } from 'features/changeBoardModal/store/slice';
-import { selectListBoardsQueryArgs } from 'features/gallery/store/gallerySelectors';
 import { memo, useCallback, useMemo, useState } from 'react';
 import { useTranslation } from 'react-i18next';
 import { useListAllBoardsQuery } from 'services/api/endpoints/boards';
@@ -25,10 +25,10 @@ const selectIsModalOpen = createSelector(
 );
 
 const ChangeBoardModal = () => {
+  useAssertSingleton('ChangeBoardModal');
   const dispatch = useAppDispatch();
   const [selectedBoard, setSelectedBoard] = useState<string | null>();
-  const queryArgs = useAppSelector(selectListBoardsQueryArgs);
-  const { data: boards, isFetching } = useListAllBoardsQuery(queryArgs);
+  const { data: boards, isFetching } = useListAllBoardsQuery({ include_archived: true });
   const isModalOpen = useAppSelector(selectIsModalOpen);
   const imagesToChange = useAppSelector(selectImagesToChange);
   const [addImagesToBoard] = useAddImagesToBoardMutation();

invokeai/frontend/web/src/features/controlLayers/components/CanvasAddEntityButtons.tsx

@@ -1,5 +1,6 @@
 import { Button, Flex, Heading } from '@invoke-ai/ui-library';
 import { useAppSelector } from 'app/store/storeHooks';
+import { InformationalPopover } from 'common/components/InformationalPopover/InformationalPopover';
 import {
   useAddControlLayer,
   useAddGlobalReferenceImage,
@@ -28,71 +29,80 @@ export const CanvasAddEntityButtons = memo(() => {
       <Flex position="relative" flexDir="column" gap={4} top="20%">
         <Flex flexDir="column" justifyContent="flex-start" gap={2}>
           <Heading size="xs">{t('controlLayers.global')}</Heading>
-          <Button
-            size="sm"
-            variant="ghost"
-            justifyContent="flex-start"
-            leftIcon={<PiPlusBold />}
-            onClick={addGlobalReferenceImage}
-            isDisabled={isFLUX}
-          >
-            {t('controlLayers.globalReferenceImage')}
-          </Button>
+          <InformationalPopover feature="globalReferenceImage">
+            <Button
+              size="sm"
+              variant="ghost"
+              justifyContent="flex-start"
+              leftIcon={<PiPlusBold />}
+              onClick={addGlobalReferenceImage}
+            >
+              {t('controlLayers.globalReferenceImage')}
+            </Button>
+          </InformationalPopover>
         </Flex>
         <Flex flexDir="column" gap={2}>
           <Heading size="xs">{t('controlLayers.regional')}</Heading>
-          <Button
-            size="sm"
-            variant="ghost"
-            justifyContent="flex-start"
-            leftIcon={<PiPlusBold />}
-            onClick={addInpaintMask}
-          >
-            {t('controlLayers.inpaintMask')}
-          </Button>
-          <Button
-            size="sm"
-            variant="ghost"
-            justifyContent="flex-start"
-            leftIcon={<PiPlusBold />}
-            onClick={addRegionalGuidance}
-            isDisabled={isFLUX}
-          >
-            {t('controlLayers.regionalGuidance')}
-          </Button>
-          <Button
-            size="sm"
-            variant="ghost"
-            justifyContent="flex-start"
-            leftIcon={<PiPlusBold />}
-            onClick={addRegionalReferenceImage}
-            isDisabled={isFLUX}
-          >
-            {t('controlLayers.regionalReferenceImage')}
-          </Button>
+          <InformationalPopover feature="inpainting">
+            <Button
+              size="sm"
+              variant="ghost"
+              justifyContent="flex-start"
+              leftIcon={<PiPlusBold />}
+              onClick={addInpaintMask}
+            >
+              {t('controlLayers.inpaintMask')}
+            </Button>
+          </InformationalPopover>
+          <InformationalPopover feature="regionalGuidance">
+            <Button
+              size="sm"
+              variant="ghost"
+              justifyContent="flex-start"
+              leftIcon={<PiPlusBold />}
+              onClick={addRegionalGuidance}
+              isDisabled={isFLUX}
+            >
+              {t('controlLayers.regionalGuidance')}
+            </Button>
+          </InformationalPopover>
+          <InformationalPopover feature="regionalReferenceImage">
+            <Button
+              size="sm"
+              variant="ghost"
+              justifyContent="flex-start"
+              leftIcon={<PiPlusBold />}
+              onClick={addRegionalReferenceImage}
+              isDisabled={isFLUX}
+            >
+              {t('controlLayers.regionalReferenceImage')}
+            </Button>
+          </InformationalPopover>
         </Flex>
         <Flex flexDir="column" justifyContent="flex-start" gap={2}>
           <Heading size="xs">{t('controlLayers.layer_other')}</Heading>
-
-          <Button
-            size="sm"
-            variant="ghost"
-            justifyContent="flex-start"
-            leftIcon={<PiPlusBold />}
-            onClick={addControlLayer}
-            isDisabled={isFLUX}
-          >
-            {t('controlLayers.controlLayer')}
-          </Button>
-          <Button
-            size="sm"
-            variant="ghost"
-            justifyContent="flex-start"
-            leftIcon={<PiPlusBold />}
-            onClick={addRasterLayer}
-          >
-            {t('controlLayers.rasterLayer')}
-          </Button>
+          <InformationalPopover feature="controlNet">
+            <Button
+              size="sm"
+              variant="ghost"
+              justifyContent="flex-start"
+              leftIcon={<PiPlusBold />}
+              onClick={addControlLayer}
+            >
+              {t('controlLayers.controlLayer')}
+            </Button>
+          </InformationalPopover>
+          <InformationalPopover feature="rasterLayer">
+            <Button
+              size="sm"
+              variant="ghost"
+              justifyContent="flex-start"
+              leftIcon={<PiPlusBold />}
+              onClick={addRasterLayer}
+            >
+              {t('controlLayers.rasterLayer')}
+            </Button>
+          </InformationalPopover>
         </Flex>
       </Flex>
     </Flex>

invokeai/frontend/web/src/features/controlLayers/components/CanvasAlerts/CanvasAlertsPreserveMask.tsx

@@ -13,7 +13,7 @@ export const CanvasAlertsPreserveMask = memo(() => {
   }
 
   return (
-    <Alert status="warning" borderRadius="base" fontSize="sm" shadow="md" w="fit-content" alignSelf="flex-end">
+    <Alert status="warning" borderRadius="base" fontSize="sm" shadow="md" w="fit-content">
       <AlertIcon />
       <AlertTitle>{t('controlLayers.settings.preserveMask.alert')}</AlertTitle>
     </Alert>

invokeai/frontend/web/src/features/controlLayers/components/CanvasAlerts/CanvasAlertsSelectedEntityStatus.tsx

@@ -98,7 +98,7 @@ const CanvasAlertsSelectedEntityStatusContent = memo(({ entityIdentifier, adapte
   }
 
   return (
-    <Alert status={alert.status} borderRadius="base" fontSize="sm" shadow="md" w="fit-content" alignSelf="flex-end">
+    <Alert status={alert.status} borderRadius="base" fontSize="sm" shadow="md" w="fit-content">
       <AlertIcon />
       <AlertTitle>{alert.title}</AlertTitle>
     </Alert>

invokeai/frontend/web/src/features/controlLayers/components/CanvasAlerts/CanvasAlertsSendingTo.tsx

@@ -2,14 +2,10 @@ import { Alert, AlertDescription, AlertIcon, AlertTitle, Button, Flex } from '@i
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
 import { useBoolean } from 'common/hooks/useBoolean';
 import { selectIsStaging } from 'features/controlLayers/store/canvasStagingAreaSlice';
-import {
-  selectCanvasRightPanelGalleryTab,
-  selectCanvasRightPanelLayersTab,
-} from 'features/controlLayers/store/ephemeral';
 import { useImageViewer } from 'features/gallery/components/ImageViewer/useImageViewer';
 import { useCurrentDestination } from 'features/queue/hooks/useCurrentDestination';
 import { selectActiveTab } from 'features/ui/store/uiSelectors';
-import { setActiveTab } from 'features/ui/store/uiSlice';
+import { activeTabCanvasRightPanelChanged, setActiveTab } from 'features/ui/store/uiSlice';
 import { AnimatePresence, motion } from 'framer-motion';
 import type { PropsWithChildren, ReactNode } from 'react';
 import { useCallback, useMemo } from 'react';
@@ -17,10 +13,11 @@ import { Trans, useTranslation } from 'react-i18next';
 
 const ActivateImageViewerButton = (props: PropsWithChildren) => {
   const imageViewer = useImageViewer();
+  const dispatch = useAppDispatch();
   const onClick = useCallback(() => {
     imageViewer.open();
-    selectCanvasRightPanelGalleryTab();
-  }, [imageViewer]);
+    dispatch(activeTabCanvasRightPanelChanged('gallery'));
+  }, [imageViewer, dispatch]);
   return (
     <Button onClick={onClick} size="sm" variant="link" color="base.50">
       {props.children}
@@ -60,7 +57,7 @@ const ActivateCanvasButton = (props: PropsWithChildren) => {
   const imageViewer = useImageViewer();
   const onClick = useCallback(() => {
     dispatch(setActiveTab('canvas'));
-    selectCanvasRightPanelLayersTab();
+    dispatch(activeTabCanvasRightPanelChanged('layers'));
     imageViewer.close();
   }, [dispatch, imageViewer]);
   return (
@@ -135,7 +132,6 @@ const AlertWrapper = ({
             fontSize="sm"
             shadow="md"
             w="fit-content"
-            alignSelf="flex-end"
           >
             <Flex w="full" alignItems="center">
               <AlertIcon />

invokeai/frontend/web/src/features/controlLayers/components/CanvasAutoProcessSwitch.tsx

@@ -0,0 +1,24 @@
+import { FormControl, FormLabel, Switch } from '@invoke-ai/ui-library';
+import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import { selectAutoProcess, settingsAutoProcessToggled } from 'features/controlLayers/store/canvasSettingsSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+
+export const CanvasAutoProcessSwitch = memo(() => {
+  const { t } = useTranslation();
+  const dispatch = useAppDispatch();
+  const autoProcess = useAppSelector(selectAutoProcess);
+
+  const onChange = useCallback(() => {
+    dispatch(settingsAutoProcessToggled());
+  }, [dispatch]);
+
+  return (
+    <FormControl w="min-content">
+      <FormLabel m={0}>{t('controlLayers.filter.autoProcess')}</FormLabel>
+      <Switch size="sm" isChecked={autoProcess} onChange={onChange} />
+    </FormControl>
+  );
+});
+
+CanvasAutoProcessSwitch.displayName = 'CanvasAutoProcessSwitch';

invokeai/frontend/web/src/features/controlLayers/components/CanvasContextMenu/CanvasContextMenuGlobalMenuItems.tsx

@@ -1,4 +1,5 @@
-import { MenuGroup, MenuItem } from '@invoke-ai/ui-library';
+import { Menu, MenuButton, MenuGroup, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
 import { CanvasContextMenuItemsCropCanvasToBbox } from 'features/controlLayers/components/CanvasContextMenu/CanvasContextMenuItemsCropCanvasToBbox';
 import { NewLayerIcon } from 'features/controlLayers/components/common/icons';
 import {
@@ -16,6 +17,8 @@ import { PiFloppyDiskBold } from 'react-icons/pi';
 
 export const CanvasContextMenuGlobalMenuItems = memo(() => {
   const { t } = useTranslation();
+  const saveSubMenu = useSubMenu();
+  const newSubMenu = useSubMenu();
   const isBusy = useCanvasIsBusy();
   const saveCanvasToGallery = useSaveCanvasToGallery();
   const saveBboxToGallery = useSaveBboxToGallery();
@@ -28,27 +31,41 @@ export const CanvasContextMenuGlobalMenuItems = memo(() => {
     <>
       <MenuGroup title={t('controlLayers.canvasContextMenu.canvasGroup')}>
         <CanvasContextMenuItemsCropCanvasToBbox />
-      </MenuGroup>
-      <MenuGroup title={t('controlLayers.canvasContextMenu.saveToGalleryGroup')}>
-        <MenuItem icon={<PiFloppyDiskBold />} isDisabled={isBusy} onClick={saveCanvasToGallery}>
-          {t('controlLayers.canvasContextMenu.saveCanvasToGallery')}
+        <MenuItem {...saveSubMenu.parentMenuItemProps} icon={<PiFloppyDiskBold />}>
+          <Menu {...saveSubMenu.menuProps}>
+            <MenuButton {...saveSubMenu.menuButtonProps}>
+              <SubMenuButtonContent label={t('controlLayers.canvasContextMenu.saveToGalleryGroup')} />
+            </MenuButton>
+            <MenuList {...saveSubMenu.menuListProps}>
+              <MenuItem icon={<PiFloppyDiskBold />} isDisabled={isBusy} onClick={saveCanvasToGallery}>
+                {t('controlLayers.canvasContextMenu.saveCanvasToGallery')}
+              </MenuItem>
+              <MenuItem icon={<PiFloppyDiskBold />} isDisabled={isBusy} onClick={saveBboxToGallery}>
+                {t('controlLayers.canvasContextMenu.saveBboxToGallery')}
+              </MenuItem>
+            </MenuList>
+          </Menu>
         </MenuItem>
-        <MenuItem icon={<PiFloppyDiskBold />} isDisabled={isBusy} onClick={saveBboxToGallery}>
-          {t('controlLayers.canvasContextMenu.saveBboxToGallery')}
-        </MenuItem>
-      </MenuGroup>
-      <MenuGroup title={t('controlLayers.canvasContextMenu.bboxGroup')}>
-        <MenuItem icon={<NewLayerIcon />} isDisabled={isBusy} onClick={newGlobalReferenceImageFromBbox}>
-          {t('controlLayers.canvasContextMenu.newGlobalReferenceImage')}
-        </MenuItem>
-        <MenuItem icon={<NewLayerIcon />} isDisabled={isBusy} onClick={newRegionalReferenceImageFromBbox}>
-          {t('controlLayers.canvasContextMenu.newRegionalReferenceImage')}
-        </MenuItem>
-        <MenuItem icon={<NewLayerIcon />} isDisabled={isBusy} onClick={newControlLayerFromBbox}>
-          {t('controlLayers.canvasContextMenu.newControlLayer')}
-        </MenuItem>
-        <MenuItem icon={<NewLayerIcon />} isDisabled={isBusy} onClick={newRasterLayerFromBbox}>
-          {t('controlLayers.canvasContextMenu.newRasterLayer')}
+        <MenuItem {...newSubMenu.parentMenuItemProps} icon={<NewLayerIcon />}>
+          <Menu {...newSubMenu.menuProps}>
+            <MenuButton {...newSubMenu.menuButtonProps}>
+              <SubMenuButtonContent label={t('controlLayers.canvasContextMenu.bboxGroup')} />
+            </MenuButton>
+            <MenuList {...newSubMenu.menuListProps}>
+              <MenuItem icon={<NewLayerIcon />} isDisabled={isBusy} onClick={newGlobalReferenceImageFromBbox}>
+                {t('controlLayers.canvasContextMenu.newGlobalReferenceImage')}
+              </MenuItem>
+              <MenuItem icon={<NewLayerIcon />} isDisabled={isBusy} onClick={newRegionalReferenceImageFromBbox}>
+                {t('controlLayers.canvasContextMenu.newRegionalReferenceImage')}
+              </MenuItem>
+              <MenuItem icon={<NewLayerIcon />} isDisabled={isBusy} onClick={newControlLayerFromBbox}>
+                {t('controlLayers.canvasContextMenu.newControlLayer')}
+              </MenuItem>
+              <MenuItem icon={<NewLayerIcon />} isDisabled={isBusy} onClick={newRasterLayerFromBbox}>
+                {t('controlLayers.canvasContextMenu.newRasterLayer')}
+              </MenuItem>
+            </MenuList>
+          </Menu>
         </MenuItem>
       </MenuGroup>
     </>

invokeai/frontend/web/src/features/controlLayers/components/CanvasContextMenu/CanvasContextMenuSelectedEntityMenuItems.tsx

@@ -1,39 +1,43 @@
 import { MenuGroup } from '@invoke-ai/ui-library';
 import { useAppSelector } from 'app/store/storeHooks';
-import { CanvasEntityMenuItemsCopyToClipboard } from 'features/controlLayers/components/common/CanvasEntityMenuItemsCopyToClipboard';
-import { CanvasEntityMenuItemsCropToBbox } from 'features/controlLayers/components/common/CanvasEntityMenuItemsCropToBbox';
-import { CanvasEntityMenuItemsDelete } from 'features/controlLayers/components/common/CanvasEntityMenuItemsDelete';
-import { CanvasEntityMenuItemsFilter } from 'features/controlLayers/components/common/CanvasEntityMenuItemsFilter';
-import { CanvasEntityMenuItemsSave } from 'features/controlLayers/components/common/CanvasEntityMenuItemsSave';
-import { CanvasEntityMenuItemsTransform } from 'features/controlLayers/components/common/CanvasEntityMenuItemsTransform';
+import { ControlLayerMenuItems } from 'features/controlLayers/components/ControlLayer/ControlLayerMenuItems';
+import { InpaintMaskMenuItems } from 'features/controlLayers/components/InpaintMask/InpaintMaskMenuItems';
+import { IPAdapterMenuItems } from 'features/controlLayers/components/IPAdapter/IPAdapterMenuItems';
+import { RasterLayerMenuItems } from 'features/controlLayers/components/RasterLayer/RasterLayerMenuItems';
+import { RegionalGuidanceMenuItems } from 'features/controlLayers/components/RegionalGuidance/RegionalGuidanceMenuItems';
 import {
   EntityIdentifierContext,
   useEntityIdentifierContext,
 } from 'features/controlLayers/contexts/EntityIdentifierContext';
-import { useEntityTitle } from 'features/controlLayers/hooks/useEntityTitle';
+import { useEntityTypeString } from 'features/controlLayers/hooks/useEntityTypeString';
 import { selectSelectedEntityIdentifier } from 'features/controlLayers/store/selectors';
-import {
-  isFilterableEntityIdentifier,
-  isSaveableEntityIdentifier,
-  isTransformableEntityIdentifier,
-} from 'features/controlLayers/store/types';
+import type { PropsWithChildren } from 'react';
 import { memo } from 'react';
+import type { Equals } from 'tsafe';
+import { assert } from 'tsafe';
 
 const CanvasContextMenuSelectedEntityMenuItemsContent = memo(() => {
   const entityIdentifier = useEntityIdentifierContext();
-  const title = useEntityTitle(entityIdentifier);
 
-  return (
-    <MenuGroup title={title}>
-      {isFilterableEntityIdentifier(entityIdentifier) && <CanvasEntityMenuItemsFilter />}
-      {isTransformableEntityIdentifier(entityIdentifier) && <CanvasEntityMenuItemsTransform />}
-      {isSaveableEntityIdentifier(entityIdentifier) && <CanvasEntityMenuItemsCopyToClipboard />}
-      {isSaveableEntityIdentifier(entityIdentifier) && <CanvasEntityMenuItemsSave />}
-      {isTransformableEntityIdentifier(entityIdentifier) && <CanvasEntityMenuItemsCropToBbox />}
-      <CanvasEntityMenuItemsDelete />
-    </MenuGroup>
-  );
+  if (entityIdentifier.type === 'raster_layer') {
+    return <RasterLayerMenuItems />;
+  }
+  if (entityIdentifier.type === 'control_layer') {
+    return <ControlLayerMenuItems />;
+  }
+  if (entityIdentifier.type === 'inpaint_mask') {
+    return <InpaintMaskMenuItems />;
+  }
+  if (entityIdentifier.type === 'regional_guidance') {
+    return <RegionalGuidanceMenuItems />;
+  }
+  if (entityIdentifier.type === 'reference_image') {
+    return <IPAdapterMenuItems />;
+  }
+
+  assert<Equals<typeof entityIdentifier.type, never>>(false);
 });
+
 CanvasContextMenuSelectedEntityMenuItemsContent.displayName = 'CanvasContextMenuSelectedEntityMenuItemsContent';
 
 export const CanvasContextMenuSelectedEntityMenuItems = memo(() => {
@@ -45,9 +49,20 @@ export const CanvasContextMenuSelectedEntityMenuItems = memo(() => {
 
   return (
     <EntityIdentifierContext.Provider value={selectedEntityIdentifier}>
-      <CanvasContextMenuSelectedEntityMenuItemsContent />
+      <CanvasContextMenuSelectedEntityMenuGroup>
+        <CanvasContextMenuSelectedEntityMenuItemsContent />
+      </CanvasContextMenuSelectedEntityMenuGroup>
     </EntityIdentifierContext.Provider>
   );
 });
 
 CanvasContextMenuSelectedEntityMenuItems.displayName = 'CanvasContextMenuSelectedEntityMenuItems';
+
+const CanvasContextMenuSelectedEntityMenuGroup = memo((props: PropsWithChildren) => {
+  const entityIdentifier = useEntityIdentifierContext();
+  const title = useEntityTypeString(entityIdentifier.type);
+
+  return <MenuGroup title={title}>{props.children}</MenuGroup>;
+});
+
+CanvasContextMenuSelectedEntityMenuGroup.displayName = 'CanvasContextMenuSelectedEntityMenuGroup';

invokeai/frontend/web/src/features/controlLayers/components/CanvasDropArea.tsx

@@ -62,6 +62,7 @@ export const CanvasDropArea = memo(() => {
             data={addControlLayerFromImageDropData}
           />
         </GridItem>
+
         <GridItem position="relative">
           <IAIDroppable
             dropLabel={t('controlLayers.canvasContextMenu.newRegionalReferenceImage')}

invokeai/frontend/web/src/features/controlLayers/components/CanvasEntityList/EntityListGlobalActionBarAddLayerMenu.tsx

@@ -29,7 +29,7 @@ export const EntityListGlobalActionBarAddLayerMenu = memo(() => {
     <Menu>
       <MenuButton
         as={IconButton}
-        size="sm"
+        minW={8}
         variant="link"
         alignSelf="stretch"
         tooltip={t('controlLayers.addLayer')}
@@ -40,7 +40,7 @@ export const EntityListGlobalActionBarAddLayerMenu = memo(() => {
       />
       <MenuList>
         <MenuGroup title={t('controlLayers.global')}>
-          <MenuItem icon={<PiPlusBold />} onClick={addGlobalReferenceImage} isDisabled={isFLUX}>
+          <MenuItem icon={<PiPlusBold />} onClick={addGlobalReferenceImage}>
             {t('controlLayers.globalReferenceImage')}
           </MenuItem>
         </MenuGroup>
@@ -56,7 +56,7 @@ export const EntityListGlobalActionBarAddLayerMenu = memo(() => {
           </MenuItem>
         </MenuGroup>
         <MenuGroup title={t('controlLayers.layer_other')}>
-          <MenuItem icon={<PiPlusBold />} onClick={addControlLayer} isDisabled={isFLUX}>
+          <MenuItem icon={<PiPlusBold />} onClick={addControlLayer}>
             {t('controlLayers.controlLayer')}
           </MenuItem>
           <MenuItem icon={<PiPlusBold />} onClick={addRasterLayer}>

invokeai/frontend/web/src/features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBar.tsx

@@ -4,6 +4,7 @@ import { EntityListSelectedEntityActionBarDuplicateButton } from 'features/contr
 import { EntityListSelectedEntityActionBarFill } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarFill';
 import { EntityListSelectedEntityActionBarFilterButton } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarFilterButton';
 import { EntityListSelectedEntityActionBarOpacity } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarOpacity';
+import { EntityListSelectedEntityActionBarSelectObjectButton } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarSelectObjectButton';
 import { EntityListSelectedEntityActionBarTransformButton } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarTransformButton';
 import { memo } from 'react';
 
@@ -16,6 +17,7 @@ export const EntityListSelectedEntityActionBar = memo(() => {
       <Spacer />
       <EntityListSelectedEntityActionBarFill />
       <Flex h="full">
+        <EntityListSelectedEntityActionBarSelectObjectButton />
         <EntityListSelectedEntityActionBarFilterButton />
         <EntityListSelectedEntityActionBarTransformButton />
         <EntityListSelectedEntityActionBarSaveToAssetsButton />