fix(package): pin python-multipart to v0.0.12 due to breakage in dependent packages with later versions

- Use a hash of the last processed points instead of a `hasProcessed` flag to determine whether or not we should re-process a given set of points.
- Store point coords in state instead of pulling them out of the konva node positions. This makes moving a point a more explicit action in code.
- Add a `roundCoord` util to round the x and y values of a coordinate.
- Ensure we always re-process when $points changes.

docker/Dockerfile

@@ -38,7 +38,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ] || [ "$GPU_DRIVER" = "cpu" ]; then \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cpu"; \
     elif [ "$GPU_DRIVER" = "rocm" ]; then \
-        extra_index_url_arg="--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/cu124"; \
     fi &&\

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",
@@ -407,7 +410,7 @@ def get_torch_source() -> Tuple[str | None, str | None]:
     optional_modules: str | None = None
     if OS == "Linux":
         if device == GpuType.ROCM:
-            url = "https://download.pytorch.org/whl/rocm5.6"
+            url = "https://download.pytorch.org/whl/rocm6.1"
         elif device == GpuType.CPU:
             url = "https://download.pytorch.org/whl/cpu"
         elif device == GpuType.CUDA:

invokeai/app/api/routers/model_manager.py

@@ -808,7 +808,11 @@ def get_is_installed(
     for model in installed_models:
         if model.source == starter_model.source:
             return True
-        if model.name == starter_model.name and model.base == starter_model.base and model.type == starter_model.type:
+        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
 

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/flux_denoise.py

@@ -1,15 +1,19 @@
 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,
@@ -17,6 +21,7 @@ from invokeai.app.invocations.fields import (
     WithMetadata,
 )
 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
@@ -26,6 +31,8 @@ from invokeai.backend.flux.denoise import denoise
 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,
@@ -49,7 +56,7 @@ from invokeai.backend.util.devices import TorchDevice
     title="FLUX Denoise",
     tags=["image", "flux"],
     category="image",
-    version="3.1.0",
+    version="3.2.0",
     classification=Classification.Prototype,
 )
 class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
@@ -82,6 +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(
@@ -96,10 +121,15 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         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:
         latents = self._run_diffusion(context)
@@ -108,6 +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,
@@ -115,13 +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
@@ -182,8 +227,16 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         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
@@ -204,6 +257,21 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                 noise=noise,
             )
 
+        # 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).
@@ -252,23 +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.
 
@@ -408,6 +541,112 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
 
         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 +149,51 @@ 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.")
+
+    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)
+
+        # 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/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/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

@@ -1,3 +1,4 @@
+import math
 from typing import Callable
 
 import torch
@@ -7,6 +8,7 @@ from invokeai.backend.flux.controlnet.controlnet_flux_output import ControlNetFl
 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
 
@@ -16,15 +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
@@ -37,10 +47,9 @@ 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.
@@ -48,7 +57,7 @@ def denoise(
         for controlnet_extension in controlnet_extensions:
             controlnet_residuals.append(
                 controlnet_extension.run_controlnet(
-                    timestep_index=step - 1,
+                    timestep_index=step_index,
                     total_num_timesteps=total_steps,
                     img=img,
                     img_ids=img_ids,
@@ -61,7 +70,7 @@ def denoise(
             )
 
         # Merge the ControlNet residuals from multiple ControlNets.
-        # TODO(ryand): We may want to alculate the sum just-in-time to keep peak memory low. Keep in mind, that the
+        # 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)
@@ -74,10 +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
 
@@ -87,13 +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/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,
@@ -88,8 +90,11 @@ class Flux(nn.Module):
         timesteps: Tensor,
         y: Tensor,
         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.")
@@ -111,7 +116,19 @@ class Flux(nn.Module):
         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):
-            img, txt = block(img=img, txt=txt, vec=vec, pe=pe)
+            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]

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/flux.py

@@ -19,6 +19,10 @@ from invokeai.backend.flux.controlnet.state_dict_utils import (
     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
@@ -35,6 +39,7 @@ from invokeai.backend.model_manager.config import (
     CLIPEmbedDiffusersConfig,
     ControlNetCheckpointConfig,
     ControlNetDiffusersConfig,
+    IPAdapterCheckpointConfig,
     MainBnbQuantized4bCheckpointConfig,
     MainCheckpointConfig,
     MainGGUFCheckpointConfig,
@@ -170,7 +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'}"
@@ -352,3 +357,26 @@ class FluxControlnetModel(ModelLoader):
 
         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

@@ -14,6 +14,7 @@ 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,
 )
@@ -243,8 +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.",
@@ -252,6 +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_")):
@@ -274,7 +277,14 @@ class ModelProbe(object):
                 )
             ):
                 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
@@ -452,8 +462,9 @@ 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",
@@ -672,6 +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

invokeai/backend/model_manager/starter_models.py

@@ -13,6 +13,9 @@ class StarterModelWithoutDependencies(BaseModel):
     type: ModelType
     format: Optional[ModelFormat] = None
     is_installed: bool = False
+    # allows us to track what models a user has installed across name changes within starter models
+    # if you update a starter model name, please add the old one to this list for that starter model
+    previous_names: list[str] = []
 
 
 class StarterModel(StarterModelWithoutDependencies):
@@ -25,22 +28,6 @@ class StarterModelBundles(BaseModel):
     models: list[StarterModel]
 
 
-ip_adapter_sd_image_encoder = StarterModel(
-    name="IP Adapter SD1.5 Image Encoder",
-    base=BaseModelType.StableDiffusion1,
-    source="InvokeAI/ip_adapter_sd_image_encoder",
-    description="IP Adapter SD Image Encoder",
-    type=ModelType.CLIPVision,
-)
-
-ip_adapter_sdxl_image_encoder = StarterModel(
-    name="IP Adapter SDXL Image Encoder",
-    base=BaseModelType.StableDiffusionXL,
-    source="InvokeAI/ip_adapter_sdxl_image_encoder",
-    description="IP Adapter SDXL Image Encoder",
-    type=ModelType.CLIPVision,
-)
-
 cyberrealistic_negative = StarterModel(
     name="CyberRealistic Negative v3",
     base=BaseModelType.StableDiffusion1,
@@ -49,6 +36,32 @@ cyberrealistic_negative = StarterModel(
     type=ModelType.TextualInversion,
 )
 
+# region CLIP Image Encoders
+ip_adapter_sd_image_encoder = StarterModel(
+    name="IP Adapter SD1.5 Image Encoder",
+    base=BaseModelType.StableDiffusion1,
+    source="InvokeAI/ip_adapter_sd_image_encoder",
+    description="IP Adapter SD Image Encoder",
+    type=ModelType.CLIPVision,
+)
+ip_adapter_sdxl_image_encoder = StarterModel(
+    name="IP Adapter SDXL Image Encoder",
+    base=BaseModelType.StableDiffusionXL,
+    source="InvokeAI/ip_adapter_sdxl_image_encoder",
+    description="IP Adapter SDXL Image Encoder",
+    type=ModelType.CLIPVision,
+)
+# Note: This model is installed from the same source as the CLIPEmbed model below. The model contains both the image
+# encoder and the text encoder, but we need separate model entries so that they get loaded correctly.
+clip_vit_l_image_encoder = StarterModel(
+    name="clip-vit-large-patch14",
+    base=BaseModelType.Any,
+    source="InvokeAI/clip-vit-large-patch14",
+    description="CLIP ViT-L Image Encoder",
+    type=ModelType.CLIPVision,
+)
+# endregion
+
 # region TextEncoders
 t5_base_encoder = StarterModel(
     name="t5_base_encoder",
@@ -186,6 +199,16 @@ dreamshaper_sdxl = StarterModel(
     type=ModelType.Main,
     dependencies=[sdxl_fp16_vae_fix],
 )
+
+archvis_sdxl = StarterModel(
+    name="Architecture (RealVisXL5)",
+    base=BaseModelType.StableDiffusionXL,
+    source="SG161222/RealVisXL_V5.0",
+    description="A photorealistic model, with architecture among its many use cases",
+    type=ModelType.Main,
+    dependencies=[sdxl_fp16_vae_fix],
+)
+
 sdxl_refiner = StarterModel(
     name="SDXL Refiner",
     base=BaseModelType.StableDiffusionXLRefiner,
@@ -223,36 +246,49 @@ easy_neg_sd1 = StarterModel(
 # endregion
 # region IP Adapter
 ip_adapter_sd1 = StarterModel(
-    name="IP Adapter",
+    name="Standard Reference (IP Adapter)",
     base=BaseModelType.StableDiffusion1,
     source="https://huggingface.co/InvokeAI/ip_adapter_sd15/resolve/main/ip-adapter_sd15.safetensors",
-    description="IP-Adapter for SD 1.5 models",
+    description="References images with a more generalized/looser degree of precision.",
     type=ModelType.IPAdapter,
     dependencies=[ip_adapter_sd_image_encoder],
+    previous_names=["IP Adapter"],
 )
 ip_adapter_plus_sd1 = StarterModel(
-    name="IP Adapter Plus",
+    name="Precise Reference (IP Adapter Plus)",
     base=BaseModelType.StableDiffusion1,
     source="https://huggingface.co/InvokeAI/ip_adapter_plus_sd15/resolve/main/ip-adapter-plus_sd15.safetensors",
-    description="Refined IP-Adapter for SD 1.5 models",
+    description="References images with a higher degree of precision.",
     type=ModelType.IPAdapter,
     dependencies=[ip_adapter_sd_image_encoder],
+    previous_names=["IP Adapter Plus"],
 )
 ip_adapter_plus_face_sd1 = StarterModel(
-    name="IP Adapter Plus Face",
+    name="Face Reference (IP Adapter Plus Face)",
     base=BaseModelType.StableDiffusion1,
     source="https://huggingface.co/InvokeAI/ip_adapter_plus_face_sd15/resolve/main/ip-adapter-plus-face_sd15.safetensors",
-    description="Refined IP-Adapter for SD 1.5 models, adapted for faces",
+    description="References images with a higher degree of precision, adapted for faces",
     type=ModelType.IPAdapter,
     dependencies=[ip_adapter_sd_image_encoder],
+    previous_names=["IP Adapter Plus Face"],
 )
 ip_adapter_sdxl = StarterModel(
-    name="IP Adapter SDXL",
+    name="Standard Reference (IP Adapter ViT-H)",
     base=BaseModelType.StableDiffusionXL,
     source="https://huggingface.co/InvokeAI/ip_adapter_sdxl_vit_h/resolve/main/ip-adapter_sdxl_vit-h.safetensors",
-    description="IP-Adapter for SDXL models",
+    description="References images with a higher degree of precision.",
     type=ModelType.IPAdapter,
     dependencies=[ip_adapter_sdxl_image_encoder],
+    previous_names=["IP Adapter SDXL"],
+)
+ip_adapter_flux = StarterModel(
+    name="Standard Reference (XLabs FLUX IP-Adapter)",
+    base=BaseModelType.Flux,
+    source="https://huggingface.co/XLabs-AI/flux-ip-adapter/resolve/main/flux-ip-adapter.safetensors",
+    description="References images with a more generalized/looser degree of precision.",
+    type=ModelType.IPAdapter,
+    dependencies=[clip_vit_l_image_encoder],
+    previous_names=["XLabs FLUX IP-Adapter"],
 )
 # endregion
 # region ControlNet
@@ -271,157 +307,162 @@ qr_code_cnet_sdxl = StarterModel(
     type=ModelType.ControlNet,
 )
 canny_sd1 = StarterModel(
-    name="canny",
+    name="Hard Edge Detection (canny)",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_canny",
-    description="ControlNet weights trained on sd-1.5 with canny conditioning.",
+    description="Uses detected edges in the image to control composition.",
     type=ModelType.ControlNet,
+    previous_names=["canny"],
 )
 inpaint_cnet_sd1 = StarterModel(
-    name="inpaint",
+    name="Inpainting",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_inpaint",
     description="ControlNet weights trained on sd-1.5 with canny conditioning, inpaint version",
     type=ModelType.ControlNet,
+    previous_names=["inpaint"],
 )
 mlsd_sd1 = StarterModel(
-    name="mlsd",
+    name="Line Drawing (mlsd)",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_mlsd",
-    description="ControlNet weights trained on sd-1.5 with canny conditioning, MLSD version",
+    description="Uses straight line detection for controlling the generation.",
     type=ModelType.ControlNet,
+    previous_names=["mlsd"],
 )
 depth_sd1 = StarterModel(
-    name="depth",
+    name="Depth Map",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11f1p_sd15_depth",
-    description="ControlNet weights trained on sd-1.5 with depth conditioning",
+    description="Uses depth information in the image to control the depth in the generation.",
     type=ModelType.ControlNet,
+    previous_names=["depth"],
 )
 normal_bae_sd1 = StarterModel(
-    name="normal_bae",
+    name="Lighting Detection (Normals)",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_normalbae",
-    description="ControlNet weights trained on sd-1.5 with normalbae image conditioning",
+    description="Uses detected lighting information to guide the lighting of the composition.",
     type=ModelType.ControlNet,
+    previous_names=["normal_bae"],
 )
 seg_sd1 = StarterModel(
-    name="seg",
+    name="Segmentation Map",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_seg",
-    description="ControlNet weights trained on sd-1.5 with seg image conditioning",
+    description="Uses segmentation maps to guide the structure of the composition.",
     type=ModelType.ControlNet,
+    previous_names=["seg"],
 )
 lineart_sd1 = StarterModel(
-    name="lineart",
+    name="Lineart",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_lineart",
-    description="ControlNet weights trained on sd-1.5 with lineart image conditioning",
+    description="Uses lineart detection to guide the lighting of the composition.",
     type=ModelType.ControlNet,
+    previous_names=["lineart"],
 )
 lineart_anime_sd1 = StarterModel(
-    name="lineart_anime",
+    name="Lineart Anime",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15s2_lineart_anime",
-    description="ControlNet weights trained on sd-1.5 with anime image conditioning",
+    description="Uses anime lineart detection to guide the lighting of the composition.",
     type=ModelType.ControlNet,
+    previous_names=["lineart_anime"],
 )
 openpose_sd1 = StarterModel(
-    name="openpose",
+    name="Pose Detection (openpose)",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_openpose",
-    description="ControlNet weights trained on sd-1.5 with openpose image conditioning",
+    description="Uses pose information to control the pose of human characters in the generation.",
     type=ModelType.ControlNet,
+    previous_names=["openpose"],
 )
 scribble_sd1 = StarterModel(
-    name="scribble",
+    name="Contour Detection (scribble)",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_scribble",
-    description="ControlNet weights trained on sd-1.5 with scribble image conditioning",
+    description="Uses edges, contours, or line art in the image to control composition.",
     type=ModelType.ControlNet,
+    previous_names=["scribble"],
 )
 softedge_sd1 = StarterModel(
-    name="softedge",
+    name="Soft Edge Detection (softedge)",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11p_sd15_softedge",
-    description="ControlNet weights trained on sd-1.5 with soft edge conditioning",
+    description="Uses a soft edge detection map to control composition.",
     type=ModelType.ControlNet,
+    previous_names=["softedge"],
 )
 shuffle_sd1 = StarterModel(
-    name="shuffle",
+    name="Remix (shuffle)",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11e_sd15_shuffle",
     description="ControlNet weights trained on sd-1.5 with shuffle image conditioning",
     type=ModelType.ControlNet,
+    previous_names=["shuffle"],
 )
 tile_sd1 = StarterModel(
-    name="tile",
+    name="Tile",
     base=BaseModelType.StableDiffusion1,
     source="lllyasviel/control_v11f1e_sd15_tile",
-    description="ControlNet weights trained on sd-1.5 with tiled image conditioning",
-    type=ModelType.ControlNet,
-)
-ip2p_sd1 = StarterModel(
-    name="ip2p",
-    base=BaseModelType.StableDiffusion1,
-    source="lllyasviel/control_v11e_sd15_ip2p",
-    description="ControlNet weights trained on sd-1.5 with ip2p conditioning.",
+    description="Uses image data to replicate exact colors/structure in the resulting generation.",
     type=ModelType.ControlNet,
+    previous_names=["tile"],
 )
 canny_sdxl = StarterModel(
-    name="canny-sdxl",
+    name="Hard Edge Detection (canny)",
     base=BaseModelType.StableDiffusionXL,
     source="xinsir/controlNet-canny-sdxl-1.0",
-    description="ControlNet weights trained on sdxl-1.0 with canny conditioning, by Xinsir.",
+    description="Uses detected edges in the image to control composition.",
     type=ModelType.ControlNet,
+    previous_names=["canny-sdxl"],
 )
 depth_sdxl = StarterModel(
-    name="depth-sdxl",
+    name="Depth Map",
     base=BaseModelType.StableDiffusionXL,
     source="diffusers/controlNet-depth-sdxl-1.0",
-    description="ControlNet weights trained on sdxl-1.0 with depth conditioning.",
+    description="Uses depth information in the image to control the depth in the generation.",
     type=ModelType.ControlNet,
+    previous_names=["depth-sdxl"],
 )
 softedge_sdxl = StarterModel(
-    name="softedge-dexined-sdxl",
+    name="Soft Edge Detection (softedge)",
     base=BaseModelType.StableDiffusionXL,
     source="SargeZT/controlNet-sd-xl-1.0-softedge-dexined",
-    description="ControlNet weights trained on sdxl-1.0 with dexined soft edge preprocessing.",
-    type=ModelType.ControlNet,
-)
-depth_zoe_16_sdxl = StarterModel(
-    name="depth-16bit-zoe-sdxl",
-    base=BaseModelType.StableDiffusionXL,
-    source="SargeZT/controlNet-sd-xl-1.0-depth-16bit-zoe",
-    description="ControlNet weights trained on sdxl-1.0 with Zoe's preprocessor (16 bits).",
-    type=ModelType.ControlNet,
-)
-depth_zoe_32_sdxl = StarterModel(
-    name="depth-zoe-sdxl",
-    base=BaseModelType.StableDiffusionXL,
-    source="diffusers/controlNet-zoe-depth-sdxl-1.0",
-    description="ControlNet weights trained on sdxl-1.0 with Zoe's preprocessor (32 bits).",
+    description="Uses a soft edge detection map to control composition.",
     type=ModelType.ControlNet,
+    previous_names=["softedge-dexined-sdxl"],
 )
 openpose_sdxl = StarterModel(
-    name="openpose-sdxl",
+    name="Pose Detection (openpose)",
     base=BaseModelType.StableDiffusionXL,
     source="xinsir/controlNet-openpose-sdxl-1.0",
-    description="ControlNet weights trained on sdxl-1.0 compatible with the DWPose processor by Xinsir.",
+    description="Uses pose information to control the pose of human characters in the generation.",
     type=ModelType.ControlNet,
+    previous_names=["openpose-sdxl", "controlnet-openpose-sdxl"],
 )
 scribble_sdxl = StarterModel(
-    name="scribble-sdxl",
+    name="Contour Detection (scribble)",
     base=BaseModelType.StableDiffusionXL,
     source="xinsir/controlNet-scribble-sdxl-1.0",
-    description="ControlNet weights trained on sdxl-1.0 compatible with various lineart processors and black/white sketches by Xinsir.",
+    description="Uses edges, contours, or line art in the image to control composition.",
     type=ModelType.ControlNet,
+    previous_names=["scribble-sdxl", "controlnet-scribble-sdxl"],
 )
 tile_sdxl = StarterModel(
-    name="tile-sdxl",
+    name="Tile",
     base=BaseModelType.StableDiffusionXL,
     source="xinsir/controlNet-tile-sdxl-1.0",
-    description="ControlNet weights trained on sdxl-1.0 with tiled image conditioning",
+    description="Uses image data to replicate exact colors/structure in the resulting generation.",
+    type=ModelType.ControlNet,
+    previous_names=["tile-sdxl"],
+)
+union_cnet_sdxl = StarterModel(
+    name="Multi-Guidance Detection (Union Pro)",
+    base=BaseModelType.StableDiffusionXL,
+    source="InvokeAI/Xinsir-SDXL_Controlnet_Union",
+    description="A unified ControlNet for SDXL model that supports 10+ control types",
     type=ModelType.ControlNet,
 )
 union_cnet_flux = StarterModel(
@@ -434,60 +475,52 @@ union_cnet_flux = StarterModel(
 # endregion
 # region T2I Adapter
 t2i_canny_sd1 = StarterModel(
-    name="canny-sd15",
+    name="Hard Edge Detection (canny)",
     base=BaseModelType.StableDiffusion1,
     source="TencentARC/t2iadapter_canny_sd15v2",
-    description="T2I Adapter weights trained on sd-1.5 with canny conditioning.",
+    description="Uses detected edges in the image to control composition",
     type=ModelType.T2IAdapter,
+    previous_names=["canny-sd15"],
 )
 t2i_sketch_sd1 = StarterModel(
-    name="sketch-sd15",
+    name="Sketch",
     base=BaseModelType.StableDiffusion1,
     source="TencentARC/t2iadapter_sketch_sd15v2",
-    description="T2I Adapter weights trained on sd-1.5 with sketch conditioning.",
+    description="Uses a sketch to control composition",
     type=ModelType.T2IAdapter,
+    previous_names=["sketch-sd15"],
 )
 t2i_depth_sd1 = StarterModel(
-    name="depth-sd15",
+    name="Depth Map",
     base=BaseModelType.StableDiffusion1,
     source="TencentARC/t2iadapter_depth_sd15v2",
-    description="T2I Adapter weights trained on sd-1.5 with depth conditioning.",
-    type=ModelType.T2IAdapter,
-)
-t2i_zoe_depth_sd1 = StarterModel(
-    name="zoedepth-sd15",
-    base=BaseModelType.StableDiffusion1,
-    source="TencentARC/t2iadapter_zoedepth_sd15v1",
-    description="T2I Adapter weights trained on sd-1.5 with zoe depth conditioning.",
+    description="Uses depth information in the image to control the depth in the generation.",
     type=ModelType.T2IAdapter,
+    previous_names=["depth-sd15"],
 )
 t2i_canny_sdxl = StarterModel(
-    name="canny-sdxl",
+    name="Hard Edge Detection (canny)",
     base=BaseModelType.StableDiffusionXL,
     source="TencentARC/t2i-adapter-canny-sdxl-1.0",
-    description="T2I Adapter weights trained on sdxl-1.0 with canny conditioning.",
-    type=ModelType.T2IAdapter,
-)
-t2i_zoe_depth_sdxl = StarterModel(
-    name="zoedepth-sdxl",
-    base=BaseModelType.StableDiffusionXL,
-    source="TencentARC/t2i-adapter-depth-zoe-sdxl-1.0",
-    description="T2I Adapter weights trained on sdxl-1.0 with zoe depth conditioning.",
+    description="Uses detected edges in the image to control composition",
     type=ModelType.T2IAdapter,
+    previous_names=["canny-sdxl"],
 )
 t2i_lineart_sdxl = StarterModel(
-    name="lineart-sdxl",
+    name="Lineart",
     base=BaseModelType.StableDiffusionXL,
     source="TencentARC/t2i-adapter-lineart-sdxl-1.0",
-    description="T2I Adapter weights trained on sdxl-1.0 with lineart conditioning.",
+    description="Uses lineart detection to guide the lighting of the composition.",
     type=ModelType.T2IAdapter,
+    previous_names=["lineart-sdxl"],
 )
 t2i_sketch_sdxl = StarterModel(
-    name="sketch-sdxl",
+    name="Sketch",
     base=BaseModelType.StableDiffusionXL,
     source="TencentARC/t2i-adapter-sketch-sdxl-1.0",
-    description="T2I Adapter weights trained on sdxl-1.0 with sketch conditioning.",
+    description="Uses a sketch to control composition",
     type=ModelType.T2IAdapter,
+    previous_names=["sketch-sdxl"],
 )
 # endregion
 # region SpandrelImageToImage
@@ -545,6 +578,7 @@ STARTER_MODELS: list[StarterModel] = [
     deliberate_inpainting_sd1,
     juggernaut_sdxl,
     dreamshaper_sdxl,
+    archvis_sdxl,
     sdxl_refiner,
     sdxl_fp16_vae_fix,
     flux_vae,
@@ -555,6 +589,7 @@ STARTER_MODELS: list[StarterModel] = [
     ip_adapter_plus_sd1,
     ip_adapter_plus_face_sd1,
     ip_adapter_sdxl,
+    ip_adapter_flux,
     qr_code_cnet_sd1,
     qr_code_cnet_sdxl,
     canny_sd1,
@@ -570,22 +605,18 @@ STARTER_MODELS: list[StarterModel] = [
     softedge_sd1,
     shuffle_sd1,
     tile_sd1,
-    ip2p_sd1,
     canny_sdxl,
     depth_sdxl,
     softedge_sdxl,
-    depth_zoe_16_sdxl,
-    depth_zoe_32_sdxl,
     openpose_sdxl,
     scribble_sdxl,
     tile_sdxl,
+    union_cnet_sdxl,
     union_cnet_flux,
     t2i_canny_sd1,
     t2i_sketch_sd1,
     t2i_depth_sd1,
-    t2i_zoe_depth_sd1,
     t2i_canny_sdxl,
-    t2i_zoe_depth_sdxl,
     t2i_lineart_sdxl,
     t2i_sketch_sdxl,
     realesrgan_x4,
@@ -616,7 +647,6 @@ sd1_bundle: list[StarterModel] = [
     softedge_sd1,
     shuffle_sd1,
     tile_sd1,
-    ip2p_sd1,
     swinir,
 ]
 
@@ -627,8 +657,6 @@ sdxl_bundle: list[StarterModel] = [
     canny_sdxl,
     depth_sdxl,
     softedge_sdxl,
-    depth_zoe_16_sdxl,
-    depth_zoe_32_sdxl,
     openpose_sdxl,
     scribble_sdxl,
     tile_sdxl,
@@ -642,6 +670,7 @@ flux_bundle: list[StarterModel] = [
     t5_8b_quantized_encoder,
     clip_l_encoder,
     union_cnet_flux,
+    ip_adapter_flux,
 ]
 
 STARTER_BUNDLES: dict[str, list[StarterModel]] = {

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/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": "^0.0.42",
+    "@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: ^0.0.42
-    version: 0.0.42(@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
@@ -1696,20 +1696,20 @@ packages:
       prettier: 3.3.3
     dev: true
 
-  /@invoke-ai/ui-library@0.0.42(@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-OuDXRipBO5mu+Nv4qN8cd8MiwiGBdq6h4PirVgPI9/ltbdcIzePgUJ0dJns26lflHSTRWW38I16wl4YTw3mNWA==}
+  /@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/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': 2.10.2(@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': 2.9.2
-      '@chakra-ui/theme-tools': 2.1.2(@chakra-ui/styled-system@2.9.2)
+      '@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
@@ -8830,10 +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": {
@@ -1137,7 +1168,9 @@
         "workflowNotes": "Notizen",
         "workflowTags": "Tags",
         "workflowVersion": "Version",
-        "saveToGallery": "In Galerie speichern"
+        "saveToGallery": "In Galerie speichern",
+        "noWorkflows": "Keine Arbeitsabläufe",
+        "noMatchingWorkflows": "Keine passenden Arbeitsabläufe"
     },
     "hrf": {
         "enableHrf": "Korrektur für hohe Auflösungen",

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

@@ -94,6 +94,7 @@
         "close": "Close",
         "copy": "Copy",
         "copyError": "$t(gallery.copy) Error",
+        "clipboard": "Clipboard",
         "on": "On",
         "off": "Off",
         "or": "or",
@@ -1251,6 +1252,33 @@
             "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": [
@@ -1688,8 +1716,18 @@
         "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",
@@ -1842,6 +1880,17 @@
             "apply": "Apply",
             "cancel": "Cancel"
         },
+        "segment": {
+            "autoMask": "Auto Mask",
+            "pointType": "Point Type",
+            "include": "Include",
+            "exclude": "Exclude",
+            "neutral": "Neutral",
+            "reset": "Reset",
+            "saveAs": "Save As",
+            "cancel": "Cancel",
+            "process": "Process"
+        },
         "settings": {
             "snapToGrid": {
                 "label": "Snap to Grid",
@@ -1852,10 +1901,10 @@
                 "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"
         },

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

@@ -6,7 +6,7 @@
         "settingsLabel": "Paramètres",
         "img2img": "Image vers Image",
         "nodes": "Processus",
-        "upload": "Télécharger",
+        "upload": "Importer",
         "load": "Charger",
         "back": "Retour",
         "statusDisconnected": "Hors ligne",
@@ -51,7 +51,7 @@
         "green": "Vert",
         "delete": "Supprimer",
         "simple": "Simple",
-        "template": "Modèle",
+        "template": "Template",
         "advanced": "Avancé",
         "copy": "Copier",
         "saveAs": "Enregistrer sous",
@@ -117,8 +117,8 @@
         "bulkDownloadRequestFailed": "Problème lors de la préparation du téléchargement",
         "copy": "Copier",
         "autoAssignBoardOnClick": "Assigner automatiquement une Planche lors du clic",
-        "dropToUpload": "$t(gallery.drop) pour Charger",
-        "dropOrUpload": "$t(gallery.drop) ou Séléctioner",
+        "dropToUpload": "$t(gallery.drop) pour Importer",
+        "dropOrUpload": "$t(gallery.drop) ou Importer",
         "oldestFirst": "Plus Ancien en premier",
         "deleteImagePermanent": "Les Images supprimées ne peuvent pas être restorées.",
         "displaySearch": "Recherche d'Image",
@@ -161,7 +161,7 @@
         "unstarImage": "Retirer le marquage de l'Image",
         "viewerImage": "Visualisation de l'Image",
         "imagesSettings": "Paramètres des images de la galerie",
-        "assetsTab": "Fichiers que vous avez chargé pour vos projets.",
+        "assetsTab": "Fichiers que vous avez importé pour vos projets.",
         "imagesTab": "Images que vous avez créées et enregistrées dans Invoke.",
         "boardsSettings": "Paramètres des planches"
     },
@@ -243,7 +243,7 @@
         "noModelsInstalled": "Aucun modèle installé",
         "urlOrLocalPath": "URL ou chemin local",
         "prune": "Vider",
-        "uploadImage": "Charger une image",
+        "uploadImage": "Importer une image",
         "addModels": "Ajouter des modèles",
         "install": "Installer",
         "localOnly": "local uniquement",
@@ -273,7 +273,18 @@
         "spandrelImageToImage": "Image vers Image (Spandrel)",
         "starterModelsInModelManager": "Les modèles de démarrage peuvent être trouvés dans le gestionnaire de modèles",
         "t5Encoder": "Encodeur T5",
-        "learnMoreAboutSupportedModels": "En savoir plus sur les modèles que nous prenons en charge"
+        "learnMoreAboutSupportedModels": "En savoir plus sur les modèles que nous prenons en charge",
+        "includesNModels": "Contient {{n}} modèles et leurs dépendances",
+        "starterBundles": "Packs de démarrages",
+        "starterBundleHelpText": "Installe facilement tous les modèles nécessaire pour démarrer avec un modèle de base, incluant un modèle principal, ControlNets, IP Adapters et plus encore. Choisir un pack igniorera tous les modèles déjà installés.",
+        "installingXModels_one": "En cours d'installation de {{count}} modèle",
+        "installingXModels_many": "En cours d'installation de {{count}} modèles",
+        "installingXModels_other": "En cours d'installation de {{count}} modèles",
+        "skippingXDuplicates_one": ", en ignorant {{count}} doublon",
+        "skippingXDuplicates_many": ", en ignorant {{count}} doublons",
+        "skippingXDuplicates_other": ", en ignorant {{count}} doublons",
+        "installingModel": "Modèle en cours d'installation",
+        "installingBundle": "Pack en cours d'installation"
     },
     "parameters": {
         "images": "Images",
@@ -414,16 +425,16 @@
         "confirmOnNewSession": "Confirmer lors d'une nouvelle session"
     },
     "toast": {
-        "uploadFailed": "Téléchargement échoué",
+        "uploadFailed": "Importation échouée",
         "imageCopied": "Image copiée",
         "parametersNotSet": "Paramètres non rappelés",
         "serverError": "Erreur du serveur",
-        "uploadFailedInvalidUploadDesc": "Doit être une unique image PNG ou JPEG",
+        "uploadFailedInvalidUploadDesc": "Doit être des images au format PNG ou JPEG.",
         "problemCopyingImage": "Impossible de copier l'image",
         "parameterSet": "Paramètre Rappelé",
         "parameterNotSet": "Paramètre non Rappelé",
         "canceled": "Traitement annulé",
-        "addedToBoard": "Ajouté à la planche",
+        "addedToBoard": "Ajouté aux ressources de la planche {{name}}",
         "workflowLoaded": "Processus chargé",
         "connected": "Connecté au serveur",
         "setNodeField": "Définir comme champ de nœud",
@@ -436,7 +447,7 @@
         "baseModelChangedCleared_one": "Effacé ou désactivé {{count}} sous-modèle incompatible",
         "baseModelChangedCleared_many": "Effacé ou désactivé {{count}} sous-modèles incompatibles",
         "baseModelChangedCleared_other": "Effacé ou désactivé {{count}} sous-modèles incompatibles",
-        "invalidUpload": "Téléchargement invalide",
+        "invalidUpload": "Importation invalide",
         "problemDownloadingImage": "Impossible de télécharger l'image",
         "problemRetrievingWorkflow": "Problème de récupération du processus",
         "problemDeletingWorkflow": "Problème de suppression du processus",
@@ -468,10 +479,15 @@
         "baseModelChanged": "Modèle de base changé",
         "problemSavingLayer": "Impossible d'enregistrer la couche",
         "imageNotLoadedDesc": "Image introuvable",
-        "linkCopied": "Lien copié"
+        "linkCopied": "Lien copié",
+        "imagesWillBeAddedTo": "Les images Importées seront ajoutées au ressources de la Planche {{boardName}}.",
+        "uploadFailedInvalidUploadDesc_withCount_one": "Doit être au maximum une image PNG ou JPEG.",
+        "uploadFailedInvalidUploadDesc_withCount_many": "Doit être au maximum {{count}} images PNG ou JPEG.",
+        "uploadFailedInvalidUploadDesc_withCount_other": "Doit être au maximum {{count}} images PNG ou JPEG.",
+        "addedToUncategorized": "Ajouté aux ressources de la planche $t(boards.uncategorized)"
     },
     "accessibility": {
-        "uploadImage": "Charger une image",
+        "uploadImage": "Importer une image",
         "reset": "Réinitialiser",
         "nextImage": "Image suivante",
         "previousImage": "Image précédente",
@@ -483,7 +499,8 @@
         "submitSupportTicket": "Envoyer un ticket de support",
         "resetUI": "$t(accessibility.reset) l'Interface Utilisateur",
         "toggleRightPanel": "Afficher/Masquer le panneau de droite (G)",
-        "toggleLeftPanel": "Afficher/Masquer le panneau de gauche (T)"
+        "toggleLeftPanel": "Afficher/Masquer le panneau de gauche (T)",
+        "uploadImages": "Importer Image(s)"
     },
     "boards": {
         "move": "Déplacer",
@@ -1400,13 +1417,14 @@
         "parameterSet": "Paramètre {{parameter}} défini",
         "parsingFailed": "L'analyse a échoué",
         "recallParameter": "Rappeler {{label}}",
-        "canvasV2Metadata": "Toile"
+        "canvasV2Metadata": "Toile",
+        "guidance": "Guide"
     },
     "sdxl": {
         "freePromptStyle": "Écriture de Prompt manuelle",
         "concatPromptStyle": "Lier Prompt & Style",
-        "negStylePrompt": "Prompt Négatif",
-        "posStylePrompt": "Prompt Positif",
+        "negStylePrompt": "Style Prompt Négatif",
+        "posStylePrompt": "Style Prompt Positif",
         "refinerStart": "Démarrer le Refiner",
         "denoisingStrength": "Force de débruitage",
         "steps": "Étapes",
@@ -1582,7 +1600,7 @@
         "noDescription": "Aucune description",
         "deleteWorkflow": "Supprimer le processus",
         "openWorkflow": "Ouvrir le processus",
-        "uploadWorkflow": "Charger à partir du fichier",
+        "uploadWorkflow": "Charger à partir d'un fichier",
         "workflowName": "Nom du processus",
         "unnamedWorkflow": "Processus sans nom",
         "saveWorkflowAs": "Enregistrer le processus sous",
@@ -1613,7 +1631,7 @@
         "projectWorkflows": "Processus du projet",
         "copyShareLink": "Copier le lien de partage",
         "chooseWorkflowFromLibrary": "Choisir le Processus dans la Bibliothèque",
-        "uploadAndSaveWorkflow": "Charger dans la bibliothèque",
+        "uploadAndSaveWorkflow": "Importer dans la bibliothèque",
         "edit": "Modifer",
         "deleteWorkflow2": "Êtes-vous sûr de vouloir supprimer ce processus ? Ceci ne peut pas être annulé.",
         "download": "Télécharger",
@@ -1980,50 +1998,50 @@
         "missingTileControlNetModel": "Aucun modèle ControlNet valide installé"
     },
     "stylePresets": {
-        "deleteTemplate": "Supprimer le modèle",
-        "editTemplate": "Modifier le modèle",
+        "deleteTemplate": "Supprimer le template",
+        "editTemplate": "Modifier le template",
         "exportFailed": "Impossible de générer et de télécharger le CSV",
         "name": "Nom",
         "acceptedColumnsKeys": "Colonnes/clés acceptées :",
-        "promptTemplatesDesc1": "Les modèles de prompt ajoutent du texte aux prompts que vous écrivez dans la zone de saisie des prompts.",
+        "promptTemplatesDesc1": "Les templates de prompt ajoutent du texte aux prompts que vous écrivez dans la zone de saisie.",
         "private": "Privé",
         "searchByName": "Rechercher par nom",
-        "viewList": "Afficher la liste des modèles",
-        "noTemplates": "Aucun modèle",
+        "viewList": "Afficher la liste des templates",
+        "noTemplates": "Aucun templates",
         "insertPlaceholder": "Insérer un placeholder",
-        "defaultTemplates": "Modèles par défaut",
+        "defaultTemplates": "Template pré-défini",
         "deleteImage": "Supprimer l'image",
-        "createPromptTemplate": "Créer un modèle de prompt",
+        "createPromptTemplate": "Créer un template de prompt",
         "negativePrompt": "Prompt négatif",
-        "promptTemplatesDesc3": "Si vous omettez le placeholder, le modèle sera ajouté à la fin de votre prompt.",
+        "promptTemplatesDesc3": "Si vous omettez le placeholder, le template sera ajouté à la fin de votre prompt.",
         "positivePrompt": "Prompt positif",
-        "choosePromptTemplate": "Choisir un modèle de prompt",
+        "choosePromptTemplate": "Choisir un template de prompt",
         "toggleViewMode": "Basculer le mode d'affichage",
-        "updatePromptTemplate": "Mettre à jour le modèle de prompt",
-        "flatten": "Intégrer le modèle sélectionné dans le prompt actuel",
-        "myTemplates": "Mes modèles",
+        "updatePromptTemplate": "Mettre à jour le template de prompt",
+        "flatten": "Intégrer le template sélectionné dans le prompt actuel",
+        "myTemplates": "Mes Templates",
         "type": "Type",
         "exportDownloaded": "Exportation téléchargée",
-        "clearTemplateSelection": "Supprimer la sélection de modèle",
-        "promptTemplateCleared": "Modèle de prompt effacé",
-        "templateDeleted": "Modèle de prompt supprimé",
-        "exportPromptTemplates": "Exporter mes modèles de prompt (CSV)",
+        "clearTemplateSelection": "Supprimer la sélection de template",
+        "promptTemplateCleared": "Template de prompt effacé",
+        "templateDeleted": "Template de prompt supprimé",
+        "exportPromptTemplates": "Exporter mes templates de prompt (CSV)",
         "nameColumn": "'nom'",
         "positivePromptColumn": "\"prompt\" ou \"prompt_positif\"",
-        "useForTemplate": "Utiliser pour le modèle de prompt",
-        "uploadImage": "Charger une image",
-        "importTemplates": "Importer des modèles de prompt (CSV/JSON)",
+        "useForTemplate": "Utiliser pour le template de prompt",
+        "uploadImage": "Importer une image",
+        "importTemplates": "Importer des templates de prompt (CSV/JSON)",
         "negativePromptColumn": "'prompt_négatif'",
-        "deleteTemplate2": "Êtes-vous sûr de vouloir supprimer ce modèle ? Cette action ne peut pas être annulée.",
+        "deleteTemplate2": "Êtes-vous sûr de vouloir supprimer ce template ? Cette action ne peut pas être annulée.",
         "preview": "Aperçu",
         "shared": "Partagé",
-        "noMatchingTemplates": "Aucun modèle correspondant",
-        "sharedTemplates": "Modèles partagés",
-        "unableToDeleteTemplate": "Impossible de supprimer le modèle de prompt",
+        "noMatchingTemplates": "Aucun templates correspondant",
+        "sharedTemplates": "Template partagés",
+        "unableToDeleteTemplate": "Impossible de supprimer le template de prompt",
         "active": "Actif",
-        "copyTemplate": "Copier le modèle",
-        "viewModeTooltip": "Voici à quoi ressemblera votre prompt avec le modèle actuellement sélectionné. Pour modifier votre prompt, cliquez n'importe où dans la zone de texte.",
-        "promptTemplatesDesc2": "Utilisez la chaîne de remplacement <Pre>{{placeholder}}</Pre> pour spécifier où votre prompt doit être inclus dans le modèle."
+        "copyTemplate": "Copier le template",
+        "viewModeTooltip": "Voici à quoi ressemblera votre prompt avec le template actuellement sélectionné. Pour modifier votre prompt, cliquez n'importe où dans la zone de texte.",
+        "promptTemplatesDesc2": "Utilisez la chaîne de remplacement <Pre>{{placeholder}}</Pre> pour spécifier où votre prompt doit être inclus dans le template."
     },
     "system": {
         "logNamespaces": {
@@ -2051,8 +2069,12 @@
         "enableLogging": "Activer la journalisation"
     },
     "newUserExperience": {
-        "toGetStarted": "Pour commencer, saisissez un prompt dans la boîte et cliquez sur <StrongComponent>Invoke</StrongComponent> pour générer votre première image. Sélectionnez un modèle de prompt pour améliorer les résultats. Vous pouvez choisir de sauvegarder vos images directement dans la <StrongComponent>Galerie</StrongComponent> ou de les modifier sur la <StrongComponent>Toile</StrongComponent>.",
-        "gettingStartedSeries": "Vous souhaitez plus de conseils ? Consultez notre <LinkComponent>Série de démarrage</LinkComponent> pour des astuces sur l'exploitation du plein potentiel de l'Invoke Studio."
+        "toGetStarted": "Pour commencer, saisissez un prompt dans la boîte et cliquez sur <StrongComponent>Invoke</StrongComponent> pour générer votre première image. Sélectionnez un template de prompt pour améliorer les résultats. Vous pouvez choisir de sauvegarder vos images directement dans la <StrongComponent>Galerie</StrongComponent> ou de les modifier sur la <StrongComponent>Toile</StrongComponent>.",
+        "gettingStartedSeries": "Vous souhaitez plus de conseils ? Consultez notre <LinkComponent>Série de démarrage</LinkComponent> pour des astuces sur l'exploitation du plein potentiel de l'Invoke Studio.",
+        "noModelsInstalled": "Il semblerait qu'aucun modèle ne soit installé",
+        "downloadStarterModels": "Télécharger les modèles de démarrage",
+        "importModels": "Importer Modèles",
+        "toGetStartedLocal": "Pour commencer, assurez-vous de télécharger ou d'importer des modèles nécessaires pour exécuter Invoke. Ensuite, saisissez le prompt dans la boîte et cliquez sur <StrongComponent>Invoke</StrongComponent> pour générer votre première image. Sélectionnez un template de prompt pour améliorer les résultats. Vous pouvez choisir de sauvegarder vos images directement sur <StrongComponent>Galerie</StrongComponent> ou les modifier sur la <StrongComponent>Toile</StrongComponent>."
     },
     "upsell": {
         "shareAccess": "Partager l'accès",

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

@@ -577,7 +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",
@@ -722,7 +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",
@@ -731,7 +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",
@@ -770,7 +781,12 @@
         "imageSavingFailed": "Salvataggio dell'immagine non riuscito",
         "layerCopiedToClipboard": "Livello copiato negli appunti",
         "imageNotLoadedDesc": "Impossibile trovare l'immagine",
-        "linkCopied": "Collegamento copiato"
+        "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",
@@ -785,7 +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",
@@ -2006,7 +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",
@@ -160,7 +161,9 @@
         "openViewer": "Открыть просмотрщик",
         "closeViewer": "Закрыть просмотрщик",
         "imagesTab": "Изображения, созданные и сохраненные в Invoke.",
-        "assetsTab": "Файлы, которые вы загрузили для использования в своих проектах."
+        "assetsTab": "Файлы, которые вы загрузили для использования в своих проектах.",
+        "boardsSettings": "Настройки доски",
+        "imagesSettings": "Настройки галереи изображений"
     },
     "hotkeys": {
         "searchHotkeys": "Поиск горячих клавиш",
@@ -583,7 +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",
@@ -730,7 +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",
@@ -742,7 +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",
@@ -777,7 +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",
@@ -792,7 +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",
@@ -933,7 +954,7 @@
         "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>"
+        "workflowHelpText": "Нужна помощь? Ознакомьтесь с нашим руководством <LinkComponent>Getting Started with Workflows</LinkComponent>."
     },
     "boards": {
         "autoAddBoard": "Авто добавление Доски",
@@ -1409,7 +1430,8 @@
         "recallParameter": "Отозвать {{label}}",
         "allPrompts": "Все запросы",
         "imageDimensions": "Размеры изображения",
-        "canvasV2Metadata": "Холст"
+        "canvasV2Metadata": "Холст",
+        "guidance": "Точность"
     },
     "queue": {
         "status": "Статус",
@@ -1561,7 +1583,12 @@
         "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"
+        "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",
@@ -1890,7 +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",
@@ -1920,7 +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": {

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';
@@ -59,6 +60,7 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
   useGlobalModifiersInit();
   useGlobalHotkeys();
   useGetOpenAPISchemaQuery();
+  useSyncLoggingConfig();
 
   const { dropzone, isHandlingUpload, setIsHandlingUpload } = useFullscreenDropzone();
 

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/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/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
@@ -119,4 +119,4 @@ export type AppConfig = {
   };
 };
 
-export type PartialAppConfig = O.Partial<AppConfig, 'deep'>;
+export type PartialAppConfig = PartialDeep<AppConfig>;

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

@@ -26,5 +26,9 @@ export const IconMenuItem = ({ tooltip, icon, ...props }: Props) => {
 };
 
 export const IconMenuItemGroup = ({ children }: { children: ReactNode }) => {
-  return <Flex gap={2}>{children}</Flex>;
+  return (
+    <Flex gap={2} justifyContent="space-between">
+      {children}
+    </Flex>
+  );
 };

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

@@ -127,8 +127,6 @@ export const buildUseDisclosure = (defaultIsOpen: boolean): [() => UseDisclosure
  *
  * Hook to manage a boolean state. Use this for a local boolean state.
  * @param defaultIsOpen Initial state of the disclosure
- *
- * @knipignore
  */
 export const useDisclosure = (defaultIsOpen: boolean): UseDisclosure => {
   const [isOpen, set] = useState(defaultIsOpen);

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

@@ -16,6 +16,7 @@ type UseGroupedModelComboboxArg<T extends AnyModelConfig> = {
   getIsDisabled?: (model: T) => boolean;
   isLoading?: boolean;
   groupByType?: boolean;
+  showDescriptions?: boolean;
 };
 
 type UseGroupedModelComboboxReturn = {
@@ -37,7 +38,15 @@ export const useGroupedModelCombobox = <T extends AnyModelConfig>(
 ): UseGroupedModelComboboxReturn => {
   const { t } = useTranslation();
   const base = useAppSelector(selectBaseWithSDXLFallback);
-  const { modelConfigs, selectedModel, getIsDisabled, onChange, isLoading, groupByType = false } = arg;
+  const {
+    modelConfigs,
+    selectedModel,
+    getIsDisabled,
+    onChange,
+    isLoading,
+    groupByType = false,
+    showDescriptions = false,
+  } = arg;
   const options = useMemo<GroupBase<ComboboxOption>[]>(() => {
     if (!modelConfigs) {
       return [];
@@ -51,6 +60,7 @@ export const useGroupedModelCombobox = <T extends AnyModelConfig>(
           options: val.map((model) => ({
             label: model.name,
             value: model.key,
+            description: (showDescriptions && model.description) || undefined,
             isDisabled: getIsDisabled ? getIsDisabled(model) : false,
           })),
         });
@@ -60,7 +70,7 @@ 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, showDescriptions]);
 
   const value = useMemo(
     () =>

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/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,
@@ -28,70 +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}
-          >
-            {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/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 +1,40 @@
-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 { selectSelectedEntityIdentifier } from 'features/controlLayers/store/selectors';
-import {
-  isFilterableEntityIdentifier,
-  isSaveableEntityIdentifier,
-  isTransformableEntityIdentifier,
-} from 'features/controlLayers/store/types';
 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(() => {

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

@@ -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>

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

@@ -1,5 +1,6 @@
 import { Flex, Spacer } from '@invoke-ai/ui-library';
 import { EntityListGlobalActionBarAddLayerMenu } from 'features/controlLayers/components/CanvasEntityList/EntityListGlobalActionBarAddLayerMenu';
+import { EntityListSelectedEntityActionBarAutoMaskButton } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarAutoMaskButton';
 import { EntityListSelectedEntityActionBarDuplicateButton } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarDuplicateButton';
 import { EntityListSelectedEntityActionBarFill } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarFill';
 import { EntityListSelectedEntityActionBarFilterButton } from 'features/controlLayers/components/CanvasEntityList/EntityListSelectedEntityActionBarFilterButton';
@@ -16,6 +17,7 @@ export const EntityListSelectedEntityActionBar = memo(() => {
       <Spacer />
       <EntityListSelectedEntityActionBarFill />
       <Flex h="full">
+        <EntityListSelectedEntityActionBarAutoMaskButton />
         <EntityListSelectedEntityActionBarFilterButton />
         <EntityListSelectedEntityActionBarTransformButton />
         <EntityListSelectedEntityActionBarSaveToAssetsButton />

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

@@ -0,0 +1,37 @@
+import { IconButton } from '@invoke-ai/ui-library';
+import { useAppSelector } from 'app/store/storeHooks';
+import { useEntitySegmentAnything } from 'features/controlLayers/hooks/useEntitySegmentAnything';
+import { selectSelectedEntityIdentifier } from 'features/controlLayers/store/selectors';
+import { isSegmentableEntityIdentifier } from 'features/controlLayers/store/types';
+import { memo } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiMaskHappyBold } from 'react-icons/pi';
+
+export const EntityListSelectedEntityActionBarAutoMaskButton = memo(() => {
+  const { t } = useTranslation();
+  const selectedEntityIdentifier = useAppSelector(selectSelectedEntityIdentifier);
+  const segment = useEntitySegmentAnything(selectedEntityIdentifier);
+
+  if (!selectedEntityIdentifier) {
+    return null;
+  }
+
+  if (!isSegmentableEntityIdentifier(selectedEntityIdentifier)) {
+    return null;
+  }
+
+  return (
+    <IconButton
+      onClick={segment.start}
+      isDisabled={segment.isDisabled}
+      size="sm"
+      variant="link"
+      alignSelf="stretch"
+      aria-label={t('controlLayers.segment.autoMask')}
+      tooltip={t('controlLayers.segment.autoMask')}
+      icon={<PiMaskHappyBold />}
+    />
+  );
+});
+
+EntityListSelectedEntityActionBarAutoMaskButton.displayName = 'EntityListSelectedEntityActionBarAutoMaskButton';

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

@@ -10,6 +10,7 @@ import { CanvasDropArea } from 'features/controlLayers/components/CanvasDropArea
 import { Filter } from 'features/controlLayers/components/Filters/Filter';
 import { CanvasHUD } from 'features/controlLayers/components/HUD/CanvasHUD';
 import { InvokeCanvasComponent } from 'features/controlLayers/components/InvokeCanvasComponent';
+import { SegmentAnything } from 'features/controlLayers/components/SegmentAnything/SegmentAnything';
 import { StagingAreaIsStagingGate } from 'features/controlLayers/components/StagingArea/StagingAreaIsStagingGate';
 import { StagingAreaToolbar } from 'features/controlLayers/components/StagingArea/StagingAreaToolbar';
 import { CanvasToolbar } from 'features/controlLayers/components/Toolbar/CanvasToolbar';
@@ -24,8 +25,8 @@ const MenuContent = () => {
   return (
     <CanvasManagerProviderGate>
       <MenuList>
-        <CanvasContextMenuGlobalMenuItems />
         <CanvasContextMenuSelectedEntityMenuItems />
+        <CanvasContextMenuGlobalMenuItems />
       </MenuList>
     </CanvasManagerProviderGate>
   );
@@ -101,6 +102,7 @@ export const CanvasMainPanelContent = memo(() => {
         <CanvasManagerProviderGate>
           <Filter />
           <Transform />
+          <SegmentAnything />
         </CanvasManagerProviderGate>
       </Flex>
       <CanvasDropArea />

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

@@ -0,0 +1,28 @@
+import { FormControl, FormLabel, Switch, Tooltip } from '@invoke-ai/ui-library';
+import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import {
+  selectIsolatedLayerPreview,
+  settingsIsolatedLayerPreviewToggled,
+} from 'features/controlLayers/store/canvasSettingsSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+
+export const CanvasOperationIsolatedLayerPreviewSwitch = memo(() => {
+  const { t } = useTranslation();
+  const dispatch = useAppDispatch();
+  const isolatedLayerPreview = useAppSelector(selectIsolatedLayerPreview);
+  const onChangeIsolatedPreview = useCallback(() => {
+    dispatch(settingsIsolatedLayerPreviewToggled());
+  }, [dispatch]);
+
+  return (
+    <Tooltip label={t('controlLayers.settings.isolatedLayerPreviewDesc')}>
+      <FormControl w="min-content">
+        <FormLabel m={0}>{t('controlLayers.settings.isolatedPreview')}</FormLabel>
+        <Switch size="sm" isChecked={isolatedLayerPreview} onChange={onChangeIsolatedPreview} />
+      </FormControl>
+    </Tooltip>
+  );
+});
+
+CanvasOperationIsolatedLayerPreviewSwitch.displayName = 'CanvasOperationIsolatedLayerPreviewSwitch';

invokeai/frontend/web/src/features/controlLayers/components/ControlLayer/ControlLayerMenuItems.tsx

@@ -1,14 +1,15 @@
 import { MenuDivider } from '@invoke-ai/ui-library';
 import { IconMenuItemGroup } from 'common/components/IconMenuItem';
 import { CanvasEntityMenuItemsArrange } from 'features/controlLayers/components/common/CanvasEntityMenuItemsArrange';
-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 { CanvasEntityMenuItemsDuplicate } from 'features/controlLayers/components/common/CanvasEntityMenuItemsDuplicate';
 import { CanvasEntityMenuItemsFilter } from 'features/controlLayers/components/common/CanvasEntityMenuItemsFilter';
 import { CanvasEntityMenuItemsSave } from 'features/controlLayers/components/common/CanvasEntityMenuItemsSave';
+import { CanvasEntityMenuItemsSegment } from 'features/controlLayers/components/common/CanvasEntityMenuItemsSegment';
 import { CanvasEntityMenuItemsTransform } from 'features/controlLayers/components/common/CanvasEntityMenuItemsTransform';
-import { ControlLayerMenuItemsConvertControlToRaster } from 'features/controlLayers/components/ControlLayer/ControlLayerMenuItemsConvertControlToRaster';
+import { ControlLayerMenuItemsConvertToSubMenu } from 'features/controlLayers/components/ControlLayer/ControlLayerMenuItemsConvertToSubMenu';
+import { ControlLayerMenuItemsCopyToSubMenu } from 'features/controlLayers/components/ControlLayer/ControlLayerMenuItemsCopyToSubMenu';
 import { ControlLayerMenuItemsTransparencyEffect } from 'features/controlLayers/components/ControlLayer/ControlLayerMenuItemsTransparencyEffect';
 import { memo } from 'react';
 
@@ -23,12 +24,14 @@ export const ControlLayerMenuItems = memo(() => {
       <MenuDivider />
       <CanvasEntityMenuItemsTransform />
       <CanvasEntityMenuItemsFilter />
-      <ControlLayerMenuItemsConvertControlToRaster />
+      <CanvasEntityMenuItemsSegment />
       <ControlLayerMenuItemsTransparencyEffect />
       <MenuDivider />
       <CanvasEntityMenuItemsCropToBbox />
-      <CanvasEntityMenuItemsCopyToClipboard />
       <CanvasEntityMenuItemsSave />
+      <MenuDivider />
+      <ControlLayerMenuItemsConvertToSubMenu />
+      <ControlLayerMenuItemsCopyToSubMenu />
     </>
   );
 });

invokeai/frontend/web/src/features/controlLayers/components/ControlLayer/ControlLayerMenuItemsConvertControlToRaster.tsx

@@ -1,27 +0,0 @@
-import { MenuItem } from '@invoke-ai/ui-library';
-import { useAppDispatch } from 'app/store/storeHooks';
-import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
-import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
-import { controlLayerConvertedToRasterLayer } from 'features/controlLayers/store/canvasSlice';
-import { memo, useCallback } from 'react';
-import { useTranslation } from 'react-i18next';
-import { PiLightningBold } from 'react-icons/pi';
-
-export const ControlLayerMenuItemsConvertControlToRaster = memo(() => {
-  const { t } = useTranslation();
-  const dispatch = useAppDispatch();
-  const entityIdentifier = useEntityIdentifierContext('control_layer');
-  const isInteractable = useIsEntityInteractable(entityIdentifier);
-
-  const convertControlLayerToRasterLayer = useCallback(() => {
-    dispatch(controlLayerConvertedToRasterLayer({ entityIdentifier }));
-  }, [dispatch, entityIdentifier]);
-
-  return (
-    <MenuItem onClick={convertControlLayerToRasterLayer} icon={<PiLightningBold />} isDisabled={!isInteractable}>
-      {t('controlLayers.convertToRasterLayer')}
-    </MenuItem>
-  );
-});
-
-ControlLayerMenuItemsConvertControlToRaster.displayName = 'ControlLayerMenuItemsConvertControlToRaster';

invokeai/frontend/web/src/features/controlLayers/components/ControlLayer/ControlLayerMenuItemsConvertToSubMenu.tsx

@@ -0,0 +1,56 @@
+import { Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
+import {
+  controlLayerConvertedToInpaintMask,
+  controlLayerConvertedToRasterLayer,
+  controlLayerConvertedToRegionalGuidance,
+} from 'features/controlLayers/store/canvasSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiSwapBold } from 'react-icons/pi';
+
+export const ControlLayerMenuItemsConvertToSubMenu = memo(() => {
+  const { t } = useTranslation();
+  const subMenu = useSubMenu();
+  const dispatch = useAppDispatch();
+  const entityIdentifier = useEntityIdentifierContext('control_layer');
+  const isInteractable = useIsEntityInteractable(entityIdentifier);
+
+  const convertToInpaintMask = useCallback(() => {
+    dispatch(controlLayerConvertedToInpaintMask({ entityIdentifier, replace: true }));
+  }, [dispatch, entityIdentifier]);
+
+  const convertToRegionalGuidance = useCallback(() => {
+    dispatch(controlLayerConvertedToRegionalGuidance({ entityIdentifier, replace: true }));
+  }, [dispatch, entityIdentifier]);
+
+  const convertToRasterLayer = useCallback(() => {
+    dispatch(controlLayerConvertedToRasterLayer({ entityIdentifier, replace: true }));
+  }, [dispatch, entityIdentifier]);
+
+  return (
+    <MenuItem {...subMenu.parentMenuItemProps} icon={<PiSwapBold />}>
+      <Menu {...subMenu.menuProps}>
+        <MenuButton {...subMenu.menuButtonProps}>
+          <SubMenuButtonContent label={t('controlLayers.convertControlLayerTo')} />
+        </MenuButton>
+        <MenuList {...subMenu.menuListProps}>
+          <MenuItem onClick={convertToInpaintMask} icon={<PiSwapBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.inpaintMask')}
+          </MenuItem>
+          <MenuItem onClick={convertToRegionalGuidance} icon={<PiSwapBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.regionalGuidance')}
+          </MenuItem>
+          <MenuItem onClick={convertToRasterLayer} icon={<PiSwapBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.rasterLayer')}
+          </MenuItem>
+        </MenuList>
+      </Menu>
+    </MenuItem>
+  );
+});
+
+ControlLayerMenuItemsConvertToSubMenu.displayName = 'ControlLayerMenuItemsConvertToSubMenu';

invokeai/frontend/web/src/features/controlLayers/components/ControlLayer/ControlLayerMenuItemsCopyToSubMenu.tsx

@@ -0,0 +1,58 @@
+import { Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
+import { CanvasEntityMenuItemsCopyToClipboard } from 'features/controlLayers/components/common/CanvasEntityMenuItemsCopyToClipboard';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
+import {
+  controlLayerConvertedToInpaintMask,
+  controlLayerConvertedToRasterLayer,
+  controlLayerConvertedToRegionalGuidance,
+} from 'features/controlLayers/store/canvasSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiCopyBold } from 'react-icons/pi';
+
+export const ControlLayerMenuItemsCopyToSubMenu = memo(() => {
+  const { t } = useTranslation();
+  const subMenu = useSubMenu();
+  const dispatch = useAppDispatch();
+  const entityIdentifier = useEntityIdentifierContext('control_layer');
+  const isInteractable = useIsEntityInteractable(entityIdentifier);
+
+  const copyToInpaintMask = useCallback(() => {
+    dispatch(controlLayerConvertedToInpaintMask({ entityIdentifier }));
+  }, [dispatch, entityIdentifier]);
+
+  const copyToRegionalGuidance = useCallback(() => {
+    dispatch(controlLayerConvertedToRegionalGuidance({ entityIdentifier }));
+  }, [dispatch, entityIdentifier]);
+
+  const copyToRasterLayer = useCallback(() => {
+    dispatch(controlLayerConvertedToRasterLayer({ entityIdentifier }));
+  }, [dispatch, entityIdentifier]);
+
+  return (
+    <MenuItem {...subMenu.parentMenuItemProps} icon={<PiCopyBold />}>
+      <Menu {...subMenu.menuProps}>
+        <MenuButton {...subMenu.menuButtonProps}>
+          <SubMenuButtonContent label={t('controlLayers.copyControlLayerTo')} />
+        </MenuButton>
+        <MenuList {...subMenu.menuListProps}>
+          <CanvasEntityMenuItemsCopyToClipboard />
+          <MenuItem onClick={copyToInpaintMask} icon={<PiCopyBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.newInpaintMask')}
+          </MenuItem>
+          <MenuItem onClick={copyToRegionalGuidance} icon={<PiCopyBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.newRegionalGuidance')}
+          </MenuItem>
+          <MenuItem onClick={copyToRasterLayer} icon={<PiCopyBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.newRasterLayer')}
+          </MenuItem>
+        </MenuList>
+      </Menu>
+    </MenuItem>
+  );
+});
+
+ControlLayerMenuItemsCopyToSubMenu.displayName = 'ControlLayerMenuItemsCopyToSubMenu';

invokeai/frontend/web/src/features/controlLayers/components/Filters/Filter.tsx

@@ -1,18 +1,15 @@
-import { Button, ButtonGroup, Flex, FormControl, FormLabel, Heading, Spacer, Switch } from '@invoke-ai/ui-library';
+import { Button, ButtonGroup, Flex, Heading, Spacer } from '@invoke-ai/ui-library';
 import { useStore } from '@nanostores/react';
-import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import { useAppSelector } from 'app/store/storeHooks';
 import { useFocusRegion, useIsRegionFocused } from 'common/hooks/focus';
+import { CanvasAutoProcessSwitch } from 'features/controlLayers/components/CanvasAutoProcessSwitch';
+import { CanvasOperationIsolatedLayerPreviewSwitch } from 'features/controlLayers/components/CanvasOperationIsolatedLayerPreviewSwitch';
 import { FilterSettings } from 'features/controlLayers/components/Filters/FilterSettings';
 import { FilterTypeSelect } from 'features/controlLayers/components/Filters/FilterTypeSelect';
 import { useCanvasManager } from 'features/controlLayers/contexts/CanvasManagerProviderGate';
 import type { CanvasEntityAdapterControlLayer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterControlLayer';
 import type { CanvasEntityAdapterRasterLayer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterRasterLayer';
-import {
-  selectAutoProcessFilter,
-  selectIsolatedFilteringPreview,
-  settingsAutoProcessFilterToggled,
-  settingsIsolatedFilteringPreviewToggled,
-} from 'features/controlLayers/store/canvasSettingsSlice';
+import { selectAutoProcess } from 'features/controlLayers/store/canvasSettingsSlice';
 import type { FilterConfig } from 'features/controlLayers/store/filters';
 import { IMAGE_FILTERS } from 'features/controlLayers/store/filters';
 import { useRegisteredHotkeys } from 'features/system/components/HotkeysModal/useHotkeyData';
@@ -23,19 +20,13 @@ import { PiArrowsCounterClockwiseBold, PiCheckBold, PiShootingStarBold, PiXBold
 const FilterContent = memo(
   ({ adapter }: { adapter: CanvasEntityAdapterRasterLayer | CanvasEntityAdapterControlLayer }) => {
     const { t } = useTranslation();
-    const dispatch = useAppDispatch();
     const ref = useRef<HTMLDivElement>(null);
     useFocusRegion('canvas', ref, { focusOnMount: true });
-
     const config = useStore(adapter.filterer.$filterConfig);
     const isCanvasFocused = useIsRegionFocused('canvas');
     const isProcessing = useStore(adapter.filterer.$isProcessing);
     const hasProcessed = useStore(adapter.filterer.$hasProcessed);
-    const autoProcessFilter = useAppSelector(selectAutoProcessFilter);
-    const isolatedFilteringPreview = useAppSelector(selectIsolatedFilteringPreview);
-    const onChangeIsolatedPreview = useCallback(() => {
-      dispatch(settingsIsolatedFilteringPreviewToggled());
-    }, [dispatch]);
+    const autoProcess = useAppSelector(selectAutoProcess);
 
     const onChangeFilterConfig = useCallback(
       (filterConfig: FilterConfig) => {
@@ -51,10 +42,6 @@ const FilterContent = memo(
       [adapter.filterer.$filterConfig]
     );
 
-    const onChangeAutoProcessFilter = useCallback(() => {
-      dispatch(settingsAutoProcessFilterToggled());
-    }, [dispatch]);
-
     const isValid = useMemo(() => {
       return IMAGE_FILTERS[config.type].validateConfig?.(config as never) ?? true;
     }, [config]);
@@ -94,14 +81,8 @@ const FilterContent = memo(
             {t('controlLayers.filter.filter')}
           </Heading>
           <Spacer />
-          <FormControl w="min-content">
-            <FormLabel m={0}>{t('controlLayers.filter.autoProcess')}</FormLabel>
-            <Switch size="sm" isChecked={autoProcessFilter} onChange={onChangeAutoProcessFilter} />
-          </FormControl>
-          <FormControl w="min-content">
-            <FormLabel m={0}>{t('controlLayers.settings.isolatedPreview')}</FormLabel>
-            <Switch size="sm" isChecked={isolatedFilteringPreview} onChange={onChangeIsolatedPreview} />
-          </FormControl>
+          <CanvasAutoProcessSwitch />
+          <CanvasOperationIsolatedLayerPreviewSwitch />
         </Flex>
         <FilterTypeSelect filterType={config.type} onChange={onChangeFilterType} />
         <FilterSettings filterConfig={config} onChange={onChangeFilterConfig} />
@@ -112,7 +93,7 @@ const FilterContent = memo(
             onClick={adapter.filterer.processImmediate}
             isLoading={isProcessing}
             loadingText={t('controlLayers.filter.process')}
-            isDisabled={!isValid || autoProcessFilter}
+            isDisabled={!isValid || autoProcess}
           >
             {t('controlLayers.filter.process')}
           </Button>

invokeai/frontend/web/src/features/controlLayers/components/IPAdapter/IPAdapterMenuItemPullBbox.tsx

@@ -0,0 +1,22 @@
+import { MenuItem } from '@invoke-ai/ui-library';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { usePullBboxIntoGlobalReferenceImage } from 'features/controlLayers/hooks/saveCanvasHooks';
+import { useCanvasIsBusy } from 'features/controlLayers/hooks/useCanvasIsBusy';
+import { memo } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiBoundingBoxBold } from 'react-icons/pi';
+
+export const IPAdapterMenuItemPullBbox = memo(() => {
+  const { t } = useTranslation();
+  const entityIdentifier = useEntityIdentifierContext('reference_image');
+  const pullBboxIntoIPAdapter = usePullBboxIntoGlobalReferenceImage(entityIdentifier);
+  const isBusy = useCanvasIsBusy();
+
+  return (
+    <MenuItem onClick={pullBboxIntoIPAdapter} icon={<PiBoundingBoxBold />} isDisabled={isBusy}>
+      {t('controlLayers.pullBboxIntoReferenceImage')}
+    </MenuItem>
+  );
+});
+
+IPAdapterMenuItemPullBbox.displayName = 'IPAdapterMenuItemPullBbox';

invokeai/frontend/web/src/features/controlLayers/components/IPAdapter/IPAdapterMenuItems.tsx

@@ -1,16 +1,22 @@
+import { MenuDivider } from '@invoke-ai/ui-library';
 import { IconMenuItemGroup } from 'common/components/IconMenuItem';
 import { CanvasEntityMenuItemsArrange } from 'features/controlLayers/components/common/CanvasEntityMenuItemsArrange';
 import { CanvasEntityMenuItemsDelete } from 'features/controlLayers/components/common/CanvasEntityMenuItemsDelete';
 import { CanvasEntityMenuItemsDuplicate } from 'features/controlLayers/components/common/CanvasEntityMenuItemsDuplicate';
+import { IPAdapterMenuItemPullBbox } from 'features/controlLayers/components/IPAdapter/IPAdapterMenuItemPullBbox';
 import { memo } from 'react';
 
 export const IPAdapterMenuItems = memo(() => {
   return (
-    <IconMenuItemGroup>
-      <CanvasEntityMenuItemsArrange />
-      <CanvasEntityMenuItemsDuplicate />
-      <CanvasEntityMenuItemsDelete asIcon />
-    </IconMenuItemGroup>
+    <>
+      <IconMenuItemGroup>
+        <CanvasEntityMenuItemsArrange />
+        <CanvasEntityMenuItemsDuplicate />
+        <CanvasEntityMenuItemsDelete asIcon />
+      </IconMenuItemGroup>
+      <MenuDivider />
+      <IPAdapterMenuItemPullBbox />
+    </>
   );
 });
 

invokeai/frontend/web/src/features/controlLayers/components/IPAdapter/IPAdapterModel.tsx

@@ -2,7 +2,7 @@ import type { ComboboxOnChange } from '@invoke-ai/ui-library';
 import { Combobox, Flex, FormControl, Tooltip } from '@invoke-ai/ui-library';
 import { useAppSelector } from 'app/store/storeHooks';
 import { useGroupedModelCombobox } from 'common/hooks/useGroupedModelCombobox';
-import { selectBase } from 'features/controlLayers/store/paramsSlice';
+import { selectBase, selectIsFLUX } from 'features/controlLayers/store/paramsSlice';
 import type { CLIPVisionModelV2 } from 'features/controlLayers/store/types';
 import { isCLIPVisionModelV2 } from 'features/controlLayers/store/types';
 import { memo, useCallback, useMemo } from 'react';
@@ -11,9 +11,13 @@ import { useIPAdapterModels } from 'services/api/hooks/modelsByType';
 import type { AnyModelConfig, IPAdapterModelConfig } from 'services/api/types';
 import { assert } from 'tsafe';
 
+// at this time, ViT-L is the only supported clip model for FLUX IP adapter
+const FLUX_CLIP_VISION = 'ViT-L';
+
 const CLIP_VISION_OPTIONS = [
   { label: 'ViT-H', value: 'ViT-H' },
   { label: 'ViT-G', value: 'ViT-G' },
+  { label: FLUX_CLIP_VISION, value: FLUX_CLIP_VISION },
 ];
 
 type Props = {
@@ -47,6 +51,8 @@ export const IPAdapterModel = memo(({ modelKey, onChangeModel, clipVisionModel,
     [onChangeCLIPVisionModel]
   );
 
+  const isFLUX = useAppSelector(selectIsFLUX);
+
   const getIsDisabled = useCallback(
     (model: AnyModelConfig): boolean => {
       const isCompatible = currentBaseModel === model.base;
@@ -64,10 +70,16 @@ export const IPAdapterModel = memo(({ modelKey, onChangeModel, clipVisionModel,
     isLoading,
   });
 
-  const clipVisionModelValue = useMemo(
-    () => CLIP_VISION_OPTIONS.find((o) => o.value === clipVisionModel),
-    [clipVisionModel]
-  );
+  const clipVisionOptions = useMemo(() => {
+    return CLIP_VISION_OPTIONS.map((option) => ({
+      ...option,
+      isDisabled: isFLUX && option.value !== FLUX_CLIP_VISION,
+    }));
+  }, [isFLUX]);
+
+  const clipVisionModelValue = useMemo(() => {
+    return CLIP_VISION_OPTIONS.find((o) => o.value === clipVisionModel);
+  }, [clipVisionModel]);
 
   return (
     <Flex gap={2}>
@@ -85,7 +97,7 @@ export const IPAdapterModel = memo(({ modelKey, onChangeModel, clipVisionModel,
       {selectedModel?.format === 'checkpoint' && (
         <FormControl isInvalid={!value || currentBaseModel !== selectedModel?.base} width="max-content" minWidth={28}>
           <Combobox
-            options={CLIP_VISION_OPTIONS}
+            options={clipVisionOptions}
             placeholder={t('common.placeholderSelectAModel')}
             value={clipVisionModelValue}
             onChange={_onChangeCLIPVisionModel}

invokeai/frontend/web/src/features/controlLayers/components/IPAdapter/IPAdapterSettings.tsx

@@ -16,6 +16,7 @@ import {
   referenceImageIPAdapterModelChanged,
   referenceImageIPAdapterWeightChanged,
 } from 'features/controlLayers/store/canvasSlice';
+import { selectIsFLUX } from 'features/controlLayers/store/paramsSlice';
 import { selectCanvasSlice, selectEntityOrThrow } from 'features/controlLayers/store/selectors';
 import type { CLIPVisionModelV2, IPMethodV2 } from 'features/controlLayers/store/types';
 import type { IPAImageDropData } from 'features/dnd/types';
@@ -90,6 +91,8 @@ export const IPAdapterSettings = memo(() => {
   const pullBboxIntoIPAdapter = usePullBboxIntoGlobalReferenceImage(entityIdentifier);
   const isBusy = useCanvasIsBusy();
 
+  const isFLUX = useAppSelector(selectIsFLUX);
+
   return (
     <CanvasEntitySettingsWrapper>
       <Flex flexDir="column" gap={2} position="relative" w="full">
@@ -113,7 +116,7 @@ export const IPAdapterSettings = memo(() => {
         </Flex>
         <Flex gap={2} w="full" alignItems="center">
           <Flex flexDir="column" gap={2} w="full">
-            <IPAdapterMethod method={ipAdapter.method} onChange={onChangeIPMethod} />
+            {!isFLUX && <IPAdapterMethod method={ipAdapter.method} onChange={onChangeIPMethod} />}
             <Weight weight={ipAdapter.weight} onChange={onChangeWeight} />
             <BeginEndStepPct beginEndStepPct={ipAdapter.beginEndStepPct} onChange={onChangeBeginEndStepPct} />
           </Flex>

invokeai/frontend/web/src/features/controlLayers/components/InpaintMask/InpaintMaskMenuItems.tsx

@@ -5,6 +5,8 @@ import { CanvasEntityMenuItemsCropToBbox } from 'features/controlLayers/componen
 import { CanvasEntityMenuItemsDelete } from 'features/controlLayers/components/common/CanvasEntityMenuItemsDelete';
 import { CanvasEntityMenuItemsDuplicate } from 'features/controlLayers/components/common/CanvasEntityMenuItemsDuplicate';
 import { CanvasEntityMenuItemsTransform } from 'features/controlLayers/components/common/CanvasEntityMenuItemsTransform';
+import { InpaintMaskMenuItemsConvertToSubMenu } from 'features/controlLayers/components/InpaintMask/InpaintMaskMenuItemsConvertToSubMenu';
+import { InpaintMaskMenuItemsCopyToSubMenu } from 'features/controlLayers/components/InpaintMask/InpaintMaskMenuItemsCopyToSubMenu';
 import { memo } from 'react';
 
 export const InpaintMaskMenuItems = memo(() => {
@@ -19,6 +21,9 @@ export const InpaintMaskMenuItems = memo(() => {
       <CanvasEntityMenuItemsTransform />
       <MenuDivider />
       <CanvasEntityMenuItemsCropToBbox />
+      <MenuDivider />
+      <InpaintMaskMenuItemsConvertToSubMenu />
+      <InpaintMaskMenuItemsCopyToSubMenu />
     </>
   );
 });

invokeai/frontend/web/src/features/controlLayers/components/InpaintMask/InpaintMaskMenuItemsConvertToSubMenu.tsx

@@ -0,0 +1,38 @@
+import { Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
+import { inpaintMaskConvertedToRegionalGuidance } from 'features/controlLayers/store/canvasSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiSwapBold } from 'react-icons/pi';
+
+export const InpaintMaskMenuItemsConvertToSubMenu = memo(() => {
+  const { t } = useTranslation();
+  const subMenu = useSubMenu();
+  const dispatch = useAppDispatch();
+  const entityIdentifier = useEntityIdentifierContext('inpaint_mask');
+  const isInteractable = useIsEntityInteractable(entityIdentifier);
+
+  const convertToRegionalGuidance = useCallback(() => {
+    dispatch(inpaintMaskConvertedToRegionalGuidance({ entityIdentifier, replace: true }));
+  }, [dispatch, entityIdentifier]);
+
+  return (
+    <MenuItem {...subMenu.parentMenuItemProps} icon={<PiSwapBold />}>
+      <Menu {...subMenu.menuProps}>
+        <MenuButton {...subMenu.menuButtonProps}>
+          <SubMenuButtonContent label={t('controlLayers.convertInpaintMaskTo')} />
+        </MenuButton>
+        <MenuList {...subMenu.menuListProps}>
+          <MenuItem onClick={convertToRegionalGuidance} icon={<PiSwapBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.regionalGuidance')}
+          </MenuItem>
+        </MenuList>
+      </Menu>
+    </MenuItem>
+  );
+});
+
+InpaintMaskMenuItemsConvertToSubMenu.displayName = 'InpaintMaskMenuItemsConvertToSubMenu';

invokeai/frontend/web/src/features/controlLayers/components/InpaintMask/InpaintMaskMenuItemsCopyToSubMenu.tsx

@@ -0,0 +1,40 @@
+import { Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
+import { CanvasEntityMenuItemsCopyToClipboard } from 'features/controlLayers/components/common/CanvasEntityMenuItemsCopyToClipboard';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
+import { inpaintMaskConvertedToRegionalGuidance } from 'features/controlLayers/store/canvasSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiCopyBold } from 'react-icons/pi';
+
+export const InpaintMaskMenuItemsCopyToSubMenu = memo(() => {
+  const { t } = useTranslation();
+  const subMenu = useSubMenu();
+  const dispatch = useAppDispatch();
+  const entityIdentifier = useEntityIdentifierContext('inpaint_mask');
+  const isInteractable = useIsEntityInteractable(entityIdentifier);
+
+  const copyToRegionalGuidance = useCallback(() => {
+    dispatch(inpaintMaskConvertedToRegionalGuidance({ entityIdentifier }));
+  }, [dispatch, entityIdentifier]);
+
+  return (
+    <MenuItem {...subMenu.parentMenuItemProps} icon={<PiCopyBold />}>
+      <Menu {...subMenu.menuProps}>
+        <MenuButton {...subMenu.menuButtonProps}>
+          <SubMenuButtonContent label={t('controlLayers.copyInpaintMaskTo')} />
+        </MenuButton>
+        <MenuList {...subMenu.menuListProps}>
+          <CanvasEntityMenuItemsCopyToClipboard />
+          <MenuItem onClick={copyToRegionalGuidance} icon={<PiCopyBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.newRegionalGuidance')}
+          </MenuItem>
+        </MenuList>
+      </Menu>
+    </MenuItem>
+  );
+});
+
+InpaintMaskMenuItemsCopyToSubMenu.displayName = 'InpaintMaskMenuItemsCopyToSubMenu';

invokeai/frontend/web/src/features/controlLayers/components/RasterLayer/RasterLayerMenuItems.tsx

@@ -1,14 +1,15 @@
 import { MenuDivider } from '@invoke-ai/ui-library';
 import { IconMenuItemGroup } from 'common/components/IconMenuItem';
 import { CanvasEntityMenuItemsArrange } from 'features/controlLayers/components/common/CanvasEntityMenuItemsArrange';
-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 { CanvasEntityMenuItemsDuplicate } from 'features/controlLayers/components/common/CanvasEntityMenuItemsDuplicate';
 import { CanvasEntityMenuItemsFilter } from 'features/controlLayers/components/common/CanvasEntityMenuItemsFilter';
 import { CanvasEntityMenuItemsSave } from 'features/controlLayers/components/common/CanvasEntityMenuItemsSave';
+import { CanvasEntityMenuItemsSegment } from 'features/controlLayers/components/common/CanvasEntityMenuItemsSegment';
 import { CanvasEntityMenuItemsTransform } from 'features/controlLayers/components/common/CanvasEntityMenuItemsTransform';
-import { RasterLayerMenuItemsConvertRasterToControl } from 'features/controlLayers/components/RasterLayer/RasterLayerMenuItemsConvertRasterToControl';
+import { RasterLayerMenuItemsConvertToSubMenu } from 'features/controlLayers/components/RasterLayer/RasterLayerMenuItemsConvertToSubMenu';
+import { RasterLayerMenuItemsCopyToSubMenu } from 'features/controlLayers/components/RasterLayer/RasterLayerMenuItemsCopyToSubMenu';
 import { memo } from 'react';
 
 export const RasterLayerMenuItems = memo(() => {
@@ -22,11 +23,13 @@ export const RasterLayerMenuItems = memo(() => {
       <MenuDivider />
       <CanvasEntityMenuItemsTransform />
       <CanvasEntityMenuItemsFilter />
-      <RasterLayerMenuItemsConvertRasterToControl />
+      <CanvasEntityMenuItemsSegment />
       <MenuDivider />
       <CanvasEntityMenuItemsCropToBbox />
-      <CanvasEntityMenuItemsCopyToClipboard />
       <CanvasEntityMenuItemsSave />
+      <MenuDivider />
+      <RasterLayerMenuItemsConvertToSubMenu />
+      <RasterLayerMenuItemsCopyToSubMenu />
     </>
   );
 });

invokeai/frontend/web/src/features/controlLayers/components/RasterLayer/RasterLayerMenuItemsConvertRasterToControl.tsx

@@ -1,36 +0,0 @@
-import { MenuItem } from '@invoke-ai/ui-library';
-import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
-import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
-import { selectDefaultControlAdapter } from 'features/controlLayers/hooks/addLayerHooks';
-import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
-import { rasterLayerConvertedToControlLayer } from 'features/controlLayers/store/canvasSlice';
-import { memo, useCallback } from 'react';
-import { useTranslation } from 'react-i18next';
-import { PiLightningBold } from 'react-icons/pi';
-
-export const RasterLayerMenuItemsConvertRasterToControl = memo(() => {
-  const { t } = useTranslation();
-  const dispatch = useAppDispatch();
-  const entityIdentifier = useEntityIdentifierContext('raster_layer');
-  const defaultControlAdapter = useAppSelector(selectDefaultControlAdapter);
-  const isInteractable = useIsEntityInteractable(entityIdentifier);
-
-  const onClick = useCallback(() => {
-    dispatch(
-      rasterLayerConvertedToControlLayer({
-        entityIdentifier,
-        overrides: {
-          controlAdapter: defaultControlAdapter,
-        },
-      })
-    );
-  }, [defaultControlAdapter, dispatch, entityIdentifier]);
-
-  return (
-    <MenuItem onClick={onClick} icon={<PiLightningBold />} isDisabled={!isInteractable}>
-      {t('controlLayers.convertToControlLayer')}
-    </MenuItem>
-  );
-});
-
-RasterLayerMenuItemsConvertRasterToControl.displayName = 'RasterLayerMenuItemsConvertRasterToControl';

invokeai/frontend/web/src/features/controlLayers/components/RasterLayer/RasterLayerMenuItemsConvertToSubMenu.tsx

@@ -0,0 +1,65 @@
+import { Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { selectDefaultControlAdapter } from 'features/controlLayers/hooks/addLayerHooks';
+import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
+import {
+  rasterLayerConvertedToControlLayer,
+  rasterLayerConvertedToInpaintMask,
+  rasterLayerConvertedToRegionalGuidance,
+} from 'features/controlLayers/store/canvasSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiSwapBold } from 'react-icons/pi';
+
+export const RasterLayerMenuItemsConvertToSubMenu = memo(() => {
+  const { t } = useTranslation();
+  const subMenu = useSubMenu();
+
+  const dispatch = useAppDispatch();
+  const entityIdentifier = useEntityIdentifierContext('raster_layer');
+  const defaultControlAdapter = useAppSelector(selectDefaultControlAdapter);
+  const isInteractable = useIsEntityInteractable(entityIdentifier);
+
+  const convertToInpaintMask = useCallback(() => {
+    dispatch(rasterLayerConvertedToInpaintMask({ entityIdentifier, replace: true }));
+  }, [dispatch, entityIdentifier]);
+
+  const convertToRegionalGuidance = useCallback(() => {
+    dispatch(rasterLayerConvertedToRegionalGuidance({ entityIdentifier, replace: true }));
+  }, [dispatch, entityIdentifier]);
+
+  const convertToControlLayer = useCallback(() => {
+    dispatch(
+      rasterLayerConvertedToControlLayer({
+        entityIdentifier,
+        replace: true,
+        overrides: { controlAdapter: defaultControlAdapter },
+      })
+    );
+  }, [defaultControlAdapter, dispatch, entityIdentifier]);
+
+  return (
+    <MenuItem {...subMenu.parentMenuItemProps} icon={<PiSwapBold />}>
+      <Menu {...subMenu.menuProps}>
+        <MenuButton {...subMenu.menuButtonProps}>
+          <SubMenuButtonContent label={t('controlLayers.convertRasterLayerTo')} />
+        </MenuButton>
+        <MenuList {...subMenu.menuListProps}>
+          <MenuItem onClick={convertToInpaintMask} icon={<PiSwapBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.inpaintMask')}
+          </MenuItem>
+          <MenuItem onClick={convertToRegionalGuidance} icon={<PiSwapBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.regionalGuidance')}
+          </MenuItem>
+          <MenuItem onClick={convertToControlLayer} icon={<PiSwapBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.controlLayer')}
+          </MenuItem>
+        </MenuList>
+      </Menu>
+    </MenuItem>
+  );
+});
+
+RasterLayerMenuItemsConvertToSubMenu.displayName = 'RasterLayerMenuItemsConvertToSubMenu';

invokeai/frontend/web/src/features/controlLayers/components/RasterLayer/RasterLayerMenuItemsCopyToSubMenu.tsx

@@ -0,0 +1,66 @@
+import { Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
+import { CanvasEntityMenuItemsCopyToClipboard } from 'features/controlLayers/components/common/CanvasEntityMenuItemsCopyToClipboard';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { selectDefaultControlAdapter } from 'features/controlLayers/hooks/addLayerHooks';
+import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
+import {
+  rasterLayerConvertedToControlLayer,
+  rasterLayerConvertedToInpaintMask,
+  rasterLayerConvertedToRegionalGuidance,
+} from 'features/controlLayers/store/canvasSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiCopyBold } from 'react-icons/pi';
+
+export const RasterLayerMenuItemsCopyToSubMenu = memo(() => {
+  const { t } = useTranslation();
+  const subMenu = useSubMenu();
+
+  const dispatch = useAppDispatch();
+  const entityIdentifier = useEntityIdentifierContext('raster_layer');
+  const defaultControlAdapter = useAppSelector(selectDefaultControlAdapter);
+  const isInteractable = useIsEntityInteractable(entityIdentifier);
+
+  const copyToInpaintMask = useCallback(() => {
+    dispatch(rasterLayerConvertedToInpaintMask({ entityIdentifier }));
+  }, [dispatch, entityIdentifier]);
+
+  const copyToRegionalGuidance = useCallback(() => {
+    dispatch(rasterLayerConvertedToRegionalGuidance({ entityIdentifier }));
+  }, [dispatch, entityIdentifier]);
+
+  const copyToControlLayer = useCallback(() => {
+    dispatch(
+      rasterLayerConvertedToControlLayer({
+        entityIdentifier,
+        overrides: { controlAdapter: defaultControlAdapter },
+      })
+    );
+  }, [defaultControlAdapter, dispatch, entityIdentifier]);
+
+  return (
+    <MenuItem {...subMenu.parentMenuItemProps} icon={<PiCopyBold />}>
+      <Menu {...subMenu.menuProps}>
+        <MenuButton {...subMenu.menuButtonProps}>
+          <SubMenuButtonContent label={t('controlLayers.copyRasterLayerTo')} />
+        </MenuButton>
+        <MenuList {...subMenu.menuListProps}>
+          <CanvasEntityMenuItemsCopyToClipboard />
+          <MenuItem onClick={copyToInpaintMask} icon={<PiCopyBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.newInpaintMask')}
+          </MenuItem>
+          <MenuItem onClick={copyToRegionalGuidance} icon={<PiCopyBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.newRegionalGuidance')}
+          </MenuItem>
+          <MenuItem onClick={copyToControlLayer} icon={<PiCopyBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.newControlLayer')}
+          </MenuItem>
+        </MenuList>
+      </Menu>
+    </MenuItem>
+  );
+});
+
+RasterLayerMenuItemsCopyToSubMenu.displayName = 'RasterLayerMenuItemsCopyToSubMenu';

invokeai/frontend/web/src/features/controlLayers/components/RegionalGuidance/RegionalGuidanceMenuItems.tsx

@@ -1,4 +1,5 @@
-import { Flex, MenuDivider } from '@invoke-ai/ui-library';
+import { MenuDivider } from '@invoke-ai/ui-library';
+import { IconMenuItemGroup } from 'common/components/IconMenuItem';
 import { CanvasEntityMenuItemsArrange } from 'features/controlLayers/components/common/CanvasEntityMenuItemsArrange';
 import { CanvasEntityMenuItemsCropToBbox } from 'features/controlLayers/components/common/CanvasEntityMenuItemsCropToBbox';
 import { CanvasEntityMenuItemsDelete } from 'features/controlLayers/components/common/CanvasEntityMenuItemsDelete';
@@ -6,16 +7,18 @@ import { CanvasEntityMenuItemsDuplicate } from 'features/controlLayers/component
 import { CanvasEntityMenuItemsTransform } from 'features/controlLayers/components/common/CanvasEntityMenuItemsTransform';
 import { RegionalGuidanceMenuItemsAddPromptsAndIPAdapter } from 'features/controlLayers/components/RegionalGuidance/RegionalGuidanceMenuItemsAddPromptsAndIPAdapter';
 import { RegionalGuidanceMenuItemsAutoNegative } from 'features/controlLayers/components/RegionalGuidance/RegionalGuidanceMenuItemsAutoNegative';
+import { RegionalGuidanceMenuItemsConvertToSubMenu } from 'features/controlLayers/components/RegionalGuidance/RegionalGuidanceMenuItemsConvertToSubMenu';
+import { RegionalGuidanceMenuItemsCopyToSubMenu } from 'features/controlLayers/components/RegionalGuidance/RegionalGuidanceMenuItemsCopyToSubMenu';
 import { memo } from 'react';
 
 export const RegionalGuidanceMenuItems = memo(() => {
   return (
     <>
-      <Flex gap={2}>
+      <IconMenuItemGroup>
         <CanvasEntityMenuItemsArrange />
         <CanvasEntityMenuItemsDuplicate />
         <CanvasEntityMenuItemsDelete asIcon />
-      </Flex>
+      </IconMenuItemGroup>
       <MenuDivider />
       <RegionalGuidanceMenuItemsAddPromptsAndIPAdapter />
       <MenuDivider />
@@ -23,6 +26,9 @@ export const RegionalGuidanceMenuItems = memo(() => {
       <RegionalGuidanceMenuItemsAutoNegative />
       <MenuDivider />
       <CanvasEntityMenuItemsCropToBbox />
+      <MenuDivider />
+      <RegionalGuidanceMenuItemsConvertToSubMenu />
+      <RegionalGuidanceMenuItemsCopyToSubMenu />
     </>
   );
 });

invokeai/frontend/web/src/features/controlLayers/components/RegionalGuidance/RegionalGuidanceMenuItemsConvertToSubMenu.tsx

@@ -0,0 +1,38 @@
+import { Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
+import { rgConvertedToInpaintMask } from 'features/controlLayers/store/canvasSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiSwapBold } from 'react-icons/pi';
+
+export const RegionalGuidanceMenuItemsConvertToSubMenu = memo(() => {
+  const { t } = useTranslation();
+  const subMenu = useSubMenu();
+  const dispatch = useAppDispatch();
+  const entityIdentifier = useEntityIdentifierContext('regional_guidance');
+  const isInteractable = useIsEntityInteractable(entityIdentifier);
+
+  const convertToInpaintMask = useCallback(() => {
+    dispatch(rgConvertedToInpaintMask({ entityIdentifier, replace: true }));
+  }, [dispatch, entityIdentifier]);
+
+  return (
+    <MenuItem {...subMenu.parentMenuItemProps} icon={<PiSwapBold />}>
+      <Menu {...subMenu.menuProps}>
+        <MenuButton {...subMenu.menuButtonProps}>
+          <SubMenuButtonContent label={t('controlLayers.convertRegionalGuidanceTo')} />
+        </MenuButton>
+        <MenuList {...subMenu.menuListProps}>
+          <MenuItem onClick={convertToInpaintMask} icon={<PiSwapBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.inpaintMask')}
+          </MenuItem>
+        </MenuList>
+      </Menu>
+    </MenuItem>
+  );
+});
+
+RegionalGuidanceMenuItemsConvertToSubMenu.displayName = 'RegionalGuidanceMenuItemsConvertToSubMenu';

invokeai/frontend/web/src/features/controlLayers/components/RegionalGuidance/RegionalGuidanceMenuItemsCopyToSubMenu.tsx

@@ -0,0 +1,40 @@
+import { Menu, MenuButton, MenuItem, MenuList } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { SubMenuButtonContent, useSubMenu } from 'common/hooks/useSubMenu';
+import { CanvasEntityMenuItemsCopyToClipboard } from 'features/controlLayers/components/common/CanvasEntityMenuItemsCopyToClipboard';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { useIsEntityInteractable } from 'features/controlLayers/hooks/useEntityIsInteractable';
+import { rgConvertedToInpaintMask } from 'features/controlLayers/store/canvasSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiCopyBold } from 'react-icons/pi';
+
+export const RegionalGuidanceMenuItemsCopyToSubMenu = memo(() => {
+  const { t } = useTranslation();
+  const subMenu = useSubMenu();
+  const dispatch = useAppDispatch();
+  const entityIdentifier = useEntityIdentifierContext('regional_guidance');
+  const isInteractable = useIsEntityInteractable(entityIdentifier);
+
+  const copyToInpaintMask = useCallback(() => {
+    dispatch(rgConvertedToInpaintMask({ entityIdentifier }));
+  }, [dispatch, entityIdentifier]);
+
+  return (
+    <MenuItem {...subMenu.parentMenuItemProps} icon={<PiCopyBold />}>
+      <Menu {...subMenu.menuProps}>
+        <MenuButton {...subMenu.menuButtonProps}>
+          <SubMenuButtonContent label={t('controlLayers.copyRegionalGuidanceTo')} />
+        </MenuButton>
+        <MenuList {...subMenu.menuListProps}>
+          <CanvasEntityMenuItemsCopyToClipboard />
+          <MenuItem onClick={copyToInpaintMask} icon={<PiCopyBold />} isDisabled={!isInteractable}>
+            {t('controlLayers.newInpaintMask')}
+          </MenuItem>
+        </MenuList>
+      </Menu>
+    </MenuItem>
+  );
+});
+
+RegionalGuidanceMenuItemsCopyToSubMenu.displayName = 'RegionalGuidanceMenuItemsCopyToSubMenu';

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

@@ -0,0 +1,168 @@
+import {
+  Button,
+  ButtonGroup,
+  Flex,
+  Heading,
+  Menu,
+  MenuButton,
+  MenuItem,
+  MenuList,
+  Spacer,
+} from '@invoke-ai/ui-library';
+import { useStore } from '@nanostores/react';
+import { useAppSelector } from 'app/store/storeHooks';
+import { useFocusRegion, useIsRegionFocused } from 'common/hooks/focus';
+import { CanvasAutoProcessSwitch } from 'features/controlLayers/components/CanvasAutoProcessSwitch';
+import { CanvasOperationIsolatedLayerPreviewSwitch } from 'features/controlLayers/components/CanvasOperationIsolatedLayerPreviewSwitch';
+import { SegmentAnythingPointType } from 'features/controlLayers/components/SegmentAnything/SegmentAnythingPointType';
+import { useCanvasManager } from 'features/controlLayers/contexts/CanvasManagerProviderGate';
+import type { CanvasEntityAdapterControlLayer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterControlLayer';
+import type { CanvasEntityAdapterRasterLayer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterRasterLayer';
+import { selectAutoProcess } from 'features/controlLayers/store/canvasSettingsSlice';
+import { useRegisteredHotkeys } from 'features/system/components/HotkeysModal/useHotkeyData';
+import { memo, useCallback, useRef } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiArrowsCounterClockwiseBold, PiFloppyDiskBold, PiStarBold, PiXBold } from 'react-icons/pi';
+
+const SegmentAnythingContent = memo(
+  ({ adapter }: { adapter: CanvasEntityAdapterRasterLayer | CanvasEntityAdapterControlLayer }) => {
+    const { t } = useTranslation();
+    const ref = useRef<HTMLDivElement>(null);
+    useFocusRegion('canvas', ref, { focusOnMount: true });
+    const isCanvasFocused = useIsRegionFocused('canvas');
+    const isProcessing = useStore(adapter.segmentAnything.$isProcessing);
+    const hasPoints = useStore(adapter.segmentAnything.$hasPoints);
+    const hasImageState = useStore(adapter.segmentAnything.$hasImageState);
+    const autoProcess = useAppSelector(selectAutoProcess);
+
+    const saveAsInpaintMask = useCallback(() => {
+      adapter.segmentAnything.saveAs('inpaint_mask');
+    }, [adapter.segmentAnything]);
+
+    const saveAsRegionalGuidance = useCallback(() => {
+      adapter.segmentAnything.saveAs('regional_guidance');
+    }, [adapter.segmentAnything]);
+
+    const saveAsRasterLayer = useCallback(() => {
+      adapter.segmentAnything.saveAs('raster_layer');
+    }, [adapter.segmentAnything]);
+
+    const saveAsControlLayer = useCallback(() => {
+      adapter.segmentAnything.saveAs('control_layer');
+    }, [adapter.segmentAnything]);
+
+    useRegisteredHotkeys({
+      id: 'applySegmentAnything',
+      category: 'canvas',
+      callback: adapter.segmentAnything.apply,
+      options: { enabled: !isProcessing && isCanvasFocused },
+      dependencies: [adapter.segmentAnything, isProcessing, isCanvasFocused],
+    });
+
+    useRegisteredHotkeys({
+      id: 'cancelSegmentAnything',
+      category: 'canvas',
+      callback: adapter.segmentAnything.cancel,
+      options: { enabled: !isProcessing && isCanvasFocused },
+      dependencies: [adapter.segmentAnything, isProcessing, isCanvasFocused],
+    });
+
+    return (
+      <Flex
+        ref={ref}
+        bg="base.800"
+        borderRadius="base"
+        p={4}
+        flexDir="column"
+        gap={4}
+        minW={420}
+        h="auto"
+        shadow="dark-lg"
+        transitionProperty="height"
+        transitionDuration="normal"
+      >
+        <Flex w="full" gap={4}>
+          <Heading size="md" color="base.300" userSelect="none">
+            {t('controlLayers.segment.autoMask')}
+          </Heading>
+          <Spacer />
+          <CanvasAutoProcessSwitch />
+          <CanvasOperationIsolatedLayerPreviewSwitch />
+        </Flex>
+
+        <SegmentAnythingPointType adapter={adapter} />
+
+        <ButtonGroup isAttached={false} size="sm" w="full">
+          <Button
+            leftIcon={<PiStarBold />}
+            onClick={adapter.segmentAnything.processImmediate}
+            isLoading={isProcessing}
+            loadingText={t('controlLayers.segment.process')}
+            variant="ghost"
+            isDisabled={!hasPoints || autoProcess}
+          >
+            {t('controlLayers.segment.process')}
+          </Button>
+          <Spacer />
+          <Button
+            leftIcon={<PiArrowsCounterClockwiseBold />}
+            onClick={adapter.segmentAnything.reset}
+            isLoading={isProcessing}
+            loadingText={t('controlLayers.segment.reset')}
+            variant="ghost"
+          >
+            {t('controlLayers.segment.reset')}
+          </Button>
+          <Menu>
+            <MenuButton
+              as={Button}
+              leftIcon={<PiFloppyDiskBold />}
+              isLoading={isProcessing}
+              loadingText={t('controlLayers.segment.saveAs')}
+              variant="ghost"
+              isDisabled={!hasImageState}
+            >
+              {t('controlLayers.segment.saveAs')}
+            </MenuButton>
+            <MenuList>
+              <MenuItem isDisabled={!hasImageState} onClick={saveAsInpaintMask}>
+                {t('controlLayers.inpaintMask')}
+              </MenuItem>
+              <MenuItem isDisabled={!hasImageState} onClick={saveAsRegionalGuidance}>
+                {t('controlLayers.regionalGuidance')}
+              </MenuItem>
+              <MenuItem isDisabled={!hasImageState} onClick={saveAsControlLayer}>
+                {t('controlLayers.controlLayer')}
+              </MenuItem>
+              <MenuItem isDisabled={!hasImageState} onClick={saveAsRasterLayer}>
+                {t('controlLayers.rasterLayer')}
+              </MenuItem>
+            </MenuList>
+          </Menu>
+          <Button
+            leftIcon={<PiXBold />}
+            onClick={adapter.segmentAnything.cancel}
+            isLoading={isProcessing}
+            loadingText={t('common.cancel')}
+            variant="ghost"
+          >
+            {t('controlLayers.segment.cancel')}
+          </Button>
+        </ButtonGroup>
+      </Flex>
+    );
+  }
+);
+
+SegmentAnythingContent.displayName = 'SegmentAnythingContent';
+
+export const SegmentAnything = () => {
+  const canvasManager = useCanvasManager();
+  const adapter = useStore(canvasManager.stateApi.$segmentingAdapter);
+
+  if (!adapter) {
+    return null;
+  }
+
+  return <SegmentAnythingContent adapter={adapter} />;
+};

invokeai/frontend/web/src/features/controlLayers/components/SegmentAnything/SegmentAnythingPointType.tsx

@@ -0,0 +1,41 @@
+import { Flex, FormControl, FormLabel, Radio, RadioGroup, Text } from '@invoke-ai/ui-library';
+import { useStore } from '@nanostores/react';
+import type { CanvasEntityAdapterControlLayer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterControlLayer';
+import type { CanvasEntityAdapterRasterLayer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterRasterLayer';
+import { SAM_POINT_LABEL_STRING_TO_NUMBER, zSAMPointLabelString } from 'features/controlLayers/store/types';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+
+export const SegmentAnythingPointType = memo(
+  ({ adapter }: { adapter: CanvasEntityAdapterRasterLayer | CanvasEntityAdapterControlLayer }) => {
+    const { t } = useTranslation();
+    const pointType = useStore(adapter.segmentAnything.$pointTypeString);
+
+    const onChange = useCallback(
+      (v: string) => {
+        const labelAsString = zSAMPointLabelString.parse(v);
+        const labelAsNumber = SAM_POINT_LABEL_STRING_TO_NUMBER[labelAsString];
+        adapter.segmentAnything.$pointType.set(labelAsNumber);
+      },
+      [adapter.segmentAnything.$pointType]
+    );
+
+    return (
+      <FormControl w="full">
+        <FormLabel>{t('controlLayers.segment.pointType')}</FormLabel>
+        <RadioGroup value={pointType} onChange={onChange} w="full" size="md">
+          <Flex alignItems="center" w="full" gap={4} fontWeight="semibold" color="base.300">
+            <Radio value="foreground">
+              <Text>{t('controlLayers.segment.include')}</Text>
+            </Radio>
+            <Radio value="background">
+              <Text>{t('controlLayers.segment.exclude')}</Text>
+            </Radio>
+          </Flex>
+        </RadioGroup>
+      </FormControl>
+    );
+  }
+);
+
+SegmentAnythingPointType.displayName = 'SegmentAnythingPointType';

invokeai/frontend/web/src/features/controlLayers/components/Settings/CanvasSettingsIsolatedLayerPreviewSwitch.tsx

@@ -1,28 +1,28 @@
 import { FormControl, FormLabel, Switch } from '@invoke-ai/ui-library';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
 import {
-  selectIsolatedFilteringPreview,
-  settingsIsolatedFilteringPreviewToggled,
+  selectIsolatedLayerPreview,
+  settingsIsolatedLayerPreviewToggled,
 } from 'features/controlLayers/store/canvasSettingsSlice';
 import { memo, useCallback } from 'react';
 import { useTranslation } from 'react-i18next';
 
-export const CanvasSettingsIsolatedFilteringPreviewSwitch = memo(() => {
+export const CanvasSettingsIsolatedLayerPreviewSwitch = memo(() => {
   const { t } = useTranslation();
   const dispatch = useAppDispatch();
-  const isolatedFilteringPreview = useAppSelector(selectIsolatedFilteringPreview);
+  const isolatedLayerPreview = useAppSelector(selectIsolatedLayerPreview);
   const onChange = useCallback(() => {
-    dispatch(settingsIsolatedFilteringPreviewToggled());
+    dispatch(settingsIsolatedLayerPreviewToggled());
   }, [dispatch]);
 
   return (
     <FormControl>
       <FormLabel m={0} flexGrow={1}>
-        {t('controlLayers.settings.isolatedFilteringPreview')}
+        {t('controlLayers.settings.isolatedLayerPreview')}
       </FormLabel>
-      <Switch size="sm" isChecked={isolatedFilteringPreview} onChange={onChange} />
+      <Switch size="sm" isChecked={isolatedLayerPreview} onChange={onChange} />
     </FormControl>
   );
 });
 
-CanvasSettingsIsolatedFilteringPreviewSwitch.displayName = 'CanvasSettingsIsolatedFilteringPreviewSwitch';
+CanvasSettingsIsolatedLayerPreviewSwitch.displayName = 'CanvasSettingsIsolatedLayerPreviewSwitch';

invokeai/frontend/web/src/features/controlLayers/components/Settings/CanvasSettingsIsolatedTransformingPreviewSwitch.tsx

@@ -1,28 +0,0 @@
-import { FormControl, FormLabel, Switch } from '@invoke-ai/ui-library';
-import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
-import {
-  selectIsolatedTransformingPreview,
-  settingsIsolatedTransformingPreviewToggled,
-} from 'features/controlLayers/store/canvasSettingsSlice';
-import { memo, useCallback } from 'react';
-import { useTranslation } from 'react-i18next';
-
-export const CanvasSettingsIsolatedTransformingPreviewSwitch = memo(() => {
-  const { t } = useTranslation();
-  const dispatch = useAppDispatch();
-  const isolatedTransformingPreview = useAppSelector(selectIsolatedTransformingPreview);
-  const onChange = useCallback(() => {
-    dispatch(settingsIsolatedTransformingPreviewToggled());
-  }, [dispatch]);
-
-  return (
-    <FormControl>
-      <FormLabel m={0} flexGrow={1}>
-        {t('controlLayers.settings.isolatedTransformingPreview')}
-      </FormLabel>
-      <Switch size="sm" isChecked={isolatedTransformingPreview} onChange={onChange} />
-    </FormControl>
-  );
-});
-
-CanvasSettingsIsolatedTransformingPreviewSwitch.displayName = 'CanvasSettingsIsolatedTransformingPreviewSwitch';

invokeai/frontend/web/src/features/controlLayers/components/Settings/CanvasSettingsPopover.tsx

@@ -16,9 +16,8 @@ import { CanvasSettingsClipToBboxCheckbox } from 'features/controlLayers/compone
 import { CanvasSettingsDynamicGridSwitch } from 'features/controlLayers/components/Settings/CanvasSettingsDynamicGridSwitch';
 import { CanvasSettingsSnapToGridCheckbox } from 'features/controlLayers/components/Settings/CanvasSettingsGridSize';
 import { CanvasSettingsInvertScrollCheckbox } from 'features/controlLayers/components/Settings/CanvasSettingsInvertScrollCheckbox';
-import { CanvasSettingsIsolatedFilteringPreviewSwitch } from 'features/controlLayers/components/Settings/CanvasSettingsIsolatedFilteringPreviewSwitch';
+import { CanvasSettingsIsolatedLayerPreviewSwitch } from 'features/controlLayers/components/Settings/CanvasSettingsIsolatedLayerPreviewSwitch';
 import { CanvasSettingsIsolatedStagingPreviewSwitch } from 'features/controlLayers/components/Settings/CanvasSettingsIsolatedStagingPreviewSwitch';
-import { CanvasSettingsIsolatedTransformingPreviewSwitch } from 'features/controlLayers/components/Settings/CanvasSettingsIsolatedTransformingPreviewSwitch';
 import { CanvasSettingsLogDebugInfoButton } from 'features/controlLayers/components/Settings/CanvasSettingsLogDebugInfo';
 import { CanvasSettingsOutputOnlyMaskedRegionsCheckbox } from 'features/controlLayers/components/Settings/CanvasSettingsOutputOnlyMaskedRegionsCheckbox';
 import { CanvasSettingsPreserveMaskCheckbox } from 'features/controlLayers/components/Settings/CanvasSettingsPreserveMaskCheckbox';
@@ -54,8 +53,7 @@ export const CanvasSettingsPopover = memo(() => {
             <CanvasSettingsPressureSensitivityCheckbox />
             <CanvasSettingsShowProgressOnCanvas />
             <CanvasSettingsIsolatedStagingPreviewSwitch />
-            <CanvasSettingsIsolatedFilteringPreviewSwitch />
-            <CanvasSettingsIsolatedTransformingPreviewSwitch />
+            <CanvasSettingsIsolatedLayerPreviewSwitch />
             <CanvasSettingsDynamicGridSwitch />
             <CanvasSettingsBboxOverlaySwitch />
             <CanvasSettingsShowHUDSwitch />

invokeai/frontend/web/src/features/controlLayers/components/Toolbar/CanvasToolbarFitBboxToLayersButton.tsx

@@ -10,8 +10,8 @@ export const CanvasToolbarFitBboxToLayersButton = memo(() => {
   const canvasManager = useCanvasManager();
   const isBusy = useCanvasIsBusy();
   const onClick = useCallback(() => {
-    canvasManager.bbox.fitToLayers();
-  }, [canvasManager.bbox]);
+    canvasManager.tool.tools.bbox.fitToLayers();
+  }, [canvasManager.tool.tools.bbox]);
 
   return (
     <IconButton

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

@@ -1,30 +1,21 @@
-import { Button, ButtonGroup, Flex, FormControl, FormLabel, Heading, Spacer, Switch } from '@invoke-ai/ui-library';
+import { Button, ButtonGroup, Flex, Heading, Spacer } from '@invoke-ai/ui-library';
 import { useStore } from '@nanostores/react';
-import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
 import { useFocusRegion, useIsRegionFocused } from 'common/hooks/focus';
+import { CanvasOperationIsolatedLayerPreviewSwitch } from 'features/controlLayers/components/CanvasOperationIsolatedLayerPreviewSwitch';
 import { TransformFitToBboxButtons } from 'features/controlLayers/components/Transform/TransformFitToBboxButtons';
 import { useCanvasManager } from 'features/controlLayers/contexts/CanvasManagerProviderGate';
 import type { CanvasEntityAdapter } from 'features/controlLayers/konva/CanvasEntity/types';
-import {
-  selectIsolatedTransformingPreview,
-  settingsIsolatedTransformingPreviewToggled,
-} from 'features/controlLayers/store/canvasSettingsSlice';
 import { useRegisteredHotkeys } from 'features/system/components/HotkeysModal/useHotkeyData';
-import { memo, useCallback, useRef } from 'react';
+import { memo, useRef } from 'react';
 import { useTranslation } from 'react-i18next';
 import { PiArrowsCounterClockwiseBold, PiCheckBold, PiXBold } from 'react-icons/pi';
 
 const TransformContent = memo(({ adapter }: { adapter: CanvasEntityAdapter }) => {
   const { t } = useTranslation();
-  const dispatch = useAppDispatch();
   const ref = useRef<HTMLDivElement>(null);
   useFocusRegion('canvas', ref, { focusOnMount: true });
   const isCanvasFocused = useIsRegionFocused('canvas');
   const isProcessing = useStore(adapter.transformer.$isProcessing);
-  const isolatedTransformingPreview = useAppSelector(selectIsolatedTransformingPreview);
-  const onChangeIsolatedPreview = useCallback(() => {
-    dispatch(settingsIsolatedTransformingPreviewToggled());
-  }, [dispatch]);
   const silentTransform = useStore(adapter.transformer.$silentTransform);
 
   useRegisteredHotkeys({
@@ -66,10 +57,7 @@ const TransformContent = memo(({ adapter }: { adapter: CanvasEntityAdapter }) =>
           {t('controlLayers.transform.transform')}
         </Heading>
         <Spacer />
-        <FormControl w="min-content">
-          <FormLabel m={0}>{t('controlLayers.settings.isolatedPreview')}</FormLabel>
-          <Switch size="sm" isChecked={isolatedTransformingPreview} onChange={onChangeIsolatedPreview} />
-        </FormControl>
+        <CanvasOperationIsolatedLayerPreviewSwitch />
       </Flex>
 
       <TransformFitToBboxButtons adapter={adapter} />

invokeai/frontend/web/src/features/controlLayers/components/common/CanvasEntityGroupList.tsx

@@ -1,9 +1,11 @@
 import type { SystemStyleObject } from '@invoke-ai/ui-library';
 import { Button, Collapse, Flex, Icon, Spacer, Text } from '@invoke-ai/ui-library';
+import { InformationalPopover } from 'common/components/InformationalPopover/InformationalPopover';
 import { useBoolean } from 'common/hooks/useBoolean';
 import { CanvasEntityAddOfTypeButton } from 'features/controlLayers/components/common/CanvasEntityAddOfTypeButton';
 import { CanvasEntityMergeVisibleButton } from 'features/controlLayers/components/common/CanvasEntityMergeVisibleButton';
 import { CanvasEntityTypeIsHiddenToggle } from 'features/controlLayers/components/common/CanvasEntityTypeIsHiddenToggle';
+import { useEntityTypeInformationalPopover } from 'features/controlLayers/hooks/useEntityTypeInformationalPopover';
 import { useEntityTypeTitle } from 'features/controlLayers/hooks/useEntityTypeTitle';
 import type { CanvasEntityIdentifier } from 'features/controlLayers/store/types';
 import type { PropsWithChildren } from 'react';
@@ -21,6 +23,7 @@ const _hover: SystemStyleObject = {
 
 export const CanvasEntityGroupList = memo(({ isSelected, type, children }: Props) => {
   const title = useEntityTypeTitle(type);
+  const informationalPopoverFeature = useEntityTypeInformationalPopover(type);
   const collapse = useBoolean(true);
   const canMergeVisible = useMemo(() => type === 'raster_layer' || type === 'inpaint_mask', [type]);
   const canHideAll = useMemo(() => type !== 'reference_image', [type]);
@@ -47,15 +50,30 @@ export const CanvasEntityGroupList = memo(({ isSelected, type, children }: Props
             transitionProperty="common"
             transitionDuration="fast"
           />
-          <Text
-            fontWeight="semibold"
-            color={isSelected ? 'base.200' : 'base.500'}
-            userSelect="none"
-            transitionProperty="common"
-            transitionDuration="fast"
-          >
-            {title}
-          </Text>
+          {informationalPopoverFeature ? (
+            <InformationalPopover feature={informationalPopoverFeature}>
+              <Text
+                fontWeight="semibold"
+                color={isSelected ? 'base.200' : 'base.500'}
+                userSelect="none"
+                transitionProperty="common"
+                transitionDuration="fast"
+              >
+                {title}
+              </Text>
+            </InformationalPopover>
+          ) : (
+            <Text
+              fontWeight="semibold"
+              color={isSelected ? 'base.200' : 'base.500'}
+              userSelect="none"
+              transitionProperty="common"
+              transitionDuration="fast"
+            >
+              {title}
+            </Text>
+          )}
+
           <Spacer />
         </Flex>
         {canMergeVisible && <CanvasEntityMergeVisibleButton type={type} />}

invokeai/frontend/web/src/features/controlLayers/components/common/CanvasEntityMenuItemsCopyToClipboard.tsx

@@ -20,7 +20,7 @@ export const CanvasEntityMenuItemsCopyToClipboard = memo(() => {
 
   return (
     <MenuItem onClick={onClick} icon={<PiCopyBold />} isDisabled={!isInteractable}>
-      {t('controlLayers.copyToClipboard')}
+      {t('common.clipboard')}
     </MenuItem>
   );
 });

invokeai/frontend/web/src/features/controlLayers/components/common/CanvasEntityMenuItemsSegment.tsx

@@ -0,0 +1,20 @@
+import { MenuItem } from '@invoke-ai/ui-library';
+import { useEntityIdentifierContext } from 'features/controlLayers/contexts/EntityIdentifierContext';
+import { useEntitySegmentAnything } from 'features/controlLayers/hooks/useEntitySegmentAnything';
+import { memo } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiMaskHappyBold } from 'react-icons/pi';
+
+export const CanvasEntityMenuItemsSegment = memo(() => {
+  const { t } = useTranslation();
+  const entityIdentifier = useEntityIdentifierContext();
+  const segmentAnything = useEntitySegmentAnything(entityIdentifier);
+
+  return (
+    <MenuItem onClick={segmentAnything.start} icon={<PiMaskHappyBold />} isDisabled={segmentAnything.isDisabled}>
+      {t('controlLayers.segment.autoMask')}
+    </MenuItem>
+  );
+});
+
+CanvasEntityMenuItemsSegment.displayName = 'CanvasEntityMenuItemsSegment';

invokeai/frontend/web/src/features/controlLayers/hooks/useEntityFilter.ts

@@ -5,11 +5,13 @@ import { useEntityAdapterSafe } from 'features/controlLayers/contexts/EntityAdap
 import { useCanvasIsBusy } from 'features/controlLayers/hooks/useCanvasIsBusy';
 import type { CanvasEntityIdentifier } from 'features/controlLayers/store/types';
 import { isFilterableEntityIdentifier } from 'features/controlLayers/store/types';
+import { useImageViewer } from 'features/gallery/components/ImageViewer/useImageViewer';
 import { useCallback, useMemo } from 'react';
 
 export const useEntityFilter = (entityIdentifier: CanvasEntityIdentifier | null) => {
   const canvasManager = useCanvasManager();
   const adapter = useEntityAdapterSafe(entityIdentifier);
+  const imageViewer = useImageViewer();
   const isBusy = useCanvasIsBusy();
   const isInteractable = useStore(adapter?.$isInteractable ?? $false);
   const isEmpty = useStore(adapter?.$isEmpty ?? $false);
@@ -50,8 +52,9 @@ export const useEntityFilter = (entityIdentifier: CanvasEntityIdentifier | null)
     if (!adapter) {
       return;
     }
+    imageViewer.close();
     adapter.filterer.start();
-  }, [isDisabled, entityIdentifier, canvasManager]);
+  }, [isDisabled, entityIdentifier, canvasManager, imageViewer]);
 
   return { isDisabled, start } as const;
 };

invokeai/frontend/web/src/features/controlLayers/hooks/useEntitySegmentAnything.ts

@@ -0,0 +1,60 @@
+import { useStore } from '@nanostores/react';
+import { $false } from 'app/store/nanostores/util';
+import { useCanvasManager } from 'features/controlLayers/contexts/CanvasManagerProviderGate';
+import { useEntityAdapterSafe } from 'features/controlLayers/contexts/EntityAdapterContext';
+import { useCanvasIsBusy } from 'features/controlLayers/hooks/useCanvasIsBusy';
+import type { CanvasEntityIdentifier } from 'features/controlLayers/store/types';
+import { isSegmentableEntityIdentifier } from 'features/controlLayers/store/types';
+import { useImageViewer } from 'features/gallery/components/ImageViewer/useImageViewer';
+import { useCallback, useMemo } from 'react';
+
+export const useEntitySegmentAnything = (entityIdentifier: CanvasEntityIdentifier | null) => {
+  const canvasManager = useCanvasManager();
+  const adapter = useEntityAdapterSafe(entityIdentifier);
+  const imageViewer = useImageViewer();
+  const isBusy = useCanvasIsBusy();
+  const isInteractable = useStore(adapter?.$isInteractable ?? $false);
+  const isEmpty = useStore(adapter?.$isEmpty ?? $false);
+
+  const isDisabled = useMemo(() => {
+    if (!entityIdentifier) {
+      return true;
+    }
+    if (!isSegmentableEntityIdentifier(entityIdentifier)) {
+      return true;
+    }
+    if (!adapter) {
+      return true;
+    }
+    if (isBusy) {
+      return true;
+    }
+    if (!isInteractable) {
+      return true;
+    }
+    if (isEmpty) {
+      return true;
+    }
+    return false;
+  }, [entityIdentifier, adapter, isBusy, isInteractable, isEmpty]);
+
+  const start = useCallback(() => {
+    if (isDisabled) {
+      return;
+    }
+    if (!entityIdentifier) {
+      return;
+    }
+    if (!isSegmentableEntityIdentifier(entityIdentifier)) {
+      return;
+    }
+    const adapter = canvasManager.getAdapter(entityIdentifier);
+    if (!adapter) {
+      return;
+    }
+    imageViewer.close();
+    adapter.segmentAnything.start();
+  }, [isDisabled, entityIdentifier, canvasManager, imageViewer]);
+
+  return { isDisabled, start } as const;
+};

invokeai/frontend/web/src/features/controlLayers/hooks/useEntityTransform.ts

@@ -5,11 +5,13 @@ import { useEntityAdapterSafe } from 'features/controlLayers/contexts/EntityAdap
 import { useCanvasIsBusy } from 'features/controlLayers/hooks/useCanvasIsBusy';
 import type { CanvasEntityIdentifier } from 'features/controlLayers/store/types';
 import { isTransformableEntityIdentifier } from 'features/controlLayers/store/types';
+import { useImageViewer } from 'features/gallery/components/ImageViewer/useImageViewer';
 import { useCallback, useMemo } from 'react';
 
 export const useEntityTransform = (entityIdentifier: CanvasEntityIdentifier | null) => {
   const canvasManager = useCanvasManager();
   const adapter = useEntityAdapterSafe(entityIdentifier);
+  const imageViewer = useImageViewer();
   const isBusy = useCanvasIsBusy();
   const isInteractable = useStore(adapter?.$isInteractable ?? $false);
   const isEmpty = useStore(adapter?.$isEmpty ?? $false);
@@ -67,10 +69,11 @@ export const useEntityTransform = (entityIdentifier: CanvasEntityIdentifier | nu
     if (!adapter) {
       return;
     }
+    imageViewer.close();
     await adapter.transformer.startTransform({ silent: true });
     adapter.transformer.fitToBboxContain();
     await adapter.transformer.applyTransform();
-  }, [canvasManager, entityIdentifier, isDisabled]);
+  }, [canvasManager, entityIdentifier, imageViewer, isDisabled]);
 
   return { isDisabled, start, fitToBbox } as const;
 };

invokeai/frontend/web/src/features/controlLayers/hooks/useEntityTypeInformationalPopover.ts

@@ -0,0 +1,25 @@
+import type { Feature } from 'common/components/InformationalPopover/constants';
+import type { CanvasEntityIdentifier } from 'features/controlLayers/store/types';
+import { useMemo } from 'react';
+
+export const useEntityTypeInformationalPopover = (type: CanvasEntityIdentifier['type']): Feature | undefined => {
+  const feature = useMemo(() => {
+    switch (type) {
+      case 'control_layer':
+        return 'controlNet';
+      case 'inpaint_mask':
+        return 'inpainting';
+      case 'raster_layer':
+        return 'rasterLayer';
+      case 'regional_guidance':
+        return 'regionalGuidanceAndReferenceImage';
+      case 'reference_image':
+        return 'globalReferenceImage';
+
+      default:
+        return undefined;
+    }
+  }, [type]);
+
+  return feature;
+};

invokeai/frontend/web/src/features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterBase.ts

@@ -10,11 +10,9 @@ import type { CanvasEntityTransformer } from 'features/controlLayers/konva/Canva
 import type { CanvasEntityAdapter } from 'features/controlLayers/konva/CanvasEntity/types';
 import type { CanvasManager } from 'features/controlLayers/konva/CanvasManager';
 import { CanvasModuleBase } from 'features/controlLayers/konva/CanvasModuleBase';
+import type { CanvasSegmentAnythingModule } from 'features/controlLayers/konva/CanvasSegmentAnythingModule';
 import { getKonvaNodeDebugAttrs, getRectIntersection } from 'features/controlLayers/konva/util';
-import {
-  selectIsolatedFilteringPreview,
-  selectIsolatedTransformingPreview,
-} from 'features/controlLayers/store/canvasSettingsSlice';
+import { selectIsolatedLayerPreview } from 'features/controlLayers/store/canvasSettingsSlice';
 import {
   buildSelectIsHidden,
   buildSelectIsSelected,
@@ -72,6 +70,15 @@ export abstract class CanvasEntityAdapterBase<
   // without requiring all adapters to implement this property and their own `destroy`?
   abstract filterer?: CanvasEntityFilterer;
 
+  /**
+   * The segment anything module for this entity adapter. Entities that support segment anything should implement
+   * this property.
+   */
+  // TODO(psyche): This is in the ABC and not in the concrete classes to allow all adapters to share the `destroy`
+  // method. If it wasn't in this ABC, we'd get a TS error in `destroy`. Maybe there's a better way to handle this
+  // without requiring all adapters to implement this property and their own `destroy`?
+  abstract segmentAnything?: CanvasSegmentAnythingModule;
+
   /**
    * Synchronizes the entity state with the canvas. This includes rendering the entity's objects, handling visibility,
    * positioning, opacity, locked state, and any other properties.
@@ -264,13 +271,11 @@ export abstract class CanvasEntityAdapterBase<
      */
     this.subscriptions.add(this.manager.stateApi.createStoreSubscription(this.selectIsHidden, this.syncVisibility));
     this.subscriptions.add(
-      this.manager.stateApi.createStoreSubscription(selectIsolatedFilteringPreview, this.syncVisibility)
+      this.manager.stateApi.createStoreSubscription(selectIsolatedLayerPreview, this.syncVisibility)
     );
     this.subscriptions.add(this.manager.stateApi.$filteringAdapter.listen(this.syncVisibility));
-    this.subscriptions.add(
-      this.manager.stateApi.createStoreSubscription(selectIsolatedTransformingPreview, this.syncVisibility)
-    );
     this.subscriptions.add(this.manager.stateApi.$transformingAdapter.listen(this.syncVisibility));
+    this.subscriptions.add(this.manager.stateApi.$segmentingAdapter.listen(this.syncVisibility));
     this.subscriptions.add(this.manager.stateApi.createStoreSubscription(this.selectIsSelected, this.syncVisibility));
 
     /**
@@ -435,8 +440,10 @@ export abstract class CanvasEntityAdapterBase<
       return;
     }
 
+    const isolatedLayerPreview = this.manager.stateApi.runSelector(selectIsolatedLayerPreview);
+
     // Handle isolated preview modes - if another entity is filtering or transforming, we may need to hide this entity.
-    if (this.manager.stateApi.runSelector(selectIsolatedFilteringPreview)) {
+    if (isolatedLayerPreview) {
       const filteringEntityIdentifier = this.manager.stateApi.$filteringAdapter.get()?.entityIdentifier;
       if (filteringEntityIdentifier && filteringEntityIdentifier.id !== this.id) {
         this.setVisibility(false);
@@ -444,7 +451,7 @@ export abstract class CanvasEntityAdapterBase<
       }
     }
 
-    if (this.manager.stateApi.runSelector(selectIsolatedTransformingPreview)) {
+    if (isolatedLayerPreview) {
       const transformingEntity = this.manager.stateApi.$transformingAdapter.get();
       if (
         transformingEntity &&
@@ -457,6 +464,14 @@ export abstract class CanvasEntityAdapterBase<
       }
     }
 
+    if (isolatedLayerPreview) {
+      const segmentingEntity = this.manager.stateApi.$segmentingAdapter.get();
+      if (segmentingEntity && segmentingEntity.entityIdentifier.id !== this.id) {
+        this.setVisibility(false);
+        return;
+      }
+    }
+
     // If the entity is not selected and offscreen, we can hide it
     if (!this.$isOnScreen.get() && !this.manager.stateApi.getIsSelected(this.entityIdentifier.id)) {
       this.setVisibility(false);
@@ -517,8 +532,17 @@ export abstract class CanvasEntityAdapterBase<
       this.transformer.stopTransform();
     }
     this.transformer.destroy();
-    if (this.filterer?.$isFiltering.get()) {
-      this.filterer.cancel();
+    if (this.filterer) {
+      if (this.filterer.$isFiltering.get()) {
+        this.filterer.cancel();
+      }
+      this.filterer?.destroy();
+    }
+    if (this.segmentAnything) {
+      if (this.segmentAnything.$isSegmenting.get()) {
+        this.segmentAnything.cancel();
+      }
+      this.segmentAnything.destroy();
     }
     this.konva.layer.destroy();
     this.manager.deleteAdapter(this.entityIdentifier);
@@ -534,6 +558,7 @@ export abstract class CanvasEntityAdapterBase<
       transformer: this.transformer.repr(),
       renderer: this.renderer.repr(),
       bufferRenderer: this.bufferRenderer.repr(),
+      segmentAnything: this.segmentAnything?.repr(),
       filterer: this.filterer?.repr(),
       hasCache: this.$canvasCache.get() !== null,
       isLocked: this.$isLocked.get(),

invokeai/frontend/web/src/features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterControlLayer.ts

@@ -5,6 +5,7 @@ import { CanvasEntityFilterer } from 'features/controlLayers/konva/CanvasEntity/
 import { CanvasEntityObjectRenderer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityObjectRenderer';
 import { CanvasEntityTransformer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityTransformer';
 import type { CanvasManager } from 'features/controlLayers/konva/CanvasManager';
+import { CanvasSegmentAnythingModule } from 'features/controlLayers/konva/CanvasSegmentAnythingModule';
 import type { CanvasControlLayerState, CanvasEntityIdentifier, Rect } from 'features/controlLayers/store/types';
 import type { GroupConfig } from 'konva/lib/Group';
 import { omit } from 'lodash-es';
@@ -17,6 +18,7 @@ export class CanvasEntityAdapterControlLayer extends CanvasEntityAdapterBase<
   bufferRenderer: CanvasEntityBufferObjectRenderer;
   transformer: CanvasEntityTransformer;
   filterer: CanvasEntityFilterer;
+  segmentAnything: CanvasSegmentAnythingModule;
 
   constructor(entityIdentifier: CanvasEntityIdentifier<'control_layer'>, manager: CanvasManager) {
     super(entityIdentifier, manager, 'control_layer_adapter');
@@ -25,6 +27,7 @@ export class CanvasEntityAdapterControlLayer extends CanvasEntityAdapterBase<
     this.bufferRenderer = new CanvasEntityBufferObjectRenderer(this);
     this.transformer = new CanvasEntityTransformer(this);
     this.filterer = new CanvasEntityFilterer(this);
+    this.segmentAnything = new CanvasSegmentAnythingModule(this);
 
     this.subscriptions.add(this.manager.stateApi.createStoreSubscription(this.selectState, this.sync));
   }

invokeai/frontend/web/src/features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterInpaintMask.ts

@@ -16,6 +16,7 @@ export class CanvasEntityAdapterInpaintMask extends CanvasEntityAdapterBase<
   bufferRenderer: CanvasEntityBufferObjectRenderer;
   transformer: CanvasEntityTransformer;
   filterer = undefined;
+  segmentAnything = undefined;
 
   constructor(entityIdentifier: CanvasEntityIdentifier<'inpaint_mask'>, manager: CanvasManager) {
     super(entityIdentifier, manager, 'inpaint_mask_adapter');

invokeai/frontend/web/src/features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterRasterLayer.ts

@@ -5,6 +5,7 @@ import { CanvasEntityFilterer } from 'features/controlLayers/konva/CanvasEntity/
 import { CanvasEntityObjectRenderer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityObjectRenderer';
 import { CanvasEntityTransformer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityTransformer';
 import type { CanvasManager } from 'features/controlLayers/konva/CanvasManager';
+import { CanvasSegmentAnythingModule } from 'features/controlLayers/konva/CanvasSegmentAnythingModule';
 import type { CanvasEntityIdentifier, CanvasRasterLayerState, Rect } from 'features/controlLayers/store/types';
 import type { GroupConfig } from 'konva/lib/Group';
 import { omit } from 'lodash-es';
@@ -17,6 +18,7 @@ export class CanvasEntityAdapterRasterLayer extends CanvasEntityAdapterBase<
   bufferRenderer: CanvasEntityBufferObjectRenderer;
   transformer: CanvasEntityTransformer;
   filterer: CanvasEntityFilterer;
+  segmentAnything: CanvasSegmentAnythingModule;
 
   constructor(entityIdentifier: CanvasEntityIdentifier<'raster_layer'>, manager: CanvasManager) {
     super(entityIdentifier, manager, 'raster_layer_adapter');
@@ -25,6 +27,7 @@ export class CanvasEntityAdapterRasterLayer extends CanvasEntityAdapterBase<
     this.bufferRenderer = new CanvasEntityBufferObjectRenderer(this);
     this.transformer = new CanvasEntityTransformer(this);
     this.filterer = new CanvasEntityFilterer(this);
+    this.segmentAnything = new CanvasSegmentAnythingModule(this);
 
     this.subscriptions.add(this.manager.stateApi.createStoreSubscription(this.selectState, this.sync));
   }

invokeai/frontend/web/src/features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterRegionalGuidance.ts

@@ -16,6 +16,7 @@ export class CanvasEntityAdapterRegionalGuidance extends CanvasEntityAdapterBase
   bufferRenderer: CanvasEntityBufferObjectRenderer;
   transformer: CanvasEntityTransformer;
   filterer = undefined;
+  segmentAnything = undefined;
 
   constructor(entityIdentifier: CanvasEntityIdentifier<'regional_guidance'>, manager: CanvasManager) {
     super(entityIdentifier, manager, 'regional_guidance_adapter');

invokeai/frontend/web/src/features/controlLayers/konva/CanvasEntity/CanvasEntityFilterer.ts

@@ -4,7 +4,7 @@ import type { CanvasEntityAdapterRasterLayer } from 'features/controlLayers/konv
 import type { CanvasManager } from 'features/controlLayers/konva/CanvasManager';
 import { CanvasModuleBase } from 'features/controlLayers/konva/CanvasModuleBase';
 import { getPrefixedId } from 'features/controlLayers/konva/util';
-import { selectAutoProcessFilter } from 'features/controlLayers/store/canvasSettingsSlice';
+import { selectAutoProcess } from 'features/controlLayers/store/canvasSettingsSlice';
 import type { FilterConfig } from 'features/controlLayers/store/filters';
 import { getFilterForModel, IMAGE_FILTERS } from 'features/controlLayers/store/filters';
 import type { CanvasImageState } from 'features/controlLayers/store/types';
@@ -15,7 +15,6 @@ import type { Logger } from 'roarr';
 import { serializeError } from 'serialize-error';
 import { buildSelectModelConfig } from 'services/api/hooks/modelsByType';
 import { isControlNetOrT2IAdapterModelConfig } from 'services/api/types';
-import { assert } from 'tsafe';
 
 type CanvasEntityFiltererConfig = {
   processDebounceMs: number;
@@ -56,30 +55,41 @@ export class CanvasEntityFilterer extends CanvasModuleBase {
     this.log = this.manager.buildLogger(this);
 
     this.log.debug('Creating filter module');
+  }
 
+  subscribe = () => {
     this.subscriptions.add(
       this.$filterConfig.listen(() => {
-        if (this.manager.stateApi.getSettings().autoProcessFilter && this.$isFiltering.get()) {
+        if (this.manager.stateApi.getSettings().autoProcess && this.$isFiltering.get()) {
           this.process();
         }
       })
     );
     this.subscriptions.add(
-      this.manager.stateApi.createStoreSubscription(selectAutoProcessFilter, (autoPreviewFilter) => {
-        if (autoPreviewFilter && this.$isFiltering.get()) {
+      this.manager.stateApi.createStoreSubscription(selectAutoProcess, (autoProcess) => {
+        if (autoProcess && this.$isFiltering.get()) {
           this.process();
         }
       })
     );
-  }
+  };
+
+  unsubscribe = () => {
+    this.subscriptions.forEach((unsubscribe) => unsubscribe());
+    this.subscriptions.clear();
+  };
 
   start = (config?: FilterConfig) => {
     const filteringAdapter = this.manager.stateApi.$filteringAdapter.get();
     if (filteringAdapter) {
-      assert(false, `Already filtering an entity: ${filteringAdapter.id}`);
+      this.log.error(`Already filtering an entity: ${filteringAdapter.id}`);
+      return;
     }
 
     this.log.trace('Initializing filter');
+
+    this.subscribe();
+
     if (config) {
       this.$filterConfig.set(config);
     } else if (this.parent.type === 'control_layer_adapter' && this.parent.state.controlAdapter.model) {
@@ -97,7 +107,7 @@ export class CanvasEntityFilterer extends CanvasModuleBase {
     }
     this.$isFiltering.set(true);
     this.manager.stateApi.$filteringAdapter.set(this.parent);
-    if (this.manager.stateApi.getSettings().autoProcessFilter) {
+    if (this.manager.stateApi.getSettings().autoProcess) {
       this.processImmediate();
     }
   };
@@ -204,6 +214,7 @@ export class CanvasEntityFilterer extends CanvasModuleBase {
       replaceObjects: true,
     });
     this.imageState = null;
+    this.unsubscribe();
     this.$isFiltering.set(false);
     this.$hasProcessed.set(false);
     this.manager.stateApi.$filteringAdapter.set(null);
@@ -225,6 +236,7 @@ export class CanvasEntityFilterer extends CanvasModuleBase {
     this.log.trace('Cancelling filter');
 
     this.reset();
+    this.unsubscribe();
     this.$isProcessing.set(false);
     this.$isFiltering.set(false);
     this.$hasProcessed.set(false);
@@ -243,4 +255,13 @@ export class CanvasEntityFilterer extends CanvasModuleBase {
       $filterConfig: this.$filterConfig.get(),
     };
   };
+
+  destroy = () => {
+    this.log.debug('Destroying module');
+    if (this.abortController && !this.abortController.signal.aborted) {
+      this.abortController.abort();
+    }
+    this.abortController = null;
+    this.unsubscribe();
+  };
 }

invokeai/frontend/web/src/features/controlLayers/konva/CanvasEntity/CanvasEntityTransformer.ts

@@ -234,8 +234,25 @@ export class CanvasEntityTransformer extends CanvasModuleBase {
 
     this.konva.transformer.on('transform', this.syncObjectGroupWithProxyRect);
     this.konva.transformer.on('transformend', this.snapProxyRectToPixelGrid);
+    this.konva.transformer.on('pointerenter', () => {
+      this.manager.stage.setCursor('move');
+    });
+    this.konva.transformer.on('pointerleave', () => {
+      this.manager.stage.setCursor('default');
+    });
     this.konva.proxyRect.on('dragmove', this.onDragMove);
     this.konva.proxyRect.on('dragend', this.onDragEnd);
+    this.konva.proxyRect.on('pointerenter', () => {
+      this.manager.stage.setCursor('move');
+    });
+    this.konva.proxyRect.on('pointerleave', () => {
+      this.manager.stage.setCursor('default');
+    });
+
+    this.subscriptions.add(() => {
+      this.konva.transformer.off('transform transformend pointerenter pointerleave');
+      this.konva.proxyRect.off('dragmove dragend pointerenter pointerleave');
+    });
 
     // When the stage scale changes, we may need to re-scale some of the transformer's components. For example,
     // the bbox outline should always be 1 screen pixel wide, so we need to update its stroke width.
@@ -574,9 +591,9 @@ export class CanvasEntityTransformer extends CanvasModuleBase {
   syncInteractionState = () => {
     this.log.trace('Syncing interaction state');
 
-    if (this.manager.$isBusy.get() && !this.$isTransforming.get()) {
-      // The canvas is busy, we can't interact with the transformer
-      this.parent.konva.layer.listening(false);
+    if (this.parent.segmentAnything?.$isSegmenting.get()) {
+      // When segmenting, the layer should listen but the transformer should not be interactable
+      this.parent.konva.layer.listening(true);
       this._setInteractionMode('off');
       return;
     }
@@ -609,6 +626,13 @@ export class CanvasEntityTransformer extends CanvasModuleBase {
     const tool = this.manager.tool.$tool.get();
     const isSelected = this.manager.stateApi.getIsSelected(this.parent.id);
 
+    if (!isSelected) {
+      // The layer is not selected
+      this.parent.konva.layer.listening(false);
+      this._setInteractionMode('off');
+      return;
+    }
+
     if (this.parent.$isEmpty.get()) {
       // The layer is totally empty, we can just disable the layer
       this.parent.konva.layer.listening(false);
@@ -616,14 +640,14 @@ export class CanvasEntityTransformer extends CanvasModuleBase {
       return;
     }
 
-    if (isSelected && !this.$isTransforming.get() && tool === 'move') {
+    if (!this.$isTransforming.get() && tool === 'move') {
       // We are moving this layer, it must be listening
       this.parent.konva.layer.listening(true);
       this._setInteractionMode('drag');
       return;
     }
 
-    if (isSelected && this.$isTransforming.get()) {
+    if (this.$isTransforming.get()) {
       // When transforming, we want the stage to still be movable if the view tool is selected. If the transformer is
       // active, it will interrupt the stage drag events. So we should disable listening when the view tool is selected.
       if (tool === 'view') {
@@ -633,11 +657,12 @@ export class CanvasEntityTransformer extends CanvasModuleBase {
         this.parent.konva.layer.listening(true);
         this._setInteractionMode('all');
       }
-    } else {
-      // The layer is not selected, or we are using a tool that doesn't need the layer to be listening - disable interaction stuff
-      this.parent.konva.layer.listening(false);
-      this._setInteractionMode('off');
+      return;
     }
+
+    // The layer is not selected
+    this.parent.konva.layer.listening(false);
+    this._setInteractionMode('off');
   };
 
   /**

invokeai/frontend/web/src/features/controlLayers/konva/CanvasManager.ts

@@ -2,7 +2,6 @@ import { logger } from 'app/logging/logger';
 import type { AppStore } from 'app/store/store';
 import type { SerializableObject } from 'common/types';
 import { SyncableMap } from 'common/util/SyncableMap/SyncableMap';
-import { CanvasBboxModule } from 'features/controlLayers/konva/CanvasBboxModule';
 import { CanvasCacheModule } from 'features/controlLayers/konva/CanvasCacheModule';
 import { CanvasCompositorModule } from 'features/controlLayers/konva/CanvasCompositorModule';
 import { CanvasEntityAdapterControlLayer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityAdapterControlLayer';
@@ -62,7 +61,6 @@ export class CanvasManager extends CanvasModuleBase {
   entityRenderer: CanvasEntityRendererModule;
   compositor: CanvasCompositorModule;
   tool: CanvasToolModule;
-  bbox: CanvasBboxModule;
   stagingArea: CanvasStagingAreaModule;
   progressImage: CanvasProgressImageModule;
 
@@ -111,11 +109,12 @@ export class CanvasManager extends CanvasModuleBase {
         this.stateApi.$isFiltering,
         this.stateApi.$isTransforming,
         this.stateApi.$isRasterizing,
+        this.stateApi.$isSegmenting,
         this.stagingArea.$isStaging,
         this.compositor.$isBusy,
       ],
-      (isFiltering, isTransforming, isRasterizing, isStaging, isCompositing) => {
-        return isFiltering || isTransforming || isRasterizing || isStaging || isCompositing;
+      (isFiltering, isTransforming, isRasterizing, isSegmenting, isStaging, isCompositing) => {
+        return isFiltering || isTransforming || isRasterizing || isSegmenting || isStaging || isCompositing;
       }
     );
 
@@ -123,18 +122,16 @@ export class CanvasManager extends CanvasModuleBase {
     this.stage.addLayer(this.background.konva.layer);
 
     this.konva = {
-      previewLayer: new Konva.Layer({ listening: false, imageSmoothingEnabled: false }),
+      previewLayer: new Konva.Layer({ listening: true, imageSmoothingEnabled: false }),
     };
     this.stage.addLayer(this.konva.previewLayer);
 
     this.tool = new CanvasToolModule(this);
     this.progressImage = new CanvasProgressImageModule(this);
-    this.bbox = new CanvasBboxModule(this);
 
     // Must add in this order for correct z-index
     this.konva.previewLayer.add(this.stagingArea.konva.group);
     this.konva.previewLayer.add(this.progressImage.konva.group);
-    this.konva.previewLayer.add(this.bbox.konva.group);
     this.konva.previewLayer.add(this.tool.konva.group);
   }
 
@@ -232,7 +229,6 @@ export class CanvasManager extends CanvasModuleBase {
 
   getAllModules = (): CanvasModuleBase[] => {
     return [
-      this.bbox,
       this.stagingArea,
       this.tool,
       this.progressImage,
@@ -280,7 +276,6 @@ export class CanvasManager extends CanvasModuleBase {
       inpaintMasks: Array.from(this.adapters.inpaintMasks.values()).map((adapter) => adapter.repr()),
       regionMasks: Array.from(this.adapters.regionMasks.values()).map((adapter) => adapter.repr()),
       stateApi: this.stateApi.repr(),
-      bbox: this.bbox.repr(),
       stagingArea: this.stagingArea.repr(),
       tool: this.tool.repr(),
       progressImage: this.progressImage.repr(),

invokeai/frontend/web/src/features/controlLayers/konva/CanvasObject/CanvasObjectImage.ts

@@ -1,10 +1,10 @@
 import { Mutex } from 'async-mutex';
 import { deepClone } from 'common/util/deepClone';
 import type { CanvasEntityBufferObjectRenderer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityBufferObjectRenderer';
-import type { CanvasEntityFilterer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityFilterer';
 import type { CanvasEntityObjectRenderer } from 'features/controlLayers/konva/CanvasEntity/CanvasEntityObjectRenderer';
 import type { CanvasManager } from 'features/controlLayers/konva/CanvasManager';
 import { CanvasModuleBase } from 'features/controlLayers/konva/CanvasModuleBase';
+import type { CanvasSegmentAnythingModule } from 'features/controlLayers/konva/CanvasSegmentAnythingModule';
 import type { CanvasStagingAreaModule } from 'features/controlLayers/konva/CanvasStagingAreaModule';
 import { loadImage } from 'features/controlLayers/konva/util';
 import type { CanvasImageState } from 'features/controlLayers/store/types';
@@ -21,7 +21,7 @@ export class CanvasObjectImage extends CanvasModuleBase {
     | CanvasEntityObjectRenderer
     | CanvasEntityBufferObjectRenderer
     | CanvasStagingAreaModule
-    | CanvasEntityFilterer;
+    | CanvasSegmentAnythingModule;
   readonly manager: CanvasManager;
   readonly log: Logger;
 
@@ -42,7 +42,7 @@ export class CanvasObjectImage extends CanvasModuleBase {
       | CanvasEntityObjectRenderer
       | CanvasEntityBufferObjectRenderer
       | CanvasStagingAreaModule
-      | CanvasEntityFilterer
+      | CanvasSegmentAnythingModule
   ) {
     super();
     this.id = state.id;

invokeai/frontend/web/src/features/controlLayers/konva/CanvasProgressImageModule.ts

@@ -8,9 +8,9 @@ import { atom } from 'nanostores';
 import type { Logger } from 'roarr';
 import { selectCanvasQueueCounts } from 'services/api/endpoints/queue';
 import type { S } from 'services/api/types';
-import type { O } from 'ts-toolbelt';
+import type { SetNonNullable } from 'type-fest';
 
-type ProgressEventWithImage = O.NonNullable<S['InvocationProgressEvent'], 'image'>;
+type ProgressEventWithImage = SetNonNullable<S['InvocationProgressEvent'], 'image'>;
 const isProgressEventWithImage = (val: S['InvocationProgressEvent']): val is ProgressEventWithImage =>
   Boolean(val.image);