chore: bump version to v5.4.1

Turns out a gallery image's `imageDTO` object can actually be a different object by reference. I thought this was not possible thanks to how we have a quasi-normalized cache.

Need to check against image name instead of reference equality when deciding whether or not to use the single image or the gallery selection for the dnd payload.

.github/pull_request_template.md

@@ -19,3 +19,4 @@
 - [ ] _The PR has a short but descriptive title, suitable for a changelog_
 - [ ] _Tests added / updated (if applicable)_
 - [ ] _Documentation added / updated (if applicable)_
+- [ ] _Updated `What's New` copy (if doing a release after this PR)_

docs/contributing/contribution_guides/newContributorChecklist.md

@@ -5,7 +5,7 @@ If you're a new contributor to InvokeAI or Open Source Projects, this is the gui
 ## New Contributor Checklist
 
 - [x] Set up your local development environment & fork of InvokAI by following [the steps outlined here](../dev-environment.md)
-- [x] Set up your local tooling with [this guide](InvokeAI/contributing/LOCAL_DEVELOPMENT/#developing-invokeai-in-vscode). Feel free to skip this step if you already have tooling you're comfortable with.
+- [x] Set up your local tooling with [this guide](../LOCAL_DEVELOPMENT.md). Feel free to skip this step if you already have tooling you're comfortable with.
 - [x] Familiarize yourself with [Git](https://www.atlassian.com/git) & our project structure by reading through the [development documentation](development.md)
 - [x] Join the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord
 - [x] Choose an issue to work on! This can be achieved by asking in the #dev-chat channel, tackling a [good first issue](https://github.com/invoke-ai/InvokeAI/contribute) or finding an item on the [roadmap](https://github.com/orgs/invoke-ai/projects/7). If nothing in any of those places catches your eye, feel free to work on something of interest to you!

docs/contributing/dev-environment.md

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

docs/faq.md

@@ -209,7 +209,7 @@ checkpoint models.
 
 To solve this, go to the Model Manager tab (the cube), select the
 checkpoint model that's giving you trouble, and press the "Convert"
-button in the upper right of your browser window. This will conver the
+button in the upper right of your browser window. This will convert the
 checkpoint into a diffusers model, after which loading should be
 faster and less memory-intensive.
 

docs/installation/patchmatch.md

@@ -97,16 +97,16 @@ Prior to installing PyPatchMatch, you need to take the following steps:
    sudo pacman -S --needed base-devel
    ```
 
-2. Install `opencv` and `blas`:
+2. Install `opencv`, `blas`, and required dependencies:
 
    ```sh
-   sudo pacman -S opencv blas
+   sudo pacman -S opencv blas fmt glew vtk hdf5
    ```
 
    or for CUDA support
 
    ```sh
-   sudo pacman -S opencv-cuda blas
+   sudo pacman -S opencv-cuda blas fmt glew vtk hdf5
    ```
 
 3. Fix the naming of the `opencv` package configuration file:

installer/lib/messages.py

@@ -259,7 +259,7 @@ def select_gpu() -> GpuType:
                     [
                         f"Detected the [gold1]{OS}-{ARCH}[/] platform",
                         "",
-                        "See [deep_sky_blue1]https://invoke-ai.github.io/InvokeAI/#system[/] to ensure your system meets the minimum requirements.",
+                        "See [deep_sky_blue1]https://invoke-ai.github.io/InvokeAI/installation/requirements/[/] to ensure your system meets the minimum requirements.",
                         "",
                         "[red3]🠶[/] [b]Your GPU drivers must be correctly installed before using InvokeAI![/] [red3]🠴[/]",
                     ]

installer/templates/invoke.sh.in

@@ -68,7 +68,7 @@ do_line_input() {
     printf "2: Open the developer console\n"
     printf "3: Command-line help\n"
     printf "Q: Quit\n\n"
-    printf "To update, download and run the installer from https://github.com/invoke-ai/InvokeAI/releases/latest.\n\n"
+    printf "To update, download and run the installer from https://github.com/invoke-ai/InvokeAI/releases/latest\n\n"
     read -p "Please enter 1-4, Q: [1] " yn
     choice=${yn:='1'}
     do_choice $choice

invokeai/app/api/routers/app_info.py

@@ -40,6 +40,8 @@ class AppVersion(BaseModel):
 
     version: str = Field(description="App version")
 
+    highlights: Optional[list[str]] = Field(default=None, description="Highlights of release")
+
 
 class AppDependencyVersions(BaseModel):
     """App depencency Versions Response"""

invokeai/app/api/routers/model_manager.py

@@ -1,6 +1,7 @@
 # Copyright (c) 2023 Lincoln D. Stein
 """FastAPI route for model configuration records."""
 
+import contextlib
 import io
 import pathlib
 import shutil
@@ -10,6 +11,7 @@ from enum import Enum
 from tempfile import TemporaryDirectory
 from typing import List, Optional, Type
 
+import huggingface_hub
 from fastapi import Body, Path, Query, Response, UploadFile
 from fastapi.responses import FileResponse, HTMLResponse
 from fastapi.routing import APIRouter
@@ -27,6 +29,7 @@ from invokeai.app.services.model_records import (
     ModelRecordChanges,
     UnknownModelException,
 )
+from invokeai.app.util.suppress_output import SuppressOutput
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
@@ -808,7 +811,11 @@ 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
 
@@ -919,3 +926,51 @@ async def get_stats() -> Optional[CacheStats]:
     """Return performance statistics on the model manager's RAM cache. Will return null if no models have been loaded."""
 
     return ApiDependencies.invoker.services.model_manager.load.ram_cache.stats
+
+
+class HFTokenStatus(str, Enum):
+    VALID = "valid"
+    INVALID = "invalid"
+    UNKNOWN = "unknown"
+
+
+class HFTokenHelper:
+    @classmethod
+    def get_status(cls) -> HFTokenStatus:
+        try:
+            if huggingface_hub.get_token_permission(huggingface_hub.get_token()):
+                # Valid token!
+                return HFTokenStatus.VALID
+            # No token set
+            return HFTokenStatus.INVALID
+        except Exception:
+            return HFTokenStatus.UNKNOWN
+
+    @classmethod
+    def set_token(cls, token: str) -> HFTokenStatus:
+        with SuppressOutput(), contextlib.suppress(Exception):
+            huggingface_hub.login(token=token, add_to_git_credential=False)
+        return cls.get_status()
+
+
+@model_manager_router.get("/hf_login", operation_id="get_hf_login_status", response_model=HFTokenStatus)
+async def get_hf_login_status() -> HFTokenStatus:
+    token_status = HFTokenHelper.get_status()
+
+    if token_status is HFTokenStatus.UNKNOWN:
+        ApiDependencies.invoker.services.logger.warning("Unable to verify HF token")
+
+    return token_status
+
+
+@model_manager_router.post("/hf_login", operation_id="do_hf_login", response_model=HFTokenStatus)
+async def do_hf_login(
+    token: str = Body(description="Hugging Face token to use for login", embed=True),
+) -> HFTokenStatus:
+    HFTokenHelper.set_token(token)
+    token_status = HFTokenHelper.get_status()
+
+    if token_status is HFTokenStatus.UNKNOWN:
+        ApiDependencies.invoker.services.logger.warning("Unable to verify HF token")
+
+    return token_status

invokeai/app/invocations/baseinvocation.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import inspect
 import re
+import sys
 import warnings
 from abc import ABC, abstractmethod
 from enum import Enum
@@ -192,12 +193,19 @@ class BaseInvocation(ABC, BaseModel):
         """Gets a pydantc TypeAdapter for the union of all invocation types."""
         if not cls._typeadapter or cls._typeadapter_needs_update:
             AnyInvocation = TypeAliasType(
-                "AnyInvocation", Annotated[Union[tuple(cls._invocation_classes)], Field(discriminator="type")]
+                "AnyInvocation", Annotated[Union[tuple(cls.get_invocations())], Field(discriminator="type")]
             )
             cls._typeadapter = TypeAdapter(AnyInvocation)
             cls._typeadapter_needs_update = False
         return cls._typeadapter
 
+    @classmethod
+    def invalidate_typeadapter(cls) -> None:
+        """Invalidates the typeadapter, forcing it to be rebuilt on next access. If the invocation allowlist or
+        denylist is changed, this should be called to ensure the typeadapter is updated and validation respects
+        the updated allowlist and denylist."""
+        cls._typeadapter_needs_update = True
+
     @classmethod
     def get_invocations(cls) -> Iterable[BaseInvocation]:
         """Gets all invocations, respecting the allowlist and denylist."""
@@ -479,6 +487,26 @@ def invocation(
             title="type", default=invocation_type, json_schema_extra={"field_kind": FieldKind.NodeAttribute}
         )
 
+        # Validate the `invoke()` method is implemented
+        if "invoke" in cls.__abstractmethods__:
+            raise ValueError(f'Invocation "{invocation_type}" must implement the "invoke" method')
+
+        # And validate that `invoke()` returns a subclass of `BaseInvocationOutput
+        invoke_return_annotation = signature(cls.invoke).return_annotation
+
+        try:
+            # TODO(psyche): If `invoke()` is not defined, `return_annotation` ends up as the string "BaseInvocationOutput"
+            # instead of the class `BaseInvocationOutput`. This may be a pydantic bug: https://github.com/pydantic/pydantic/issues/7978
+            if isinstance(invoke_return_annotation, str):
+                invoke_return_annotation = getattr(sys.modules[cls.__module__], invoke_return_annotation)
+
+            assert invoke_return_annotation is not BaseInvocationOutput
+            assert issubclass(invoke_return_annotation, BaseInvocationOutput)
+        except Exception:
+            raise ValueError(
+                f'Invocation "{invocation_type}" must have a return annotation of a subclass of BaseInvocationOutput (got "{invoke_return_annotation}")'
+            )
+
         docstring = cls.__doc__
         cls = create_model(
             cls.__qualname__,

invokeai/app/invocations/compel.py

@@ -95,6 +95,7 @@ class CompelInvocation(BaseInvocation):
                 ti_manager,
             ),
         ):
+            context.util.signal_progress("Building conditioning")
             assert isinstance(text_encoder, CLIPTextModel)
             assert isinstance(tokenizer, CLIPTokenizer)
             compel = Compel(
@@ -191,6 +192,7 @@ class SDXLPromptInvocationBase:
                 ti_manager,
             ),
         ):
+            context.util.signal_progress("Building conditioning")
             assert isinstance(text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
             assert isinstance(tokenizer, CLIPTokenizer)
 

invokeai/app/invocations/create_denoise_mask.py

@@ -65,6 +65,7 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
             img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
             masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
             # TODO:
+            context.util.signal_progress("Running VAE encoder")
             masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
 
             masked_latents_name = context.tensors.save(tensor=masked_latents)

invokeai/app/invocations/create_gradient_mask.py

@@ -131,6 +131,7 @@ class CreateGradientMaskInvocation(BaseInvocation):
                     image_tensor = image_tensor.unsqueeze(0)
                 img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
                 masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
+                context.util.signal_progress("Running VAE encoder")
                 masked_latents = ImageToLatentsInvocation.vae_encode(
                     vae_info, self.fp32, self.tiled, masked_image.clone()
                 )

invokeai/app/invocations/denoise_latents.py

@@ -13,6 +13,7 @@ from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
 from diffusers.schedulers.scheduling_dpmsolver_sde import DPMSolverSDEScheduler
 from diffusers.schedulers.scheduling_tcd import TCDScheduler
 from diffusers.schedulers.scheduling_utils import SchedulerMixin as Scheduler
+from PIL import Image
 from pydantic import field_validator
 from torchvision.transforms.functional import resize as tv_resize
 from transformers import CLIPVisionModelWithProjection
@@ -510,6 +511,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         context: InvocationContext,
         t2i_adapters: Optional[Union[T2IAdapterField, list[T2IAdapterField]]],
         ext_manager: ExtensionsManager,
+        bgr_mode: bool = False,
     ) -> None:
         if t2i_adapters is None:
             return
@@ -519,6 +521,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
             t2i_adapters = [t2i_adapters]
 
         for t2i_adapter_field in t2i_adapters:
+            image = context.images.get_pil(t2i_adapter_field.image.image_name)
+            if bgr_mode:  # SDXL t2i trained on cv2's BGR outputs, but PIL won't convert straight to BGR
+                r, g, b = image.split()
+                image = Image.merge("RGB", (b, g, r))
             ext_manager.add_extension(
                 T2IAdapterExt(
                     node_context=context,
@@ -616,13 +622,17 @@ class DenoiseLatentsInvocation(BaseInvocation):
         for t2i_adapter_field in t2i_adapter:
             t2i_adapter_model_config = context.models.get_config(t2i_adapter_field.t2i_adapter_model.key)
             t2i_adapter_loaded_model = context.models.load(t2i_adapter_field.t2i_adapter_model)
-            image = context.images.get_pil(t2i_adapter_field.image.image_name)
+            image = context.images.get_pil(t2i_adapter_field.image.image_name, mode="RGB")
 
             # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
             if t2i_adapter_model_config.base == BaseModelType.StableDiffusion1:
                 max_unet_downscale = 8
             elif t2i_adapter_model_config.base == BaseModelType.StableDiffusionXL:
                 max_unet_downscale = 4
+
+                # SDXL adapters are trained on cv2's BGR outputs
+                r, g, b = image.split()
+                image = Image.merge("RGB", (b, g, r))
             else:
                 raise ValueError(f"Unexpected T2I-Adapter base model type: '{t2i_adapter_model_config.base}'.")
 
@@ -630,29 +640,39 @@ class DenoiseLatentsInvocation(BaseInvocation):
             with t2i_adapter_loaded_model as t2i_adapter_model:
                 total_downscale_factor = t2i_adapter_model.total_downscale_factor
 
-                # Resize the T2I-Adapter input image.
-                # We select the resize dimensions so that after the T2I-Adapter's total_downscale_factor is applied, the
-                # result will match the latent image's dimensions after max_unet_downscale is applied.
-                t2i_input_height = latents_shape[2] // max_unet_downscale * total_downscale_factor
-                t2i_input_width = latents_shape[3] // max_unet_downscale * total_downscale_factor
-
                 # Note: We have hard-coded `do_classifier_free_guidance=False`. This is because we only want to prepare
                 # a single image. If CFG is enabled, we will duplicate the resultant tensor after applying the
                 # T2I-Adapter model.
                 #
                 # Note: We re-use the `prepare_control_image(...)` from ControlNet for T2I-Adapter, because it has many
                 # of the same requirements (e.g. preserving binary masks during resize).
+
+                # Assuming fixed dimensional scaling of LATENT_SCALE_FACTOR.
+                _, _, latent_height, latent_width = latents_shape
+                control_height_resize = latent_height * LATENT_SCALE_FACTOR
+                control_width_resize = latent_width * LATENT_SCALE_FACTOR
                 t2i_image = prepare_control_image(
                     image=image,
                     do_classifier_free_guidance=False,
-                    width=t2i_input_width,
-                    height=t2i_input_height,
+                    width=control_width_resize,
+                    height=control_height_resize,
                     num_channels=t2i_adapter_model.config["in_channels"],  # mypy treats this as a FrozenDict
                     device=t2i_adapter_model.device,
                     dtype=t2i_adapter_model.dtype,
                     resize_mode=t2i_adapter_field.resize_mode,
                 )
 
+                # Resize the T2I-Adapter input image.
+                # We select the resize dimensions so that after the T2I-Adapter's total_downscale_factor is applied, the
+                # result will match the latent image's dimensions after max_unet_downscale is applied.
+                # We crop the image to this size so that the positions match the input image on non-standard resolutions
+                t2i_input_height = latents_shape[2] // max_unet_downscale * total_downscale_factor
+                t2i_input_width = latents_shape[3] // max_unet_downscale * total_downscale_factor
+                if t2i_image.shape[2] > t2i_input_height or t2i_image.shape[3] > t2i_input_width:
+                    t2i_image = t2i_image[
+                        :, :, : min(t2i_image.shape[2], t2i_input_height), : min(t2i_image.shape[3], t2i_input_width)
+                    ]
+
                 adapter_state = t2i_adapter_model(t2i_image)
 
             if do_classifier_free_guidance:
@@ -900,7 +920,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
             #    ext = extension_field.to_extension(exit_stack, context, ext_manager)
             #    ext_manager.add_extension(ext)
             self.parse_controlnet_field(exit_stack, context, self.control, ext_manager)
-            self.parse_t2i_adapter_field(exit_stack, context, self.t2i_adapter, ext_manager)
+            bgr_mode = self.unet.unet.base == BaseModelType.StableDiffusionXL
+            self.parse_t2i_adapter_field(exit_stack, context, self.t2i_adapter, ext_manager, bgr_mode)
 
             # ext: t2i/ip adapter
             ext_manager.run_callback(ExtensionCallbackType.SETUP, denoise_ctx)

invokeai/app/invocations/fields.py

@@ -41,6 +41,7 @@ class UIType(str, Enum, metaclass=MetaEnum):
     # region Model Field Types
     MainModel = "MainModelField"
     FluxMainModel = "FluxMainModelField"
+    SD3MainModel = "SD3MainModelField"
     SDXLMainModel = "SDXLMainModelField"
     SDXLRefinerModel = "SDXLRefinerModelField"
     ONNXModel = "ONNXModelField"
@@ -52,6 +53,8 @@ class UIType(str, Enum, metaclass=MetaEnum):
     T2IAdapterModel = "T2IAdapterModelField"
     T5EncoderModel = "T5EncoderModelField"
     CLIPEmbedModel = "CLIPEmbedModelField"
+    CLIPLEmbedModel = "CLIPLEmbedModelField"
+    CLIPGEmbedModel = "CLIPGEmbedModelField"
     SpandrelImageToImageModel = "SpandrelImageToImageModelField"
     # endregion
 
@@ -131,6 +134,7 @@ class FieldDescriptions:
     clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
     t5_encoder = "T5 tokenizer and text encoder"
     clip_embed_model = "CLIP Embed loader"
+    clip_g_model = "CLIP-G Embed loader"
     unet = "UNet (scheduler, LoRAs)"
     transformer = "Transformer"
     mmditx = "MMDiTX"
@@ -248,6 +252,12 @@ class FluxConditioningField(BaseModel):
     conditioning_name: str = Field(description="The name of conditioning tensor")
 
 
+class SD3ConditioningField(BaseModel):
+    """A conditioning tensor primitive value"""
+
+    conditioning_name: str = Field(description="The name of conditioning tensor")
+
+
 class ConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 

invokeai/app/invocations/flux_denoise.py

@@ -56,7 +56,7 @@ from invokeai.backend.util.devices import TorchDevice
     title="FLUX Denoise",
     tags=["image", "flux"],
     category="image",
-    version="3.2.0",
+    version="3.2.1",
     classification=Classification.Prototype,
 )
 class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
@@ -81,6 +81,7 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         description=FieldDescriptions.denoising_start,
     )
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
+    add_noise: bool = InputField(default=True, description="Add noise based on denoising start.")
     transformer: TransformerField = InputField(
         description=FieldDescriptions.flux_model,
         input=Input.Connection,
@@ -207,9 +208,12 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                     "to be poor. Consider using a FLUX dev model instead."
                 )
 
-            # Noise the orig_latents by the appropriate amount for the first timestep.
-            t_0 = timesteps[0]
-            x = t_0 * noise + (1.0 - t_0) * init_latents
+            if self.add_noise:
+                # Noise the orig_latents by the appropriate amount for the first timestep.
+                t_0 = timesteps[0]
+                x = t_0 * noise + (1.0 - t_0) * init_latents
+            else:
+                x = init_latents
         else:
             # init_latents are not provided, so we are not doing image-to-image (i.e. we are starting from pure noise).
             if self.denoising_start > 1e-5:

invokeai/app/invocations/flux_model_loader.py

@@ -11,7 +11,10 @@ from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField
 from invokeai.app.invocations.model import CLIPField, ModelIdentifierField, T5EncoderField, TransformerField, VAEField
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.flux.util import max_seq_lengths
-from invokeai.backend.model_manager.config import CheckpointConfigBase, SubModelType
+from invokeai.backend.model_manager.config import (
+    CheckpointConfigBase,
+    SubModelType,
+)
 
 
 @invocation_output("flux_model_loader_output")

invokeai/app/invocations/flux_text_encoder.py

@@ -71,6 +71,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             t5_encoder = HFEncoder(t5_text_encoder, t5_tokenizer, False, self.t5_max_seq_len)
 
+            context.util.signal_progress("Running T5 encoder")
             prompt_embeds = t5_encoder(prompt)
 
         assert isinstance(prompt_embeds, torch.Tensor)
@@ -111,6 +112,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             clip_encoder = HFEncoder(clip_text_encoder, clip_tokenizer, True, 77)
 
+            context.util.signal_progress("Running CLIP encoder")
             pooled_prompt_embeds = clip_encoder(prompt)
 
         assert isinstance(pooled_prompt_embeds, torch.Tensor)

invokeai/app/invocations/flux_vae_decode.py

@@ -41,7 +41,8 @@ class FluxVaeDecodeInvocation(BaseInvocation, WithMetadata, WithBoard):
     def _vae_decode(self, vae_info: LoadedModel, latents: torch.Tensor) -> Image.Image:
         with vae_info as vae:
             assert isinstance(vae, AutoEncoder)
-            latents = latents.to(device=TorchDevice.choose_torch_device(), dtype=TorchDevice.choose_torch_dtype())
+            vae_dtype = next(iter(vae.parameters())).dtype
+            latents = latents.to(device=TorchDevice.choose_torch_device(), dtype=vae_dtype)
             img = vae.decode(latents)
 
         img = img.clamp(-1, 1)
@@ -53,6 +54,7 @@ class FluxVaeDecodeInvocation(BaseInvocation, WithMetadata, WithBoard):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         latents = context.tensors.load(self.latents.latents_name)
         vae_info = context.models.load(self.vae.vae)
+        context.util.signal_progress("Running VAE")
         image = self._vae_decode(vae_info=vae_info, latents=latents)
 
         TorchDevice.empty_cache()

invokeai/app/invocations/flux_vae_encode.py

@@ -44,9 +44,8 @@ class FluxVaeEncodeInvocation(BaseInvocation):
         generator = torch.Generator(device=TorchDevice.choose_torch_device()).manual_seed(0)
         with vae_info as vae:
             assert isinstance(vae, AutoEncoder)
-            image_tensor = image_tensor.to(
-                device=TorchDevice.choose_torch_device(), dtype=TorchDevice.choose_torch_dtype()
-            )
+            vae_dtype = next(iter(vae.parameters())).dtype
+            image_tensor = image_tensor.to(device=TorchDevice.choose_torch_device(), dtype=vae_dtype)
             latents = vae.encode(image_tensor, sample=True, generator=generator)
             return latents
 
@@ -60,6 +59,7 @@ class FluxVaeEncodeInvocation(BaseInvocation):
         if image_tensor.dim() == 3:
             image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
 
+        context.util.signal_progress("Running VAE")
         latents = self.vae_encode(vae_info=vae_info, image_tensor=image_tensor)
 
         latents = latents.to("cpu")

invokeai/app/invocations/image_to_latents.py

@@ -117,6 +117,7 @@ class ImageToLatentsInvocation(BaseInvocation):
         if image_tensor.dim() == 3:
             image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
 
+        context.util.signal_progress("Running VAE encoder")
         latents = self.vae_encode(
             vae_info=vae_info, upcast=self.fp32, tiled=self.tiled, image_tensor=image_tensor, tile_size=self.tile_size
         )

invokeai/app/invocations/latents_to_image.py

@@ -60,6 +60,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
         vae_info = context.models.load(self.vae.vae)
         assert isinstance(vae_info.model, (AutoencoderKL, AutoencoderTiny))
         with SeamlessExt.static_patch_model(vae_info.model, self.vae.seamless_axes), vae_info as vae:
+            context.util.signal_progress("Running VAE decoder")
             assert isinstance(vae, (AutoencoderKL, AutoencoderTiny))
             latents = latents.to(vae.device)
             if self.fp32:

invokeai/app/invocations/mask.py

@@ -165,6 +165,7 @@ class ApplyMaskTensorToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
 
     mask: TensorField = InputField(description="The mask tensor to apply.")
     image: ImageField = InputField(description="The image to apply the mask to.")
+    invert: bool = InputField(default=False, description="Whether to invert the mask.")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.images.get_pil(self.image.image_name, mode="RGBA")
@@ -179,6 +180,9 @@ class ApplyMaskTensorToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
             mask = mask > 0.5
         mask_np = (mask.float() * 255).byte().cpu().numpy().astype(np.uint8)
 
+        if self.invert:
+            mask_np = 255 - mask_np
+
         # Apply the mask only to the alpha channel where the original alpha is non-zero. This preserves the original
         # image's transparency - else the transparent regions would end up as opaque black.
 

invokeai/app/invocations/metadata.py

@@ -147,6 +147,10 @@ GENERATION_MODES = Literal[
     "flux_img2img",
     "flux_inpaint",
     "flux_outpaint",
+    "sd3_txt2img",
+    "sd3_img2img",
+    "sd3_inpaint",
+    "sd3_outpaint",
 ]
 
 

invokeai/app/invocations/primitives.py

@@ -18,6 +18,7 @@ from invokeai.app.invocations.fields import (
     InputField,
     LatentsField,
     OutputField,
+    SD3ConditioningField,
     TensorField,
     UIComponent,
 )
@@ -426,6 +427,17 @@ class FluxConditioningOutput(BaseInvocationOutput):
         return cls(conditioning=FluxConditioningField(conditioning_name=conditioning_name))
 
 
+@invocation_output("sd3_conditioning_output")
+class SD3ConditioningOutput(BaseInvocationOutput):
+    """Base class for nodes that output a single SD3 conditioning tensor"""
+
+    conditioning: SD3ConditioningField = OutputField(description=FieldDescriptions.cond)
+
+    @classmethod
+    def build(cls, conditioning_name: str) -> "SD3ConditioningOutput":
+        return cls(conditioning=SD3ConditioningField(conditioning_name=conditioning_name))
+
+
 @invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""

invokeai/app/invocations/sd3_denoise.py

@@ -0,0 +1,338 @@
+from typing import Callable, Optional, Tuple
+
+import torch
+import torchvision.transforms as tv_transforms
+from diffusers.models.transformers.transformer_sd3 import SD3Transformer2DModel
+from torchvision.transforms.functional import resize as tv_resize
+from tqdm import tqdm
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import (
+    DenoiseMaskField,
+    FieldDescriptions,
+    Input,
+    InputField,
+    LatentsField,
+    SD3ConditioningField,
+    WithBoard,
+    WithMetadata,
+)
+from invokeai.app.invocations.model import TransformerField
+from invokeai.app.invocations.primitives import LatentsOutput
+from invokeai.app.invocations.sd3_text_encoder import SD3_T5_MAX_SEQ_LEN
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.flux.sampling_utils import clip_timestep_schedule_fractional
+from invokeai.backend.model_manager.config import BaseModelType
+from invokeai.backend.sd3.extensions.inpaint_extension import InpaintExtension
+from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineIntermediateState
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import SD3ConditioningInfo
+from invokeai.backend.util.devices import TorchDevice
+
+
+@invocation(
+    "sd3_denoise",
+    title="SD3 Denoise",
+    tags=["image", "sd3"],
+    category="image",
+    version="1.1.0",
+    classification=Classification.Prototype,
+)
+class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Run denoising process with a SD3 model."""
+
+    # If latents is provided, this means we are doing image-to-image.
+    latents: Optional[LatentsField] = InputField(
+        default=None, description=FieldDescriptions.latents, input=Input.Connection
+    )
+    # denoise_mask is used for image-to-image inpainting. Only the masked region is modified.
+    denoise_mask: Optional[DenoiseMaskField] = InputField(
+        default=None, description=FieldDescriptions.denoise_mask, input=Input.Connection
+    )
+    denoising_start: float = InputField(default=0.0, ge=0, le=1, description=FieldDescriptions.denoising_start)
+    denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
+    transformer: TransformerField = InputField(
+        description=FieldDescriptions.sd3_model, input=Input.Connection, title="Transformer"
+    )
+    positive_conditioning: SD3ConditioningField = InputField(
+        description=FieldDescriptions.positive_cond, input=Input.Connection
+    )
+    negative_conditioning: SD3ConditioningField = InputField(
+        description=FieldDescriptions.negative_cond, input=Input.Connection
+    )
+    cfg_scale: float | list[float] = InputField(default=3.5, description=FieldDescriptions.cfg_scale, title="CFG Scale")
+    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.")
+    steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
+    seed: int = InputField(default=0, description="Randomness seed for reproducibility.")
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = self._run_diffusion(context)
+        latents = latents.detach().to("cpu")
+
+        name = context.tensors.save(tensor=latents)
+        return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
+
+    def _prep_inpaint_mask(self, context: InvocationContext, latents: torch.Tensor) -> torch.Tensor | None:
+        """Prepare the inpaint mask.
+        - Loads the mask
+        - Resizes if necessary
+        - Casts to same device/dtype as latents
+
+        Args:
+            context (InvocationContext): The invocation context, for loading the inpaint mask.
+            latents (torch.Tensor): A latent image tensor. Used to determine the target shape, device, and dtype for the
+                inpaint mask.
+
+        Returns:
+            torch.Tensor | None: Inpaint mask. Values of 0.0 represent the regions to be fully denoised, and 1.0
+                represent the regions to be preserved.
+        """
+        if self.denoise_mask is None:
+            return None
+        mask = context.tensors.load(self.denoise_mask.mask_name)
+
+        # The input denoise_mask contains values in [0, 1], where 0.0 represents the regions to be fully denoised, and
+        # 1.0 represents the regions to be preserved.
+        # We invert the mask so that the regions to be preserved are 0.0 and the regions to be denoised are 1.0.
+        mask = 1.0 - mask
+
+        _, _, latent_height, latent_width = latents.shape
+        mask = tv_resize(
+            img=mask,
+            size=[latent_height, latent_width],
+            interpolation=tv_transforms.InterpolationMode.BILINEAR,
+            antialias=False,
+        )
+
+        mask = mask.to(device=latents.device, dtype=latents.dtype)
+        return mask
+
+    def _load_text_conditioning(
+        self,
+        context: InvocationContext,
+        conditioning_name: str,
+        joint_attention_dim: int,
+        dtype: torch.dtype,
+        device: torch.device,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        # Load the conditioning data.
+        cond_data = context.conditioning.load(conditioning_name)
+        assert len(cond_data.conditionings) == 1
+        sd3_conditioning = cond_data.conditionings[0]
+        assert isinstance(sd3_conditioning, SD3ConditioningInfo)
+        sd3_conditioning = sd3_conditioning.to(dtype=dtype, device=device)
+
+        t5_embeds = sd3_conditioning.t5_embeds
+        if t5_embeds is None:
+            t5_embeds = torch.zeros(
+                (1, SD3_T5_MAX_SEQ_LEN, joint_attention_dim),
+                device=device,
+                dtype=dtype,
+            )
+
+        clip_prompt_embeds = torch.cat([sd3_conditioning.clip_l_embeds, sd3_conditioning.clip_g_embeds], dim=-1)
+        clip_prompt_embeds = torch.nn.functional.pad(
+            clip_prompt_embeds, (0, t5_embeds.shape[-1] - clip_prompt_embeds.shape[-1])
+        )
+
+        prompt_embeds = torch.cat([clip_prompt_embeds, t5_embeds], dim=-2)
+        pooled_prompt_embeds = torch.cat(
+            [sd3_conditioning.clip_l_pooled_embeds, sd3_conditioning.clip_g_pooled_embeds], dim=-1
+        )
+
+        return prompt_embeds, pooled_prompt_embeds
+
+    def _get_noise(
+        self,
+        num_samples: int,
+        num_channels_latents: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        seed: int,
+    ) -> torch.Tensor:
+        # We always generate noise on the same device and dtype then cast to ensure consistency across devices/dtypes.
+        rand_device = "cpu"
+        rand_dtype = torch.float16
+
+        return torch.randn(
+            num_samples,
+            num_channels_latents,
+            int(height) // LATENT_SCALE_FACTOR,
+            int(width) // LATENT_SCALE_FACTOR,
+            device=rand_device,
+            dtype=rand_dtype,
+            generator=torch.Generator(device=rand_device).manual_seed(seed),
+        ).to(device=device, dtype=dtype)
+
+    def _prepare_cfg_scale(self, num_timesteps: int) -> list[float]:
+        """Prepare the CFG scale list.
+
+        Args:
+            num_timesteps (int): The number of timesteps in the scheduler. Could be different from num_steps depending
+            on the scheduler used (e.g. higher order schedulers).
+
+        Returns:
+            list[float]: _description_
+        """
+        if isinstance(self.cfg_scale, float):
+            cfg_scale = [self.cfg_scale] * num_timesteps
+        elif isinstance(self.cfg_scale, list):
+            assert len(self.cfg_scale) == num_timesteps
+            cfg_scale = self.cfg_scale
+        else:
+            raise ValueError(f"Invalid CFG scale type: {type(self.cfg_scale)}")
+
+        return cfg_scale
+
+    def _run_diffusion(
+        self,
+        context: InvocationContext,
+    ):
+        inference_dtype = TorchDevice.choose_torch_dtype()
+        device = TorchDevice.choose_torch_device()
+
+        transformer_info = context.models.load(self.transformer.transformer)
+
+        # Load/process the conditioning data.
+        # TODO(ryand): Make CFG optional.
+        do_classifier_free_guidance = True
+        pos_prompt_embeds, pos_pooled_prompt_embeds = self._load_text_conditioning(
+            context=context,
+            conditioning_name=self.positive_conditioning.conditioning_name,
+            joint_attention_dim=transformer_info.model.config.joint_attention_dim,
+            dtype=inference_dtype,
+            device=device,
+        )
+        neg_prompt_embeds, neg_pooled_prompt_embeds = self._load_text_conditioning(
+            context=context,
+            conditioning_name=self.negative_conditioning.conditioning_name,
+            joint_attention_dim=transformer_info.model.config.joint_attention_dim,
+            dtype=inference_dtype,
+            device=device,
+        )
+        # TODO(ryand): Support both sequential and batched CFG inference.
+        prompt_embeds = torch.cat([neg_prompt_embeds, pos_prompt_embeds], dim=0)
+        pooled_prompt_embeds = torch.cat([neg_pooled_prompt_embeds, pos_pooled_prompt_embeds], dim=0)
+
+        # Prepare the timestep schedule.
+        # We add an extra step to the end to account for the final timestep of 0.0.
+        timesteps: list[float] = torch.linspace(1, 0, self.steps + 1).tolist()
+        # Clip the timesteps schedule based on denoising_start and denoising_end.
+        timesteps = clip_timestep_schedule_fractional(timesteps, self.denoising_start, self.denoising_end)
+        total_steps = len(timesteps) - 1
+
+        # Prepare the CFG scale list.
+        cfg_scale = self._prepare_cfg_scale(total_steps)
+
+        # Load the input latents, if provided.
+        init_latents = context.tensors.load(self.latents.latents_name) if self.latents else None
+        if init_latents is not None:
+            init_latents = init_latents.to(device=device, dtype=inference_dtype)
+
+        # Generate initial latent noise.
+        num_channels_latents = transformer_info.model.config.in_channels
+        assert isinstance(num_channels_latents, int)
+        noise = self._get_noise(
+            num_samples=1,
+            num_channels_latents=num_channels_latents,
+            height=self.height,
+            width=self.width,
+            dtype=inference_dtype,
+            device=device,
+            seed=self.seed,
+        )
+
+        # Prepare input latent image.
+        if init_latents is not None:
+            # Noise the init_latents by the appropriate amount for the first timestep.
+            t_0 = timesteps[0]
+            latents = t_0 * noise + (1.0 - t_0) * init_latents
+        else:
+            # init_latents are not provided, so we are not doing image-to-image (i.e. we are starting from pure noise).
+            if self.denoising_start > 1e-5:
+                raise ValueError("denoising_start should be 0 when initial latents are not provided.")
+            latents = noise
+
+        # If len(timesteps) == 1, then short-circuit. We are just noising the input latents, but not taking any
+        # denoising steps.
+        if len(timesteps) <= 1:
+            return latents
+
+        # Prepare inpaint extension.
+        inpaint_mask = self._prep_inpaint_mask(context, latents)
+        inpaint_extension: InpaintExtension | None = None
+        if inpaint_mask is not None:
+            assert init_latents is not None
+            inpaint_extension = InpaintExtension(
+                init_latents=init_latents,
+                inpaint_mask=inpaint_mask,
+                noise=noise,
+            )
+
+        step_callback = self._build_step_callback(context)
+
+        step_callback(
+            PipelineIntermediateState(
+                step=0,
+                order=1,
+                total_steps=total_steps,
+                timestep=int(timesteps[0]),
+                latents=latents,
+            ),
+        )
+
+        with transformer_info.model_on_device() as (cached_weights, transformer):
+            assert isinstance(transformer, SD3Transformer2DModel)
+
+            # 6. Denoising loop
+            for step_idx, (t_curr, t_prev) in tqdm(list(enumerate(zip(timesteps[:-1], timesteps[1:], strict=True)))):
+                # Expand the latents if we are doing CFG.
+                latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
+                # Expand the timestep to match the latent model input.
+                # Multiply by 1000 to match the default FlowMatchEulerDiscreteScheduler num_train_timesteps.
+                timestep = torch.tensor([t_curr * 1000], device=device).expand(latent_model_input.shape[0])
+
+                noise_pred = transformer(
+                    hidden_states=latent_model_input,
+                    timestep=timestep,
+                    encoder_hidden_states=prompt_embeds,
+                    pooled_projections=pooled_prompt_embeds,
+                    joint_attention_kwargs=None,
+                    return_dict=False,
+                )[0]
+
+                # Apply CFG.
+                if do_classifier_free_guidance:
+                    noise_pred_uncond, noise_pred_cond = noise_pred.chunk(2)
+                    noise_pred = noise_pred_uncond + cfg_scale[step_idx] * (noise_pred_cond - noise_pred_uncond)
+
+                # Compute the previous noisy sample x_t -> x_t-1.
+                latents_dtype = latents.dtype
+                latents = latents.to(dtype=torch.float32)
+                latents = latents + (t_prev - t_curr) * noise_pred
+                latents = latents.to(dtype=latents_dtype)
+
+                if inpaint_extension is not None:
+                    latents = inpaint_extension.merge_intermediate_latents_with_init_latents(latents, t_prev)
+
+                step_callback(
+                    PipelineIntermediateState(
+                        step=step_idx + 1,
+                        order=1,
+                        total_steps=total_steps,
+                        timestep=int(t_curr),
+                        latents=latents,
+                    ),
+                )
+
+        return latents
+
+    def _build_step_callback(self, context: InvocationContext) -> Callable[[PipelineIntermediateState], None]:
+        def step_callback(state: PipelineIntermediateState) -> None:
+            context.util.sd_step_callback(state, BaseModelType.StableDiffusion3)
+
+        return step_callback

invokeai/app/invocations/sd3_image_to_latents.py

@@ -0,0 +1,65 @@
+import einops
+import torch
+from diffusers.models.autoencoders.autoencoder_kl import AutoencoderKL
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    WithBoard,
+    WithMetadata,
+)
+from invokeai.app.invocations.model import VAEField
+from invokeai.app.invocations.primitives import LatentsOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager.load.load_base import LoadedModel
+from invokeai.backend.stable_diffusion.diffusers_pipeline import image_resized_to_grid_as_tensor
+
+
+@invocation(
+    "sd3_i2l",
+    title="SD3 Image to Latents",
+    tags=["image", "latents", "vae", "i2l", "sd3"],
+    category="image",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class SD3ImageToLatentsInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Generates latents from an image."""
+
+    image: ImageField = InputField(description="The image to encode")
+    vae: VAEField = InputField(description=FieldDescriptions.vae, input=Input.Connection)
+
+    @staticmethod
+    def vae_encode(vae_info: LoadedModel, image_tensor: torch.Tensor) -> torch.Tensor:
+        with vae_info as vae:
+            assert isinstance(vae, AutoencoderKL)
+
+            vae.disable_tiling()
+
+            image_tensor = image_tensor.to(device=vae.device, dtype=vae.dtype)
+            with torch.inference_mode():
+                image_tensor_dist = vae.encode(image_tensor).latent_dist
+                # TODO: Use seed to make sampling reproducible.
+                latents: torch.Tensor = image_tensor_dist.sample().to(dtype=vae.dtype)
+
+            latents = vae.config.scaling_factor * latents
+
+        return latents
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        image = context.images.get_pil(self.image.image_name)
+
+        image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+        if image_tensor.dim() == 3:
+            image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
+
+        vae_info = context.models.load(self.vae.vae)
+        latents = self.vae_encode(vae_info=vae_info, image_tensor=image_tensor)
+
+        latents = latents.to("cpu")
+        name = context.tensors.save(tensor=latents)
+        return LatentsOutput.build(latents_name=name, latents=latents, seed=None)

invokeai/app/invocations/sd3_latents_to_image.py

@@ -0,0 +1,74 @@
+from contextlib import nullcontext
+
+import torch
+from diffusers.models.autoencoders.autoencoder_kl import AutoencoderKL
+from einops import rearrange
+from PIL import Image
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    Input,
+    InputField,
+    LatentsField,
+    WithBoard,
+    WithMetadata,
+)
+from invokeai.app.invocations.model import VAEField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.stable_diffusion.extensions.seamless import SeamlessExt
+from invokeai.backend.util.devices import TorchDevice
+
+
+@invocation(
+    "sd3_l2i",
+    title="SD3 Latents to Image",
+    tags=["latents", "image", "vae", "l2i", "sd3"],
+    category="latents",
+    version="1.3.0",
+)
+class SD3LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Generates an image from latents."""
+
+    latents: LatentsField = InputField(
+        description=FieldDescriptions.latents,
+        input=Input.Connection,
+    )
+    vae: VAEField = InputField(
+        description=FieldDescriptions.vae,
+        input=Input.Connection,
+    )
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        latents = context.tensors.load(self.latents.latents_name)
+
+        vae_info = context.models.load(self.vae.vae)
+        assert isinstance(vae_info.model, (AutoencoderKL))
+        with SeamlessExt.static_patch_model(vae_info.model, self.vae.seamless_axes), vae_info as vae:
+            context.util.signal_progress("Running VAE")
+            assert isinstance(vae, (AutoencoderKL))
+            latents = latents.to(vae.device)
+
+            vae.disable_tiling()
+
+            tiling_context = nullcontext()
+
+            # clear memory as vae decode can request a lot
+            TorchDevice.empty_cache()
+
+            with torch.inference_mode(), tiling_context:
+                # copied from diffusers pipeline
+                latents = latents / vae.config.scaling_factor
+                img = vae.decode(latents, return_dict=False)[0]
+
+            img = img.clamp(-1, 1)
+            img = rearrange(img[0], "c h w -> h w c")  # noqa: F821
+            img_pil = Image.fromarray((127.5 * (img + 1.0)).byte().cpu().numpy())
+
+        TorchDevice.empty_cache()
+
+        image_dto = context.images.save(image=img_pil)
+
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/sd3_model_loader.py

@@ -1,3 +1,5 @@
+from typing import Optional
+
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -8,14 +10,14 @@ from invokeai.app.invocations.baseinvocation import (
 from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
 from invokeai.app.invocations.model import CLIPField, ModelIdentifierField, T5EncoderField, TransformerField, VAEField
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.model_manager.config import CheckpointConfigBase, SubModelType
+from invokeai.backend.model_manager.config import SubModelType
 
 
 @invocation_output("sd3_model_loader_output")
 class Sd3ModelLoaderOutput(BaseInvocationOutput):
     """SD3 base model loader output."""
 
-    mmditx: TransformerField = OutputField(description=FieldDescriptions.mmditx, title="MMDiTX")
+    transformer: TransformerField = OutputField(description=FieldDescriptions.transformer, title="Transformer")
     clip_l: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP L")
     clip_g: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP G")
     t5_encoder: T5EncoderField = OutputField(description=FieldDescriptions.t5_encoder, title="T5 Encoder")
@@ -33,68 +35,72 @@ class Sd3ModelLoaderOutput(BaseInvocationOutput):
 class Sd3ModelLoaderInvocation(BaseInvocation):
     """Loads a SD3 base model, outputting its submodels."""
 
-    # TODO(ryand): Create a UIType.Sd3MainModelField to use here.
     model: ModelIdentifierField = InputField(
         description=FieldDescriptions.sd3_model,
-        ui_type=UIType.MainModel,
+        ui_type=UIType.SD3MainModel,
         input=Input.Direct,
     )
 
-    # TODO(ryand): Make the text encoders optional.
-    # Note: The text encoders are optional for SD3. The model was trained with dropout, so any can be left out at
-    # inference time. Typically, only the T5 encoder is omitted, since it is the largest by far.
-    t5_encoder_model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.t5_encoder, ui_type=UIType.T5EncoderModel, input=Input.Direct, title="T5 Encoder"
+    t5_encoder_model: Optional[ModelIdentifierField] = InputField(
+        description=FieldDescriptions.t5_encoder,
+        ui_type=UIType.T5EncoderModel,
+        input=Input.Direct,
+        title="T5 Encoder",
+        default=None,
     )
 
-    clip_l_embed_model: ModelIdentifierField = InputField(
+    clip_l_model: Optional[ModelIdentifierField] = InputField(
         description=FieldDescriptions.clip_embed_model,
-        ui_type=UIType.CLIPEmbedModel,
+        ui_type=UIType.CLIPLEmbedModel,
         input=Input.Direct,
-        title="CLIP L Embed",
+        title="CLIP L Encoder",
+        default=None,
     )
 
-    clip_g_embed_model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.clip_embed_model,
-        ui_type=UIType.CLIPEmbedModel,
+    clip_g_model: Optional[ModelIdentifierField] = InputField(
+        description=FieldDescriptions.clip_g_model,
+        ui_type=UIType.CLIPGEmbedModel,
         input=Input.Direct,
-        title="CLIP G Embed",
+        title="CLIP G Encoder",
+        default=None,
     )
 
-    # TODO(ryand): Create a UIType.Sd3VaModelField to use here.
-    vae_model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.vae_model, ui_type=UIType.VAEModel, title="VAE"
+    vae_model: Optional[ModelIdentifierField] = InputField(
+        description=FieldDescriptions.vae_model, ui_type=UIType.VAEModel, title="VAE", default=None
     )
 
     def invoke(self, context: InvocationContext) -> Sd3ModelLoaderOutput:
-        for key in [
-            self.model.key,
-            self.t5_encoder_model.key,
-            self.clip_l_embed_model.key,
-            self.clip_g_embed_model.key,
-            self.vae_model.key,
-        ]:
-            if not context.models.exists(key):
-                raise ValueError(f"Unknown model: {key}")
-
-        # TODO(ryand): Figure out the sub-model types for SD3.
-        mmditx = self.model.model_copy(update={"submodel_type": SubModelType.Transformer})
-        vae = self.vae_model.model_copy(update={"submodel_type": SubModelType.VAE})
-
-        tokenizer_l = self.clip_l_embed_model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
-        clip_encoder_l = self.clip_l_embed_model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
-
-        tokenizer_g = self.clip_g_embed_model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
-        clip_encoder_g = self.clip_g_embed_model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
-
-        tokenizer_t5 = self.t5_encoder_model.model_copy(update={"submodel_type": SubModelType.Tokenizer2})
-        t5_encoder = self.t5_encoder_model.model_copy(update={"submodel_type": SubModelType.TextEncoder2})
-
-        transformer_config = context.models.get_config(mmditx)
-        assert isinstance(transformer_config, CheckpointConfigBase)
+        transformer = self.model.model_copy(update={"submodel_type": SubModelType.Transformer})
+        vae = (
+            self.vae_model.model_copy(update={"submodel_type": SubModelType.VAE})
+            if self.vae_model
+            else self.model.model_copy(update={"submodel_type": SubModelType.VAE})
+        )
+        tokenizer_l = self.model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
+        clip_encoder_l = (
+            self.clip_l_model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
+            if self.clip_l_model
+            else self.model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
+        )
+        tokenizer_g = self.model.model_copy(update={"submodel_type": SubModelType.Tokenizer2})
+        clip_encoder_g = (
+            self.clip_g_model.model_copy(update={"submodel_type": SubModelType.TextEncoder2})
+            if self.clip_g_model
+            else self.model.model_copy(update={"submodel_type": SubModelType.TextEncoder2})
+        )
+        tokenizer_t5 = (
+            self.t5_encoder_model.model_copy(update={"submodel_type": SubModelType.Tokenizer3})
+            if self.t5_encoder_model
+            else self.model.model_copy(update={"submodel_type": SubModelType.Tokenizer3})
+        )
+        t5_encoder = (
+            self.t5_encoder_model.model_copy(update={"submodel_type": SubModelType.TextEncoder3})
+            if self.t5_encoder_model
+            else self.model.model_copy(update={"submodel_type": SubModelType.TextEncoder3})
+        )
 
         return Sd3ModelLoaderOutput(
-            mmditx=TransformerField(transformer=mmditx, loras=[]),
+            transformer=TransformerField(transformer=transformer, loras=[]),
             clip_l=CLIPField(tokenizer=tokenizer_l, text_encoder=clip_encoder_l, loras=[], skipped_layers=0),
             clip_g=CLIPField(tokenizer=tokenizer_g, text_encoder=clip_encoder_g, loras=[], skipped_layers=0),
             t5_encoder=T5EncoderField(tokenizer=tokenizer_t5, text_encoder=t5_encoder),

invokeai/app/invocations/sd3_text_encoder.py

@@ -0,0 +1,201 @@
+from contextlib import ExitStack
+from typing import Iterator, Tuple
+
+import torch
+from transformers import (
+    CLIPTextModel,
+    CLIPTextModelWithProjection,
+    CLIPTokenizer,
+    T5EncoderModel,
+    T5Tokenizer,
+    T5TokenizerFast,
+)
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField
+from invokeai.app.invocations.model import CLIPField, T5EncoderField
+from invokeai.app.invocations.primitives import SD3ConditioningOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.lora.conversions.flux_lora_constants import FLUX_LORA_CLIP_PREFIX
+from invokeai.backend.lora.lora_model_raw import LoRAModelRaw
+from invokeai.backend.lora.lora_patcher import LoRAPatcher
+from invokeai.backend.model_manager.config import ModelFormat
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData, SD3ConditioningInfo
+
+# The SD3 T5 Max Sequence Length set based on the default in diffusers.
+SD3_T5_MAX_SEQ_LEN = 256
+
+
+@invocation(
+    "sd3_text_encoder",
+    title="SD3 Text Encoding",
+    tags=["prompt", "conditioning", "sd3"],
+    category="conditioning",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class Sd3TextEncoderInvocation(BaseInvocation):
+    """Encodes and preps a prompt for a SD3 image."""
+
+    clip_l: CLIPField = InputField(
+        title="CLIP L",
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+    )
+    clip_g: CLIPField = InputField(
+        title="CLIP G",
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+    )
+
+    # The SD3 models were trained with text encoder dropout, so the T5 encoder can be omitted to save time/memory.
+    t5_encoder: T5EncoderField | None = InputField(
+        title="T5Encoder",
+        default=None,
+        description=FieldDescriptions.t5_encoder,
+        input=Input.Connection,
+    )
+    prompt: str = InputField(description="Text prompt to encode.")
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> SD3ConditioningOutput:
+        # Note: The text encoding model are run in separate functions to ensure that all model references are locally
+        # scoped. This ensures that earlier models can be freed and gc'd before loading later models (if necessary).
+
+        clip_l_embeddings, clip_l_pooled_embeddings = self._clip_encode(context, self.clip_l)
+        clip_g_embeddings, clip_g_pooled_embeddings = self._clip_encode(context, self.clip_g)
+
+        t5_embeddings: torch.Tensor | None = None
+        if self.t5_encoder is not None:
+            t5_embeddings = self._t5_encode(context, SD3_T5_MAX_SEQ_LEN)
+
+        conditioning_data = ConditioningFieldData(
+            conditionings=[
+                SD3ConditioningInfo(
+                    clip_l_embeds=clip_l_embeddings,
+                    clip_l_pooled_embeds=clip_l_pooled_embeddings,
+                    clip_g_embeds=clip_g_embeddings,
+                    clip_g_pooled_embeds=clip_g_pooled_embeddings,
+                    t5_embeds=t5_embeddings,
+                )
+            ]
+        )
+
+        conditioning_name = context.conditioning.save(conditioning_data)
+        return SD3ConditioningOutput.build(conditioning_name)
+
+    def _t5_encode(self, context: InvocationContext, max_seq_len: int) -> torch.Tensor:
+        assert self.t5_encoder is not None
+        t5_tokenizer_info = context.models.load(self.t5_encoder.tokenizer)
+        t5_text_encoder_info = context.models.load(self.t5_encoder.text_encoder)
+
+        prompt = [self.prompt]
+
+        with (
+            t5_text_encoder_info as t5_text_encoder,
+            t5_tokenizer_info as t5_tokenizer,
+        ):
+            context.util.signal_progress("Running T5 encoder")
+            assert isinstance(t5_text_encoder, T5EncoderModel)
+            assert isinstance(t5_tokenizer, (T5Tokenizer, T5TokenizerFast))
+
+            text_inputs = t5_tokenizer(
+                prompt,
+                padding="max_length",
+                max_length=max_seq_len,
+                truncation=True,
+                add_special_tokens=True,
+                return_tensors="pt",
+            )
+            text_input_ids = text_inputs.input_ids
+            untruncated_ids = t5_tokenizer(prompt, padding="longest", return_tensors="pt").input_ids
+            assert isinstance(text_input_ids, torch.Tensor)
+            assert isinstance(untruncated_ids, torch.Tensor)
+            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(
+                text_input_ids, untruncated_ids
+            ):
+                removed_text = t5_tokenizer.batch_decode(untruncated_ids[:, max_seq_len - 1 : -1])
+                context.logger.warning(
+                    "The following part of your input was truncated because `max_sequence_length` is set to "
+                    f" {max_seq_len} tokens: {removed_text}"
+                )
+
+            prompt_embeds = t5_text_encoder(text_input_ids.to(t5_text_encoder.device))[0]
+
+        assert isinstance(prompt_embeds, torch.Tensor)
+        return prompt_embeds
+
+    def _clip_encode(
+        self, context: InvocationContext, clip_model: CLIPField, tokenizer_max_length: int = 77
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        clip_tokenizer_info = context.models.load(clip_model.tokenizer)
+        clip_text_encoder_info = context.models.load(clip_model.text_encoder)
+
+        prompt = [self.prompt]
+
+        with (
+            clip_text_encoder_info.model_on_device() as (cached_weights, clip_text_encoder),
+            clip_tokenizer_info as clip_tokenizer,
+            ExitStack() as exit_stack,
+        ):
+            context.util.signal_progress("Running CLIP encoder")
+            assert isinstance(clip_text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
+            assert isinstance(clip_tokenizer, CLIPTokenizer)
+
+            clip_text_encoder_config = clip_text_encoder_info.config
+            assert clip_text_encoder_config is not None
+
+            # Apply LoRA models to the CLIP encoder.
+            # Note: We apply the LoRA after the transformer has been moved to its target device for faster patching.
+            if clip_text_encoder_config.format in [ModelFormat.Diffusers]:
+                # The model is non-quantized, so we can apply the LoRA weights directly into the model.
+                exit_stack.enter_context(
+                    LoRAPatcher.apply_lora_patches(
+                        model=clip_text_encoder,
+                        patches=self._clip_lora_iterator(context, clip_model),
+                        prefix=FLUX_LORA_CLIP_PREFIX,
+                        cached_weights=cached_weights,
+                    )
+                )
+            else:
+                # There are currently no supported CLIP quantized models. Add support here if needed.
+                raise ValueError(f"Unsupported model format: {clip_text_encoder_config.format}")
+
+            clip_text_encoder = clip_text_encoder.eval().requires_grad_(False)
+
+            text_inputs = clip_tokenizer(
+                prompt,
+                padding="max_length",
+                max_length=tokenizer_max_length,
+                truncation=True,
+                return_tensors="pt",
+            )
+
+            text_input_ids = text_inputs.input_ids
+            untruncated_ids = clip_tokenizer(prompt, padding="longest", return_tensors="pt").input_ids
+            assert isinstance(text_input_ids, torch.Tensor)
+            assert isinstance(untruncated_ids, torch.Tensor)
+            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(
+                text_input_ids, untruncated_ids
+            ):
+                removed_text = clip_tokenizer.batch_decode(untruncated_ids[:, tokenizer_max_length - 1 : -1])
+                context.logger.warning(
+                    "The following part of your input was truncated because CLIP can only handle sequences up to"
+                    f" {tokenizer_max_length} tokens: {removed_text}"
+                )
+            prompt_embeds = clip_text_encoder(
+                input_ids=text_input_ids.to(clip_text_encoder.device), output_hidden_states=True
+            )
+            pooled_prompt_embeds = prompt_embeds[0]
+            prompt_embeds = prompt_embeds.hidden_states[-2]
+
+            return prompt_embeds, pooled_prompt_embeds
+
+    def _clip_lora_iterator(
+        self, context: InvocationContext, clip_model: CLIPField
+    ) -> Iterator[Tuple[LoRAModelRaw, float]]:
+        for lora in clip_model.loras:
+            lora_info = context.models.load(lora.lora)
+            assert isinstance(lora_info.model, LoRAModelRaw)
+            yield (lora_info.model, lora.weight)
+            del lora_info

invokeai/app/invocations/segment_anything.py

@@ -5,7 +5,7 @@ from typing import Literal
 import numpy as np
 import torch
 from PIL import Image
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, Field
 from transformers import AutoModelForMaskGeneration, AutoProcessor
 from transformers.models.sam import SamModel
 from transformers.models.sam.processing_sam import SamProcessor
@@ -77,19 +77,14 @@ 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 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.")
+
         if (not self.bounding_boxes or len(self.bounding_boxes) == 0) and (
             not self.point_lists or len(self.point_lists) == 0
         ):

invokeai/app/services/model_records/model_records_base.py

@@ -15,6 +15,7 @@ from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
+    ClipVariantType,
     ControlAdapterDefaultSettings,
     MainModelDefaultSettings,
     ModelFormat,
@@ -85,7 +86,7 @@ class ModelRecordChanges(BaseModelExcludeNull):
 
     # Checkpoint-specific changes
     # TODO(MM2): Should we expose these? Feels footgun-y...
-    variant: Optional[ModelVariantType] = Field(description="The variant of the model.", default=None)
+    variant: Optional[ModelVariantType | ClipVariantType] = Field(description="The variant of the model.", default=None)
     prediction_type: Optional[SchedulerPredictionType] = Field(
         description="The prediction type of the model.", default=None
     )

invokeai/app/services/shared/invocation_context.py

@@ -1,3 +1,4 @@
+from copy import deepcopy
 from dataclasses import dataclass
 from pathlib import Path
 from typing import TYPE_CHECKING, Callable, Optional, Union
@@ -159,6 +160,10 @@ class LoggerInterface(InvocationContextInterface):
 
 
 class ImagesInterface(InvocationContextInterface):
+    def __init__(self, services: InvocationServices, data: InvocationContextData, util: "UtilInterface") -> None:
+        super().__init__(services, data)
+        self._util = util
+
     def save(
         self,
         image: Image,
@@ -185,6 +190,8 @@ class ImagesInterface(InvocationContextInterface):
             The saved image DTO.
         """
 
+        self._util.signal_progress("Saving image")
+
         # If `metadata` is provided directly, use that. Else, use the metadata provided by `WithMetadata`, falling back to None.
         metadata_ = None
         if metadata:
@@ -221,7 +228,7 @@ class ImagesInterface(InvocationContextInterface):
         )
 
     def get_pil(self, image_name: str, mode: IMAGE_MODES | None = None) -> Image:
-        """Gets an image as a PIL Image object.
+        """Gets an image as a PIL Image object. This method returns a copy of the image.
 
         Args:
             image_name: The name of the image to get.
@@ -233,11 +240,15 @@ class ImagesInterface(InvocationContextInterface):
         image = self._services.images.get_pil_image(image_name)
         if mode and mode != image.mode:
             try:
+                # convert makes a copy!
                 image = image.convert(mode)
             except ValueError:
                 self._services.logger.warning(
                     f"Could not convert image from {image.mode} to {mode}. Using original mode instead."
                 )
+        else:
+            # copy the image to prevent the user from modifying the original
+            image = image.copy()
         return image
 
     def get_metadata(self, image_name: str) -> Optional[MetadataField]:
@@ -290,15 +301,15 @@ class TensorsInterface(InvocationContextInterface):
         return name
 
     def load(self, name: str) -> Tensor:
-        """Loads a tensor by name.
+        """Loads a tensor by name. This method returns a copy of the tensor.
 
         Args:
             name: The name of the tensor to load.
 
         Returns:
-            The loaded tensor.
+            The tensor.
         """
-        return self._services.tensors.load(name)
+        return self._services.tensors.load(name).clone()
 
 
 class ConditioningInterface(InvocationContextInterface):
@@ -316,21 +327,25 @@ class ConditioningInterface(InvocationContextInterface):
         return name
 
     def load(self, name: str) -> ConditioningFieldData:
-        """Loads conditioning data by name.
+        """Loads conditioning data by name. This method returns a copy of the conditioning data.
 
         Args:
             name: The name of the conditioning data to load.
 
         Returns:
-            The loaded conditioning data.
+            The conditioning data.
         """
 
-        return self._services.conditioning.load(name)
+        return deepcopy(self._services.conditioning.load(name))
 
 
 class ModelsInterface(InvocationContextInterface):
     """Common API for loading, downloading and managing models."""
 
+    def __init__(self, services: InvocationServices, data: InvocationContextData, util: "UtilInterface") -> None:
+        super().__init__(services, data)
+        self._util = util
+
     def exists(self, identifier: Union[str, "ModelIdentifierField"]) -> bool:
         """Check if a model exists.
 
@@ -363,11 +378,15 @@ class ModelsInterface(InvocationContextInterface):
 
         if isinstance(identifier, str):
             model = self._services.model_manager.store.get_model(identifier)
-            return self._services.model_manager.load.load_model(model, submodel_type)
         else:
-            _submodel_type = submodel_type or identifier.submodel_type
+            submodel_type = submodel_type or identifier.submodel_type
             model = self._services.model_manager.store.get_model(identifier.key)
-            return self._services.model_manager.load.load_model(model, _submodel_type)
+
+        message = f"Loading model {model.name}"
+        if submodel_type:
+            message += f" ({submodel_type.value})"
+        self._util.signal_progress(message)
+        return self._services.model_manager.load.load_model(model, submodel_type)
 
     def load_by_attrs(
         self, name: str, base: BaseModelType, type: ModelType, submodel_type: Optional[SubModelType] = None
@@ -392,6 +411,10 @@ class ModelsInterface(InvocationContextInterface):
         if len(configs) > 1:
             raise ValueError(f"More than one model found with name {name}, base {base}, and type {type}")
 
+        message = f"Loading model {name}"
+        if submodel_type:
+            message += f" ({submodel_type.value})"
+        self._util.signal_progress(message)
         return self._services.model_manager.load.load_model(configs[0], submodel_type)
 
     def get_config(self, identifier: Union[str, "ModelIdentifierField"]) -> AnyModelConfig:
@@ -462,6 +485,7 @@ class ModelsInterface(InvocationContextInterface):
         Returns:
             Path to the downloaded model
         """
+        self._util.signal_progress(f"Downloading model {source}")
         return self._services.model_manager.install.download_and_cache_model(source=source)
 
     def load_local_model(
@@ -484,6 +508,8 @@ class ModelsInterface(InvocationContextInterface):
         Returns:
             A LoadedModelWithoutConfig object.
         """
+
+        self._util.signal_progress(f"Loading model {model_path.name}")
         return self._services.model_manager.load.load_model_from_path(model_path=model_path, loader=loader)
 
     def load_remote_model(
@@ -509,6 +535,8 @@ class ModelsInterface(InvocationContextInterface):
             A LoadedModelWithoutConfig object.
         """
         model_path = self._services.model_manager.install.download_and_cache_model(source=str(source))
+
+        self._util.signal_progress(f"Loading model {source}")
         return self._services.model_manager.load.load_model_from_path(model_path=model_path, loader=loader)
 
 
@@ -702,12 +730,12 @@ def build_invocation_context(
     """
 
     logger = LoggerInterface(services=services, data=data)
-    images = ImagesInterface(services=services, data=data)
     tensors = TensorsInterface(services=services, data=data)
-    models = ModelsInterface(services=services, data=data)
     config = ConfigInterface(services=services, data=data)
     util = UtilInterface(services=services, data=data, is_canceled=is_canceled)
     conditioning = ConditioningInterface(services=services, data=data)
+    models = ModelsInterface(services=services, data=data, util=util)
+    images = ImagesInterface(services=services, data=data, util=util)
     boards = BoardsInterface(services=services, data=data)
 
     ctx = InvocationContext(

invokeai/app/services/workflow_records/default_workflows/SD3.5 Text to Image.json

@@ -0,0 +1,382 @@
+{
+    "name": "SD3.5 Text to Image",
+   "author": "InvokeAI",
+    "description": "Sample text to image workflow for Stable Diffusion 3.5",
+    "version": "1.0.0",
+    "contact": "invoke@invoke.ai",
+    "tags": "text2image, SD3.5, default",
+  "notes": "",
+    "exposedFields": [
+      {
+        "nodeId": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "fieldName": "model"
+      },
+      {
+        "nodeId": "e17d34e7-6ed1-493c-9a85-4fcd291cb084",
+        "fieldName": "prompt"
+      }
+    ],
+    "meta": {
+      "version": "3.0.0",
+      "category": "default"
+    },
+    "id": "e3a51d6b-8208-4d6d-b187-fcfe8b32934c",
+    "nodes": [
+      {
+        "id": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "type": "invocation",
+        "data": {
+          "id": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+          "type": "sd3_model_loader",
+          "version": "1.0.0",
+          "label": "",
+          "notes": "",
+          "isOpen": true,
+          "isIntermediate": true,
+          "useCache": true,
+          "nodePack": "invokeai",
+          "inputs": {
+            "model": {
+              "name": "model",
+              "label": "",
+              "value": {
+                "key": "f7b20be9-92a8-4cfb-bca4-6c3b5535c10b",
+                "hash": "placeholder",
+                "name": "stable-diffusion-3.5-medium",
+                "base": "sd-3",
+                "type": "main"
+              }
+            },
+            "t5_encoder_model": {
+              "name": "t5_encoder_model",
+              "label": ""
+            },
+            "clip_l_model": {
+              "name": "clip_l_model",
+              "label": ""
+            },
+            "clip_g_model": {
+              "name": "clip_g_model",
+              "label": ""
+            },
+            "vae_model": {
+              "name": "vae_model",
+              "label": ""
+            }
+          }
+        },
+        "position": {
+          "x": -55.58689609637031,
+          "y": -111.53602444662268
+        }
+      },
+      {
+        "id": "f7e394ac-6394-4096-abcb-de0d346506b3",
+        "type": "invocation",
+        "data": {
+          "id": "f7e394ac-6394-4096-abcb-de0d346506b3",
+          "type": "rand_int",
+          "version": "1.0.1",
+          "label": "",
+          "notes": "",
+          "isOpen": true,
+          "isIntermediate": true,
+          "useCache": false,
+          "nodePack": "invokeai",
+          "inputs": {
+            "low": {
+              "name": "low",
+              "label": "",
+              "value": 0
+            },
+            "high": {
+              "name": "high",
+              "label": "",
+              "value": 2147483647
+            }
+          }
+        },
+        "position": {
+          "x": 470.45870147220353,
+          "y": 350.3141781644303
+        }
+      },
+      {
+        "id": "9eb72af0-dd9e-4ec5-ad87-d65e3c01f48b",
+        "type": "invocation",
+        "data": {
+          "id": "9eb72af0-dd9e-4ec5-ad87-d65e3c01f48b",
+          "type": "sd3_l2i",
+          "version": "1.3.0",
+          "label": "",
+          "notes": "",
+          "isOpen": true,
+          "isIntermediate": false,
+          "useCache": true,
+          "nodePack": "invokeai",
+          "inputs": {
+            "board": {
+              "name": "board",
+              "label": ""
+            },
+            "metadata": {
+              "name": "metadata",
+              "label": ""
+            },
+            "latents": {
+              "name": "latents",
+              "label": ""
+            },
+            "vae": {
+              "name": "vae",
+              "label": ""
+            }
+          }
+        },
+        "position": {
+          "x": 1192.3097009334897,
+          "y": -366.0994675072209
+        }
+      },
+      {
+        "id": "3b4f7f27-cfc0-4373-a009-99c5290d0cd6",
+        "type": "invocation",
+        "data": {
+          "id": "3b4f7f27-cfc0-4373-a009-99c5290d0cd6",
+          "type": "sd3_text_encoder",
+          "version": "1.0.0",
+          "label": "",
+          "notes": "",
+          "isOpen": true,
+          "isIntermediate": true,
+          "useCache": true,
+          "nodePack": "invokeai",
+          "inputs": {
+            "clip_l": {
+              "name": "clip_l",
+              "label": ""
+            },
+            "clip_g": {
+              "name": "clip_g",
+              "label": ""
+            },
+            "t5_encoder": {
+              "name": "t5_encoder",
+              "label": ""
+            },
+            "prompt": {
+              "name": "prompt",
+              "label": "",
+              "value": ""
+            }
+          }
+        },
+        "position": {
+          "x": 408.16054647924784,
+          "y": 65.06415352118786
+        }
+      },
+      {
+        "id": "e17d34e7-6ed1-493c-9a85-4fcd291cb084",
+        "type": "invocation",
+        "data": {
+          "id": "e17d34e7-6ed1-493c-9a85-4fcd291cb084",
+          "type": "sd3_text_encoder",
+          "version": "1.0.0",
+          "label": "",
+          "notes": "",
+          "isOpen": true,
+          "isIntermediate": true,
+          "useCache": true,
+          "nodePack": "invokeai",
+          "inputs": {
+            "clip_l": {
+              "name": "clip_l",
+              "label": ""
+            },
+            "clip_g": {
+              "name": "clip_g",
+              "label": ""
+            },
+            "t5_encoder": {
+              "name": "t5_encoder",
+              "label": ""
+            },
+            "prompt": {
+              "name": "prompt",
+              "label": "",
+              "value": ""
+            }
+          }
+        },
+        "position": {
+          "x": 378.9283412440941,
+          "y": -302.65777497352553
+        }
+      },
+      {
+        "id": "c7539f7b-7ac5-49b9-93eb-87ede611409f",
+        "type": "invocation",
+        "data": {
+          "id": "c7539f7b-7ac5-49b9-93eb-87ede611409f",
+          "type": "sd3_denoise",
+          "version": "1.0.0",
+          "label": "",
+          "notes": "",
+          "isOpen": true,
+          "isIntermediate": true,
+          "useCache": true,
+          "nodePack": "invokeai",
+          "inputs": {
+            "board": {
+              "name": "board",
+              "label": ""
+            },
+            "metadata": {
+              "name": "metadata",
+              "label": ""
+            },
+            "transformer": {
+              "name": "transformer",
+              "label": ""
+            },
+            "positive_conditioning": {
+              "name": "positive_conditioning",
+              "label": ""
+            },
+            "negative_conditioning": {
+              "name": "negative_conditioning",
+              "label": ""
+            },
+            "cfg_scale": {
+              "name": "cfg_scale",
+              "label": "",
+              "value": 3.5
+            },
+            "width": {
+              "name": "width",
+              "label": "",
+              "value": 1024
+            },
+            "height": {
+              "name": "height",
+              "label": "",
+              "value": 1024
+            },
+            "steps": {
+              "name": "steps",
+              "label": "",
+              "value": 30
+            },
+            "seed": {
+              "name": "seed",
+              "label": "",
+              "value": 0
+            }
+          }
+        },
+        "position": {
+          "x": 813.7814762740603,
+          "y": -142.20529727605867
+        }
+      }
+    ],
+    "edges": [
+      {
+        "id": "reactflow__edge-3f22f668-0e02-4fde-a2bb-c339586ceb4cvae-9eb72af0-dd9e-4ec5-ad87-d65e3c01f48bvae",
+        "type": "default",
+        "source": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "target": "9eb72af0-dd9e-4ec5-ad87-d65e3c01f48b",
+        "sourceHandle": "vae",
+        "targetHandle": "vae"
+      },
+      {
+        "id": "reactflow__edge-3f22f668-0e02-4fde-a2bb-c339586ceb4ct5_encoder-3b4f7f27-cfc0-4373-a009-99c5290d0cd6t5_encoder",
+        "type": "default",
+        "source": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "target": "3b4f7f27-cfc0-4373-a009-99c5290d0cd6",
+        "sourceHandle": "t5_encoder",
+        "targetHandle": "t5_encoder"
+      },
+      {
+        "id": "reactflow__edge-3f22f668-0e02-4fde-a2bb-c339586ceb4ct5_encoder-e17d34e7-6ed1-493c-9a85-4fcd291cb084t5_encoder",
+        "type": "default",
+        "source": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "target": "e17d34e7-6ed1-493c-9a85-4fcd291cb084",
+        "sourceHandle": "t5_encoder",
+        "targetHandle": "t5_encoder"
+      },
+      {
+        "id": "reactflow__edge-3f22f668-0e02-4fde-a2bb-c339586ceb4cclip_g-3b4f7f27-cfc0-4373-a009-99c5290d0cd6clip_g",
+        "type": "default",
+        "source": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "target": "3b4f7f27-cfc0-4373-a009-99c5290d0cd6",
+        "sourceHandle": "clip_g",
+        "targetHandle": "clip_g"
+      },
+      {
+        "id": "reactflow__edge-3f22f668-0e02-4fde-a2bb-c339586ceb4cclip_g-e17d34e7-6ed1-493c-9a85-4fcd291cb084clip_g",
+        "type": "default",
+        "source": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "target": "e17d34e7-6ed1-493c-9a85-4fcd291cb084",
+        "sourceHandle": "clip_g",
+        "targetHandle": "clip_g"
+      },
+      {
+        "id": "reactflow__edge-3f22f668-0e02-4fde-a2bb-c339586ceb4cclip_l-3b4f7f27-cfc0-4373-a009-99c5290d0cd6clip_l",
+        "type": "default",
+        "source": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "target": "3b4f7f27-cfc0-4373-a009-99c5290d0cd6",
+        "sourceHandle": "clip_l",
+        "targetHandle": "clip_l"
+      },
+      {
+        "id": "reactflow__edge-3f22f668-0e02-4fde-a2bb-c339586ceb4cclip_l-e17d34e7-6ed1-493c-9a85-4fcd291cb084clip_l",
+        "type": "default",
+        "source": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "target": "e17d34e7-6ed1-493c-9a85-4fcd291cb084",
+        "sourceHandle": "clip_l",
+        "targetHandle": "clip_l"
+      },
+      {
+        "id": "reactflow__edge-3f22f668-0e02-4fde-a2bb-c339586ceb4ctransformer-c7539f7b-7ac5-49b9-93eb-87ede611409ftransformer",
+        "type": "default",
+        "source": "3f22f668-0e02-4fde-a2bb-c339586ceb4c",
+        "target": "c7539f7b-7ac5-49b9-93eb-87ede611409f",
+        "sourceHandle": "transformer",
+        "targetHandle": "transformer"
+      },
+      {
+        "id": "reactflow__edge-f7e394ac-6394-4096-abcb-de0d346506b3value-c7539f7b-7ac5-49b9-93eb-87ede611409fseed",
+        "type": "default",
+        "source": "f7e394ac-6394-4096-abcb-de0d346506b3",
+        "target": "c7539f7b-7ac5-49b9-93eb-87ede611409f",
+        "sourceHandle": "value",
+        "targetHandle": "seed"
+      },
+      {
+        "id": "reactflow__edge-c7539f7b-7ac5-49b9-93eb-87ede611409flatents-9eb72af0-dd9e-4ec5-ad87-d65e3c01f48blatents",
+        "type": "default",
+        "source": "c7539f7b-7ac5-49b9-93eb-87ede611409f",
+        "target": "9eb72af0-dd9e-4ec5-ad87-d65e3c01f48b",
+        "sourceHandle": "latents",
+        "targetHandle": "latents"
+      },
+      {
+        "id": "reactflow__edge-e17d34e7-6ed1-493c-9a85-4fcd291cb084conditioning-c7539f7b-7ac5-49b9-93eb-87ede611409fpositive_conditioning",
+        "type": "default",
+        "source": "e17d34e7-6ed1-493c-9a85-4fcd291cb084",
+        "target": "c7539f7b-7ac5-49b9-93eb-87ede611409f",
+        "sourceHandle": "conditioning",
+        "targetHandle": "positive_conditioning"
+      },
+      {
+        "id": "reactflow__edge-3b4f7f27-cfc0-4373-a009-99c5290d0cd6conditioning-c7539f7b-7ac5-49b9-93eb-87ede611409fnegative_conditioning",
+        "type": "default",
+        "source": "3b4f7f27-cfc0-4373-a009-99c5290d0cd6",
+        "target": "c7539f7b-7ac5-49b9-93eb-87ede611409f",
+        "sourceHandle": "conditioning",
+        "targetHandle": "negative_conditioning"
+      }
+    ]
+  }

invokeai/app/util/step_callback.py

@@ -34,6 +34,25 @@ SD1_5_LATENT_RGB_FACTORS = [
     [-0.1307, -0.1874, -0.7445],  # L4
 ]
 
+SD3_5_LATENT_RGB_FACTORS = [
+    [-0.05240681, 0.03251581, 0.0749016],
+    [-0.0580572, 0.00759826, 0.05729818],
+    [0.16144888, 0.01270368, -0.03768577],
+    [0.14418615, 0.08460266, 0.15941818],
+    [0.04894035, 0.0056485, -0.06686988],
+    [0.05187166, 0.19222395, 0.06261094],
+    [0.1539433, 0.04818359, 0.07103094],
+    [-0.08601796, 0.09013458, 0.10893912],
+    [-0.12398469, -0.06766567, 0.0033688],
+    [-0.0439737, 0.07825329, 0.02258823],
+    [0.03101129, 0.06382551, 0.07753657],
+    [-0.01315361, 0.08554491, -0.08772475],
+    [0.06464487, 0.05914605, 0.13262741],
+    [-0.07863674, -0.02261737, -0.12761454],
+    [-0.09923835, -0.08010759, -0.06264447],
+    [-0.03392309, -0.0804029, -0.06078822],
+]
+
 FLUX_LATENT_RGB_FACTORS = [
     [-0.0412, 0.0149, 0.0521],
     [0.0056, 0.0291, 0.0768],
@@ -110,6 +129,9 @@ def stable_diffusion_step_callback(
         sdxl_latent_rgb_factors = torch.tensor(SDXL_LATENT_RGB_FACTORS, dtype=sample.dtype, device=sample.device)
         sdxl_smooth_matrix = torch.tensor(SDXL_SMOOTH_MATRIX, dtype=sample.dtype, device=sample.device)
         image = sample_to_lowres_estimated_image(sample, sdxl_latent_rgb_factors, sdxl_smooth_matrix)
+    elif base_model == BaseModelType.StableDiffusion3:
+        sd3_latent_rgb_factors = torch.tensor(SD3_5_LATENT_RGB_FACTORS, dtype=sample.dtype, device=sample.device)
+        image = sample_to_lowres_estimated_image(sample, sd3_latent_rgb_factors)
     else:
         v1_5_latent_rgb_factors = torch.tensor(SD1_5_LATENT_RGB_FACTORS, dtype=sample.dtype, device=sample.device)
         image = sample_to_lowres_estimated_image(sample, v1_5_latent_rgb_factors)

invokeai/backend/lora/conversions/flux_diffusers_lora_conversion_utils.py

@@ -45,8 +45,9 @@ def lora_model_from_flux_diffusers_state_dict(state_dict: Dict[str, torch.Tensor
     # Constants for FLUX.1
     num_double_layers = 19
     num_single_layers = 38
-    # inner_dim = 3072
-    # mlp_ratio = 4.0
+    hidden_size = 3072
+    mlp_ratio = 4.0
+    mlp_hidden_dim = int(hidden_size * mlp_ratio)
 
     layers: dict[str, AnyLoRALayer] = {}
 
@@ -62,30 +63,43 @@ def lora_model_from_flux_diffusers_state_dict(state_dict: Dict[str, torch.Tensor
             layers[dst_key] = LoRALayer.from_state_dict_values(values=value)
             assert len(src_layer_dict) == 0
 
-    def add_qkv_lora_layer_if_present(src_keys: list[str], dst_qkv_key: str) -> None:
+    def add_qkv_lora_layer_if_present(
+        src_keys: list[str],
+        src_weight_shapes: list[tuple[int, int]],
+        dst_qkv_key: str,
+        allow_missing_keys: bool = False,
+    ) -> None:
         """Handle the Q, K, V matrices for a transformer block. We need special handling because the diffusers format
         stores them in separate matrices, whereas the BFL format used internally by InvokeAI concatenates them.
         """
-        # We expect that either all src keys are present or none of them are. Verify this.
-        keys_present = [key in grouped_state_dict for key in src_keys]
-        assert all(keys_present) or not any(keys_present)
-
         # If none of the keys are present, return early.
+        keys_present = [key in grouped_state_dict for key in src_keys]
         if not any(keys_present):
             return
 
-        src_layer_dicts = [grouped_state_dict.pop(key) for key in src_keys]
         sub_layers: list[LoRALayer] = []
-        for src_layer_dict in src_layer_dicts:
-            values = {
-                "lora_down.weight": src_layer_dict.pop("lora_A.weight"),
-                "lora_up.weight": src_layer_dict.pop("lora_B.weight"),
-            }
-            if alpha is not None:
-                values["alpha"] = torch.tensor(alpha)
-            sub_layers.append(LoRALayer.from_state_dict_values(values=values))
-            assert len(src_layer_dict) == 0
-        layers[dst_qkv_key] = ConcatenatedLoRALayer(lora_layers=sub_layers, concat_axis=0)
+        for src_key, src_weight_shape in zip(src_keys, src_weight_shapes, strict=True):
+            src_layer_dict = grouped_state_dict.pop(src_key, None)
+            if src_layer_dict is not None:
+                values = {
+                    "lora_down.weight": src_layer_dict.pop("lora_A.weight"),
+                    "lora_up.weight": src_layer_dict.pop("lora_B.weight"),
+                }
+                if alpha is not None:
+                    values["alpha"] = torch.tensor(alpha)
+                assert values["lora_down.weight"].shape[1] == src_weight_shape[1]
+                assert values["lora_up.weight"].shape[0] == src_weight_shape[0]
+                sub_layers.append(LoRALayer.from_state_dict_values(values=values))
+                assert len(src_layer_dict) == 0
+            else:
+                if not allow_missing_keys:
+                    raise ValueError(f"Missing LoRA layer: '{src_key}'.")
+                values = {
+                    "lora_up.weight": torch.zeros((src_weight_shape[0], 1)),
+                    "lora_down.weight": torch.zeros((1, src_weight_shape[1])),
+                }
+                sub_layers.append(LoRALayer.from_state_dict_values(values=values))
+        layers[dst_qkv_key] = ConcatenatedLoRALayer(lora_layers=sub_layers)
 
     # time_text_embed.timestep_embedder -> time_in.
     add_lora_layer_if_present("time_text_embed.timestep_embedder.linear_1", "time_in.in_layer")
@@ -118,6 +132,7 @@ def lora_model_from_flux_diffusers_state_dict(state_dict: Dict[str, torch.Tensor
                 f"transformer_blocks.{i}.attn.to_k",
                 f"transformer_blocks.{i}.attn.to_v",
             ],
+            [(hidden_size, hidden_size), (hidden_size, hidden_size), (hidden_size, hidden_size)],
             f"double_blocks.{i}.img_attn.qkv",
         )
         add_qkv_lora_layer_if_present(
@@ -126,6 +141,7 @@ def lora_model_from_flux_diffusers_state_dict(state_dict: Dict[str, torch.Tensor
                 f"transformer_blocks.{i}.attn.add_k_proj",
                 f"transformer_blocks.{i}.attn.add_v_proj",
             ],
+            [(hidden_size, hidden_size), (hidden_size, hidden_size), (hidden_size, hidden_size)],
             f"double_blocks.{i}.txt_attn.qkv",
         )
 
@@ -175,7 +191,14 @@ def lora_model_from_flux_diffusers_state_dict(state_dict: Dict[str, torch.Tensor
                 f"single_transformer_blocks.{i}.attn.to_v",
                 f"single_transformer_blocks.{i}.proj_mlp",
             ],
+            [
+                (hidden_size, hidden_size),
+                (hidden_size, hidden_size),
+                (hidden_size, hidden_size),
+                (mlp_hidden_dim, hidden_size),
+            ],
             f"single_blocks.{i}.linear1",
+            allow_missing_keys=True,
         )
 
         # Output projections.

invokeai/backend/model_manager/config.py

@@ -53,8 +53,7 @@ class BaseModelType(str, Enum):
     Any = "any"
     StableDiffusion1 = "sd-1"
     StableDiffusion2 = "sd-2"
-    # TODO(ryand): Should this just be StableDiffusion3?
-    StableDiffusion35 = "sd-3.5"
+    StableDiffusion3 = "sd-3"
     StableDiffusionXL = "sdxl"
     StableDiffusionXLRefiner = "sdxl-refiner"
     Flux = "flux"
@@ -85,8 +84,10 @@ class SubModelType(str, Enum):
     Transformer = "transformer"
     TextEncoder = "text_encoder"
     TextEncoder2 = "text_encoder_2"
+    TextEncoder3 = "text_encoder_3"
     Tokenizer = "tokenizer"
     Tokenizer2 = "tokenizer_2"
+    Tokenizer3 = "tokenizer_3"
     VAE = "vae"
     VAEDecoder = "vae_decoder"
     VAEEncoder = "vae_encoder"
@@ -94,6 +95,13 @@ class SubModelType(str, Enum):
     SafetyChecker = "safety_checker"
 
 
+class ClipVariantType(str, Enum):
+    """Variant type."""
+
+    L = "large"
+    G = "gigantic"
+
+
 class ModelVariantType(str, Enum):
     """Variant type."""
 
@@ -149,6 +157,17 @@ class ModelSourceType(str, Enum):
 DEFAULTS_PRECISION = Literal["fp16", "fp32"]
 
 
+AnyVariant: TypeAlias = Union[ModelVariantType, ClipVariantType, None]
+
+
+class SubmodelDefinition(BaseModel):
+    path_or_prefix: str
+    model_type: ModelType
+    variant: AnyVariant = None
+
+    model_config = ConfigDict(protected_namespaces=())
+
+
 class MainModelDefaultSettings(BaseModel):
     vae: str | None = Field(default=None, description="Default VAE for this model (model key)")
     vae_precision: DEFAULTS_PRECISION | None = Field(default=None, description="Default VAE precision for this model")
@@ -195,6 +214,9 @@ class ModelConfigBase(BaseModel):
         schema["required"].extend(["key", "type", "format"])
 
     model_config = ConfigDict(validate_assignment=True, json_schema_extra=json_schema_extra)
+    submodels: Optional[Dict[SubModelType, SubmodelDefinition]] = Field(
+        description="Loadable submodels in this model", default=None
+    )
 
 
 class CheckpointConfigBase(ModelConfigBase):
@@ -337,7 +359,7 @@ class MainConfigBase(ModelConfigBase):
     default_settings: Optional[MainModelDefaultSettings] = Field(
         description="Default settings for this model", default=None
     )
-    variant: ModelVariantType = ModelVariantType.Normal
+    variant: AnyVariant = ModelVariantType.Normal
 
 
 class MainCheckpointConfig(CheckpointConfigBase, MainConfigBase):
@@ -421,12 +443,33 @@ class CLIPEmbedDiffusersConfig(DiffusersConfigBase):
 
     type: Literal[ModelType.CLIPEmbed] = ModelType.CLIPEmbed
     format: Literal[ModelFormat.Diffusers] = ModelFormat.Diffusers
+    variant: ClipVariantType = ClipVariantType.L
 
     @staticmethod
     def get_tag() -> Tag:
         return Tag(f"{ModelType.CLIPEmbed.value}.{ModelFormat.Diffusers.value}")
 
 
+class CLIPGEmbedDiffusersConfig(CLIPEmbedDiffusersConfig):
+    """Model config for CLIP-G Embeddings."""
+
+    variant: ClipVariantType = ClipVariantType.G
+
+    @staticmethod
+    def get_tag() -> Tag:
+        return Tag(f"{ModelType.CLIPEmbed.value}.{ModelFormat.Diffusers.value}.{ClipVariantType.G}")
+
+
+class CLIPLEmbedDiffusersConfig(CLIPEmbedDiffusersConfig):
+    """Model config for CLIP-L Embeddings."""
+
+    variant: ClipVariantType = ClipVariantType.L
+
+    @staticmethod
+    def get_tag() -> Tag:
+        return Tag(f"{ModelType.CLIPEmbed.value}.{ModelFormat.Diffusers.value}.{ClipVariantType.L}")
+
+
 class CLIPVisionDiffusersConfig(DiffusersConfigBase):
     """Model config for CLIPVision."""
 
@@ -503,6 +546,8 @@ AnyModelConfig = Annotated[
         Annotated[SpandrelImageToImageConfig, SpandrelImageToImageConfig.get_tag()],
         Annotated[CLIPVisionDiffusersConfig, CLIPVisionDiffusersConfig.get_tag()],
         Annotated[CLIPEmbedDiffusersConfig, CLIPEmbedDiffusersConfig.get_tag()],
+        Annotated[CLIPLEmbedDiffusersConfig, CLIPLEmbedDiffusersConfig.get_tag()],
+        Annotated[CLIPGEmbedDiffusersConfig, CLIPGEmbedDiffusersConfig.get_tag()],
     ],
     Discriminator(get_model_discriminator_value),
 ]

invokeai/backend/model_manager/load/load_default.py

@@ -35,6 +35,7 @@ class ModelLoader(ModelLoaderBase):
         self._logger = logger
         self._ram_cache = ram_cache
         self._torch_dtype = TorchDevice.choose_torch_dtype()
+        self._torch_device = TorchDevice.choose_torch_device()
 
     def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
         """

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

@@ -84,7 +84,15 @@ class FluxVAELoader(ModelLoader):
             model = AutoEncoder(ae_params[config.config_path])
             sd = load_file(model_path)
             model.load_state_dict(sd, assign=True)
-            model.to(dtype=self._torch_dtype)
+            # VAE is broken in float16, which mps defaults to
+            if self._torch_dtype == torch.float16:
+                try:
+                    vae_dtype = torch.tensor([1.0], dtype=torch.bfloat16, device=self._torch_device).dtype
+                except TypeError:
+                    vae_dtype = torch.float32
+            else:
+                vae_dtype = self._torch_dtype
+            model.to(vae_dtype)
 
         return model
 
@@ -128,9 +136,9 @@ class BnbQuantizedLlmInt8bCheckpointModel(ModelLoader):
                 "The bnb modules are not available. Please install bitsandbytes if available on your platform."
             )
         match submodel_type:
-            case SubModelType.Tokenizer2:
+            case SubModelType.Tokenizer2 | SubModelType.Tokenizer3:
                 return T5Tokenizer.from_pretrained(Path(config.path) / "tokenizer_2", max_length=512)
-            case SubModelType.TextEncoder2:
+            case SubModelType.TextEncoder2 | SubModelType.TextEncoder3:
                 te2_model_path = Path(config.path) / "text_encoder_2"
                 model_config = AutoConfig.from_pretrained(te2_model_path)
                 with accelerate.init_empty_weights():
@@ -172,9 +180,9 @@ class T5EncoderCheckpointModel(ModelLoader):
             raise ValueError("Only T5EncoderConfig models are currently supported here.")
 
         match submodel_type:
-            case SubModelType.Tokenizer2:
+            case SubModelType.Tokenizer2 | SubModelType.Tokenizer3:
                 return T5Tokenizer.from_pretrained(Path(config.path) / "tokenizer_2", max_length=512)
-            case SubModelType.TextEncoder2:
+            case SubModelType.TextEncoder2 | SubModelType.TextEncoder3:
                 return T5EncoderModel.from_pretrained(Path(config.path) / "text_encoder_2", torch_dtype="auto")
 
         raise ValueError(

invokeai/backend/model_manager/load/model_loaders/sd3.py

@@ -1,55 +0,0 @@
-from pathlib import Path
-from typing import Optional
-
-from invokeai.backend.model_manager.config import (
-    AnyModel,
-    AnyModelConfig,
-    BaseModelType,
-    CheckpointConfigBase,
-    MainCheckpointConfig,
-    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.StableDiffusion35, type=ModelType.Main, format=ModelFormat.Checkpoint)
-class FluxCheckpointModel(ModelLoader):
-    """Class to load main models."""
-
-    def _load_model(
-        self,
-        config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-    ) -> AnyModel:
-        if not isinstance(config, CheckpointConfigBase):
-            raise ValueError("Only CheckpointConfigBase models are currently supported here.")
-
-        match submodel_type:
-            case SubModelType.Transformer:
-                return self._load_from_singlefile(config)
-
-        raise ValueError(
-            f"Only Transformer submodels are currently supported. Received: {submodel_type.value if submodel_type else 'None'}"
-        )
-
-    def _load_from_singlefile(
-        self,
-        config: AnyModelConfig,
-    ) -> AnyModel:
-        assert isinstance(config, MainCheckpointConfig)
-        model_path = Path(config.path)
-
-        # model = Flux(params[config.config_path])
-        # sd = load_file(model_path)
-        # if "model.diffusion_model.double_blocks.0.img_attn.norm.key_norm.scale" in sd:
-        #     sd = convert_bundle_to_flux_transformer_checkpoint(sd)
-        # new_sd_size = sum([ten.nelement() * torch.bfloat16.itemsize for ten in sd.values()])
-        # self._ram_cache.make_room(new_sd_size)
-        # for k in sd.keys():
-        #     # We need to cast to bfloat16 due to it being the only currently supported dtype for inference
-        #     sd[k] = sd[k].to(torch.bfloat16)
-        # model.load_state_dict(sd, assign=True)
-        return model

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

@@ -42,6 +42,7 @@ VARIANT_TO_IN_CHANNEL_MAP = {
 @ModelLoaderRegistry.register(
     base=BaseModelType.StableDiffusionXLRefiner, type=ModelType.Main, format=ModelFormat.Diffusers
 )
+@ModelLoaderRegistry.register(base=BaseModelType.StableDiffusion3, type=ModelType.Main, format=ModelFormat.Diffusers)
 @ModelLoaderRegistry.register(base=BaseModelType.StableDiffusion1, type=ModelType.Main, format=ModelFormat.Checkpoint)
 @ModelLoaderRegistry.register(base=BaseModelType.StableDiffusion2, type=ModelType.Main, format=ModelFormat.Checkpoint)
 @ModelLoaderRegistry.register(base=BaseModelType.StableDiffusionXL, type=ModelType.Main, format=ModelFormat.Checkpoint)
@@ -51,13 +52,6 @@ VARIANT_TO_IN_CHANNEL_MAP = {
 class StableDiffusionDiffusersModel(GenericDiffusersLoader):
     """Class to load main models."""
 
-    model_base_to_model_type = {
-        BaseModelType.StableDiffusion1: "FrozenCLIPEmbedder",
-        BaseModelType.StableDiffusion2: "FrozenOpenCLIPEmbedder",
-        BaseModelType.StableDiffusionXL: "SDXL",
-        BaseModelType.StableDiffusionXLRefiner: "SDXL-Refiner",
-    }
-
     def _load_model(
         self,
         config: AnyModelConfig,
@@ -117,8 +111,6 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
             load_class = load_classes[config.base][config.variant]
         except KeyError as e:
             raise Exception(f"No diffusers pipeline known for base={config.base}, variant={config.variant}") from e
-        prediction_type = config.prediction_type.value
-        upcast_attention = config.upcast_attention
 
         # Without SilenceWarnings we get log messages like this:
         # site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
@@ -129,13 +121,7 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
         # ['text_model.embeddings.position_ids']
 
         with SilenceWarnings():
-            pipeline = load_class.from_single_file(
-                config.path,
-                torch_dtype=self._torch_dtype,
-                prediction_type=prediction_type,
-                upcast_attention=upcast_attention,
-                load_safety_checker=False,
-            )
+            pipeline = load_class.from_single_file(config.path, torch_dtype=self._torch_dtype)
 
         if not submodel_type:
             return pipeline

invokeai/backend/model_manager/metadata/fetch/huggingface.py

@@ -20,7 +20,7 @@ from typing import Optional
 
 import requests
 from huggingface_hub import HfApi, configure_http_backend, hf_hub_url
-from huggingface_hub.utils._errors import RepositoryNotFoundError, RevisionNotFoundError
+from huggingface_hub.errors import RepositoryNotFoundError, RevisionNotFoundError
 from pydantic.networks import AnyHttpUrl
 from requests.sessions import Session
 

invokeai/backend/model_manager/probe.py

@@ -1,7 +1,7 @@
 import json
 import re
 from pathlib import Path
-from typing import Any, Dict, Literal, Optional, Union
+from typing import Any, Callable, Dict, Literal, Optional, Union
 
 import safetensors.torch
 import spandrel
@@ -22,6 +22,7 @@ from invokeai.backend.lora.conversions.flux_kohya_lora_conversion_utils import i
 from invokeai.backend.model_hash.model_hash import HASHING_ALGORITHMS, ModelHash
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
+    AnyVariant,
     BaseModelType,
     ControlAdapterDefaultSettings,
     InvalidModelConfigException,
@@ -33,11 +34,17 @@ from invokeai.backend.model_manager.config import (
     ModelType,
     ModelVariantType,
     SchedulerPredictionType,
+    SubmodelDefinition,
+    SubModelType,
+)
+from invokeai.backend.model_manager.load.model_loaders.generic_diffusers import ConfigLoader
+from invokeai.backend.model_manager.util.model_util import (
+    get_clip_variant_type,
+    lora_token_vector_length,
+    read_checkpoint_meta,
 )
-from invokeai.backend.model_manager.util.model_util import lora_token_vector_length, read_checkpoint_meta
 from invokeai.backend.quantization.gguf.ggml_tensor import GGMLTensor
 from invokeai.backend.quantization.gguf.loaders import gguf_sd_loader
-from invokeai.backend.sd3.sd3_state_dict_utils import is_sd3_checkpoint
 from invokeai.backend.spandrel_image_to_image_model import SpandrelImageToImageModel
 from invokeai.backend.util.silence_warnings import SilenceWarnings
 
@@ -113,6 +120,7 @@ class ModelProbe(object):
         "StableDiffusionXLPipeline": ModelType.Main,
         "StableDiffusionXLImg2ImgPipeline": ModelType.Main,
         "StableDiffusionXLInpaintPipeline": ModelType.Main,
+        "StableDiffusion3Pipeline": ModelType.Main,
         "LatentConsistencyModelPipeline": ModelType.Main,
         "AutoencoderKL": ModelType.VAE,
         "AutoencoderTiny": ModelType.VAE,
@@ -121,11 +129,14 @@ class ModelProbe(object):
         "T2IAdapter": ModelType.T2IAdapter,
         "CLIPModel": ModelType.CLIPEmbed,
         "CLIPTextModel": ModelType.CLIPEmbed,
-        "CLIPTextModelWithProjection": ModelType.CLIPEmbed,
         "T5EncoderModel": ModelType.T5Encoder,
         "FluxControlNetModel": ModelType.ControlNet,
+        "SD3Transformer2DModel": ModelType.Main,
+        "CLIPTextModelWithProjection": ModelType.CLIPEmbed,
     }
 
+    TYPE2VARIANT: Dict[ModelType, Callable[[str], Optional[AnyVariant]]] = {ModelType.CLIPEmbed: get_clip_variant_type}
+
     @classmethod
     def register_probe(
         cls, format: Literal["diffusers", "checkpoint", "onnx"], model_type: ModelType, probe_class: type[ProbeBase]
@@ -172,7 +183,10 @@ class ModelProbe(object):
         fields["path"] = model_path.as_posix()
         fields["type"] = fields.get("type") or model_type
         fields["base"] = fields.get("base") or probe.get_base_type()
-        fields["variant"] = fields.get("variant") or probe.get_variant_type()
+        variant_func = cls.TYPE2VARIANT.get(fields["type"], None)
+        fields["variant"] = (
+            fields.get("variant") or (variant_func and variant_func(model_path.as_posix())) or probe.get_variant_type()
+        )
         fields["prediction_type"] = fields.get("prediction_type") or probe.get_scheduler_prediction_type()
         fields["image_encoder_model_id"] = fields.get("image_encoder_model_id") or probe.get_image_encoder_model_id()
         fields["name"] = fields.get("name") or cls.get_model_name(model_path)
@@ -219,6 +233,10 @@ class ModelProbe(object):
                 and fields["prediction_type"] == SchedulerPredictionType.VPrediction
             )
 
+        get_submodels = getattr(probe, "get_submodels", None)
+        if fields["base"] == BaseModelType.StableDiffusion3 and callable(get_submodels):
+            fields["submodels"] = get_submodels()
+
         model_info = ModelConfigFactory.make_config(fields)  # , key=fields.get("key", None))
         return model_info
 
@@ -243,11 +261,6 @@ class ModelProbe(object):
         for key in [str(k) for k in ckpt.keys()]:
             if key.startswith(
                 (
-                    # The following prefixes appear when multiple models have been bundled together in a single file (I
-                    # believe the format originated in ComfyUI).
-                    # first_stage_model = VAE
-                    # cond_stage_model = Text Encoder
-                    # model.diffusion_model = UNet / Transformer
                     "cond_stage_model.",
                     "first_stage_model.",
                     "model.diffusion_model.",
@@ -404,9 +417,6 @@ class ModelProbe(object):
                     #   is used rather than attempting to support flux with separate model types and format
                     #   If changed in the future, please fix me
                     config_file = "flux-schnell"
-            elif base_type == BaseModelType.StableDiffusion35:
-                # TODO(ryand): Think about what to do here.
-                config_file = "sd3.5-large"
             else:
                 config_file = LEGACY_CONFIGS[base_type][variant_type]
                 if isinstance(config_file, dict):  # need another tier for sd-2.x models
@@ -472,8 +482,9 @@ 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",
@@ -526,7 +537,7 @@ class CheckpointProbeBase(ProbeBase):
     def get_variant_type(self) -> ModelVariantType:
         model_type = ModelProbe.get_model_type_from_checkpoint(self.model_path, self.checkpoint)
         base_type = self.get_base_type()
-        if model_type != ModelType.Main or base_type in (BaseModelType.Flux, BaseModelType.StableDiffusion35):
+        if model_type != ModelType.Main or base_type == BaseModelType.Flux:
             return ModelVariantType.Normal
         state_dict = self.checkpoint.get("state_dict") or self.checkpoint
         in_channels = state_dict["model.diffusion_model.input_blocks.0.0.weight"].shape[1]
@@ -551,10 +562,6 @@ class PipelineCheckpointProbe(CheckpointProbeBase):
             or "model.diffusion_model.double_blocks.0.img_attn.norm.key_norm.scale" in state_dict
         ):
             return BaseModelType.Flux
-
-        if is_sd3_checkpoint(state_dict):
-            return BaseModelType.StableDiffusion35
-
         key_name = "model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight"
         if key_name in state_dict and state_dict[key_name].shape[-1] == 768:
             return BaseModelType.StableDiffusion1
@@ -760,18 +767,33 @@ class FolderProbeBase(ProbeBase):
 
 class PipelineFolderProbe(FolderProbeBase):
     def get_base_type(self) -> BaseModelType:
-        with open(self.model_path / "unet" / "config.json", "r") as file:
-            unet_conf = json.load(file)
-        if unet_conf["cross_attention_dim"] == 768:
-            return BaseModelType.StableDiffusion1
-        elif unet_conf["cross_attention_dim"] == 1024:
-            return BaseModelType.StableDiffusion2
-        elif unet_conf["cross_attention_dim"] == 1280:
-            return BaseModelType.StableDiffusionXLRefiner
-        elif unet_conf["cross_attention_dim"] == 2048:
-            return BaseModelType.StableDiffusionXL
-        else:
-            raise InvalidModelConfigException(f"Unknown base model for {self.model_path}")
+        # Handle pipelines with a UNet (i.e SD 1.x, SD2, SDXL).
+        config_path = self.model_path / "unet" / "config.json"
+        if config_path.exists():
+            with open(config_path) as file:
+                unet_conf = json.load(file)
+            if unet_conf["cross_attention_dim"] == 768:
+                return BaseModelType.StableDiffusion1
+            elif unet_conf["cross_attention_dim"] == 1024:
+                return BaseModelType.StableDiffusion2
+            elif unet_conf["cross_attention_dim"] == 1280:
+                return BaseModelType.StableDiffusionXLRefiner
+            elif unet_conf["cross_attention_dim"] == 2048:
+                return BaseModelType.StableDiffusionXL
+            else:
+                raise InvalidModelConfigException(f"Unknown base model for {self.model_path}")
+
+        # Handle pipelines with a transformer (i.e. SD3).
+        config_path = self.model_path / "transformer" / "config.json"
+        if config_path.exists():
+            with open(config_path) as file:
+                transformer_conf = json.load(file)
+            if transformer_conf["_class_name"] == "SD3Transformer2DModel":
+                return BaseModelType.StableDiffusion3
+            else:
+                raise InvalidModelConfigException(f"Unknown base model for {self.model_path}")
+
+        raise InvalidModelConfigException(f"Unknown base model for {self.model_path}")
 
     def get_scheduler_prediction_type(self) -> SchedulerPredictionType:
         with open(self.model_path / "scheduler" / "scheduler_config.json", "r") as file:
@@ -783,6 +805,23 @@ class PipelineFolderProbe(FolderProbeBase):
         else:
             raise InvalidModelConfigException("Unknown scheduler prediction type: {scheduler_conf['prediction_type']}")
 
+    def get_submodels(self) -> Dict[SubModelType, SubmodelDefinition]:
+        config = ConfigLoader.load_config(self.model_path, config_name="model_index.json")
+        submodels: Dict[SubModelType, SubmodelDefinition] = {}
+        for key, value in config.items():
+            if key.startswith("_") or not (isinstance(value, list) and len(value) == 2):
+                continue
+            model_loader = str(value[1])
+            if model_type := ModelProbe.CLASS2TYPE.get(model_loader):
+                variant_func = ModelProbe.TYPE2VARIANT.get(model_type, None)
+                submodels[SubModelType(key)] = SubmodelDefinition(
+                    path_or_prefix=(self.model_path / key).resolve().as_posix(),
+                    model_type=model_type,
+                    variant=variant_func and variant_func((self.model_path / key).as_posix()),
+                )
+
+        return submodels
+
     def get_variant_type(self) -> ModelVariantType:
         # This only works for pipelines! Any kind of
         # exception results in our returning the

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):
@@ -137,6 +140,22 @@ flux_dev = StarterModel(
     type=ModelType.Main,
     dependencies=[t5_base_encoder, flux_vae, clip_l_encoder],
 )
+sd35_medium = StarterModel(
+    name="SD3.5 Medium",
+    base=BaseModelType.StableDiffusion3,
+    source="stabilityai/stable-diffusion-3.5-medium",
+    description="Medium SD3.5 Model: ~15GB",
+    type=ModelType.Main,
+    dependencies=[],
+)
+sd35_large = StarterModel(
+    name="SD3.5 Large",
+    base=BaseModelType.StableDiffusion3,
+    source="stabilityai/stable-diffusion-3.5-large",
+    description="Large SD3.5 Model: ~19G",
+    type=ModelType.Main,
+    dependencies=[],
+)
 cyberrealistic_sd1 = StarterModel(
     name="CyberRealistic v4.1",
     base=BaseModelType.StableDiffusion1,
@@ -243,44 +262,49 @@ 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="XLabs FLUX IP-Adapter",
+    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="FLUX IP-Adapter",
+    source="https://huggingface.co/XLabs-AI/flux-ip-adapter/resolve/main/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
@@ -299,157 +323,162 @@ 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(
@@ -462,60 +491,52 @@ 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
@@ -565,6 +586,8 @@ STARTER_MODELS: list[StarterModel] = [
     flux_dev_quantized,
     flux_schnell,
     flux_dev,
+    sd35_medium,
+    sd35_large,
     cyberrealistic_sd1,
     rev_animated_sd1,
     dreamshaper_8_sd1,
@@ -600,22 +623,18 @@ 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,
@@ -646,7 +665,6 @@ sd1_bundle: list[StarterModel] = [
     softedge_sd1,
     shuffle_sd1,
     tile_sd1,
-    ip2p_sd1,
     swinir,
 ]
 
@@ -657,8 +675,6 @@ sdxl_bundle: list[StarterModel] = [
     canny_sdxl,
     depth_sdxl,
     softedge_sdxl,
-    depth_zoe_16_sdxl,
-    depth_zoe_32_sdxl,
     openpose_sdxl,
     scribble_sdxl,
     tile_sdxl,

invokeai/backend/model_manager/util/model_util.py

@@ -8,6 +8,7 @@ import safetensors
 import torch
 from picklescan.scanner import scan_file_path
 
+from invokeai.backend.model_manager.config import ClipVariantType
 from invokeai.backend.quantization.gguf.loaders import gguf_sd_loader
 
 
@@ -165,3 +166,25 @@ def convert_bundle_to_flux_transformer_checkpoint(
         del transformer_state_dict[k]
 
     return original_state_dict
+
+
+def get_clip_variant_type(location: str) -> Optional[ClipVariantType]:
+    try:
+        path = Path(location)
+        config_path = path / "config.json"
+        if not config_path.exists():
+            config_path = path / "text_encoder" / "config.json"
+        if not config_path.exists():
+            return ClipVariantType.L
+        with open(config_path) as file:
+            clip_conf = json.load(file)
+            hidden_size = clip_conf.get("hidden_size", -1)
+            match hidden_size:
+                case 1280:
+                    return ClipVariantType.G
+                case 768:
+                    return ClipVariantType.L
+                case _:
+                    return ClipVariantType.L
+    except Exception:
+        return ClipVariantType.L

invokeai/backend/model_manager/util/select_hf_files.py

@@ -85,6 +85,7 @@ def _filter_by_variant(files: List[Path], variant: ModelRepoVariant) -> Set[Path
     """Select the proper variant files from a list of HuggingFace repo_id paths."""
     result: set[Path] = set()
     subfolder_weights: dict[Path, list[SubfolderCandidate]] = {}
+    safetensors_detected = False
     for path in files:
         if path.suffix in [".onnx", ".pb", ".onnx_data"]:
             if variant == ModelRepoVariant.ONNX:
@@ -119,19 +120,27 @@ def _filter_by_variant(files: List[Path], variant: ModelRepoVariant) -> Set[Path
             # We prefer safetensors over other file formats and an exact variant match. We'll score each file based on
             # variant and format and select the best one.
 
+            if safetensors_detected and path.suffix == ".bin":
+                continue
+
             parent = path.parent
             score = 0
 
             if path.suffix == ".safetensors":
+                safetensors_detected = True
+                if parent in subfolder_weights:
+                    subfolder_weights[parent] = [sfc for sfc in subfolder_weights[parent] if sfc.path.suffix != ".bin"]
                 score += 1
 
             candidate_variant_label = path.suffixes[0] if len(path.suffixes) == 2 else None
 
             # Some special handling is needed here if there is not an exact match and if we cannot infer the variant
             # from the file name. In this case, we only give this file a point if the requested variant is FP32 or DEFAULT.
-            if candidate_variant_label == f".{variant}" or (
-                not candidate_variant_label and variant in [ModelRepoVariant.FP32, ModelRepoVariant.Default]
-            ):
+            if (
+                variant is not ModelRepoVariant.Default
+                and candidate_variant_label
+                and candidate_variant_label.startswith(f".{variant.value}")
+            ) or (not candidate_variant_label and variant in [ModelRepoVariant.FP32, ModelRepoVariant.Default]):
                 score += 1
 
             if parent not in subfolder_weights:
@@ -146,7 +155,7 @@ def _filter_by_variant(files: List[Path], variant: ModelRepoVariant) -> Set[Path
         # Check if at least one of the files has the explicit fp16 variant.
         at_least_one_fp16 = False
         for candidate in candidate_list:
-            if len(candidate.path.suffixes) == 2 and candidate.path.suffixes[0] == ".fp16":
+            if len(candidate.path.suffixes) == 2 and candidate.path.suffixes[0].startswith(".fp16"):
                 at_least_one_fp16 = True
                 break
 
@@ -162,7 +171,16 @@ def _filter_by_variant(files: List[Path], variant: ModelRepoVariant) -> Set[Path
         # candidate.
         highest_score_candidate = max(candidate_list, key=lambda candidate: candidate.score)
         if highest_score_candidate:
-            result.add(highest_score_candidate.path)
+            pattern = r"^(.*?)-\d+-of-\d+(\.\w+)$"
+            match = re.match(pattern, highest_score_candidate.path.as_posix())
+            if match:
+                for candidate in candidate_list:
+                    if candidate.path.as_posix().startswith(match.group(1)) and candidate.path.as_posix().endswith(
+                        match.group(2)
+                    ):
+                        result.add(candidate.path)
+            else:
+                result.add(highest_score_candidate.path)
 
     # If one of the architecture-related variants was specified and no files matched other than
     # config and text files then we return an empty list

invokeai/backend/sd3/extensions/inpaint_extension.py

@@ -0,0 +1,58 @@
+import torch
+
+
+class InpaintExtension:
+    """A class for managing inpainting with SD3."""
+
+    def __init__(self, init_latents: torch.Tensor, inpaint_mask: torch.Tensor, noise: torch.Tensor):
+        """Initialize InpaintExtension.
+
+        Args:
+            init_latents (torch.Tensor): The initial latents (i.e. un-noised at timestep 0).
+            inpaint_mask (torch.Tensor): A mask specifying which elements to inpaint. Range [0, 1]. Values of 1 will be
+                re-generated. Values of 0 will remain unchanged. Values between 0 and 1 can be used to blend the
+                inpainted region with the background.
+            noise (torch.Tensor): The noise tensor used to noise the init_latents.
+        """
+        assert init_latents.dim() == inpaint_mask.dim() == noise.dim() == 4
+        assert init_latents.shape[-2:] == inpaint_mask.shape[-2:] == noise.shape[-2:]
+
+        self._init_latents = init_latents
+        self._inpaint_mask = inpaint_mask
+        self._noise = noise
+
+    def _apply_mask_gradient_adjustment(self, t_prev: float) -> torch.Tensor:
+        """Applies inpaint mask gradient adjustment and returns the inpaint mask to be used at the current timestep."""
+        # As we progress through the denoising process, we promote gradient regions of the mask to have a full weight of
+        # 1.0. This helps to produce more coherent seams around the inpainted region. We experimented with a (small)
+        # number of promotion strategies (e.g. gradual promotion based on timestep), but found that a simple cutoff
+        # threshold worked well.
+        # We use a small epsilon to avoid any potential issues with floating point precision.
+        eps = 1e-4
+        mask_gradient_t_cutoff = 0.5
+        if t_prev > mask_gradient_t_cutoff:
+            # Early in the denoising process, use the inpaint mask as-is.
+            return self._inpaint_mask
+        else:
+            # After the cut-off, promote all non-zero mask values to 1.0.
+            mask = self._inpaint_mask.where(self._inpaint_mask <= (0.0 + eps), 1.0)
+
+        return mask
+
+    def merge_intermediate_latents_with_init_latents(
+        self, intermediate_latents: torch.Tensor, t_prev: float
+    ) -> torch.Tensor:
+        """Merge the intermediate latents with the initial latents for the current timestep using the inpaint mask. I.e.
+        update the intermediate latents to keep the regions that are not being inpainted on the correct noise
+        trajectory.
+
+        This function should be called after each denoising step.
+        """
+
+        mask = self._apply_mask_gradient_adjustment(t_prev)
+
+        # Noise the init latents for the current timestep.
+        noised_init_latents = self._noise * t_prev + (1.0 - t_prev) * self._init_latents
+
+        # Merge the intermediate latents with the noised_init_latents using the inpaint_mask.
+        return intermediate_latents * mask + noised_init_latents * (1.0 - mask)

invokeai/backend/sd3/mmditx.py

@@ -1,891 +0,0 @@
-# This file was originally copied from:
-# https://github.com/Stability-AI/sd3.5/blob/19bf11c4e1e37324c5aa5a61f010d4127848a09c/mmditx.py
-
-
-### This file contains impls for MM-DiT, the core model component of SD3
-
-import math
-from typing import Dict, List, Optional
-
-import numpy as np
-import torch
-from einops import rearrange, repeat
-
-from invokeai.backend.sd3.other_impls import Mlp, attention
-
-
-class PatchEmbed(torch.nn.Module):
-    """2D Image to Patch Embedding"""
-
-    def __init__(
-        self,
-        img_size: Optional[int] = 224,
-        patch_size: int = 16,
-        in_chans: int = 3,
-        embed_dim: int = 768,
-        flatten: bool = True,
-        bias: bool = True,
-        strict_img_size: bool = True,
-        dynamic_img_pad: bool = False,
-        dtype: torch.dtype | None = None,
-        device: torch.device | None = None,
-    ):
-        super().__init__()
-        self.patch_size = (patch_size, patch_size)
-        if img_size is not None:
-            self.img_size = (img_size, img_size)
-            self.grid_size = tuple([s // p for s, p in zip(self.img_size, self.patch_size, strict=False)])
-            self.num_patches = self.grid_size[0] * self.grid_size[1]
-        else:
-            self.img_size = None
-            self.grid_size = None
-            self.num_patches = None
-
-        # flatten spatial dim and transpose to channels last, kept for bwd compat
-        self.flatten = flatten
-        self.strict_img_size = strict_img_size
-        self.dynamic_img_pad = dynamic_img_pad
-
-        self.proj = torch.nn.Conv2d(
-            in_chans,
-            embed_dim,
-            kernel_size=patch_size,
-            stride=patch_size,
-            bias=bias,
-            dtype=dtype,
-            device=device,
-        )
-
-    def forward(self, x: torch.Tensor) -> torch.Tensor:
-        x = self.proj(x)
-        if self.flatten:
-            x = x.flatten(2).transpose(1, 2)  # NCHW -> NLC
-        return x
-
-
-def modulate(x: torch.Tensor, shift: torch.Tensor | None, scale: torch.Tensor) -> torch.Tensor:
-    if shift is None:
-        shift = torch.zeros_like(scale)
-    return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)
-
-
-#################################################################################
-#                   Sine/Cosine Positional Embedding Functions                  #
-#################################################################################
-
-
-def get_2d_sincos_pos_embed(
-    embed_dim: int,
-    grid_size: int,
-    cls_token: bool = False,
-    extra_tokens: int = 0,
-    scaling_factor: Optional[float] = None,
-    offset: Optional[float] = None,
-):
-    """
-    grid_size: int of the grid height and width
-    return:
-    pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/ or w/o cls_token)
-    """
-    grid_h = np.arange(grid_size, dtype=np.float32)
-    grid_w = np.arange(grid_size, dtype=np.float32)
-    grid = np.meshgrid(grid_w, grid_h)  # here w goes first
-    grid = np.stack(grid, axis=0)
-    if scaling_factor is not None:
-        grid = grid / scaling_factor
-    if offset is not None:
-        grid = grid - offset
-    grid = grid.reshape([2, 1, grid_size, grid_size])
-    pos_embed = get_2d_sincos_pos_embed_from_grid(embed_dim, grid)
-    if cls_token and extra_tokens > 0:
-        pos_embed = np.concatenate([np.zeros([extra_tokens, embed_dim]), pos_embed], axis=0)
-    return pos_embed
-
-
-def get_2d_sincos_pos_embed_from_grid(embed_dim: int, grid):
-    assert embed_dim % 2 == 0
-    # use half of dimensions to encode grid_h
-    emb_h = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[0])  # (H*W, D/2)
-    emb_w = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[1])  # (H*W, D/2)
-    emb = np.concatenate([emb_h, emb_w], axis=1)  # (H*W, D)
-    return emb
-
-
-def get_1d_sincos_pos_embed_from_grid(embed_dim: int, pos):
-    """
-    embed_dim: output dimension for each position
-    pos: a list of positions to be encoded: size (M,)
-    out: (M, D)
-    """
-    assert embed_dim % 2 == 0
-    omega = np.arange(embed_dim // 2, dtype=np.float64)
-    omega /= embed_dim / 2.0
-    omega = 1.0 / 10000**omega  # (D/2,)
-    pos = pos.reshape(-1)  # (M,)
-    out = np.einsum("m,d->md", pos, omega)  # (M, D/2), outer product
-    emb_sin = np.sin(out)  # (M, D/2)
-    emb_cos = np.cos(out)  # (M, D/2)
-    return np.concatenate([emb_sin, emb_cos], axis=1)  # (M, D)
-
-
-#################################################################################
-#               Embedding Layers for Timesteps and Class Labels                 #
-#################################################################################
-
-
-class TimestepEmbedder(torch.nn.Module):
-    """Embeds scalar timesteps into vector representations."""
-
-    def __init__(self, hidden_size, frequency_embedding_size=256, dtype=None, device=None):
-        super().__init__()
-        self.mlp = torch.nn.Sequential(
-            torch.nn.Linear(
-                frequency_embedding_size,
-                hidden_size,
-                bias=True,
-                dtype=dtype,
-                device=device,
-            ),
-            torch.nn.SiLU(),
-            torch.nn.Linear(hidden_size, hidden_size, bias=True, dtype=dtype, device=device),
-        )
-        self.frequency_embedding_size = frequency_embedding_size
-
-    @staticmethod
-    def timestep_embedding(t, dim, max_period=10000):
-        """
-        Create sinusoidal timestep embeddings.
-        :param t: a 1-D Tensor of N indices, one per batch element.
-                          These may be fractional.
-        :param dim: the dimension of the output.
-        :param max_period: controls the minimum frequency of the embeddings.
-        :return: an (N, D) Tensor of positional embeddings.
-        """
-        half = dim // 2
-        freqs = torch.exp(-math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half).to(
-            device=t.device
-        )
-        args = t[:, None].float() * freqs[None]
-        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
-        if dim % 2:
-            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
-        if torch.is_floating_point(t):
-            embedding = embedding.to(dtype=t.dtype)
-        return embedding
-
-    def forward(self, t, dtype, **kwargs):
-        t_freq = self.timestep_embedding(t, self.frequency_embedding_size).to(dtype)
-        t_emb = self.mlp(t_freq)
-        return t_emb
-
-
-class VectorEmbedder(torch.nn.Module):
-    """Embeds a flat vector of dimension input_dim"""
-
-    def __init__(self, input_dim: int, hidden_size: int, dtype=None, device=None):
-        super().__init__()
-        self.mlp = torch.nn.Sequential(
-            torch.nn.Linear(input_dim, hidden_size, bias=True, dtype=dtype, device=device),
-            torch.nn.SiLU(),
-            torch.nn.Linear(hidden_size, hidden_size, bias=True, dtype=dtype, device=device),
-        )
-
-    def forward(self, x: torch.Tensor) -> torch.Tensor:
-        return self.mlp(x)
-
-
-#################################################################################
-#                                 Core DiT Model                                #
-#################################################################################
-
-
-def split_qkv(qkv, head_dim):
-    qkv = qkv.reshape(qkv.shape[0], qkv.shape[1], 3, -1, head_dim).movedim(2, 0)
-    return qkv[0], qkv[1], qkv[2]
-
-
-def optimized_attention(qkv, num_heads):
-    return attention(qkv[0], qkv[1], qkv[2], num_heads)
-
-
-class SelfAttention(torch.nn.Module):
-    ATTENTION_MODES = ("xformers", "torch", "torch-hb", "math", "debug")
-
-    def __init__(
-        self,
-        dim: int,
-        num_heads: int = 8,
-        qkv_bias: bool = False,
-        qk_scale: Optional[float] = None,
-        attn_mode: str = "xformers",
-        pre_only: bool = False,
-        qk_norm: Optional[str] = None,
-        rmsnorm: bool = False,
-        dtype=None,
-        device=None,
-    ):
-        super().__init__()
-        self.num_heads = num_heads
-        self.head_dim = dim // num_heads
-
-        self.qkv = torch.nn.Linear(dim, dim * 3, bias=qkv_bias, dtype=dtype, device=device)
-        if not pre_only:
-            self.proj = torch.nn.Linear(dim, dim, dtype=dtype, device=device)
-        assert attn_mode in self.ATTENTION_MODES
-        self.attn_mode = attn_mode
-        self.pre_only = pre_only
-
-        if qk_norm == "rms":
-            self.ln_q = RMSNorm(
-                self.head_dim,
-                elementwise_affine=True,
-                eps=1.0e-6,
-                dtype=dtype,
-                device=device,
-            )
-            self.ln_k = RMSNorm(
-                self.head_dim,
-                elementwise_affine=True,
-                eps=1.0e-6,
-                dtype=dtype,
-                device=device,
-            )
-        elif qk_norm == "ln":
-            self.ln_q = torch.nn.LayerNorm(
-                self.head_dim,
-                elementwise_affine=True,
-                eps=1.0e-6,
-                dtype=dtype,
-                device=device,
-            )
-            self.ln_k = torch.nn.LayerNorm(
-                self.head_dim,
-                elementwise_affine=True,
-                eps=1.0e-6,
-                dtype=dtype,
-                device=device,
-            )
-        elif qk_norm is None:
-            self.ln_q = torch.nn.Identity()
-            self.ln_k = torch.nn.Identity()
-        else:
-            raise ValueError(qk_norm)
-
-    def pre_attention(self, x: torch.Tensor):
-        B, L, C = x.shape
-        qkv = self.qkv(x)
-        q, k, v = split_qkv(qkv, self.head_dim)
-        q = self.ln_q(q).reshape(q.shape[0], q.shape[1], -1)
-        k = self.ln_k(k).reshape(q.shape[0], q.shape[1], -1)
-        return (q, k, v)
-
-    def post_attention(self, x: torch.Tensor) -> torch.Tensor:
-        assert not self.pre_only
-        x = self.proj(x)
-        return x
-
-    def forward(self, x: torch.Tensor) -> torch.Tensor:
-        (q, k, v) = self.pre_attention(x)
-        x = attention(q, k, v, self.num_heads)
-        x = self.post_attention(x)
-        return x
-
-
-class RMSNorm(torch.nn.Module):
-    def __init__(
-        self,
-        dim: int,
-        elementwise_affine: bool = False,
-        eps: float = 1e-6,
-        device=None,
-        dtype=None,
-    ):
-        """
-        Initialize the RMSNorm normalization layer.
-        Args:
-            dim (int): The dimension of the input tensor.
-            eps (float, optional): A small value added to the denominator for numerical stability. Default is 1e-6.
-        Attributes:
-            eps (float): A small value added to the denominator for numerical stability.
-            weight (torch.nn.Parameter): Learnable scaling parameter.
-        """
-        super().__init__()
-        self.eps = eps
-        self.learnable_scale = elementwise_affine
-        if self.learnable_scale:
-            self.weight = torch.nn.Parameter(torch.empty(dim, device=device, dtype=dtype))
-        else:
-            self.register_parameter("weight", None)
-
-    def _norm(self, x):
-        """
-        Apply the RMSNorm normalization to the input tensor.
-        Args:
-            x (torch.Tensor): The input tensor.
-        Returns:
-            torch.Tensor: The normalized tensor.
-        """
-        return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
-
-    def forward(self, x):
-        """
-        Forward pass through the RMSNorm layer.
-        Args:
-            x (torch.Tensor): The input tensor.
-        Returns:
-            torch.Tensor: The output tensor after applying RMSNorm.
-        """
-        x = self._norm(x)
-        if self.learnable_scale:
-            return x * self.weight.to(device=x.device, dtype=x.dtype)
-        else:
-            return x
-
-
-class SwiGLUFeedForward(torch.nn.Module):
-    def __init__(
-        self,
-        dim: int,
-        hidden_dim: int,
-        multiple_of: int,
-        ffn_dim_multiplier: Optional[float] = None,
-    ):
-        """
-        Initialize the FeedForward module.
-
-        Args:
-            dim (int): Input dimension.
-            hidden_dim (int): Hidden dimension of the feedforward layer.
-            multiple_of (int): Value to ensure hidden dimension is a multiple of this value.
-            ffn_dim_multiplier (float, optional): Custom multiplier for hidden dimension. Defaults to None.
-
-        Attributes:
-            w1 (ColumnParallelLinear): Linear transformation for the first layer.
-            w2 (RowParallelLinear): Linear transformation for the second layer.
-            w3 (ColumnParallelLinear): Linear transformation for the third layer.
-
-        """
-        super().__init__()
-        hidden_dim = int(2 * hidden_dim / 3)
-        # custom dim factor multiplier
-        if ffn_dim_multiplier is not None:
-            hidden_dim = int(ffn_dim_multiplier * hidden_dim)
-        hidden_dim = multiple_of * ((hidden_dim + multiple_of - 1) // multiple_of)
-
-        self.w1 = torch.nn.Linear(dim, hidden_dim, bias=False)
-        self.w2 = torch.nn.Linear(hidden_dim, dim, bias=False)
-        self.w3 = torch.nn.Linear(dim, hidden_dim, bias=False)
-
-    def forward(self, x):
-        return self.w2(torch.nn.functional.silu(self.w1(x)) * self.w3(x))
-
-
-class DismantledBlock(torch.nn.Module):
-    """A DiT block with gated adaptive layer norm (adaLN) conditioning."""
-
-    ATTENTION_MODES = ("xformers", "torch", "torch-hb", "math", "debug")
-
-    def __init__(
-        self,
-        hidden_size: int,
-        num_heads: int,
-        mlp_ratio: float = 4.0,
-        attn_mode: str = "xformers",
-        qkv_bias: bool = False,
-        pre_only: bool = False,
-        rmsnorm: bool = False,
-        scale_mod_only: bool = False,
-        swiglu: bool = False,
-        qk_norm: Optional[str] = None,
-        x_block_self_attn: bool = False,
-        dtype=None,
-        device=None,
-        **block_kwargs,
-    ):
-        super().__init__()
-        assert attn_mode in self.ATTENTION_MODES
-        if not rmsnorm:
-            self.norm1 = torch.nn.LayerNorm(
-                hidden_size,
-                elementwise_affine=False,
-                eps=1e-6,
-                dtype=dtype,
-                device=device,
-            )
-        else:
-            self.norm1 = RMSNorm(hidden_size, elementwise_affine=False, eps=1e-6)
-        self.attn = SelfAttention(
-            dim=hidden_size,
-            num_heads=num_heads,
-            qkv_bias=qkv_bias,
-            attn_mode=attn_mode,
-            pre_only=pre_only,
-            qk_norm=qk_norm,
-            rmsnorm=rmsnorm,
-            dtype=dtype,
-            device=device,
-        )
-        if x_block_self_attn:
-            assert not pre_only
-            assert not scale_mod_only
-            self.x_block_self_attn = True
-            self.attn2 = SelfAttention(
-                dim=hidden_size,
-                num_heads=num_heads,
-                qkv_bias=qkv_bias,
-                attn_mode=attn_mode,
-                pre_only=False,
-                qk_norm=qk_norm,
-                rmsnorm=rmsnorm,
-                dtype=dtype,
-                device=device,
-            )
-        else:
-            self.x_block_self_attn = False
-        if not pre_only:
-            if not rmsnorm:
-                self.norm2 = torch.nn.LayerNorm(
-                    hidden_size,
-                    elementwise_affine=False,
-                    eps=1e-6,
-                    dtype=dtype,
-                    device=device,
-                )
-            else:
-                self.norm2 = RMSNorm(hidden_size, elementwise_affine=False, eps=1e-6)
-        mlp_hidden_dim = int(hidden_size * mlp_ratio)
-        if not pre_only:
-            if not swiglu:
-                self.mlp = Mlp(
-                    in_features=hidden_size,
-                    hidden_features=mlp_hidden_dim,
-                    act_layer=torch.nn.GELU(approximate="tanh"),
-                    dtype=dtype,
-                    device=device,
-                )
-            else:
-                self.mlp = SwiGLUFeedForward(dim=hidden_size, hidden_dim=mlp_hidden_dim, multiple_of=256)
-        self.scale_mod_only = scale_mod_only
-        if x_block_self_attn:
-            assert not pre_only
-            assert not scale_mod_only
-            n_mods = 9
-        elif not scale_mod_only:
-            n_mods = 6 if not pre_only else 2
-        else:
-            n_mods = 4 if not pre_only else 1
-        self.adaLN_modulation = torch.nn.Sequential(
-            torch.nn.SiLU(),
-            torch.nn.Linear(hidden_size, n_mods * hidden_size, bias=True, dtype=dtype, device=device),
-        )
-        self.pre_only = pre_only
-
-    def pre_attention(self, x: torch.Tensor, c: torch.Tensor):
-        assert x is not None, "pre_attention called with None input"
-        if not self.pre_only:
-            if not self.scale_mod_only:
-                shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(
-                    6, dim=1
-                )
-            else:
-                shift_msa = None
-                shift_mlp = None
-                scale_msa, gate_msa, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(4, dim=1)
-            qkv = self.attn.pre_attention(modulate(self.norm1(x), shift_msa, scale_msa))
-            return qkv, (x, gate_msa, shift_mlp, scale_mlp, gate_mlp)
-        else:
-            if not self.scale_mod_only:
-                shift_msa, scale_msa = self.adaLN_modulation(c).chunk(2, dim=1)
-            else:
-                shift_msa = None
-                scale_msa = self.adaLN_modulation(c)
-            qkv = self.attn.pre_attention(modulate(self.norm1(x), shift_msa, scale_msa))
-            return qkv, None
-
-    def post_attention(
-        self,
-        attn: torch.Tensor,
-        x: torch.Tensor,
-        gate_msa: torch.Tensor,
-        shift_mlp: torch.Tensor,
-        scale_mlp: torch.Tensor,
-        gate_mlp: torch.Tensor,
-    ) -> torch.Tensor:
-        assert not self.pre_only
-        x = x + gate_msa.unsqueeze(1) * self.attn.post_attention(attn)
-        x = x + gate_mlp.unsqueeze(1) * self.mlp(modulate(self.norm2(x), shift_mlp, scale_mlp))
-        return x
-
-    def pre_attention_x(
-        self, x: torch.Tensor, c: torch.Tensor
-    ) -> tuple[
-        tuple[torch.Tensor, torch.Tensor, torch.Tensor],
-        tuple[torch.Tensor, torch.Tensor, torch.Tensor],
-        tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor],
-    ]:
-        assert self.x_block_self_attn
-        (
-            shift_msa,
-            scale_msa,
-            gate_msa,
-            shift_mlp,
-            scale_mlp,
-            gate_mlp,
-            shift_msa2,
-            scale_msa2,
-            gate_msa2,
-        ) = self.adaLN_modulation(c).chunk(9, dim=1)
-        x_norm = self.norm1(x)
-        qkv = self.attn.pre_attention(modulate(x_norm, shift_msa, scale_msa))
-        qkv2 = self.attn2.pre_attention(modulate(x_norm, shift_msa2, scale_msa2))
-        return (
-            qkv,
-            qkv2,
-            (
-                x,
-                gate_msa,
-                shift_mlp,
-                scale_mlp,
-                gate_mlp,
-                gate_msa2,
-            ),
-        )
-
-    def post_attention_x(
-        self,
-        attn: torch.Tensor,
-        attn2: torch.Tensor,
-        x: torch.Tensor,
-        gate_msa: torch.Tensor,
-        shift_mlp: torch.Tensor,
-        scale_mlp: torch.Tensor,
-        gate_mlp: torch.Tensor,
-        gate_msa2: torch.Tensor,
-        attn1_dropout: float = 0.0,
-    ):
-        assert not self.pre_only
-        if attn1_dropout > 0.0:
-            # Use torch.bernoulli to implement dropout, only dropout the batch dimension
-            attn1_dropout = torch.bernoulli(torch.full((attn.size(0), 1, 1), 1 - attn1_dropout, device=attn.device))
-            attn_ = gate_msa.unsqueeze(1) * self.attn.post_attention(attn) * attn1_dropout
-        else:
-            attn_ = gate_msa.unsqueeze(1) * self.attn.post_attention(attn)
-        x = x + attn_
-        attn2_ = gate_msa2.unsqueeze(1) * self.attn2.post_attention(attn2)
-        x = x + attn2_
-        mlp_ = gate_mlp.unsqueeze(1) * self.mlp(modulate(self.norm2(x), shift_mlp, scale_mlp))
-        x = x + mlp_
-        return x, (gate_msa, gate_msa2, gate_mlp, attn_, attn2_)
-
-    def forward(self, x: torch.Tensor, c: torch.Tensor):
-        assert not self.pre_only
-        if self.x_block_self_attn:
-            (q, k, v), (q2, k2, v2), intermediates = self.pre_attention_x(x, c)
-            attn = attention(q, k, v, self.attn.num_heads)
-            attn2 = attention(q2, k2, v2, self.attn2.num_heads)
-            return self.post_attention_x(attn, attn2, *intermediates)
-        else:
-            (q, k, v), intermediates = self.pre_attention(x, c)
-            attn = attention(q, k, v, self.attn.num_heads)
-            return self.post_attention(attn, *intermediates)
-
-
-def block_mixing(
-    context: torch.Tensor, x: torch.Tensor, context_block: DismantledBlock, x_block: DismantledBlock, c: torch.Tensor
-):
-    assert context is not None, "block_mixing called with None context"
-    context_qkv, context_intermediates = context_block.pre_attention(context, c)
-
-    if x_block.x_block_self_attn:
-        x_qkv, x_qkv2, x_intermediates = x_block.pre_attention_x(x, c)
-    else:
-        x_qkv, x_intermediates = x_block.pre_attention(x, c)
-
-    o: list[torch.Tensor] = []
-    for t in range(3):
-        o.append(torch.cat((context_qkv[t], x_qkv[t]), dim=1))
-    q, k, v = tuple(o)
-
-    attn = attention(q, k, v, x_block.attn.num_heads)
-    context_attn, x_attn = (
-        attn[:, : context_qkv[0].shape[1]],
-        attn[:, context_qkv[0].shape[1] :],
-    )
-
-    if not context_block.pre_only:
-        context = context_block.post_attention(context_attn, *context_intermediates)
-    else:
-        context = None
-
-    if x_block.x_block_self_attn:
-        x_q2, x_k2, x_v2 = x_qkv2
-        attn2 = attention(x_q2, x_k2, x_v2, x_block.attn2.num_heads)
-    else:
-        x = x_block.post_attention(x_attn, *x_intermediates)
-
-    return context, x
-
-
-class JointBlock(torch.nn.Module):
-    """just a small wrapper to serve as a fsdp unit"""
-
-    def __init__(self, *args, **kwargs):
-        super().__init__()
-        pre_only = kwargs.pop("pre_only")
-        qk_norm = kwargs.pop("qk_norm", None)
-        x_block_self_attn = kwargs.pop("x_block_self_attn", False)
-        self.context_block = DismantledBlock(*args, pre_only=pre_only, qk_norm=qk_norm, **kwargs)
-        self.x_block = DismantledBlock(
-            *args,
-            pre_only=False,
-            qk_norm=qk_norm,
-            x_block_self_attn=x_block_self_attn,
-            **kwargs,
-        )
-
-    def forward(self, *args, **kwargs):
-        return block_mixing(*args, context_block=self.context_block, x_block=self.x_block, **kwargs)
-
-
-class FinalLayer(torch.nn.Module):
-    """
-    The final layer of DiT.
-    """
-
-    def __init__(
-        self,
-        hidden_size: int,
-        patch_size: int,
-        out_channels: int,
-        total_out_channels: Optional[int] = None,
-        dtype: Optional[torch.dtype] = None,
-        device: Optional[torch.device] = None,
-    ):
-        super().__init__()
-        self.norm_final = torch.nn.LayerNorm(
-            hidden_size, elementwise_affine=False, eps=1e-6, dtype=dtype, device=device
-        )
-        self.linear = (
-            torch.nn.Linear(
-                hidden_size,
-                patch_size * patch_size * out_channels,
-                bias=True,
-                dtype=dtype,
-                device=device,
-            )
-            if (total_out_channels is None)
-            else torch.nn.Linear(hidden_size, total_out_channels, bias=True, dtype=dtype, device=device)
-        )
-        self.adaLN_modulation = torch.nn.Sequential(
-            torch.nn.SiLU(),
-            torch.nn.Linear(hidden_size, 2 * hidden_size, bias=True, dtype=dtype, device=device),
-        )
-
-    def forward(self, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
-        shift, scale = self.adaLN_modulation(c).chunk(2, dim=1)
-        x = modulate(self.norm_final(x), shift, scale)
-        x = self.linear(x)
-        return x
-
-
-class MMDiTX(torch.nn.Module):
-    """Diffusion model with a Transformer backbone."""
-
-    def __init__(
-        self,
-        input_size: int | None = 32,
-        patch_size: int = 2,
-        in_channels: int = 4,
-        depth: int = 28,
-        mlp_ratio: float = 4.0,
-        learn_sigma: bool = False,
-        adm_in_channels: Optional[int] = None,
-        context_embedder_config: Optional[Dict] = None,
-        register_length: int = 0,
-        attn_mode: str = "torch",
-        rmsnorm: bool = False,
-        scale_mod_only: bool = False,
-        swiglu: bool = False,
-        out_channels: Optional[int] = None,
-        pos_embed_scaling_factor: Optional[float] = None,
-        pos_embed_offset: Optional[float] = None,
-        pos_embed_max_size: Optional[int] = None,
-        num_patches: Optional[int] = None,
-        qk_norm: Optional[str] = None,
-        x_block_self_attn_layers: Optional[List[int]] = None,
-        qkv_bias: bool = True,
-        dtype: Optional[torch.dtype] = None,
-        device: Optional[torch.device] = None,
-        verbose: bool = False,
-    ):
-        super().__init__()
-        if verbose:
-            print(
-                f"mmdit initializing with: {input_size=}, {patch_size=}, {in_channels=}, {depth=}, {mlp_ratio=}, {learn_sigma=}, {adm_in_channels=}, {context_embedder_config=}, {register_length=}, {attn_mode=}, {rmsnorm=}, {scale_mod_only=}, {swiglu=}, {out_channels=}, {pos_embed_scaling_factor=}, {pos_embed_offset=}, {pos_embed_max_size=}, {num_patches=}, {qk_norm=}, {qkv_bias=}, {dtype=}, {device=}"
-            )
-        self.dtype = dtype
-        self.learn_sigma = learn_sigma
-        self.in_channels = in_channels
-        default_out_channels = in_channels * 2 if learn_sigma else in_channels
-        self.out_channels = out_channels if out_channels is not None else default_out_channels
-        self.patch_size = patch_size
-        self.pos_embed_scaling_factor = pos_embed_scaling_factor
-        self.pos_embed_offset = pos_embed_offset
-        self.pos_embed_max_size = pos_embed_max_size
-        self.x_block_self_attn_layers = x_block_self_attn_layers or []
-
-        # apply magic --> this defines a head_size of 64
-        hidden_size = 64 * depth
-        num_heads = depth
-
-        self.num_heads = num_heads
-
-        self.x_embedder = PatchEmbed(
-            input_size,
-            patch_size,
-            in_channels,
-            hidden_size,
-            bias=True,
-            strict_img_size=self.pos_embed_max_size is None,
-            dtype=dtype,
-            device=device,
-        )
-        self.t_embedder = TimestepEmbedder(hidden_size, dtype=dtype, device=device)
-
-        if adm_in_channels is not None:
-            assert isinstance(adm_in_channels, int)
-            self.y_embedder = VectorEmbedder(adm_in_channels, hidden_size, dtype=dtype, device=device)
-
-        self.context_embedder = torch.nn.Identity()
-        if context_embedder_config is not None:
-            if context_embedder_config["target"] == "torch.nn.Linear":
-                self.context_embedder = torch.nn.Linear(**context_embedder_config["params"], dtype=dtype, device=device)
-
-        self.register_length = register_length
-        if self.register_length > 0:
-            self.register = torch.nn.Parameter(torch.randn(1, register_length, hidden_size, dtype=dtype, device=device))
-
-        # num_patches = self.x_embedder.num_patches
-        # Will use fixed sin-cos embedding:
-        # just use a buffer already
-        if num_patches is not None:
-            self.register_buffer(
-                "pos_embed",
-                torch.zeros(1, num_patches, hidden_size, dtype=dtype, device=device),
-            )
-        else:
-            self.pos_embed = None
-
-        self.joint_blocks = torch.nn.ModuleList(
-            [
-                JointBlock(
-                    hidden_size,
-                    num_heads,
-                    mlp_ratio=mlp_ratio,
-                    qkv_bias=qkv_bias,
-                    attn_mode=attn_mode,
-                    pre_only=i == depth - 1,
-                    rmsnorm=rmsnorm,
-                    scale_mod_only=scale_mod_only,
-                    swiglu=swiglu,
-                    qk_norm=qk_norm,
-                    x_block_self_attn=(i in self.x_block_self_attn_layers),
-                    dtype=dtype,
-                    device=device,
-                )
-                for i in range(depth)
-            ]
-        )
-
-        self.final_layer = FinalLayer(hidden_size, patch_size, self.out_channels, dtype=dtype, device=device)
-
-    def cropped_pos_embed(self, hw: torch.Size) -> torch.Tensor:
-        assert self.pos_embed_max_size is not None
-        p = self.x_embedder.patch_size[0]
-        h, w = hw
-        # patched size
-        h = h // p
-        w = w // p
-        assert h <= self.pos_embed_max_size, (h, self.pos_embed_max_size)
-        assert w <= self.pos_embed_max_size, (w, self.pos_embed_max_size)
-        top = (self.pos_embed_max_size - h) // 2
-        left = (self.pos_embed_max_size - w) // 2
-        spatial_pos_embed: torch.Tensor = rearrange(
-            self.pos_embed,
-            "1 (h w) c -> 1 h w c",
-            h=self.pos_embed_max_size,
-            w=self.pos_embed_max_size,
-        )  # type: ignore Type checking does not correctly infer the type of the self.pos_embed buffer.
-        spatial_pos_embed = spatial_pos_embed[:, top : top + h, left : left + w, :]
-        spatial_pos_embed = rearrange(spatial_pos_embed, "1 h w c -> 1 (h w) c")
-        return spatial_pos_embed
-
-    def unpatchify(self, x: torch.Tensor, hw: Optional[torch.Size] = None) -> torch.Tensor:
-        """
-        x: (N, T, patch_size**2 * C)
-        imgs: (N, H, W, C)
-        """
-        c = self.out_channels
-        p = self.x_embedder.patch_size[0]
-        if hw is None:
-            h = w = int(x.shape[1] ** 0.5)
-        else:
-            h, w = hw
-            h = h // p
-            w = w // p
-        assert h * w == x.shape[1]
-
-        x = x.reshape(shape=(x.shape[0], h, w, p, p, c))
-        x = torch.einsum("nhwpqc->nchpwq", x)
-        imgs = x.reshape(shape=(x.shape[0], c, h * p, w * p))
-        return imgs
-
-    def forward_core_with_concat(
-        self,
-        x: torch.Tensor,
-        c_mod: torch.Tensor,
-        context: Optional[torch.Tensor] = None,
-    ) -> torch.Tensor:
-        if self.register_length > 0:
-            context = torch.cat(
-                (
-                    repeat(self.register, "1 ... -> b ...", b=x.shape[0]),
-                    context if context is not None else torch.Tensor([]).type_as(x),
-                ),
-                1,
-            )
-
-        # context is B, L', D
-        # x is B, L, D
-        for block in self.joint_blocks:
-            context, x = block(context, x, c=c_mod)
-
-        x = self.final_layer(x, c_mod)  # (N, T, patch_size ** 2 * out_channels)
-        return x
-
-    def forward(
-        self,
-        x: torch.Tensor,
-        t: torch.Tensor,
-        y: Optional[torch.Tensor] = None,
-        context: Optional[torch.Tensor] = None,
-    ) -> torch.Tensor:
-        """
-        Forward pass of DiT.
-        x: (N, C, H, W) tensor of spatial inputs (images or latent representations of images)
-        t: (N,) tensor of diffusion timesteps
-        y: (N,) tensor of class labels
-        """
-        hw = x.shape[-2:]
-        x = self.x_embedder(x) + self.cropped_pos_embed(hw)
-        c = self.t_embedder(t, dtype=x.dtype)  # (N, D)
-        if y is not None:
-            y = self.y_embedder(y)  # (N, D)
-            c = c + y  # (N, D)
-
-        context = self.context_embedder(context)
-
-        x = self.forward_core_with_concat(x, c, context)
-
-        x = self.unpatchify(x, hw=hw)  # (N, out_channels, H, W)
-        return x

invokeai/backend/sd3/other_impls.py

@@ -1,795 +0,0 @@
-# This file was originally copied from:
-# https://github.com/Stability-AI/sd3.5/blob/19bf11c4e1e37324c5aa5a61f010d4127848a09c/other_impls.py
-
-### This file contains impls for underlying related models (CLIP, T5, etc)
-
-import math
-from typing import Callable, Optional
-
-import torch
-from transformers import CLIPTokenizer, T5TokenizerFast
-
-#################################################################################################
-### Core/Utility
-#################################################################################################
-
-
-def attention(
-    q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, heads: int, mask: Optional[torch.Tensor] = None
-) -> torch.Tensor:
-    """Convenience wrapper around a basic attention operation"""
-    b, _, dim_head = q.shape
-    dim_head //= heads
-    q, k, v = map(lambda t: t.view(b, -1, heads, dim_head).transpose(1, 2), (q, k, v))
-    out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
-    return out.transpose(1, 2).reshape(b, -1, heads * dim_head)
-
-
-class Mlp(torch.nn.Module):
-    """MLP as used in Vision Transformer, MLP-Mixer and related networks"""
-
-    def __init__(
-        self,
-        in_features: int,
-        hidden_features: Optional[int] = None,
-        out_features: Optional[int] = None,
-        act_layer: Callable[[torch.Tensor], torch.Tensor] | None = None,
-        bias: bool = True,
-        dtype: Optional[torch.dtype] = None,
-        device: Optional[torch.device] = None,
-    ):
-        super().__init__()
-        out_features = out_features or in_features
-        hidden_features = hidden_features or in_features
-        if act_layer is None:
-            act_layer = torch.nn.functional.gelu
-
-        self.fc1 = torch.nn.Linear(in_features, hidden_features, bias=bias, dtype=dtype, device=device)
-        self.act = act_layer
-        self.fc2 = torch.nn.Linear(hidden_features, out_features, bias=bias, dtype=dtype, device=device)
-
-    def forward(self, x: torch.Tensor) -> torch.Tensor:
-        x = self.fc1(x)
-        x = self.act(x)
-        x = self.fc2(x)
-        return x
-
-
-#################################################################################################
-### CLIP
-#################################################################################################
-
-
-class CLIPAttention(torch.nn.Module):
-    def __init__(self, embed_dim, heads, dtype, device):
-        super().__init__()
-        self.heads = heads
-        self.q_proj = torch.nn.Linear(embed_dim, embed_dim, bias=True, dtype=dtype, device=device)
-        self.k_proj = torch.nn.Linear(embed_dim, embed_dim, bias=True, dtype=dtype, device=device)
-        self.v_proj = torch.nn.Linear(embed_dim, embed_dim, bias=True, dtype=dtype, device=device)
-        self.out_proj = torch.nn.Linear(embed_dim, embed_dim, bias=True, dtype=dtype, device=device)
-
-    def forward(self, x, mask=None):
-        q = self.q_proj(x)
-        k = self.k_proj(x)
-        v = self.v_proj(x)
-        out = attention(q, k, v, self.heads, mask)
-        return self.out_proj(out)
-
-
-ACTIVATIONS = {
-    "quick_gelu": lambda a: a * torch.sigmoid(1.702 * a),
-    "gelu": torch.nn.functional.gelu,
-}
-
-
-class CLIPLayer(torch.nn.Module):
-    def __init__(
-        self,
-        embed_dim,
-        heads,
-        intermediate_size,
-        intermediate_activation,
-        dtype,
-        device,
-    ):
-        super().__init__()
-        self.layer_norm1 = torch.nn.LayerNorm(embed_dim, dtype=dtype, device=device)
-        self.self_attn = CLIPAttention(embed_dim, heads, dtype, device)
-        self.layer_norm2 = torch.nn.LayerNorm(embed_dim, dtype=dtype, device=device)
-        # self.mlp = CLIPMLP(embed_dim, intermediate_size, intermediate_activation, dtype, device)
-        self.mlp = Mlp(
-            embed_dim,
-            intermediate_size,
-            embed_dim,
-            act_layer=ACTIVATIONS[intermediate_activation],
-            dtype=dtype,
-            device=device,
-        )
-
-    def forward(self, x, mask=None):
-        x += self.self_attn(self.layer_norm1(x), mask)
-        x += self.mlp(self.layer_norm2(x))
-        return x
-
-
-class CLIPEncoder(torch.nn.Module):
-    def __init__(
-        self,
-        num_layers,
-        embed_dim,
-        heads,
-        intermediate_size,
-        intermediate_activation,
-        dtype,
-        device,
-    ):
-        super().__init__()
-        self.layers = torch.nn.ModuleList(
-            [
-                CLIPLayer(
-                    embed_dim,
-                    heads,
-                    intermediate_size,
-                    intermediate_activation,
-                    dtype,
-                    device,
-                )
-                for i in range(num_layers)
-            ]
-        )
-
-    def forward(self, x, mask=None, intermediate_output=None):
-        if intermediate_output is not None:
-            if intermediate_output < 0:
-                intermediate_output = len(self.layers) + intermediate_output
-        intermediate = None
-        for i, l in enumerate(self.layers):
-            x = l(x, mask)
-            if i == intermediate_output:
-                intermediate = x.clone()
-        return x, intermediate
-
-
-class CLIPEmbeddings(torch.nn.Module):
-    def __init__(self, embed_dim, vocab_size=49408, num_positions=77, dtype=None, device=None):
-        super().__init__()
-        self.token_embedding = torch.nn.Embedding(vocab_size, embed_dim, dtype=dtype, device=device)
-        self.position_embedding = torch.nn.Embedding(num_positions, embed_dim, dtype=dtype, device=device)
-
-    def forward(self, input_tokens):
-        return self.token_embedding(input_tokens) + self.position_embedding.weight
-
-
-class CLIPTextModel_(torch.nn.Module):
-    def __init__(self, config_dict, dtype, device):
-        num_layers = config_dict["num_hidden_layers"]
-        embed_dim = config_dict["hidden_size"]
-        heads = config_dict["num_attention_heads"]
-        intermediate_size = config_dict["intermediate_size"]
-        intermediate_activation = config_dict["hidden_act"]
-        super().__init__()
-        self.embeddings = CLIPEmbeddings(embed_dim, dtype=torch.float32, device=device)
-        self.encoder = CLIPEncoder(
-            num_layers,
-            embed_dim,
-            heads,
-            intermediate_size,
-            intermediate_activation,
-            dtype,
-            device,
-        )
-        self.final_layer_norm = torch.nn.LayerNorm(embed_dim, dtype=dtype, device=device)
-
-    def forward(self, input_tokens, intermediate_output=None, final_layer_norm_intermediate=True):
-        x = self.embeddings(input_tokens)
-        causal_mask = torch.empty(x.shape[1], x.shape[1], dtype=x.dtype, device=x.device).fill_(float("-inf")).triu_(1)
-        x, i = self.encoder(x, mask=causal_mask, intermediate_output=intermediate_output)
-        x = self.final_layer_norm(x)
-        if i is not None and final_layer_norm_intermediate:
-            i = self.final_layer_norm(i)
-        pooled_output = x[
-            torch.arange(x.shape[0], device=x.device),
-            input_tokens.to(dtype=torch.int, device=x.device).argmax(dim=-1),
-        ]
-        return x, i, pooled_output
-
-
-class CLIPTextModel(torch.nn.Module):
-    def __init__(self, config_dict, dtype, device):
-        super().__init__()
-        self.num_layers = config_dict["num_hidden_layers"]
-        self.text_model = CLIPTextModel_(config_dict, dtype, device)
-        embed_dim = config_dict["hidden_size"]
-        self.text_projection = torch.nn.Linear(embed_dim, embed_dim, bias=False, dtype=dtype, device=device)
-        self.text_projection.weight.copy_(torch.eye(embed_dim))
-        self.dtype = dtype
-
-    def get_input_embeddings(self):
-        return self.text_model.embeddings.token_embedding
-
-    def set_input_embeddings(self, embeddings):
-        self.text_model.embeddings.token_embedding = embeddings
-
-    def forward(self, *args, **kwargs):
-        x = self.text_model(*args, **kwargs)
-        out = self.text_projection(x[2])
-        return (x[0], x[1], out, x[2])
-
-
-def parse_parentheses(string):
-    result = []
-    current_item = ""
-    nesting_level = 0
-    for char in string:
-        if char == "(":
-            if nesting_level == 0:
-                if current_item:
-                    result.append(current_item)
-                    current_item = "("
-                else:
-                    current_item = "("
-            else:
-                current_item += char
-            nesting_level += 1
-        elif char == ")":
-            nesting_level -= 1
-            if nesting_level == 0:
-                result.append(current_item + ")")
-                current_item = ""
-            else:
-                current_item += char
-        else:
-            current_item += char
-    if current_item:
-        result.append(current_item)
-    return result
-
-
-def token_weights(string, current_weight):
-    a = parse_parentheses(string)
-    out = []
-    for x in a:
-        weight = current_weight
-        if len(x) >= 2 and x[-1] == ")" and x[0] == "(":
-            x = x[1:-1]
-            xx = x.rfind(":")
-            weight *= 1.1
-            if xx > 0:
-                try:
-                    weight = float(x[xx + 1 :])
-                    x = x[:xx]
-                except:
-                    pass
-            out += token_weights(x, weight)
-        else:
-            out += [(x, current_weight)]
-    return out
-
-
-def escape_important(text):
-    text = text.replace("\\)", "\0\1")
-    text = text.replace("\\(", "\0\2")
-    return text
-
-
-def unescape_important(text):
-    text = text.replace("\0\1", ")")
-    text = text.replace("\0\2", "(")
-    return text
-
-
-class SDTokenizer:
-    def __init__(
-        self,
-        max_length=77,
-        pad_with_end=True,
-        tokenizer=None,
-        has_start_token=True,
-        pad_to_max_length=True,
-        min_length=None,
-        extra_padding_token=None,
-    ):
-        self.tokenizer = tokenizer
-        self.max_length = max_length
-        self.min_length = min_length
-
-        empty = self.tokenizer("")["input_ids"]
-        if has_start_token:
-            self.tokens_start = 1
-            self.start_token = empty[0]
-            self.end_token = empty[1]
-        else:
-            self.tokens_start = 0
-            self.start_token = None
-            self.end_token = empty[0]
-        self.pad_with_end = pad_with_end
-        self.pad_to_max_length = pad_to_max_length
-        self.extra_padding_token = extra_padding_token
-
-        vocab = self.tokenizer.get_vocab()
-        self.inv_vocab = {v: k for k, v in vocab.items()}
-        self.max_word_length = 8
-
-    def tokenize_with_weights(self, text: str, return_word_ids=False):
-        """
-        Tokenize the text, with weight values - presume 1.0 for all and ignore other features here.
-        The details aren't relevant for a reference impl, and weights themselves has weak effect on SD3.
-        """
-        if self.pad_with_end:
-            pad_token = self.end_token
-        else:
-            pad_token = 0
-
-        text = escape_important(text)
-        parsed_weights = token_weights(text, 1.0)
-
-        # tokenize words
-        tokens = []
-        for weighted_segment, weight in parsed_weights:
-            to_tokenize = unescape_important(weighted_segment).replace("\n", " ").split(" ")
-            to_tokenize = [x for x in to_tokenize if x != ""]
-            for word in to_tokenize:
-                # parse word
-                tokens.append([(t, weight) for t in self.tokenizer(word)["input_ids"][self.tokens_start : -1]])
-
-        # reshape token array to CLIP input size
-        batched_tokens = []
-        batch = []
-        if self.start_token is not None:
-            batch.append((self.start_token, 1.0, 0))
-        batched_tokens.append(batch)
-        for i, t_group in enumerate(tokens):
-            # determine if we're going to try and keep the tokens in a single batch
-            is_large = len(t_group) >= self.max_word_length
-
-            while len(t_group) > 0:
-                if len(t_group) + len(batch) > self.max_length - 1:
-                    remaining_length = self.max_length - len(batch) - 1
-                    # break word in two and add end token
-                    if is_large:
-                        batch.extend([(t, w, i + 1) for t, w in t_group[:remaining_length]])
-                        batch.append((self.end_token, 1.0, 0))
-                        t_group = t_group[remaining_length:]
-                    # add end token and pad
-                    else:
-                        batch.append((self.end_token, 1.0, 0))
-                        if self.pad_to_max_length:
-                            batch.extend([(pad_token, 1.0, 0)] * (remaining_length))
-                    # start new batch
-                    batch = []
-                    if self.start_token is not None:
-                        batch.append((self.start_token, 1.0, 0))
-                    batched_tokens.append(batch)
-                else:
-                    batch.extend([(t, w, i + 1) for t, w in t_group])
-                    t_group = []
-
-        # pad extra padding token first befor getting to the end token
-        if self.extra_padding_token is not None:
-            batch.extend([(self.extra_padding_token, 1.0, 0)] * (self.min_length - len(batch) - 1))
-        # fill last batch
-        batch.append((self.end_token, 1.0, 0))
-        if self.pad_to_max_length:
-            batch.extend([(pad_token, 1.0, 0)] * (self.max_length - len(batch)))
-        if self.min_length is not None and len(batch) < self.min_length:
-            batch.extend([(pad_token, 1.0, 0)] * (self.min_length - len(batch)))
-
-        if not return_word_ids:
-            batched_tokens = [[(t, w) for t, w, _ in x] for x in batched_tokens]
-
-        return batched_tokens
-
-    def untokenize(self, token_weight_pair):
-        return list(map(lambda a: (a, self.inv_vocab[a[0]]), token_weight_pair))
-
-
-class SDXLClipGTokenizer(SDTokenizer):
-    def __init__(self, tokenizer):
-        super().__init__(pad_with_end=False, tokenizer=tokenizer)
-
-
-class SD3Tokenizer:
-    def __init__(self):
-        clip_tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")
-        self.clip_l = SDTokenizer(tokenizer=clip_tokenizer)
-        self.clip_g = SDXLClipGTokenizer(clip_tokenizer)
-        self.t5xxl = T5XXLTokenizer()
-
-    def tokenize_with_weights(self, text: str):
-        out = {}
-        out["l"] = self.clip_l.tokenize_with_weights(text)
-        out["g"] = self.clip_g.tokenize_with_weights(text)
-        out["t5xxl"] = self.t5xxl.tokenize_with_weights(text[:226])
-        return out
-
-
-class ClipTokenWeightEncoder:
-    def encode_token_weights(self, token_weight_pairs):
-        tokens = list(map(lambda a: a[0], token_weight_pairs[0]))
-        out, pooled = self([tokens])
-        if pooled is not None:
-            first_pooled = pooled[0:1].cpu()
-        else:
-            first_pooled = pooled
-        output = [out[0:1]]
-        return torch.cat(output, dim=-2).cpu(), first_pooled
-
-
-class SDClipModel(torch.nn.Module, ClipTokenWeightEncoder):
-    """Uses the CLIP transformer encoder for text (from huggingface)"""
-
-    LAYERS = ["last", "pooled", "hidden"]
-
-    def __init__(
-        self,
-        device="cpu",
-        max_length=77,
-        layer="last",
-        layer_idx=None,
-        textmodel_json_config=None,
-        dtype=None,
-        model_class=CLIPTextModel,
-        special_tokens={"start": 49406, "end": 49407, "pad": 49407},
-        layer_norm_hidden_state=True,
-        return_projected_pooled=True,
-    ):
-        super().__init__()
-        assert layer in self.LAYERS
-        self.transformer = model_class(textmodel_json_config, dtype, device)
-        self.num_layers = self.transformer.num_layers
-        self.max_length = max_length
-        self.transformer = self.transformer.eval()
-        for param in self.parameters():
-            param.requires_grad = False
-        self.layer = layer
-        self.layer_idx = None
-        self.special_tokens = special_tokens
-        self.logit_scale = torch.nn.Parameter(torch.tensor(4.6055))
-        self.layer_norm_hidden_state = layer_norm_hidden_state
-        self.return_projected_pooled = return_projected_pooled
-        if layer == "hidden":
-            assert layer_idx is not None
-            assert abs(layer_idx) < self.num_layers
-            self.set_clip_options({"layer": layer_idx})
-        self.options_default = (
-            self.layer,
-            self.layer_idx,
-            self.return_projected_pooled,
-        )
-
-    def set_clip_options(self, options):
-        layer_idx = options.get("layer", self.layer_idx)
-        self.return_projected_pooled = options.get("projected_pooled", self.return_projected_pooled)
-        if layer_idx is None or abs(layer_idx) > self.num_layers:
-            self.layer = "last"
-        else:
-            self.layer = "hidden"
-            self.layer_idx = layer_idx
-
-    def forward(self, tokens):
-        backup_embeds = self.transformer.get_input_embeddings()
-        device = backup_embeds.weight.device
-        tokens = torch.LongTensor(tokens).to(device)
-        outputs = self.transformer(
-            tokens,
-            intermediate_output=self.layer_idx,
-            final_layer_norm_intermediate=self.layer_norm_hidden_state,
-        )
-        self.transformer.set_input_embeddings(backup_embeds)
-        if self.layer == "last":
-            z = outputs[0]
-        else:
-            z = outputs[1]
-        pooled_output = None
-        if len(outputs) >= 3:
-            if not self.return_projected_pooled and len(outputs) >= 4 and outputs[3] is not None:
-                pooled_output = outputs[3].float()
-            elif outputs[2] is not None:
-                pooled_output = outputs[2].float()
-        return z.float(), pooled_output
-
-
-class SDXLClipG(SDClipModel):
-    """Wraps the CLIP-G model into the SD-CLIP-Model interface"""
-
-    def __init__(self, config, device="cpu", layer="penultimate", layer_idx=None, dtype=None):
-        if layer == "penultimate":
-            layer = "hidden"
-            layer_idx = -2
-        super().__init__(
-            device=device,
-            layer=layer,
-            layer_idx=layer_idx,
-            textmodel_json_config=config,
-            dtype=dtype,
-            special_tokens={"start": 49406, "end": 49407, "pad": 0},
-            layer_norm_hidden_state=False,
-        )
-
-
-class T5XXLModel(SDClipModel):
-    """Wraps the T5-XXL model into the SD-CLIP-Model interface for convenience"""
-
-    def __init__(self, config, device="cpu", layer="last", layer_idx=None, dtype=None):
-        super().__init__(
-            device=device,
-            layer=layer,
-            layer_idx=layer_idx,
-            textmodel_json_config=config,
-            dtype=dtype,
-            special_tokens={"end": 1, "pad": 0},
-            model_class=T5,
-        )
-
-
-#################################################################################################
-### T5 implementation, for the T5-XXL text encoder portion, largely pulled from upstream impl
-#################################################################################################
-
-
-class T5XXLTokenizer(SDTokenizer):
-    """Wraps the T5 Tokenizer from HF into the SDTokenizer interface"""
-
-    def __init__(self):
-        super().__init__(
-            pad_with_end=False,
-            tokenizer=T5TokenizerFast.from_pretrained("google/t5-v1_1-xxl"),
-            has_start_token=False,
-            pad_to_max_length=False,
-            max_length=99999999,
-            min_length=77,
-        )
-
-
-class T5LayerNorm(torch.nn.Module):
-    def __init__(self, hidden_size, eps=1e-6, dtype=None, device=None):
-        super().__init__()
-        self.weight = torch.nn.Parameter(torch.ones(hidden_size, dtype=dtype, device=device))
-        self.variance_epsilon = eps
-
-    def forward(self, x):
-        variance = x.pow(2).mean(-1, keepdim=True)
-        x = x * torch.rsqrt(variance + self.variance_epsilon)
-        return self.weight.to(device=x.device, dtype=x.dtype) * x
-
-
-class T5DenseGatedActDense(torch.nn.Module):
-    def __init__(self, model_dim, ff_dim, dtype, device):
-        super().__init__()
-        self.wi_0 = torch.nn.Linear(model_dim, ff_dim, bias=False, dtype=dtype, device=device)
-        self.wi_1 = torch.nn.Linear(model_dim, ff_dim, bias=False, dtype=dtype, device=device)
-        self.wo = torch.nn.Linear(ff_dim, model_dim, bias=False, dtype=dtype, device=device)
-
-    def forward(self, x):
-        hidden_gelu = torch.nn.functional.gelu(self.wi_0(x), approximate="tanh")
-        hidden_linear = self.wi_1(x)
-        x = hidden_gelu * hidden_linear
-        x = self.wo(x)
-        return x
-
-
-class T5LayerFF(torch.nn.Module):
-    def __init__(self, model_dim, ff_dim, dtype, device):
-        super().__init__()
-        self.DenseReluDense = T5DenseGatedActDense(model_dim, ff_dim, dtype, device)
-        self.layer_norm = T5LayerNorm(model_dim, dtype=dtype, device=device)
-
-    def forward(self, x):
-        forwarded_states = self.layer_norm(x)
-        forwarded_states = self.DenseReluDense(forwarded_states)
-        x += forwarded_states
-        return x
-
-
-class T5Attention(torch.nn.Module):
-    def __init__(self, model_dim, inner_dim, num_heads, relative_attention_bias, dtype, device):
-        super().__init__()
-        # Mesh TensorFlow initialization to avoid scaling before softmax
-        self.q = torch.nn.Linear(model_dim, inner_dim, bias=False, dtype=dtype, device=device)
-        self.k = torch.nn.Linear(model_dim, inner_dim, bias=False, dtype=dtype, device=device)
-        self.v = torch.nn.Linear(model_dim, inner_dim, bias=False, dtype=dtype, device=device)
-        self.o = torch.nn.Linear(inner_dim, model_dim, bias=False, dtype=dtype, device=device)
-        self.num_heads = num_heads
-        self.relative_attention_bias = None
-        if relative_attention_bias:
-            self.relative_attention_num_buckets = 32
-            self.relative_attention_max_distance = 128
-            self.relative_attention_bias = torch.nn.Embedding(
-                self.relative_attention_num_buckets, self.num_heads, device=device
-            )
-
-    @staticmethod
-    def _relative_position_bucket(relative_position, bidirectional=True, num_buckets=32, max_distance=128):
-        """
-        Adapted from Mesh Tensorflow:
-        https://github.com/tensorflow/mesh/blob/0cb87fe07da627bf0b7e60475d59f95ed6b5be3d/mesh_tensorflow/transformer/transformer_layers.py#L593
-
-        Translate relative position to a bucket number for relative attention. The relative position is defined as
-        memory_position - query_position, i.e. the distance in tokens from the attending position to the attended-to
-        position. If bidirectional=False, then positive relative positions are invalid. We use smaller buckets for
-        small absolute relative_position and larger buckets for larger absolute relative_positions. All relative
-        positions >=max_distance map to the same bucket. All relative positions <=-max_distance map to the same bucket.
-        This should allow for more graceful generalization to longer sequences than the model has been trained on
-
-        Args:
-            relative_position: an int32 Tensor
-            bidirectional: a boolean - whether the attention is bidirectional
-            num_buckets: an integer
-            max_distance: an integer
-
-        Returns:
-            a Tensor with the same shape as relative_position, containing int32 values in the range [0, num_buckets)
-        """
-        relative_buckets = 0
-        if bidirectional:
-            num_buckets //= 2
-            relative_buckets += (relative_position > 0).to(torch.long) * num_buckets
-            relative_position = torch.abs(relative_position)
-        else:
-            relative_position = -torch.min(relative_position, torch.zeros_like(relative_position))
-        # now relative_position is in the range [0, inf)
-        # half of the buckets are for exact increments in positions
-        max_exact = num_buckets // 2
-        is_small = relative_position < max_exact
-        # The other half of the buckets are for logarithmically bigger bins in positions up to max_distance
-        relative_position_if_large = max_exact + (
-            torch.log(relative_position.float() / max_exact)
-            / math.log(max_distance / max_exact)
-            * (num_buckets - max_exact)
-        ).to(torch.long)
-        relative_position_if_large = torch.min(
-            relative_position_if_large,
-            torch.full_like(relative_position_if_large, num_buckets - 1),
-        )
-        relative_buckets += torch.where(is_small, relative_position, relative_position_if_large)
-        return relative_buckets
-
-    def compute_bias(self, query_length, key_length, device):
-        """Compute binned relative position bias"""
-        context_position = torch.arange(query_length, dtype=torch.long, device=device)[:, None]
-        memory_position = torch.arange(key_length, dtype=torch.long, device=device)[None, :]
-        relative_position = memory_position - context_position  # shape (query_length, key_length)
-        relative_position_bucket = self._relative_position_bucket(
-            relative_position,  # shape (query_length, key_length)
-            bidirectional=True,
-            num_buckets=self.relative_attention_num_buckets,
-            max_distance=self.relative_attention_max_distance,
-        )
-        values = self.relative_attention_bias(relative_position_bucket)  # shape (query_length, key_length, num_heads)
-        values = values.permute([2, 0, 1]).unsqueeze(0)  # shape (1, num_heads, query_length, key_length)
-        return values
-
-    def forward(self, x, past_bias=None):
-        q = self.q(x)
-        k = self.k(x)
-        v = self.v(x)
-        if self.relative_attention_bias is not None:
-            past_bias = self.compute_bias(x.shape[1], x.shape[1], x.device)
-        if past_bias is not None:
-            mask = past_bias
-        out = attention(q, k * ((k.shape[-1] / self.num_heads) ** 0.5), v, self.num_heads, mask)
-        return self.o(out), past_bias
-
-
-class T5LayerSelfAttention(torch.nn.Module):
-    def __init__(
-        self,
-        model_dim,
-        inner_dim,
-        ff_dim,
-        num_heads,
-        relative_attention_bias,
-        dtype,
-        device,
-    ):
-        super().__init__()
-        self.SelfAttention = T5Attention(model_dim, inner_dim, num_heads, relative_attention_bias, dtype, device)
-        self.layer_norm = T5LayerNorm(model_dim, dtype=dtype, device=device)
-
-    def forward(self, x, past_bias=None):
-        output, past_bias = self.SelfAttention(self.layer_norm(x), past_bias=past_bias)
-        x += output
-        return x, past_bias
-
-
-class T5Block(torch.nn.Module):
-    def __init__(
-        self,
-        model_dim,
-        inner_dim,
-        ff_dim,
-        num_heads,
-        relative_attention_bias,
-        dtype,
-        device,
-    ):
-        super().__init__()
-        self.layer = torch.nn.ModuleList()
-        self.layer.append(
-            T5LayerSelfAttention(
-                model_dim,
-                inner_dim,
-                ff_dim,
-                num_heads,
-                relative_attention_bias,
-                dtype,
-                device,
-            )
-        )
-        self.layer.append(T5LayerFF(model_dim, ff_dim, dtype, device))
-
-    def forward(self, x, past_bias=None):
-        x, past_bias = self.layer[0](x, past_bias)
-        x = self.layer[-1](x)
-        return x, past_bias
-
-
-class T5Stack(torch.nn.Module):
-    def __init__(
-        self,
-        num_layers,
-        model_dim,
-        inner_dim,
-        ff_dim,
-        num_heads,
-        vocab_size,
-        dtype,
-        device,
-    ):
-        super().__init__()
-        self.embed_tokens = torch.nn.Embedding(vocab_size, model_dim, device=device)
-        self.block = torch.nn.ModuleList(
-            [
-                T5Block(
-                    model_dim,
-                    inner_dim,
-                    ff_dim,
-                    num_heads,
-                    relative_attention_bias=(i == 0),
-                    dtype=dtype,
-                    device=device,
-                )
-                for i in range(num_layers)
-            ]
-        )
-        self.final_layer_norm = T5LayerNorm(model_dim, dtype=dtype, device=device)
-
-    def forward(self, input_ids, intermediate_output=None, final_layer_norm_intermediate=True):
-        intermediate = None
-        x = self.embed_tokens(input_ids)
-        past_bias = None
-        for i, l in enumerate(self.block):
-            x, past_bias = l(x, past_bias)
-            if i == intermediate_output:
-                intermediate = x.clone()
-        x = self.final_layer_norm(x)
-        if intermediate is not None and final_layer_norm_intermediate:
-            intermediate = self.final_layer_norm(intermediate)
-        return x, intermediate
-
-
-class T5(torch.nn.Module):
-    def __init__(self, config_dict, dtype, device):
-        super().__init__()
-        self.num_layers = config_dict["num_layers"]
-        self.encoder = T5Stack(
-            self.num_layers,
-            config_dict["d_model"],
-            config_dict["d_model"],
-            config_dict["d_ff"],
-            config_dict["num_heads"],
-            config_dict["vocab_size"],
-            dtype,
-            device,
-        )
-        self.dtype = dtype
-
-    def get_input_embeddings(self):
-        return self.encoder.embed_tokens
-
-    def set_input_embeddings(self, embeddings):
-        self.encoder.embed_tokens = embeddings
-
-    def forward(self, *args, **kwargs):
-        return self.encoder(*args, **kwargs)

invokeai/backend/sd3/sd3_impls.py

@@ -1,609 +0,0 @@
-# This file was originally copied from:
-# https://github.com/Stability-AI/sd3.5/blob/19bf11c4e1e37324c5aa5a61f010d4127848a09c/sd3_impls.py
-
-
-### Impls of the SD3 core diffusion model and VAE
-
-import math
-import re
-
-import einops
-import torch
-from PIL import Image
-from tqdm import tqdm
-
-from invokeai.backend.sd3.mmditx import MMDiTX
-
-#################################################################################################
-### MMDiT Model Wrapping
-#################################################################################################
-
-
-class ModelSamplingDiscreteFlow(torch.nn.Module):
-    """Helper for sampler scheduling (ie timestep/sigma calculations) for Discrete Flow models"""
-
-    def __init__(self, shift: float = 1.0):
-        super().__init__()
-        self.shift = shift
-        timesteps = 1000
-        ts = self.sigma(torch.arange(1, timesteps + 1, 1))
-        self.register_buffer("sigmas", ts)
-
-    @property
-    def sigma_min(self):
-        return self.sigmas[0]
-
-    @property
-    def sigma_max(self):
-        return self.sigmas[-1]
-
-    def timestep(self, sigma: torch.Tensor) -> torch.Tensor:
-        return sigma * 1000
-
-    def sigma(self, timestep: torch.Tensor):
-        timestep = timestep / 1000.0
-        if self.shift == 1.0:
-            return timestep
-        return self.shift * timestep / (1 + (self.shift - 1) * timestep)
-
-    def calculate_denoised(
-        self, sigma: torch.Tensor, model_output: torch.Tensor, model_input: torch.Tensor
-    ) -> torch.Tensor:
-        sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1))
-        return model_input - model_output * sigma
-
-    def noise_scaling(self, sigma, noise, latent_image, max_denoise=False):
-        return sigma * noise + (1.0 - sigma) * latent_image
-
-
-class BaseModel(torch.nn.Module):
-    """Wrapper around the core MM-DiT model"""
-
-    def __init__(
-        self,
-        shift=1.0,
-        device=None,
-        dtype=torch.float32,
-        file=None,
-        prefix="",
-        verbose=False,
-    ):
-        super().__init__()
-        # Important configuration values can be quickly determined by checking shapes in the source file
-        # Some of these will vary between models (eg 2B vs 8B primarily differ in their depth, but also other details change)
-        patch_size = file.get_tensor(f"{prefix}x_embedder.proj.weight").shape[2]
-        depth = file.get_tensor(f"{prefix}x_embedder.proj.weight").shape[0] // 64
-        num_patches = file.get_tensor(f"{prefix}pos_embed").shape[1]
-        pos_embed_max_size = round(math.sqrt(num_patches))
-        adm_in_channels = file.get_tensor(f"{prefix}y_embedder.mlp.0.weight").shape[1]
-        context_shape = file.get_tensor(f"{prefix}context_embedder.weight").shape
-        qk_norm = "rms" if f"{prefix}joint_blocks.0.context_block.attn.ln_k.weight" in file.keys() else None
-        x_block_self_attn_layers = sorted(
-            [
-                int(key.split(".x_block.attn2.ln_k.weight")[0].split(".")[-1])
-                for key in list(filter(re.compile(".*.x_block.attn2.ln_k.weight").match, file.keys()))
-            ]
-        )
-
-        context_embedder_config = {
-            "target": "torch.nn.Linear",
-            "params": {
-                "in_features": context_shape[1],
-                "out_features": context_shape[0],
-            },
-        }
-        self.diffusion_model = MMDiTX(
-            input_size=None,
-            pos_embed_scaling_factor=None,
-            pos_embed_offset=None,
-            pos_embed_max_size=pos_embed_max_size,
-            patch_size=patch_size,
-            in_channels=16,
-            depth=depth,
-            num_patches=num_patches,
-            adm_in_channels=adm_in_channels,
-            context_embedder_config=context_embedder_config,
-            qk_norm=qk_norm,
-            x_block_self_attn_layers=x_block_self_attn_layers,
-            device=device,
-            dtype=dtype,
-            verbose=verbose,
-        )
-        self.model_sampling = ModelSamplingDiscreteFlow(shift=shift)
-
-    def apply_model(
-        self, x: torch.Tensor, sigma: float, c_crossattn: torch.Tensor | None = None, y: torch.Tensor | None = None
-    ):
-        dtype = self.get_dtype()
-        timestep = self.model_sampling.timestep(sigma).float()
-        model_output = self.diffusion_model(x.to(dtype), timestep, context=c_crossattn.to(dtype), y=y.to(dtype)).float()
-        return self.model_sampling.calculate_denoised(sigma, model_output, x)
-
-    def forward(self, *args, **kwargs):
-        return self.apply_model(*args, **kwargs)
-
-    def get_dtype(self):
-        return self.diffusion_model.dtype
-
-
-class CFGDenoiser(torch.nn.Module):
-    """Helper for applying CFG Scaling to diffusion outputs"""
-
-    def __init__(self, model):
-        super().__init__()
-        self.model = model
-
-    def forward(self, x, timestep, cond, uncond, cond_scale):
-        # Run cond and uncond in a batch together
-        batched = self.model.apply_model(
-            torch.cat([x, x]),
-            torch.cat([timestep, timestep]),
-            c_crossattn=torch.cat([cond["c_crossattn"], uncond["c_crossattn"]]),
-            y=torch.cat([cond["y"], uncond["y"]]),
-        )
-        # Then split and apply CFG Scaling
-        pos_out, neg_out = batched.chunk(2)
-        scaled = neg_out + (pos_out - neg_out) * cond_scale
-        return scaled
-
-
-class SD3LatentFormat:
-    """Latents are slightly shifted from center - this class must be called after VAE Decode to correct for the shift"""
-
-    def __init__(self):
-        self.scale_factor = 1.5305
-        self.shift_factor = 0.0609
-
-    def process_in(self, latent):
-        return (latent - self.shift_factor) * self.scale_factor
-
-    def process_out(self, latent):
-        return (latent / self.scale_factor) + self.shift_factor
-
-    def decode_latent_to_preview(self, x0):
-        """Quick RGB approximate preview of sd3 latents"""
-        factors = torch.tensor(
-            [
-                [-0.0645, 0.0177, 0.1052],
-                [0.0028, 0.0312, 0.0650],
-                [0.1848, 0.0762, 0.0360],
-                [0.0944, 0.0360, 0.0889],
-                [0.0897, 0.0506, -0.0364],
-                [-0.0020, 0.1203, 0.0284],
-                [0.0855, 0.0118, 0.0283],
-                [-0.0539, 0.0658, 0.1047],
-                [-0.0057, 0.0116, 0.0700],
-                [-0.0412, 0.0281, -0.0039],
-                [0.1106, 0.1171, 0.1220],
-                [-0.0248, 0.0682, -0.0481],
-                [0.0815, 0.0846, 0.1207],
-                [-0.0120, -0.0055, -0.0867],
-                [-0.0749, -0.0634, -0.0456],
-                [-0.1418, -0.1457, -0.1259],
-            ],
-            device="cpu",
-        )
-        latent_image = x0[0].permute(1, 2, 0).cpu() @ factors
-
-        latents_ubyte = (
-            ((latent_image + 1) / 2)
-            .clamp(0, 1)  # change scale from -1..1 to 0..1
-            .mul(0xFF)  # to 0..255
-            .byte()
-        ).cpu()
-
-        return Image.fromarray(latents_ubyte.numpy())
-
-
-#################################################################################################
-### Samplers
-#################################################################################################
-
-
-def append_dims(x, target_dims):
-    """Appends dimensions to the end of a tensor until it has target_dims dimensions."""
-    dims_to_append = target_dims - x.ndim
-    return x[(...,) + (None,) * dims_to_append]
-
-
-def to_d(x, sigma, denoised):
-    """Converts a denoiser output to a Karras ODE derivative."""
-    return (x - denoised) / append_dims(sigma, x.ndim)
-
-
-@torch.no_grad()
-@torch.autocast("cuda", dtype=torch.float16)
-def sample_euler(model, x, sigmas, extra_args=None):
-    """Implements Algorithm 2 (Euler steps) from Karras et al. (2022)."""
-    extra_args = {} if extra_args is None else extra_args
-    s_in = x.new_ones([x.shape[0]])
-    for i in tqdm(range(len(sigmas) - 1)):
-        sigma_hat = sigmas[i]
-        denoised = model(x, sigma_hat * s_in, **extra_args)
-        d = to_d(x, sigma_hat, denoised)
-        dt = sigmas[i + 1] - sigma_hat
-        # Euler method
-        x = x + d * dt
-    return x
-
-
-@torch.no_grad()
-@torch.autocast("cuda", dtype=torch.float16)
-def sample_dpmpp_2m(model, x, sigmas, extra_args=None):
-    """DPM-Solver++(2M)."""
-    extra_args = {} if extra_args is None else extra_args
-    s_in = x.new_ones([x.shape[0]])
-    sigma_fn = lambda t: t.neg().exp()
-    t_fn = lambda sigma: sigma.log().neg()
-    old_denoised = None
-    for i in tqdm(range(len(sigmas) - 1)):
-        denoised = model(x, sigmas[i] * s_in, **extra_args)
-        t, t_next = t_fn(sigmas[i]), t_fn(sigmas[i + 1])
-        h = t_next - t
-        if old_denoised is None or sigmas[i + 1] == 0:
-            x = (sigma_fn(t_next) / sigma_fn(t)) * x - (-h).expm1() * denoised
-        else:
-            h_last = t - t_fn(sigmas[i - 1])
-            r = h_last / h
-            denoised_d = (1 + 1 / (2 * r)) * denoised - (1 / (2 * r)) * old_denoised
-            x = (sigma_fn(t_next) / sigma_fn(t)) * x - (-h).expm1() * denoised_d
-        old_denoised = denoised
-    return x
-
-
-#################################################################################################
-### VAE
-#################################################################################################
-
-
-def Normalize(in_channels, num_groups=32, dtype=torch.float32, device=None):
-    return torch.nn.GroupNorm(
-        num_groups=num_groups,
-        num_channels=in_channels,
-        eps=1e-6,
-        affine=True,
-        dtype=dtype,
-        device=device,
-    )
-
-
-class ResnetBlock(torch.nn.Module):
-    def __init__(self, *, in_channels, out_channels=None, dtype=torch.float32, device=None):
-        super().__init__()
-        self.in_channels = in_channels
-        out_channels = in_channels if out_channels is None else out_channels
-        self.out_channels = out_channels
-
-        self.norm1 = Normalize(in_channels, dtype=dtype, device=device)
-        self.conv1 = torch.nn.Conv2d(
-            in_channels,
-            out_channels,
-            kernel_size=3,
-            stride=1,
-            padding=1,
-            dtype=dtype,
-            device=device,
-        )
-        self.norm2 = Normalize(out_channels, dtype=dtype, device=device)
-        self.conv2 = torch.nn.Conv2d(
-            out_channels,
-            out_channels,
-            kernel_size=3,
-            stride=1,
-            padding=1,
-            dtype=dtype,
-            device=device,
-        )
-        if self.in_channels != self.out_channels:
-            self.nin_shortcut = torch.nn.Conv2d(
-                in_channels,
-                out_channels,
-                kernel_size=1,
-                stride=1,
-                padding=0,
-                dtype=dtype,
-                device=device,
-            )
-        else:
-            self.nin_shortcut = None
-        self.swish = torch.nn.SiLU(inplace=True)
-
-    def forward(self, x):
-        hidden = x
-        hidden = self.norm1(hidden)
-        hidden = self.swish(hidden)
-        hidden = self.conv1(hidden)
-        hidden = self.norm2(hidden)
-        hidden = self.swish(hidden)
-        hidden = self.conv2(hidden)
-        if self.in_channels != self.out_channels:
-            x = self.nin_shortcut(x)
-        return x + hidden
-
-
-class AttnBlock(torch.nn.Module):
-    def __init__(self, in_channels, dtype=torch.float32, device=None):
-        super().__init__()
-        self.norm = Normalize(in_channels, dtype=dtype, device=device)
-        self.q = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            dtype=dtype,
-            device=device,
-        )
-        self.k = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            dtype=dtype,
-            device=device,
-        )
-        self.v = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            dtype=dtype,
-            device=device,
-        )
-        self.proj_out = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            dtype=dtype,
-            device=device,
-        )
-
-    def forward(self, x):
-        hidden = self.norm(x)
-        q = self.q(hidden)
-        k = self.k(hidden)
-        v = self.v(hidden)
-        b, c, h, w = q.shape
-        q, k, v = map(
-            lambda x: einops.rearrange(x, "b c h w -> b 1 (h w) c").contiguous(),
-            (q, k, v),
-        )
-        hidden = torch.nn.functional.scaled_dot_product_attention(q, k, v)  # scale is dim ** -0.5 per default
-        hidden = einops.rearrange(hidden, "b 1 (h w) c -> b c h w", h=h, w=w, c=c, b=b)
-        hidden = self.proj_out(hidden)
-        return x + hidden
-
-
-class Downsample(torch.nn.Module):
-    def __init__(self, in_channels, dtype=torch.float32, device=None):
-        super().__init__()
-        self.conv = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=3,
-            stride=2,
-            padding=0,
-            dtype=dtype,
-            device=device,
-        )
-
-    def forward(self, x):
-        pad = (0, 1, 0, 1)
-        x = torch.nn.functional.pad(x, pad, mode="constant", value=0)
-        x = self.conv(x)
-        return x
-
-
-class Upsample(torch.nn.Module):
-    def __init__(self, in_channels, dtype=torch.float32, device=None):
-        super().__init__()
-        self.conv = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=3,
-            stride=1,
-            padding=1,
-            dtype=dtype,
-            device=device,
-        )
-
-    def forward(self, x):
-        x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
-        x = self.conv(x)
-        return x
-
-
-class VAEEncoder(torch.nn.Module):
-    def __init__(
-        self,
-        ch=128,
-        ch_mult=(1, 2, 4, 4),
-        num_res_blocks=2,
-        in_channels=3,
-        z_channels=16,
-        dtype=torch.float32,
-        device=None,
-    ):
-        super().__init__()
-        self.num_resolutions = len(ch_mult)
-        self.num_res_blocks = num_res_blocks
-        # downsampling
-        self.conv_in = torch.nn.Conv2d(
-            in_channels,
-            ch,
-            kernel_size=3,
-            stride=1,
-            padding=1,
-            dtype=dtype,
-            device=device,
-        )
-        in_ch_mult = (1,) + tuple(ch_mult)
-        self.in_ch_mult = in_ch_mult
-        self.down = torch.nn.ModuleList()
-        for i_level in range(self.num_resolutions):
-            block = torch.nn.ModuleList()
-            attn = torch.nn.ModuleList()
-            block_in = ch * in_ch_mult[i_level]
-            block_out = ch * ch_mult[i_level]
-            for i_block in range(num_res_blocks):
-                block.append(
-                    ResnetBlock(
-                        in_channels=block_in,
-                        out_channels=block_out,
-                        dtype=dtype,
-                        device=device,
-                    )
-                )
-                block_in = block_out
-            down = torch.nn.Module()
-            down.block = block
-            down.attn = attn
-            if i_level != self.num_resolutions - 1:
-                down.downsample = Downsample(block_in, dtype=dtype, device=device)
-            self.down.append(down)
-        # middle
-        self.mid = torch.nn.Module()
-        self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in, dtype=dtype, device=device)
-        self.mid.attn_1 = AttnBlock(block_in, dtype=dtype, device=device)
-        self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in, dtype=dtype, device=device)
-        # end
-        self.norm_out = Normalize(block_in, dtype=dtype, device=device)
-        self.conv_out = torch.nn.Conv2d(
-            block_in,
-            2 * z_channels,
-            kernel_size=3,
-            stride=1,
-            padding=1,
-            dtype=dtype,
-            device=device,
-        )
-        self.swish = torch.nn.SiLU(inplace=True)
-
-    def forward(self, x):
-        # downsampling
-        hs = [self.conv_in(x)]
-        for i_level in range(self.num_resolutions):
-            for i_block in range(self.num_res_blocks):
-                h = self.down[i_level].block[i_block](hs[-1])
-                hs.append(h)
-            if i_level != self.num_resolutions - 1:
-                hs.append(self.down[i_level].downsample(hs[-1]))
-        # middle
-        h = hs[-1]
-        h = self.mid.block_1(h)
-        h = self.mid.attn_1(h)
-        h = self.mid.block_2(h)
-        # end
-        h = self.norm_out(h)
-        h = self.swish(h)
-        h = self.conv_out(h)
-        return h
-
-
-class VAEDecoder(torch.nn.Module):
-    def __init__(
-        self,
-        ch=128,
-        out_ch=3,
-        ch_mult=(1, 2, 4, 4),
-        num_res_blocks=2,
-        resolution=256,
-        z_channels=16,
-        dtype=torch.float32,
-        device=None,
-    ):
-        super().__init__()
-        self.num_resolutions = len(ch_mult)
-        self.num_res_blocks = num_res_blocks
-        block_in = ch * ch_mult[self.num_resolutions - 1]
-        curr_res = resolution // 2 ** (self.num_resolutions - 1)
-        # z to block_in
-        self.conv_in = torch.nn.Conv2d(
-            z_channels,
-            block_in,
-            kernel_size=3,
-            stride=1,
-            padding=1,
-            dtype=dtype,
-            device=device,
-        )
-        # middle
-        self.mid = torch.nn.Module()
-        self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in, dtype=dtype, device=device)
-        self.mid.attn_1 = AttnBlock(block_in, dtype=dtype, device=device)
-        self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in, dtype=dtype, device=device)
-        # upsampling
-        self.up = torch.nn.ModuleList()
-        for i_level in reversed(range(self.num_resolutions)):
-            block = torch.nn.ModuleList()
-            block_out = ch * ch_mult[i_level]
-            for i_block in range(self.num_res_blocks + 1):
-                block.append(
-                    ResnetBlock(
-                        in_channels=block_in,
-                        out_channels=block_out,
-                        dtype=dtype,
-                        device=device,
-                    )
-                )
-                block_in = block_out
-            up = torch.nn.Module()
-            up.block = block
-            if i_level != 0:
-                up.upsample = Upsample(block_in, dtype=dtype, device=device)
-                curr_res = curr_res * 2
-            self.up.insert(0, up)  # prepend to get consistent order
-        # end
-        self.norm_out = Normalize(block_in, dtype=dtype, device=device)
-        self.conv_out = torch.nn.Conv2d(
-            block_in,
-            out_ch,
-            kernel_size=3,
-            stride=1,
-            padding=1,
-            dtype=dtype,
-            device=device,
-        )
-        self.swish = torch.nn.SiLU(inplace=True)
-
-    def forward(self, z):
-        # z to block_in
-        hidden = self.conv_in(z)
-        # middle
-        hidden = self.mid.block_1(hidden)
-        hidden = self.mid.attn_1(hidden)
-        hidden = self.mid.block_2(hidden)
-        # upsampling
-        for i_level in reversed(range(self.num_resolutions)):
-            for i_block in range(self.num_res_blocks + 1):
-                hidden = self.up[i_level].block[i_block](hidden)
-            if i_level != 0:
-                hidden = self.up[i_level].upsample(hidden)
-        # end
-        hidden = self.norm_out(hidden)
-        hidden = self.swish(hidden)
-        hidden = self.conv_out(hidden)
-        return hidden
-
-
-class SDVAE(torch.nn.Module):
-    def __init__(self, dtype=torch.float32, device=None):
-        super().__init__()
-        self.encoder = VAEEncoder(dtype=dtype, device=device)
-        self.decoder = VAEDecoder(dtype=dtype, device=device)
-
-    @torch.autocast("cuda", dtype=torch.float16)
-    def decode(self, latent):
-        return self.decoder(latent)
-
-    @torch.autocast("cuda", dtype=torch.float16)
-    def encode(self, image):
-        hidden = self.encoder(image)
-        mean, logvar = torch.chunk(hidden, 2, dim=1)
-        logvar = torch.clamp(logvar, -30.0, 20.0)
-        std = torch.exp(0.5 * logvar)
-        return mean + std * torch.randn_like(mean)

invokeai/backend/sd3/sd3_infer.py

@@ -1,426 +0,0 @@
-# This file was originally copied from:
-# https://github.com/Stability-AI/sd3.5/blob/19bf11c4e1e37324c5aa5a61f010d4127848a09c/sd3_infer.py
-
-# NOTE: Must have folder `models` with the following files:
-# - `clip_g.safetensors` (openclip bigG, same as SDXL)
-# - `clip_l.safetensors` (OpenAI CLIP-L, same as SDXL)
-# - `t5xxl.safetensors` (google T5-v1.1-XXL)
-# - `sd3_medium.safetensors` (or whichever main MMDiT model file)
-# Also can have
-# - `sd3_vae.safetensors` (holds the VAE separately if needed)
-
-import datetime
-import math
-import os
-
-import fire
-import numpy as np
-import sd3_impls
-import torch
-from other_impls import SD3Tokenizer, SDClipModel, SDXLClipG, T5XXLModel
-from PIL import Image
-from safetensors import safe_open
-from sd3_impls import SDVAE, BaseModel, CFGDenoiser, SD3LatentFormat
-from tqdm import tqdm
-
-#################################################################################################
-### Wrappers for model parts
-#################################################################################################
-
-
-def load_into(f, model, prefix, device, dtype=None):
-    """Just a debugging-friendly hack to apply the weights in a safetensors file to the pytorch module."""
-    for key in f.keys():
-        if key.startswith(prefix) and not key.startswith("loss."):
-            path = key[len(prefix) :].split(".")
-            obj = model
-            for p in path:
-                if obj is list:
-                    obj = obj[int(p)]
-                else:
-                    obj = getattr(obj, p, None)
-                    if obj is None:
-                        print(f"Skipping key '{key}' in safetensors file as '{p}' does not exist in python model")
-                        break
-            if obj is None:
-                continue
-            try:
-                tensor = f.get_tensor(key).to(device=device)
-                if dtype is not None:
-                    tensor = tensor.to(dtype=dtype)
-                obj.requires_grad_(False)
-                obj.set_(tensor)
-            except Exception as e:
-                print(f"Failed to load key '{key}' in safetensors file: {e}")
-                raise e
-
-
-CLIPG_CONFIG = {
-    "hidden_act": "gelu",
-    "hidden_size": 1280,
-    "intermediate_size": 5120,
-    "num_attention_heads": 20,
-    "num_hidden_layers": 32,
-}
-
-
-class ClipG:
-    def __init__(self):
-        with safe_open("models/clip_g.safetensors", framework="pt", device="cpu") as f:
-            self.model = SDXLClipG(CLIPG_CONFIG, device="cpu", dtype=torch.float32)
-            load_into(f, self.model.transformer, "", "cpu", torch.float32)
-
-
-CLIPL_CONFIG = {
-    "hidden_act": "quick_gelu",
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "num_attention_heads": 12,
-    "num_hidden_layers": 12,
-}
-
-
-class ClipL:
-    def __init__(self):
-        with safe_open("models/clip_l.safetensors", framework="pt", device="cpu") as f:
-            self.model = SDClipModel(
-                layer="hidden",
-                layer_idx=-2,
-                device="cpu",
-                dtype=torch.float32,
-                layer_norm_hidden_state=False,
-                return_projected_pooled=False,
-                textmodel_json_config=CLIPL_CONFIG,
-            )
-            load_into(f, self.model.transformer, "", "cpu", torch.float32)
-
-
-T5_CONFIG = {
-    "d_ff": 10240,
-    "d_model": 4096,
-    "num_heads": 64,
-    "num_layers": 24,
-    "vocab_size": 32128,
-}
-
-
-class T5XXL:
-    def __init__(self):
-        with safe_open("models/t5xxl.safetensors", framework="pt", device="cpu") as f:
-            self.model = T5XXLModel(T5_CONFIG, device="cpu", dtype=torch.float32)
-            load_into(f, self.model.transformer, "", "cpu", torch.float32)
-
-
-class SD3:
-    def __init__(self, model, shift, verbose=False):
-        with safe_open(model, framework="pt", device="cpu") as f:
-            self.model = BaseModel(
-                shift=shift,
-                file=f,
-                prefix="model.diffusion_model.",
-                device="cpu",
-                dtype=torch.float16,
-                verbose=verbose,
-            ).eval()
-            load_into(f, self.model, "model.", "cpu", torch.float16)
-
-
-class VAE:
-    def __init__(self, model):
-        with safe_open(model, framework="pt", device="cpu") as f:
-            self.model = SDVAE(device="cpu", dtype=torch.float16).eval().cpu()
-            prefix = ""
-            if any(k.startswith("first_stage_model.") for k in f.keys()):
-                prefix = "first_stage_model."
-            load_into(f, self.model, prefix, "cpu", torch.float16)
-
-
-#################################################################################################
-### Main inference logic
-#################################################################################################
-
-
-# Note: Sigma shift value, publicly released models use 3.0
-SHIFT = 3.0
-# Naturally, adjust to the width/height of the model you have
-WIDTH = 1024
-HEIGHT = 1024
-# Pick your prompt
-PROMPT = "a photo of a cat"
-# Most models prefer the range of 4-5, but still work well around 7
-CFG_SCALE = 4.5
-# Different models want different step counts but most will be good at 50, albeit that's slow to run
-# sd3_medium is quite decent at 28 steps
-STEPS = 40
-# Seed
-SEED = 23
-# SEEDTYPE = "fixed"
-SEEDTYPE = "rand"
-# SEEDTYPE = "roll"
-# Actual model file path
-# MODEL = "models/sd3_medium.safetensors"
-# MODEL = "models/sd3.5_large_turbo.safetensors"
-MODEL = "models/sd3.5_large.safetensors"
-# VAE model file path, or set None to use the same model file
-VAEFile = None  # "models/sd3_vae.safetensors"
-# Optional init image file path
-INIT_IMAGE = None
-# If init_image is given, this is the percentage of denoising steps to run (1.0 = full denoise, 0.0 = no denoise at all)
-DENOISE = 0.6
-# Output file path
-OUTDIR = "outputs"
-# SAMPLER
-# SAMPLER = "euler"
-SAMPLER = "dpmpp_2m"
-
-
-class SD3Inferencer:
-    def print(self, txt):
-        if self.verbose:
-            print(txt)
-
-    def load(self, model=MODEL, vae=VAEFile, shift=SHIFT, verbose=False):
-        self.verbose = verbose
-        print("Loading tokenizers...")
-        # NOTE: if you need a reference impl for a high performance CLIP tokenizer instead of just using the HF transformers one,
-        # check https://github.com/Stability-AI/StableSwarmUI/blob/master/src/Utils/CliplikeTokenizer.cs
-        # (T5 tokenizer is different though)
-        self.tokenizer = SD3Tokenizer()
-        print("Loading OpenAI CLIP L...")
-        self.clip_l = ClipL()
-        print("Loading OpenCLIP bigG...")
-        self.clip_g = ClipG()
-        print("Loading Google T5-v1-XXL...")
-        self.t5xxl = T5XXL()
-        print(f"Loading SD3 model {os.path.basename(model)}...")
-        self.sd3 = SD3(model, shift, verbose)
-        print("Loading VAE model...")
-        self.vae = VAE(vae or model)
-        print("Models loaded.")
-
-    def get_empty_latent(self, width, height):
-        self.print("Prep an empty latent...")
-        return torch.ones(1, 16, height // 8, width // 8, device="cpu") * 0.0609
-
-    def get_sigmas(self, sampling, steps):
-        start = sampling.timestep(sampling.sigma_max)
-        end = sampling.timestep(sampling.sigma_min)
-        timesteps = torch.linspace(start, end, steps)
-        sigs = []
-        for x in range(len(timesteps)):
-            ts = timesteps[x]
-            sigs.append(sampling.sigma(ts))
-        sigs += [0.0]
-        return torch.FloatTensor(sigs)
-
-    def get_noise(self, seed, latent):
-        generator = torch.manual_seed(seed)
-        self.print(f"dtype = {latent.dtype}, layout = {latent.layout}, device = {latent.device}")
-        return torch.randn(
-            latent.size(),
-            dtype=torch.float32,
-            layout=latent.layout,
-            generator=generator,
-            device="cpu",
-        ).to(latent.dtype)
-
-    def get_cond(self, prompt):
-        self.print("Encode prompt...")
-        tokens = self.tokenizer.tokenize_with_weights(prompt)
-        l_out, l_pooled = self.clip_l.model.encode_token_weights(tokens["l"])
-        g_out, g_pooled = self.clip_g.model.encode_token_weights(tokens["g"])
-        t5_out, t5_pooled = self.t5xxl.model.encode_token_weights(tokens["t5xxl"])
-        lg_out = torch.cat([l_out, g_out], dim=-1)
-        lg_out = torch.nn.functional.pad(lg_out, (0, 4096 - lg_out.shape[-1]))
-        return torch.cat([lg_out, t5_out], dim=-2), torch.cat((l_pooled, g_pooled), dim=-1)
-
-    def max_denoise(self, sigmas):
-        max_sigma = float(self.sd3.model.model_sampling.sigma_max)
-        sigma = float(sigmas[0])
-        return math.isclose(max_sigma, sigma, rel_tol=1e-05) or sigma > max_sigma
-
-    def fix_cond(self, cond):
-        cond, pooled = (cond[0].half().cuda(), cond[1].half().cuda())
-        return {"c_crossattn": cond, "y": pooled}
-
-    def do_sampling(
-        self,
-        latent,
-        seed,
-        conditioning,
-        neg_cond,
-        steps,
-        cfg_scale,
-        sampler="dpmpp_2m",
-        denoise=1.0,
-    ) -> torch.Tensor:
-        self.print("Sampling...")
-        latent = latent.half().cuda()
-        self.sd3.model = self.sd3.model.cuda()
-        noise = self.get_noise(seed, latent).cuda()
-        sigmas = self.get_sigmas(self.sd3.model.model_sampling, steps).cuda()
-        sigmas = sigmas[int(steps * (1 - denoise)) :]
-        conditioning = self.fix_cond(conditioning)
-        neg_cond = self.fix_cond(neg_cond)
-        extra_args = {"cond": conditioning, "uncond": neg_cond, "cond_scale": cfg_scale}
-        noise_scaled = self.sd3.model.model_sampling.noise_scaling(sigmas[0], noise, latent, self.max_denoise(sigmas))
-        sample_fn = getattr(sd3_impls, f"sample_{sampler}")
-        latent = sample_fn(CFGDenoiser(self.sd3.model), noise_scaled, sigmas, extra_args=extra_args)
-        latent = SD3LatentFormat().process_out(latent)
-        self.sd3.model = self.sd3.model.cpu()
-        self.print("Sampling done")
-        return latent
-
-    def vae_encode(self, image) -> torch.Tensor:
-        self.print("Encoding image to latent...")
-        image = image.convert("RGB")
-        image_np = np.array(image).astype(np.float32) / 255.0
-        image_np = np.moveaxis(image_np, 2, 0)
-        batch_images = np.expand_dims(image_np, axis=0).repeat(1, axis=0)
-        image_torch = torch.from_numpy(batch_images)
-        image_torch = 2.0 * image_torch - 1.0
-        image_torch = image_torch.cuda()
-        self.vae.model = self.vae.model.cuda()
-        latent = self.vae.model.encode(image_torch).cpu()
-        self.vae.model = self.vae.model.cpu()
-        self.print("Encoded")
-        return latent
-
-    def vae_decode(self, latent) -> Image.Image:
-        self.print("Decoding latent to image...")
-        latent = latent.cuda()
-        self.vae.model = self.vae.model.cuda()
-        image = self.vae.model.decode(latent)
-        image = image.float()
-        self.vae.model = self.vae.model.cpu()
-        image = torch.clamp((image + 1.0) / 2.0, min=0.0, max=1.0)[0]
-        decoded_np = 255.0 * np.moveaxis(image.cpu().numpy(), 0, 2)
-        decoded_np = decoded_np.astype(np.uint8)
-        out_image = Image.fromarray(decoded_np)
-        self.print("Decoded")
-        return out_image
-
-    def gen_image(
-        self,
-        prompts=[PROMPT],
-        width=WIDTH,
-        height=HEIGHT,
-        steps=STEPS,
-        cfg_scale=CFG_SCALE,
-        sampler=SAMPLER,
-        seed=SEED,
-        seed_type=SEEDTYPE,
-        out_dir=OUTDIR,
-        init_image=INIT_IMAGE,
-        denoise=DENOISE,
-    ):
-        latent = self.get_empty_latent(width, height)
-        if init_image:
-            image_data = Image.open(init_image)
-            image_data = image_data.resize((width, height), Image.LANCZOS)
-            latent = self.vae_encode(image_data)
-            latent = SD3LatentFormat().process_in(latent)
-        neg_cond = self.get_cond("")
-        seed_num = None
-        pbar = tqdm(enumerate(prompts), total=len(prompts), position=0, leave=True)
-        for i, prompt in pbar:
-            if seed_type == "roll":
-                seed_num = seed if seed_num is None else seed_num + 1
-            elif seed_type == "rand":
-                seed_num = torch.randint(0, 100000, (1,)).item()
-            else:  # fixed
-                seed_num = seed
-            conditioning = self.get_cond(prompt)
-            sampled_latent = self.do_sampling(
-                latent,
-                seed_num,
-                conditioning,
-                neg_cond,
-                steps,
-                cfg_scale,
-                sampler,
-                denoise if init_image else 1.0,
-            )
-            image = self.vae_decode(sampled_latent)
-            save_path = os.path.join(out_dir, f"{i:06d}.png")
-            self.print(f"Will save to {save_path}")
-            image.save(save_path)
-            self.print("Done")
-
-
-CONFIGS = {
-    "sd3_medium": {
-        "shift": 1.0,
-        "cfg": 5.0,
-        "steps": 50,
-        "sampler": "dpmpp_2m",
-    },
-    "sd3.5_large": {
-        "shift": 3.0,
-        "cfg": 4.5,
-        "steps": 40,
-        "sampler": "dpmpp_2m",
-    },
-    "sd3.5_large_turbo": {"shift": 3.0, "cfg": 1.0, "steps": 4, "sampler": "euler"},
-}
-
-
-@torch.no_grad()
-def main(
-    prompt=PROMPT,
-    model=MODEL,
-    out_dir=OUTDIR,
-    postfix=None,
-    seed=SEED,
-    seed_type=SEEDTYPE,
-    sampler=None,
-    steps=None,
-    cfg=None,
-    shift=None,
-    width=WIDTH,
-    height=HEIGHT,
-    vae=VAEFile,
-    init_image=INIT_IMAGE,
-    denoise=DENOISE,
-    verbose=False,
-):
-    steps = steps or CONFIGS[os.path.splitext(os.path.basename(model))[0]]["steps"]
-    cfg = cfg or CONFIGS[os.path.splitext(os.path.basename(model))[0]]["cfg"]
-    shift = shift or CONFIGS[os.path.splitext(os.path.basename(model))[0]]["shift"]
-    sampler = sampler or CONFIGS[os.path.splitext(os.path.basename(model))[0]]["sampler"]
-
-    inferencer = SD3Inferencer()
-    inferencer.load(model, vae, shift, verbose)
-
-    if isinstance(prompt, str):
-        if os.path.splitext(prompt)[-1] == ".txt":
-            with open(prompt, "r") as f:
-                prompts = [l.strip() for l in f.readlines()]
-        else:
-            prompts = [prompt]
-
-    out_dir = os.path.join(
-        out_dir,
-        os.path.splitext(os.path.basename(model))[0],
-        os.path.splitext(os.path.basename(prompt))[0][:50]
-        + (postfix or datetime.datetime.now().strftime("_%Y-%m-%dT%H-%M-%S")),
-    )
-    print(f"Saving images to {out_dir}")
-    os.makedirs(out_dir, exist_ok=False)
-
-    inferencer.gen_image(
-        prompts,
-        width,
-        height,
-        steps,
-        cfg,
-        sampler,
-        seed,
-        seed_type,
-        out_dir,
-        init_image,
-        denoise,
-    )
-
-
-fire.Fire(main)

invokeai/backend/sd3/sd3_mmditx.py

@@ -1,72 +0,0 @@
-from dataclasses import dataclass
-from typing import Literal, TypedDict
-
-import torch
-
-from invokeai.backend.sd3.mmditx import MMDiTX
-from invokeai.backend.sd3.sd3_impls import ModelSamplingDiscreteFlow
-
-
-class ContextEmbedderConfig(TypedDict):
-    target: Literal["torch.nn.Linear"]
-    params: dict[str, int]
-
-
-@dataclass
-class Sd3MMDiTXParams:
-    patch_size: int
-    depth: int
-    num_patches: int
-    pos_embed_max_size: int
-    adm_in_channels: int
-    context_shape: tuple[int, int]
-    qk_norm: Literal["rms", None]
-    x_block_self_attn_layers: list[int]
-    context_embedder_config: ContextEmbedderConfig
-
-
-class Sd3MMDiTX(torch.nn.Module):
-    """This class is based closely on
-    https://github.com/Stability-AI/sd3.5/blob/19bf11c4e1e37324c5aa5a61f010d4127848a09c/sd3_impls.py#L53
-    but has more standard model loading semantics.
-    """
-
-    def __init__(
-        self,
-        params: Sd3MMDiTXParams,
-        shift: float = 1.0,
-        device: torch.device | None = None,
-        dtype: torch.dtype | None = None,
-        verbose: bool = False,
-    ):
-        super().__init__()
-        self.diffusion_model = MMDiTX(
-            input_size=None,
-            pos_embed_scaling_factor=None,
-            pos_embed_offset=None,
-            pos_embed_max_size=params.pos_embed_max_size,
-            patch_size=params.patch_size,
-            in_channels=16,
-            depth=params.depth,
-            num_patches=params.num_patches,
-            adm_in_channels=params.adm_in_channels,
-            context_embedder_config=params.context_embedder_config,
-            qk_norm=params.qk_norm,
-            x_block_self_attn_layers=params.x_block_self_attn_layers,
-            device=device,
-            dtype=dtype,
-            verbose=verbose,
-        )
-        self.model_sampling = ModelSamplingDiscreteFlow(shift=shift)
-
-    def apply_model(self, x: torch.Tensor, sigma: torch.Tensor, c_crossattn: torch.Tensor, y: torch.Tensor):
-        dtype = self.get_dtype()
-        timestep = self.model_sampling.timestep(sigma).float()
-        model_output = self.diffusion_model(x.to(dtype), timestep, context=c_crossattn.to(dtype), y=y.to(dtype)).float()
-        return self.model_sampling.calculate_denoised(sigma, model_output, x)
-
-    def forward(self, x: torch.Tensor, sigma: float, c_crossattn: torch.Tensor, y: torch.Tensor):
-        return self.apply_model(x=x, sigma=sigma, c_crossattn=c_crossattn, y=y)
-
-    def get_dtype(self):
-        return self.diffusion_model.dtype

invokeai/backend/sd3/sd3_state_dict_utils.py

@@ -1,70 +0,0 @@
-import math
-import re
-from typing import Any, Dict
-
-from invokeai.backend.sd3.sd3_mmditx import ContextEmbedderConfig, Sd3MMDiTXParams
-
-
-def is_sd3_checkpoint(sd: Dict[str, Any]) -> bool:
-    """Is the state dict for an SD3 checkpoint like this one?:
-    https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/sd3.5_large.safetensors
-
-    Note that this checkpoint format contains both the VAE and the MMDiTX 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 a SD3 checkpoint.
-    expected_keys = {
-        # VAE decoder and encoder keys.
-        "first_stage_model.decoder.conv_in.bias",
-        "first_stage_model.decoder.conv_in.weight",
-        "first_stage_model.encoder.conv_in.bias",
-        "first_stage_model.encoder.conv_in.weight",
-        # MMDiTX keys.
-        "model.diffusion_model.final_layer.linear.bias",
-        "model.diffusion_model.final_layer.linear.weight",
-        "model.diffusion_model.joint_blocks.0.context_block.attn.ln_k.weight",
-        "model.diffusion_model.joint_blocks.0.context_block.attn.ln_q.weight",
-    }
-
-    return expected_keys.issubset(sd.keys())
-
-
-def infer_sd3_mmditx_params(sd: Dict[str, Any], prefix: str = "model.diffusion_model.") -> Sd3MMDiTXParams:
-    """Infer the MMDiTX model parameters from the state dict.
-
-    This logic is based on:
-    https://github.com/Stability-AI/sd3.5/blob/19bf11c4e1e37324c5aa5a61f010d4127848a09c/sd3_impls.py#L68-L88
-    """
-    patch_size = sd[f"{prefix}x_embedder.proj.weight"].shape[2]
-    depth = sd[f"{prefix}x_embedder.proj.weight"].shape[0] // 64
-    num_patches = sd[f"{prefix}pos_embed"].shape[1]
-    pos_embed_max_size = round(math.sqrt(num_patches))
-    adm_in_channels = sd[f"{prefix}y_embedder.mlp.0.weight"].shape[1]
-    context_shape = sd[f"{prefix}context_embedder.weight"].shape
-    qk_norm = "rms" if f"{prefix}joint_blocks.0.context_block.attn.ln_k.weight" in sd else None
-    x_block_self_attn_layers = sorted(
-        [
-            int(key.split(".x_block.attn2.ln_k.weight")[0].split(".")[-1])
-            for key in list(filter(re.compile(".*.x_block.attn2.ln_k.weight").match, sd.keys()))
-        ]
-    )
-
-    context_embedder_config: ContextEmbedderConfig = {
-        "target": "torch.nn.Linear",
-        "params": {
-            "in_features": context_shape[1],
-            "out_features": context_shape[0],
-        },
-    }
-    return Sd3MMDiTXParams(
-        patch_size=patch_size,
-        depth=depth,
-        num_patches=num_patches,
-        pos_embed_max_size=pos_embed_max_size,
-        adm_in_channels=adm_in_channels,
-        context_shape=context_shape,
-        qk_norm=qk_norm,
-        x_block_self_attn_layers=x_block_self_attn_layers,
-        context_embedder_config=context_embedder_config,
-    )

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -499,6 +499,22 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
                     for idx, value in enumerate(single_t2i_adapter_data.adapter_state):
                         accum_adapter_state[idx] += value * t2i_adapter_weight
 
+            # Hack: force compatibility with irregular resolutions by padding the feature map with zeros
+            for idx, tensor in enumerate(accum_adapter_state):
+                # The tensor size is supposed to be some integer downscale factor of the latents size.
+                # Internally, the unet will pad the latents before downscaling between levels when it is no longer divisible by its downscale factor.
+                # If the latent size does not scale down evenly, we need to pad the tensor so that it matches the the downscaled padded latents later on.
+                scale_factor = latents.size()[-1] // tensor.size()[-1]
+                required_padding_width = math.ceil(latents.size()[-1] / scale_factor) - tensor.size()[-1]
+                required_padding_height = math.ceil(latents.size()[-2] / scale_factor) - tensor.size()[-2]
+                tensor = torch.nn.functional.pad(
+                    tensor,
+                    (0, required_padding_width, 0, required_padding_height, 0, 0, 0, 0),
+                    mode="constant",
+                    value=0,
+                )
+                accum_adapter_state[idx] = tensor
+
             down_intrablock_additional_residuals = accum_adapter_state
 
         # Handle inpainting models.

invokeai/backend/stable_diffusion/diffusion/conditioning_data.py

@@ -49,9 +49,32 @@ class FLUXConditioningInfo:
         return self
 
 
+@dataclass
+class SD3ConditioningInfo:
+    clip_l_pooled_embeds: torch.Tensor
+    clip_l_embeds: torch.Tensor
+    clip_g_pooled_embeds: torch.Tensor
+    clip_g_embeds: torch.Tensor
+    t5_embeds: torch.Tensor | None
+
+    def to(self, device: torch.device | None = None, dtype: torch.dtype | None = None):
+        self.clip_l_pooled_embeds = self.clip_l_pooled_embeds.to(device=device, dtype=dtype)
+        self.clip_l_embeds = self.clip_l_embeds.to(device=device, dtype=dtype)
+        self.clip_g_pooled_embeds = self.clip_g_pooled_embeds.to(device=device, dtype=dtype)
+        self.clip_g_embeds = self.clip_g_embeds.to(device=device, dtype=dtype)
+        if self.t5_embeds is not None:
+            self.t5_embeds = self.t5_embeds.to(device=device, dtype=dtype)
+        return self
+
+
 @dataclass
 class ConditioningFieldData:
-    conditionings: List[BasicConditioningInfo] | List[SDXLConditioningInfo] | List[FLUXConditioningInfo]
+    conditionings: (
+        List[BasicConditioningInfo]
+        | List[SDXLConditioningInfo]
+        | List[FLUXConditioningInfo]
+        | List[SD3ConditioningInfo]
+    )
 
 
 @dataclass

invokeai/backend/stable_diffusion/extensions/preview.py

@@ -33,7 +33,7 @@ class PreviewExt(ExtensionBase):
     def initial_preview(self, ctx: DenoiseContext):
         self.callback(
             PipelineIntermediateState(
-                step=-1,
+                step=0,
                 order=ctx.scheduler.order,
                 total_steps=len(ctx.inputs.timesteps),
                 timestep=int(ctx.scheduler.config.num_train_timesteps),  # TODO: is there any code which uses it?

invokeai/backend/util/hotfixes.py

@@ -3,7 +3,7 @@ from typing import Any, Dict, List, Optional, Tuple, Union
 import diffusers
 import torch
 from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.loaders import FromOriginalControlNetMixin
+from diffusers.loaders.single_file_model import FromOriginalModelMixin
 from diffusers.models.attention_processor import AttentionProcessor, AttnProcessor
 from diffusers.models.controlnet import ControlNetConditioningEmbedding, ControlNetOutput, zero_module
 from diffusers.models.embeddings import (
@@ -32,7 +32,9 @@ from invokeai.backend.util.logging import InvokeAILogger
 logger = InvokeAILogger.get_logger(__name__)
 
 
-class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlNetMixin):
+# NOTE(ryand): I'm not the origina author of this code, but for future reference, it appears that this class was copied
+# from diffusers in order to add support for the encoder_attention_mask argument.
+class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalModelMixin):
     """
     A ControlNet model.
 

invokeai/frontend/web/knip.ts

@@ -9,6 +9,7 @@ const config: KnipConfig = {
     'src/services/api/schema.ts',
     'src/features/nodes/types/v1/**',
     'src/features/nodes/types/v2/**',
+    'src/features/parameters/types/parameterSchemas.ts',
     // TODO(psyche): maybe we can clean up these utils after canvas v2 release
     'src/features/controlLayers/konva/util.ts',
     // TODO(psyche): restore HRF functionality?

invokeai/frontend/web/package.json

@@ -52,13 +52,13 @@
     }
   },
   "dependencies": {
+    "@atlaskit/pragmatic-drag-and-drop": "^1.4.0",
+    "@atlaskit/pragmatic-drag-and-drop-auto-scroll": "^1.4.0",
+    "@atlaskit/pragmatic-drag-and-drop-hitbox": "^1.0.3",
     "@dagrejs/dagre": "^1.1.4",
     "@dagrejs/graphlib": "^2.2.4",
-    "@dnd-kit/core": "^6.1.0",
-    "@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",

invokeai/frontend/web/pnpm-lock.yaml

@@ -5,27 +5,27 @@ settings:
   excludeLinksFromLockfile: false
 
 dependencies:
+  '@atlaskit/pragmatic-drag-and-drop':
+    specifier: ^1.4.0
+    version: 1.4.0
+  '@atlaskit/pragmatic-drag-and-drop-auto-scroll':
+    specifier: ^1.4.0
+    version: 1.4.0
+  '@atlaskit/pragmatic-drag-and-drop-hitbox':
+    specifier: ^1.0.3
+    version: 1.0.3
   '@dagrejs/dagre':
     specifier: ^1.1.4
     version: 1.1.4
   '@dagrejs/graphlib':
     specifier: ^2.2.4
     version: 2.2.4
-  '@dnd-kit/core':
-    specifier: ^6.1.0
-    version: 6.1.0(react-dom@18.3.1)(react@18.3.1)
-  '@dnd-kit/sortable':
-    specifier: ^8.0.0
-    version: 8.0.0(@dnd-kit/core@6.1.0)(react@18.3.1)
-  '@dnd-kit/utilities':
-    specifier: ^3.2.2
-    version: 3.2.2(react@18.3.1)
   '@fontsource-variable/inter':
     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)
@@ -319,6 +319,28 @@ packages:
       '@jridgewell/trace-mapping': 0.3.25
     dev: true
 
+  /@atlaskit/pragmatic-drag-and-drop-auto-scroll@1.4.0:
+    resolution: {integrity: sha512-5GoikoTSW13UX76F9TDeWB8x3jbbGlp/Y+3aRkHe1MOBMkrWkwNpJ42MIVhhX/6NSeaZiPumP0KbGJVs2tOWSQ==}
+    dependencies:
+      '@atlaskit/pragmatic-drag-and-drop': 1.4.0
+      '@babel/runtime': 7.25.7
+    dev: false
+
+  /@atlaskit/pragmatic-drag-and-drop-hitbox@1.0.3:
+    resolution: {integrity: sha512-/Sbu/HqN2VGLYBhnsG7SbRNg98XKkbF6L7XDdBi+izRybfaK1FeMfodPpm/xnBHPJzwYMdkE0qtLyv6afhgMUA==}
+    dependencies:
+      '@atlaskit/pragmatic-drag-and-drop': 1.4.0
+      '@babel/runtime': 7.25.7
+    dev: false
+
+  /@atlaskit/pragmatic-drag-and-drop@1.4.0:
+    resolution: {integrity: sha512-qRY3PTJIcxfl/QB8Gwswz+BRvlmgAC5pB+J2hL6dkIxgqAgVwOhAamMUKsrOcFU/axG2Q7RbNs1xfoLKDuhoPg==}
+    dependencies:
+      '@babel/runtime': 7.25.7
+      bind-event-listener: 3.0.0
+      raf-schd: 4.0.3
+    dev: false
+
   /@babel/code-frame@7.25.7:
     resolution: {integrity: sha512-0xZJFNE5XMpENsgfHYTw8FbX4kv53mFLn2i3XPoq69LyhYSCBJtitaHx9QnsVTrsogI4Z3+HtEfZ2/GFPOtf5g==}
     engines: {node: '>=6.9.0'}
@@ -980,49 +1002,6 @@ packages:
     engines: {node: '>17.0.0'}
     dev: false
 
-  /@dnd-kit/accessibility@3.1.0(react@18.3.1):
-    resolution: {integrity: sha512-ea7IkhKvlJUv9iSHJOnxinBcoOI3ppGnnL+VDJ75O45Nss6HtZd8IdN8touXPDtASfeI2T2LImb8VOZcL47wjQ==}
-    peerDependencies:
-      react: '>=16.8.0'
-    dependencies:
-      react: 18.3.1
-      tslib: 2.7.0
-    dev: false
-
-  /@dnd-kit/core@6.1.0(react-dom@18.3.1)(react@18.3.1):
-    resolution: {integrity: sha512-J3cQBClB4TVxwGo3KEjssGEXNJqGVWx17aRTZ1ob0FliR5IjYgTxl5YJbKTzA6IzrtelotH19v6y7uoIRUZPSg==}
-    peerDependencies:
-      react: '>=16.8.0'
-      react-dom: '>=16.8.0'
-    dependencies:
-      '@dnd-kit/accessibility': 3.1.0(react@18.3.1)
-      '@dnd-kit/utilities': 3.2.2(react@18.3.1)
-      react: 18.3.1
-      react-dom: 18.3.1(react@18.3.1)
-      tslib: 2.7.0
-    dev: false
-
-  /@dnd-kit/sortable@8.0.0(@dnd-kit/core@6.1.0)(react@18.3.1):
-    resolution: {integrity: sha512-U3jk5ebVXe1Lr7c2wU7SBZjcWdQP+j7peHJfCspnA81enlu88Mgd7CC8Q+pub9ubP7eKVETzJW+IBAhsqbSu/g==}
-    peerDependencies:
-      '@dnd-kit/core': ^6.1.0
-      react: '>=16.8.0'
-    dependencies:
-      '@dnd-kit/core': 6.1.0(react-dom@18.3.1)(react@18.3.1)
-      '@dnd-kit/utilities': 3.2.2(react@18.3.1)
-      react: 18.3.1
-      tslib: 2.7.0
-    dev: false
-
-  /@dnd-kit/utilities@3.2.2(react@18.3.1):
-    resolution: {integrity: sha512-+MKAJEOfaBe5SmV6t34p80MMKhjvUz0vRrvVJbPT0WElzaOJ/1xs+D+KDv+tD/NE5ujfrChEcshd4fLn0wpiqg==}
-    peerDependencies:
-      react: '>=16.8.0'
-    dependencies:
-      react: 18.3.1
-      tslib: 2.7.0
-    dev: false
-
   /@emotion/babel-plugin@11.12.0:
     resolution: {integrity: sha512-y2WQb+oP8Jqvvclh8Q55gLUyb7UFvgv7eJfsj7td5TToBrIUtPay2kMrZi4xjq9qw2vD0ZR5fSho0yqoFgX7Rw==}
     dependencies:
@@ -1696,20 +1675,20 @@ 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
@@ -4313,6 +4292,10 @@ packages:
       open: 8.4.2
     dev: true
 
+  /bind-event-listener@3.0.0:
+    resolution: {integrity: sha512-PJvH288AWQhKs2v9zyfYdPzlPqf5bXbGMmhmUIY9x4dAUGIWgomO771oBQNwJnMQSnUIXhKu6sgzpBRXTlvb8Q==}
+    dev: false
+
   /bl@4.1.0:
     resolution: {integrity: sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==}
     dependencies:
@@ -7557,6 +7540,10 @@ packages:
     resolution: {integrity: sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==}
     dev: true
 
+  /raf-schd@4.0.3:
+    resolution: {integrity: sha512-tQkJl2GRWh83ui2DiPTJz9wEiMN20syf+5oKfB03yYP7ioZcJwsIK8FjrtLwH1m7C7e+Tt2yYBlrOpdT+dyeIQ==}
+    dev: false
+
   /raf-throttle@2.0.6:
     resolution: {integrity: sha512-C7W6hy78A+vMmk5a/B6C5szjBHrUzWJkVyakjKCK59Uy2CcA7KhO1JUvvH32IXYFIcyJ3FMKP3ZzCc2/71I6Vg==}
     dev: false

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

@@ -95,7 +95,8 @@
         "none": "Keine",
         "new": "Neu",
         "ok": "OK",
-        "close": "Schließen"
+        "close": "Schließen",
+        "clipboard": "Zwischenablage"
     },
     "gallery": {
         "galleryImageSize": "Bildgröße",
@@ -535,14 +536,12 @@
         "addModels": "Model hinzufügen",
         "deleteModelImage": "Lösche Model Bild",
         "huggingFaceRepoID": "HuggingFace Repo ID",
-        "hfToken": "HuggingFace Schlüssel",
         "huggingFacePlaceholder": "besitzer/model-name",
         "modelSettings": "Modelleinstellungen",
         "typePhraseHere": "Phrase hier eingeben",
         "spandrelImageToImage": "Bild zu Bild (Spandrel)",
         "starterModels": "Einstiegsmodelle",
         "t5Encoder": "T5-Kodierer",
-        "useDefaultSettings": "Standardeinstellungen verwenden",
         "uploadImage": "Bild hochladen",
         "urlOrLocalPath": "URL oder lokaler Pfad",
         "install": "Installieren",
@@ -678,10 +677,41 @@
     "toast": {
         "uploadFailed": "Hochladen fehlgeschlagen",
         "imageCopied": "Bild kopiert",
-        "parametersNotSet": "Parameter nicht festgelegt",
+        "parametersNotSet": "Parameter nicht zurückgerufen",
         "addedToBoard": "Dem Board hinzugefügt",
         "loadedWithWarnings": "Workflow mit Warnungen geladen",
-        "imageSaved": "Bild gespeichert"
+        "imageSaved": "Bild gespeichert",
+        "linkCopied": "Link kopiert",
+        "problemCopyingLayer": "Ebene kann nicht kopiert werden",
+        "problemSavingLayer": "Ebene kann nicht gespeichert werden",
+        "parameterSetDesc": "{{parameter}} zurückgerufen",
+        "imageUploaded": "Bild hochgeladen",
+        "problemCopyingImage": "Bild kann nicht kopiert werden",
+        "parameterNotSetDesc": "{{parameter}} kann nicht zurückgerufen werden",
+        "prunedQueue": "Warteschlange bereinigt",
+        "modelAddedSimple": "Modell zur Warteschlange hinzugefügt",
+        "parametersSet": "Parameter zurückgerufen",
+        "imageNotLoadedDesc": "Bild konnte nicht gefunden werden",
+        "setControlImage": "Als Kontrollbild festlegen",
+        "sentToUpscale": "An Vergrößerung gesendet",
+        "parameterNotSetDescWithMessage": "{{parameter}} kann nicht zurückgerufen werden: {{message}}",
+        "unableToLoadImageMetadata": "Bildmetadaten können nicht geladen werden",
+        "unableToLoadImage": "Bild kann nicht geladen werden",
+        "serverError": "Serverfehler",
+        "parameterNotSet": "Parameter nicht zurückgerufen",
+        "sessionRef": "Sitzung: {{sessionId}}",
+        "problemDownloadingImage": "Bild kann nicht heruntergeladen werden",
+        "parameters": "Parameter",
+        "parameterSet": "Parameter zurückgerufen",
+        "importFailed": "Import fehlgeschlagen",
+        "importSuccessful": "Import erfolgreich",
+        "setNodeField": "Als Knotenfeld festlegen",
+        "somethingWentWrong": "Etwas ist schief gelaufen",
+        "workflowLoaded": "Arbeitsablauf geladen",
+        "workflowDeleted": "Arbeitsablauf gelöscht",
+        "errorCopied": "Fehler kopiert",
+        "layerCopiedToClipboard": "Ebene in die Zwischenablage kopiert",
+        "sentToCanvas": "An Leinwand gesendet"
     },
     "accessibility": {
         "uploadImage": "Bild hochladen",
@@ -825,7 +855,6 @@
         "width": "Breite",
         "createdBy": "Erstellt von",
         "steps": "Schritte",
-        "seamless": "Nahtlos",
         "positivePrompt": "Positiver Prompt",
         "generationMode": "Generierungsmodus",
         "Threshold": "Rauschen-Schwelle",
@@ -1170,7 +1199,19 @@
         "workflowVersion": "Version",
         "saveToGallery": "In Galerie speichern",
         "noWorkflows": "Keine Arbeitsabläufe",
-        "noMatchingWorkflows": "Keine passenden Arbeitsabläufe"
+        "noMatchingWorkflows": "Keine passenden Arbeitsabläufe",
+        "unknownErrorValidatingWorkflow": "Unbekannter Fehler beim Validieren des Arbeitsablaufes",
+        "inputFieldTypeParseError": "Typ des Eingabefelds {{node}}.{{field}} kann nicht analysiert werden ({{message}})",
+        "workflowSettings": "Arbeitsablauf Editor Einstellungen",
+        "unableToLoadWorkflow": "Arbeitsablauf kann nicht geladen werden",
+        "viewMode": "In linearen Ansicht verwenden",
+        "unableToValidateWorkflow": "Arbeitsablauf kann nicht validiert werden",
+        "outputFieldTypeParseError": "Typ des Ausgabefelds {{node}}.{{field}} kann nicht analysiert werden ({{message}})",
+        "unableToGetWorkflowVersion": "Version des Arbeitsablaufschemas kann nicht bestimmt werden",
+        "unknownFieldType": "$t(nodes.unknownField) Typ: {{type}}",
+        "unknownField": "Unbekanntes Feld",
+        "unableToUpdateNodes_one": "{{count}} Knoten kann nicht aktualisiert werden",
+        "unableToUpdateNodes_other": "{{count}} Knoten können nicht aktualisiert werden"
     },
     "hrf": {
         "enableHrf": "Korrektur für hohe Auflösungen",
@@ -1300,15 +1341,7 @@
         "enableLogging": "Protokollierung aktivieren"
     },
     "whatsNew": {
-        "whatsNewInInvoke": "Was gibt's Neues",
-        "canvasV2Announcement": {
-            "fluxSupport": "Unterstützung für Flux-Modelle",
-            "newCanvas": "Eine leistungsstarke neue Kontrollfläche",
-            "newLayerTypes": "Neue Ebenentypen für noch mehr Kontrolle",
-            "readReleaseNotes": "Anmerkungen zu dieser Version lesen",
-            "watchReleaseVideo": "Video über diese Version anzeigen",
-            "watchUiUpdatesOverview": "Interface-Updates Übersicht"
-        }
+        "whatsNewInInvoke": "Was gibt's Neues"
     },
     "stylePresets": {
         "name": "Name",

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",
@@ -173,7 +174,8 @@
         "placeholderSelectAModel": "Select a model",
         "reset": "Reset",
         "none": "None",
-        "new": "New"
+        "new": "New",
+        "generating": "Generating"
     },
     "hrf": {
         "hrf": "High Resolution Fix",
@@ -681,7 +683,8 @@
         "recallParameters": "Recall Parameters",
         "recallParameter": "Recall {{label}}",
         "scheduler": "Scheduler",
-        "seamless": "Seamless",
+        "seamlessXAxis": "Seamless X Axis",
+        "seamlessYAxis": "Seamless Y Axis",
         "seed": "Seed",
         "steps": "Steps",
         "strength": "Image to image strength",
@@ -702,6 +705,8 @@
         "baseModel": "Base Model",
         "cancel": "Cancel",
         "clipEmbed": "CLIP Embed",
+        "clipLEmbed": "CLIP-L Embed",
+        "clipGEmbed": "CLIP-G Embed",
         "config": "Config",
         "convert": "Convert",
         "convertingModelBegin": "Converting Model. Please wait.",
@@ -712,8 +717,12 @@
         "convertToDiffusersHelpText4": "This is a one time process only. It might take around 30s-60s depending on the specifications of your computer.",
         "convertToDiffusersHelpText5": "Please make sure you have enough disk space. Models generally vary between 2GB-7GB in size.",
         "convertToDiffusersHelpText6": "Do you wish to convert this model?",
+        "noDefaultSettings": "No default settings configured for this model. Visit the Model Manager to add default settings.",
         "defaultSettings": "Default Settings",
         "defaultSettingsSaved": "Default Settings Saved",
+        "defaultSettingsOutOfSync": "Some settings do not match the model's defaults:",
+        "restoreDefaultSettings": "Click to use the model's default settings.",
+        "usingDefaultSettings": "Using model's default settings",
         "delete": "Delete",
         "deleteConfig": "Delete Config",
         "deleteModel": "Delete Model",
@@ -727,7 +736,17 @@
         "huggingFacePlaceholder": "owner/model-name",
         "huggingFaceRepoID": "HuggingFace Repo ID",
         "huggingFaceHelper": "If multiple models are found in this repo, you will be prompted to select one to install.",
-        "hfToken": "HuggingFace Token",
+        "hfTokenLabel": "HuggingFace Token (Required for some models)",
+        "hfTokenHelperText": "A HF token is required to use some models. Click here to create or get your token.",
+        "hfTokenInvalid": "Invalid or Missing HF Token",
+        "hfForbidden": "You do not have access to this HF model",
+        "hfForbiddenErrorMessage": "We recommend visiting the repo page on HuggingFace.com. The owner may require acceptance of terms in order to download.",
+        "hfTokenInvalidErrorMessage": "Invalid or missing HuggingFace token.",
+        "hfTokenRequired": "You are trying to download a model that requires a valid HuggingFace Token.",
+        "hfTokenInvalidErrorMessage2": "Update it in the ",
+        "hfTokenUnableToVerify": "Unable to Verify HF Token",
+        "hfTokenUnableToVerifyErrorMessage": "Unable to verify HuggingFace token. This is likely due to a network error. Please try again later.",
+        "hfTokenSaved": "HF Token Saved",
         "imageEncoderModelId": "Image Encoder Model ID",
         "includesNModels": "Includes {{n}} models and their dependencies",
         "installQueue": "Install Queue",
@@ -798,7 +817,6 @@
         "uploadImage": "Upload Image",
         "urlOrLocalPath": "URL or Local Path",
         "urlOrLocalPathHelper": "URLs should point to a single file. Local paths can point to a single file or folder for a single diffusers model.",
-        "useDefaultSettings": "Use Default Settings",
         "vae": "VAE",
         "vaePrecision": "VAE Precision",
         "variant": "Variant",
@@ -982,6 +1000,7 @@
         "controlNetControlMode": "Control Mode",
         "copyImage": "Copy Image",
         "denoisingStrength": "Denoising Strength",
+        "disabledNoRasterContent": "Disabled (No Raster Content)",
         "downloadImage": "Download Image",
         "general": "General",
         "guidance": "Guidance",
@@ -1032,6 +1051,7 @@
         "patchmatchDownScaleSize": "Downscale",
         "perlinNoise": "Perlin Noise",
         "positivePromptPlaceholder": "Positive Prompt",
+        "recallMetadata": "Recall Metadata",
         "iterations": "Iterations",
         "scale": "Scale",
         "scaleBeforeProcessing": "Scale Before Processing",
@@ -1108,6 +1128,9 @@
         "enableInformationalPopovers": "Enable Informational Popovers",
         "informationalPopoversDisabled": "Informational Popovers Disabled",
         "informationalPopoversDisabledDesc": "Informational popovers have been disabled. Enable them in Settings.",
+        "enableModelDescriptions": "Enable Model Descriptions in Dropdowns",
+        "modelDescriptionsDisabled": "Model Descriptions in Dropdowns Disabled",
+        "modelDescriptionsDisabledDesc": "Model descriptions in dropdowns have been disabled. Enable them in Settings.",
         "enableInvisibleWatermark": "Enable Invisible Watermark",
         "enableNSFWChecker": "Enable NSFW Checker",
         "general": "General",
@@ -1117,6 +1140,7 @@
         "resetWebUI": "Reset Web UI",
         "resetWebUIDesc1": "Resetting the web UI only resets the browser's local cache of your images and remembered settings. It does not delete any images from disk.",
         "resetWebUIDesc2": "If images aren't showing up in the gallery or something else isn't working, please try resetting before submitting an issue on GitHub.",
+        "showDetailedInvocationProgress": "Show Progress Details",
         "showProgressInViewer": "Show Progress Images in Viewer",
         "ui": "User Interface",
         "clearIntermediatesDisabled": "Queue must be empty to clear intermediates",
@@ -1251,6 +1275,33 @@
             "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": [
@@ -1366,8 +1417,9 @@
         "paramDenoisingStrength": {
             "heading": "Denoising Strength",
             "paragraphs": [
-                "How much noise is added to the input image.",
-                "0 will result in an identical image, while 1 will result in a completely new image."
+                "Controls how much the generated image varies from the raster layer(s).",
+                "Lower strength stays closer to the combined visible raster layers. Higher strength relies more on the global prompt.",
+                "When there are no raster layers with visible content, this setting is ignored."
             ]
         },
         "paramHeight": {
@@ -1606,21 +1658,24 @@
         "newControlLayerError": "Problem Creating Control Layer",
         "newRasterLayerOk": "Created Raster Layer",
         "newRasterLayerError": "Problem Creating Raster Layer",
+        "newFromImage": "New from Image",
         "pullBboxIntoLayerOk": "Bbox Pulled Into Layer",
         "pullBboxIntoLayerError": "Problem Pulling BBox Into Layer",
         "pullBboxIntoReferenceImageOk": "Bbox Pulled Into ReferenceImage",
         "pullBboxIntoReferenceImageError": "Problem Pulling BBox Into ReferenceImage",
         "regionIsEmpty": "Selected region is empty",
         "mergeVisible": "Merge Visible",
-        "mergeVisibleOk": "Merged visible layers",
-        "mergeVisibleError": "Error merging visible layers",
+        "mergeDown": "Merge Down",
+        "mergeVisibleOk": "Merged layers",
+        "mergeVisibleError": "Error merging layers",
+        "mergingLayers": "Merging layers",
         "clearHistory": "Clear History",
         "bboxOverlay": "Show Bbox Overlay",
         "resetCanvas": "Reset Canvas",
         "clearCaches": "Clear Caches",
         "recalculateRects": "Recalculate Rects",
         "clipToBbox": "Clip Strokes to Bbox",
-        "outputOnlyMaskedRegions": "Output Only Masked Regions",
+        "outputOnlyMaskedRegions": "Output Only Generated Regions",
         "addLayer": "Add Layer",
         "duplicate": "Duplicate",
         "moveToFront": "Move to Front",
@@ -1648,6 +1703,8 @@
         "controlLayer": "Control Layer",
         "inpaintMask": "Inpaint Mask",
         "regionalGuidance": "Regional Guidance",
+        "canvasAsRasterLayer": "$t(controlLayers.canvas) as $t(controlLayers.rasterLayer)",
+        "canvasAsControlLayer": "$t(controlLayers.canvas) as $t(controlLayers.controlLayer)",
         "referenceImage": "Reference Image",
         "regionalReferenceImage": "Regional Reference Image",
         "globalReferenceImage": "Global Reference Image",
@@ -1688,8 +1745,18 @@
         "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",
@@ -1713,16 +1780,18 @@
         "newGallerySessionDesc": "This will clear the canvas and all settings except for your model selection. Generations will be sent to the gallery.",
         "newCanvasSession": "New Canvas Session",
         "newCanvasSessionDesc": "This will clear the canvas and all settings except for your model selection. Generations will be staged on the canvas.",
+        "replaceCurrent": "Replace Current",
+        "controlLayerEmptyState": "<UploadButton>Upload an image</UploadButton>, drag an image from the <GalleryButton>gallery</GalleryButton> onto this layer, or draw on the canvas to get started.",
         "controlMode": {
             "controlMode": "Control Mode",
-            "balanced": "Balanced",
+            "balanced": "Balanced (recommended)",
             "prompt": "Prompt",
             "control": "Control",
             "megaControl": "Mega Control"
         },
         "ipAdapterMethod": {
             "ipAdapterMethod": "IP Adapter Method",
-            "full": "Full",
+            "full": "Style and Composition",
             "style": "Style Only",
             "composition": "Composition Only"
         },
@@ -1754,6 +1823,9 @@
             "process": "Process",
             "apply": "Apply",
             "cancel": "Cancel",
+            "advanced": "Advanced",
+            "processingLayerWith": "Processing layer with the {{type}} filter.",
+            "forMoreControl": "For more control, click Advanced below.",
             "spandrel_filter": {
                 "label": "Image-to-Image Model",
                 "description": "Run an image-to-image model on the selected layer.",
@@ -1842,16 +1914,24 @@
             "apply": "Apply",
             "cancel": "Cancel"
         },
-        "segment": {
-            "autoMask": "Auto Mask",
+        "selectObject": {
+            "selectObject": "Select Object",
             "pointType": "Point Type",
-            "foreground": "Foreground",
-            "background": "Background",
+            "invertSelection": "Invert Selection",
+            "include": "Include",
+            "exclude": "Exclude",
             "neutral": "Neutral",
-            "reset": "Reset",
             "apply": "Apply",
+            "reset": "Reset",
+            "saveAs": "Save As",
             "cancel": "Cancel",
-            "process": "Process"
+            "process": "Process",
+            "help1": "Select a single target object. Add <Bold>Include</Bold> and <Bold>Exclude</Bold> points to indicate which parts of the layer are part of the target object.",
+            "help2": "Start with one <Bold>Include</Bold> point within the target object. Add more points to refine the selection. Fewer points typically produce better results.",
+            "help3": "Invert the selection to select everything except the target object.",
+            "clickToAdd": "Click on the layer to add a point",
+            "dragToMove": "Drag a point to move it",
+            "clickToRemove": "Click on a point to remove it"
         },
         "settings": {
             "snapToGrid": {
@@ -1892,6 +1972,8 @@
             "newRegionalReferenceImage": "New Regional Reference Image",
             "newControlLayer": "New Control Layer",
             "newRasterLayer": "New Raster Layer",
+            "newInpaintMask": "New Inpaint Mask",
+            "newRegionalGuidance": "New Regional Guidance",
             "cropCanvasToBbox": "Crop Canvas to Bbox"
         },
         "stagingArea": {
@@ -1921,7 +2003,9 @@
         "upscaleModelDesc": "Upscale (image to image) model",
         "missingUpscaleInitialImage": "Missing initial image for upscaling",
         "missingUpscaleModel": "Missing upscale model",
-        "missingTileControlNetModel": "No valid tile ControlNet models installed"
+        "missingTileControlNetModel": "No valid tile ControlNet models installed",
+        "incompatibleBaseModel": "Unsupported main model architecture for upscaling",
+        "incompatibleBaseModelDesc": "Upscaling is supported for SD1.5 and SDXL architecture models only. Change the main model to enable upscaling."
     },
     "stylePresets": {
         "active": "Active",
@@ -2024,13 +2108,12 @@
     },
     "whatsNew": {
         "whatsNewInInvoke": "What's New in Invoke",
-        "canvasV2Announcement": {
-            "newCanvas": "A powerful new control canvas",
-            "newLayerTypes": "New layer types for even more control",
-            "fluxSupport": "Support for the Flux family of models",
-            "readReleaseNotes": "Read Release Notes",
-            "watchReleaseVideo": "Watch Release Video",
-            "watchUiUpdatesOverview": "Watch UI Updates Overview"
-        }
+        "items": [
+            "<StrongComponent>SD 3.5</StrongComponent>: Support for Text-to-Image in Workflows with SD 3.5 Medium and Large.",
+            "<StrongComponent>Canvas</StrongComponent>: Streamlined Control Layer processing and improved default Control settings."
+        ],
+        "readReleaseNotes": "Read Release Notes",
+        "watchRecentReleaseVideos": "Watch Recent Release Videos",
+        "watchUiUpdatesOverview": "Watch UI Updates Overview"
     }
 }

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

@@ -5,7 +5,7 @@
         "reportBugLabel": "Signaler un bug",
         "settingsLabel": "Paramètres",
         "img2img": "Image vers Image",
-        "nodes": "Processus",
+        "nodes": "Workflows",
         "upload": "Importer",
         "load": "Charger",
         "back": "Retour",
@@ -95,7 +95,8 @@
         "positivePrompt": "Prompt Positif",
         "negativePrompt": "Prompt Négatif",
         "ok": "Ok",
-        "close": "Fermer"
+        "close": "Fermer",
+        "clipboard": "Presse-papier"
     },
     "gallery": {
         "galleryImageSize": "Taille de l'image",
@@ -161,7 +162,7 @@
         "unstarImage": "Retirer le marquage de l'Image",
         "viewerImage": "Visualisation de l'Image",
         "imagesSettings": "Paramètres des images de la galerie",
-        "assetsTab": "Fichiers que vous avez importé pour vos projets.",
+        "assetsTab": "Fichiers que vous avez importés pour vos projets.",
         "imagesTab": "Images que vous avez créées et enregistrées dans Invoke.",
         "boardsSettings": "Paramètres des planches"
     },
@@ -219,7 +220,6 @@
         "typePhraseHere": "Écrire une phrase ici",
         "cancel": "Annuler",
         "defaultSettingsSaved": "Paramètres par défaut enregistrés",
-        "hfToken": "Token HuggingFace",
         "imageEncoderModelId": "ID du modèle d'encodeur d'image",
         "path": "Chemin sur le disque",
         "repoVariant": "Variante de dépôt",
@@ -254,7 +254,6 @@
         "loraModels": "LoRAs",
         "main": "Principal",
         "urlOrLocalPathHelper": "Les URL doivent pointer vers un seul fichier. Les chemins locaux peuvent pointer vers un seul fichier ou un dossier pour un seul modèle de diffuseurs.",
-        "useDefaultSettings": "Utiliser les paramètres par défaut",
         "modelImageUpdateFailed": "Mise à jour de l'image du modèle échouée",
         "loraTriggerPhrases": "Phrases de déclenchement LoRA",
         "mainModelTriggerPhrases": "Phrases de déclenchement du modèle principal",
@@ -284,24 +283,28 @@
         "skippingXDuplicates_many": ", en ignorant {{count}} doublons",
         "skippingXDuplicates_other": ", en ignorant {{count}} doublons",
         "installingModel": "Modèle en cours d'installation",
-        "installingBundle": "Pack en cours d'installation"
+        "installingBundle": "Pack en cours d'installation",
+        "noDefaultSettings": "Aucun paramètre par défaut configuré pour ce modèle. Visitez le Gestionnaire de Modèles pour ajouter des paramètres par défaut.",
+        "usingDefaultSettings": "Utilisation des paramètres par défaut du modèle",
+        "defaultSettingsOutOfSync": "Certain paramètres ne correspondent pas aux valeurs par défaut du modèle :",
+        "restoreDefaultSettings": "Cliquez pour utiliser les paramètres par défaut du modèle."
     },
     "parameters": {
         "images": "Images",
-        "steps": "Etapes",
-        "cfgScale": "CFG Echelle",
+        "steps": "Étapes",
+        "cfgScale": "Échelle CFG",
         "width": "Largeur",
         "height": "Hauteur",
         "seed": "Graine",
-        "shuffle": "Mélanger la graine",
+        "shuffle": "Nouvelle graine",
         "noiseThreshold": "Seuil de Bruit",
         "perlinNoise": "Bruit de Perlin",
         "type": "Type",
         "strength": "Force",
         "upscaling": "Agrandissement",
-        "scale": "Echelle",
+        "scale": "Échelle",
         "imageFit": "Ajuster Image Initiale à la Taille de Sortie",
-        "scaleBeforeProcessing": "Echelle Avant Traitement",
+        "scaleBeforeProcessing": "Échelle Avant Traitement",
         "scaledWidth": "Larg. Échelle",
         "scaledHeight": "Haut. Échelle",
         "infillMethod": "Méthode de Remplissage",
@@ -422,7 +425,10 @@
         "clearIntermediatesWithCount_other": "Effacé {{count}} Intermédiaires",
         "informationalPopoversDisabled": "Pop-ups d'information désactivés",
         "informationalPopoversDisabledDesc": "Les pop-ups d'information ont été désactivés. Activez-les dans les paramètres.",
-        "confirmOnNewSession": "Confirmer lors d'une nouvelle session"
+        "confirmOnNewSession": "Confirmer lors d'une nouvelle session",
+        "modelDescriptionsDisabledDesc": "Les descriptions des modèles dans les menus déroulants ont été désactivées. Activez-les dans les paramètres.",
+        "enableModelDescriptions": "Activer les descriptions de modèle dans les menus déroulants",
+        "modelDescriptionsDisabled": "Descriptions de modèle dans les menus déroulants désactivés"
     },
     "toast": {
         "uploadFailed": "Importation échouée",
@@ -435,22 +441,22 @@
         "parameterNotSet": "Paramètre non Rappelé",
         "canceled": "Traitement annulé",
         "addedToBoard": "Ajouté aux ressources de la planche {{name}}",
-        "workflowLoaded": "Processus chargé",
+        "workflowLoaded": "Workflow chargé",
         "connected": "Connecté au serveur",
         "setNodeField": "Définir comme champ de nœud",
         "imageUploadFailed": "Échec de l'importation de l'image",
-        "loadedWithWarnings": "Processus chargé avec des avertissements",
+        "loadedWithWarnings": "Workflow chargé avec des avertissements",
         "imageUploaded": "Image importée",
         "modelAddedSimple": "Modèle ajouté à la file d'attente",
         "setControlImage": "Définir comme image de contrôle",
-        "workflowDeleted": "Processus supprimé",
+        "workflowDeleted": "Workflow supprimé",
         "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": "Importation invalide",
         "problemDownloadingImage": "Impossible de télécharger l'image",
-        "problemRetrievingWorkflow": "Problème de récupération du processus",
-        "problemDeletingWorkflow": "Problème de suppression du processus",
+        "problemRetrievingWorkflow": "Problème de récupération du Workflow",
+        "problemDeletingWorkflow": "Problème de suppression du Workflow",
         "prunedQueue": "File d'attente vidée",
         "parameters": "Paramètres",
         "modelImportCanceled": "Importation du modèle annulée",
@@ -550,7 +556,7 @@
     "accordions": {
         "advanced": {
             "title": "Avancé",
-            "options": "$t(accordions.advanced.title) Options"
+            "options": "Options $t(accordions.advanced.title)"
         },
         "image": {
             "title": "Image"
@@ -631,7 +637,7 @@
         "graphQueued": "Graph ajouté à la file d'attente",
         "other": "Autre",
         "generation": "Génération",
-        "workflows": "Processus",
+        "workflows": "Workflows",
         "batchFailedToQueue": "Impossible d'ajouter le Lot dans à la file d'attente",
         "graphFailedToQueue": "Impossible d'ajouter le graph à la file d'attente",
         "item": "Élément",
@@ -704,8 +710,8 @@
                 "desc": "Rappelle toutes les métadonnées pour l'image actuelle."
             },
             "loadWorkflow": {
-                "title": "Charger le processus",
-                "desc": "Charge le processus enregistré de l'image actuelle (s'il en a un)."
+                "title": "Ouvrir un Workflow",
+                "desc": "Charge le workflow enregistré lié à l'image actuelle (s'il en a un)."
             },
             "recallSeed": {
                 "desc": "Rappelle la graine pour l'image actuelle.",
@@ -756,8 +762,8 @@
                 "desc": "Séléctionne l'onglet Agrandissement."
             },
             "selectWorkflowsTab": {
-                "desc": "Sélectionne l'onglet Processus.",
-                "title": "Sélectionner l'onglet Processus"
+                "desc": "Sélectionne l'onglet Workflows.",
+                "title": "Sélectionner l'onglet Workflows"
             },
             "togglePanels": {
                 "desc": "Affiche ou masque les panneaux gauche et droit en même temps.",
@@ -963,11 +969,11 @@
             },
             "undo": {
                 "title": "Annuler",
-                "desc": "Annule la dernière action de processus."
+                "desc": "Annule la dernière action de workflow."
             },
             "redo": {
                 "title": "Rétablir",
-                "desc": "Rétablit la dernière action de processus."
+                "desc": "Rétablit la dernière action de workflow."
             },
             "addNode": {
                 "desc": "Ouvre le menu d'ajout de nœud.",
@@ -985,7 +991,7 @@
                 "desc": "Colle les nœuds et les connections copiés.",
                 "title": "Coller"
             },
-            "title": "Processus"
+            "title": "Workflows"
         }
     },
     "popovers": {
@@ -1372,6 +1378,43 @@
                 "Des valeurs de guidage élevées peuvent entraîner une saturation excessive, et un guidage élevé ou faible peut entraîner des résultats de génération déformés. Le guidage ne s'applique qu'aux modèles FLUX DEV."
             ],
             "heading": "Guidage"
+        },
+        "globalReferenceImage": {
+            "heading": "Image de Référence Globale",
+            "paragraphs": [
+                "Applique une image de référence pour influencer l'ensemble de la génération."
+            ]
+        },
+        "regionalReferenceImage": {
+            "heading": "Image de Référence Régionale",
+            "paragraphs": [
+                "Pinceau pour appliquer une image de référence à des zones spécifiques."
+            ]
+        },
+        "inpainting": {
+            "heading": "Inpainting",
+            "paragraphs": [
+                "Contrôle la zone qui est modifiée, guidé par la force de débruitage."
+            ]
+        },
+        "regionalGuidance": {
+            "heading": "Guide Régional",
+            "paragraphs": [
+                "Pinceau pour guider l'emplacement des éléments provenant des prompts globaux."
+            ]
+        },
+        "regionalGuidanceAndReferenceImage": {
+            "heading": "Guide régional et image de référence régionale",
+            "paragraphs": [
+                "Pour le Guide Régional, utilisez le pinceau pour indiquer où les éléments des prompts globaux doivent apparaître.",
+                "Pour l'image de référence régionale, pinceau pour appliquer une image de référence à des zones spécifiques."
+            ]
+        },
+        "rasterLayer": {
+            "heading": "Couche Rastérisation",
+            "paragraphs": [
+                "Contenu basé sur les pixels de votre toile, utilisé lors de la génération d'images."
+            ]
         }
     },
     "dynamicPrompts": {
@@ -1392,12 +1435,11 @@
         "positivePrompt": "Prompt Positif",
         "allPrompts": "Tous les Prompts",
         "negativePrompt": "Prompt Négatif",
-        "seamless": "Sans jointure",
         "metadata": "Métadonné",
         "scheduler": "Planificateur",
         "imageDetails": "Détails de l'Image",
         "seed": "Graine",
-        "workflow": "Processus",
+        "workflow": "Workflow",
         "width": "Largeur",
         "Threshold": "Seuil de bruit",
         "noMetaData": "Aucune métadonnée trouvée",
@@ -1446,8 +1488,8 @@
         "hideMinimapnodes": "Masquer MiniCarte",
         "zoomOutNodes": "Dézoomer",
         "zoomInNodes": "Zoomer",
-        "downloadWorkflow": "Télécharger processus en JSON",
-        "loadWorkflow": "Charger le processus",
+        "downloadWorkflow": "Exporter le Workflow au format JSON",
+        "loadWorkflow": "Charger un Workflow",
         "reloadNodeTemplates": "Recharger les modèles de nœuds",
         "animatedEdges": "Connexions animées",
         "cannotConnectToSelf": "Impossible de se connecter à soi-même",
@@ -1470,16 +1512,16 @@
         "float": "Flottant",
         "mismatchedVersion": "Nœud invalide : le nœud {{node}} de type {{type}} a une version incompatible (essayez de mettre à jour ?)",
         "missingTemplate": "Nœud invalide : le nœud {{node}} de type {{type}} modèle manquant (non installé ?)",
-        "noWorkflow": "Pas de processus",
+        "noWorkflow": "Pas de Workflow",
         "validateConnectionsHelp": "Prévenir la création de connexions invalides et l'invocation de graphes invalides",
-        "workflowSettings": "Paramètres de l'Éditeur de Processus",
-        "workflowValidation": "Erreur de validation du processus",
+        "workflowSettings": "Paramètres de l'Éditeur de Workflow",
+        "workflowValidation": "Erreur de validation du Workflow",
         "executionStateInProgress": "En cours",
         "node": "Noeud",
         "scheduler": "Planificateur",
         "notes": "Notes",
-        "notesDescription": "Ajouter des notes sur votre processus",
-        "unableToLoadWorkflow": "Impossible de charger le processus",
+        "notesDescription": "Ajouter des notes sur votre workflow",
+        "unableToLoadWorkflow": "Impossible de charger le Workflow",
         "addNode": "Ajouter un nœud",
         "problemSettingTitle": "Problème lors de définition du Titre",
         "connectionWouldCreateCycle": "La connexion créerait un cycle",
@@ -1502,7 +1544,7 @@
         "noOutputRecorded": "Aucun résultat enregistré",
         "removeLinearView": "Retirer de la vue linéaire",
         "snapToGrid": "Aligner sur la grille",
-        "workflow": "Processus",
+        "workflow": "Workflow",
         "updateApp": "Mettre à jour l'application",
         "updateNode": "Mettre à jour le nœud",
         "nodeOutputs": "Sorties de nœud",
@@ -1515,7 +1557,7 @@
         "string": "Chaîne de caractères",
         "workflowName": "Nom",
         "snapToGridHelp": "Aligner les nœuds sur la grille lors du déplacement",
-        "unableToValidateWorkflow": "Impossible de valider le processus",
+        "unableToValidateWorkflow": "Impossible de valider le Workflow",
         "validateConnections": "Valider les connexions et le graphique",
         "unableToUpdateNodes_one": "Impossible de mettre à jour {{count}} nœud",
         "unableToUpdateNodes_many": "Impossible de mettre à jour {{count}} nœuds",
@@ -1528,15 +1570,15 @@
         "nodePack": "Paquet de nœuds",
         "sourceNodeDoesNotExist": "Connexion invalide : le nœud source/de sortie {{node}} n'existe pas",
         "sourceNodeFieldDoesNotExist": "Connexion invalide : {{node}}.{{field}} n'existe pas",
-        "unableToGetWorkflowVersion": "Impossible d'obtenir la version du schéma de processus",
-        "newWorkflowDesc2": "Votre processus actuel comporte des modifications non enregistrées.",
+        "unableToGetWorkflowVersion": "Impossible d'obtenir la version du schéma du Workflow",
+        "newWorkflowDesc2": "Votre workflow actuel comporte des modifications non enregistrées.",
         "deletedInvalidEdge": "Connexion invalide supprimé {{source}} -> {{target}}",
         "targetNodeDoesNotExist": "Connexion invalide : le nœud cible/entrée {{node}} n'existe pas",
         "targetNodeFieldDoesNotExist": "Connexion invalide : le champ {{node}}.{{field}} n'existe pas",
         "nodeVersion": "Version du noeud",
-        "clearWorkflowDesc2": "Votre processus actuel comporte des modifications non enregistrées.",
-        "clearWorkflow": "Effacer le Processus",
-        "clearWorkflowDesc": "Effacer ce processus et en commencer un nouveau ?",
+        "clearWorkflowDesc2": "Votre workflow actuel comporte des modifications non enregistrées.",
+        "clearWorkflow": "Effacer le Workflow",
+        "clearWorkflowDesc": "Effacer ce workflow et en commencer un nouveau ?",
         "unsupportedArrayItemType": "type d'élément de tableau non pris en charge \"{{type}}\"",
         "addLinearView": "Ajouter à la vue linéaire",
         "collectionOrScalarFieldType": "{{name}} (Unique ou Collection)",
@@ -1545,7 +1587,7 @@
         "ipAdapter": "IP-Adapter",
         "viewMode": "Utiliser en vue linéaire",
         "collectionFieldType": "{{name}} (Collection)",
-        "newWorkflow": "Nouveau processus",
+        "newWorkflow": "Nouveau Workflow",
         "reorderLinearView": "Réorganiser la vue linéaire",
         "unknownOutput": "Sortie inconnue : {{name}}",
         "outputFieldTypeParseError": "Impossible d'analyser le type du champ de sortie {{node}}.{{field}} ({{message}})",
@@ -1555,13 +1597,13 @@
         "unknownFieldType": "$t(nodes.unknownField) type : {{type}}",
         "inputFieldTypeParseError": "Impossible d'analyser le type du champ d'entrée {{node}}.{{field}} ({{message}})",
         "unableToExtractSchemaNameFromRef": "impossible d'extraire le nom du schéma à partir de la référence",
-        "editMode": "Modifier dans l'éditeur de processus",
-        "unknownErrorValidatingWorkflow": "Erreur inconnue lors de la validation du processus",
+        "editMode": "Modifier dans l'éditeur de Workflow",
+        "unknownErrorValidatingWorkflow": "Erreur inconnue lors de la validation du Workflow",
         "updateAllNodes": "Mettre à jour les nœuds",
         "allNodesUpdated": "Tous les nœuds mis à jour",
-        "newWorkflowDesc": "Créer un nouveau processus ?",
+        "newWorkflowDesc": "Créer un nouveau workflow ?",
         "edit": "Modifier",
-        "noFieldsViewMode": "Ce processus n'a aucun champ sélectionné à afficher. Consultez le processus complet pour configurer les valeurs.",
+        "noFieldsViewMode": "Ce workflow n'a aucun champ sélectionné à afficher. Consultez le workflow complet pour configurer les valeurs.",
         "graph": "Graph",
         "modelAccessError": "Impossible de trouver le modèle {{key}}, réinitialisation aux paramètres par défaut",
         "showEdgeLabelsHelp": "Afficher le nom sur les connections, indiquant les nœuds connectés",
@@ -1575,9 +1617,9 @@
         "missingInvocationTemplate": "Modèle d'invocation manquant",
         "imageAccessError": "Impossible de trouver l'image {{image_name}}, réinitialisation à la valeur par défaut",
         "boardAccessError": "Impossible de trouver la planche {{board_id}}, réinitialisation à la valeur par défaut",
-        "workflowHelpText": "Besoin d'aide ? Consultez notre guide sur <LinkComponent>Comment commencer avec les Processus</LinkComponent>.",
-        "noWorkflows": "Aucun Processus",
-        "noMatchingWorkflows": "Aucun processus correspondant"
+        "workflowHelpText": "Besoin d'aide ? Consultez notre guide sur <LinkComponent>Comment commencer avec les Workflows</LinkComponent>.",
+        "noWorkflows": "Aucun Workflows",
+        "noMatchingWorkflows": "Aucun Workflows correspondant"
     },
     "models": {
         "noMatchingModels": "Aucun modèle correspondant",
@@ -1594,59 +1636,51 @@
     },
     "workflows": {
         "workflowLibrary": "Bibliothèque",
-        "loading": "Chargement des processus",
-        "searchWorkflows": "Rechercher des processus",
-        "workflowCleared": "Processus effacé",
+        "loading": "Chargement des Workflows",
+        "searchWorkflows": "Chercher des Workflows",
+        "workflowCleared": "Workflow effacé",
         "noDescription": "Aucune description",
-        "deleteWorkflow": "Supprimer le processus",
-        "openWorkflow": "Ouvrir le processus",
+        "deleteWorkflow": "Supprimer le Workflow",
+        "openWorkflow": "Ouvrir le Workflow",
         "uploadWorkflow": "Charger à partir d'un fichier",
-        "workflowName": "Nom du processus",
-        "unnamedWorkflow": "Processus sans nom",
-        "saveWorkflowAs": "Enregistrer le processus sous",
-        "workflows": "Processus",
-        "savingWorkflow": "Enregistrement du processus...",
-        "saveWorkflowToProject": "Enregistrer le processus dans le projet",
+        "workflowName": "Nom du Workflow",
+        "unnamedWorkflow": "Workflow sans nom",
+        "saveWorkflowAs": "Enregistrer le Workflow sous",
+        "workflows": "Workflows",
+        "savingWorkflow": "Enregistrement du Workflow...",
+        "saveWorkflowToProject": "Enregistrer le Workflow dans le projet",
         "downloadWorkflow": "Enregistrer dans le fichier",
-        "saveWorkflow": "Enregistrer le processus",
-        "problemSavingWorkflow": "Problème de sauvegarde du processus",
-        "workflowEditorMenu": "Menu de l'Éditeur de Processus",
-        "newWorkflowCreated": "Nouveau processus créé",
-        "clearWorkflowSearchFilter": "Réinitialiser le filtre de recherche de processus",
-        "problemLoading": "Problème de chargement des processus",
-        "workflowSaved": "Processus enregistré",
-        "noWorkflows": "Pas de processus",
+        "saveWorkflow": "Enregistrer le Workflow",
+        "problemSavingWorkflow": "Problème de sauvegarde du Workflow",
+        "workflowEditorMenu": "Menu de l'Éditeur de Workflow",
+        "newWorkflowCreated": "Nouveau Workflow créé",
+        "clearWorkflowSearchFilter": "Réinitialiser le filtre de recherche de Workflow",
+        "problemLoading": "Problème de chargement des Workflows",
+        "workflowSaved": "Workflow enregistré",
+        "noWorkflows": "Pas de Workflows",
         "ascending": "Ascendant",
-        "loadFromGraph": "Charger le processus à partir du graphique",
+        "loadFromGraph": "Charger le Workflow à partir du graphique",
         "descending": "Descendant",
         "created": "Créé",
         "updated": "Mis à jour",
-        "loadWorkflow": "$t(common.load) Processus",
+        "loadWorkflow": "$t(common.load) Workflow",
         "convertGraph": "Convertir le graphique",
         "opened": "Ouvert",
         "name": "Nom",
         "autoLayout": "Mise en page automatique",
-        "defaultWorkflows": "Processus par défaut",
-        "userWorkflows": "Processus utilisateur",
-        "projectWorkflows": "Processus du projet",
+        "defaultWorkflows": "Workflows par défaut",
+        "userWorkflows": "Workflows de l'utilisateur",
+        "projectWorkflows": "Workflows du projet",
         "copyShareLink": "Copier le lien de partage",
-        "chooseWorkflowFromLibrary": "Choisir le Processus dans la Bibliothèque",
+        "chooseWorkflowFromLibrary": "Choisir le Workflow 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.",
+        "deleteWorkflow2": "Êtes-vous sûr de vouloir supprimer ce Workflow ? Cette action ne peut pas être annulé.",
         "download": "Télécharger",
-        "copyShareLinkForWorkflow": "Copier le lien de partage pour le processus",
+        "copyShareLinkForWorkflow": "Copier le lien de partage pour le Workflow",
         "delete": "Supprimer"
     },
     "whatsNew": {
-        "canvasV2Announcement": {
-            "watchReleaseVideo": "Regarder la vidéo de lancement",
-            "newLayerTypes": "Nouveaux types de couches pour un contrôle encore plus précis",
-            "fluxSupport": "Support pour la famille de modèles Flux",
-            "readReleaseNotes": "Lire les notes de version",
-            "newCanvas": "Une nouvelle Toile de contrôle puissant",
-            "watchUiUpdatesOverview": "Regarder l'aperçu des mises à jour de l'UI"
-        },
         "whatsNewInInvoke": "Quoi de neuf dans Invoke"
     },
     "ui": {
@@ -1657,7 +1691,7 @@
             "gallery": "Galerie",
             "upscalingTab": "$t(ui.tabs.upscaling) $t(common.tab)",
             "generation": "Génération",
-            "workflows": "Processus",
+            "workflows": "Workflows",
             "workflowsTab": "$t(ui.tabs.workflows) $t(common.tab)",
             "models": "Modèles",
             "modelsTab": "$t(ui.tabs.models) $t(common.tab)"
@@ -1767,7 +1801,9 @@
             "bboxGroup": "Créer à partir de la bounding box",
             "newRegionalReferenceImage": "Nouvelle image de référence régionale",
             "newGlobalReferenceImage": "Nouvelle image de référence globale",
-            "newControlLayer": "Nouveau couche de contrôle"
+            "newControlLayer": "Nouveau couche de contrôle",
+            "newInpaintMask": "Nouveau Masque Inpaint",
+            "newRegionalGuidance": "Nouveau Guide Régional"
         },
         "bookmark": "Marque-page pour Changement Rapide",
         "saveLayerToAssets": "Enregistrer la couche dans les ressources",
@@ -1780,8 +1816,6 @@
                 "on": "Activé",
                 "label": "Aligner sur la grille"
             },
-            "isolatedFilteringPreview": "Aperçu de filtrage isolé",
-            "isolatedTransformingPreview": "Aperçu de transformation isolée",
             "invertBrushSizeScrollDirection": "Inverser le défilement pour la taille du pinceau",
             "pressureSensitivity": "Sensibilité à la pression",
             "preserveMask": {
@@ -1789,9 +1823,10 @@
                 "alert": "Préserver la zone masquée"
             },
             "isolatedPreview": "Aperçu Isolé",
-            "isolatedStagingPreview": "Aperçu de l'attente isolé"
+            "isolatedStagingPreview": "Aperçu de l'attente isolé",
+            "isolatedLayerPreview": "Aperçu de la couche isolée",
+            "isolatedLayerPreviewDesc": "Pour afficher uniquement cette couche lors de l'exécution d'opérations telles que le filtrage ou la transformation."
         },
-        "convertToRasterLayer": "Convertir en Couche de Rastérisation",
         "transparency": "Transparence",
         "moveBackward": "Reculer",
         "rectangle": "Rectangle",
@@ -1914,7 +1949,6 @@
         "globalReferenceImage_withCount_one": "$t(controlLayers.globalReferenceImage)",
         "globalReferenceImage_withCount_many": "Images de référence globales",
         "globalReferenceImage_withCount_other": "Images de référence globales",
-        "convertToControlLayer": "Convertir en Couche de Contrôle",
         "layer_withCount_one": "Couche {{count}}",
         "layer_withCount_many": "Couches {{count}}",
         "layer_withCount_other": "Couches {{count}}",
@@ -1977,7 +2011,41 @@
         "pullBboxIntoReferenceImageOk": "Bounding Box insérée dans l'Image de référence",
         "controlLayer_withCount_one": "$t(controlLayers.controlLayer)",
         "controlLayer_withCount_many": "Controler les couches",
-        "controlLayer_withCount_other": "Controler les couches"
+        "controlLayer_withCount_other": "Controler les couches",
+        "copyInpaintMaskTo": "Copier $t(controlLayers.inpaintMask) vers",
+        "copyRegionalGuidanceTo": "Copier $t(controlLayers.regionalGuidance) vers",
+        "convertRasterLayerTo": "Convertir $t(controlLayers.rasterLayer) vers",
+        "selectObject": {
+            "selectObject": "Sélectionner l'objet",
+            "clickToAdd": "Cliquez sur la couche pour ajouter un point",
+            "apply": "Appliquer",
+            "cancel": "Annuler",
+            "dragToMove": "Faites glisser un point pour le déplacer",
+            "clickToRemove": "Cliquez sur un point pour le supprimer",
+            "include": "Inclure",
+            "invertSelection": "Sélection Inversée",
+            "saveAs": "Enregistrer sous",
+            "neutral": "Neutre",
+            "pointType": "Type de point",
+            "exclude": "Exclure",
+            "process": "Traiter",
+            "reset": "Réinitialiser",
+            "help1": "Sélectionnez un seul objet cible. Ajoutez des points <Bold>Inclure</Bold> et <Bold>Exclure</Bold> pour indiquer quelles parties de la couche font partie de l'objet cible.",
+            "help2": "Commencez par un point <Bold>Inclure</Bold> au sein de l'objet cible. Ajoutez d'autres points pour affiner la sélection. Moins de points produisent généralement de meilleurs résultats.",
+            "help3": "Inversez la sélection pour sélectionner tout sauf l'objet cible."
+        },
+        "canvasAsControlLayer": "$t(controlLayers.canvas) en tant que $t(controlLayers.controlLayer)",
+        "convertRegionalGuidanceTo": "Convertir $t(controlLayers.regionalGuidance) vers",
+        "copyRasterLayerTo": "Copier $t(controlLayers.rasterLayer) vers",
+        "newControlLayer": "Nouveau $t(controlLayers.controlLayer)",
+        "newRegionalGuidance": "Nouveau $t(controlLayers.regionalGuidance)",
+        "replaceCurrent": "Remplacer Actuel",
+        "convertControlLayerTo": "Convertir $t(controlLayers.controlLayer) vers",
+        "convertInpaintMaskTo": "Convertir $t(controlLayers.inpaintMask) vers",
+        "copyControlLayerTo": "Copier $t(controlLayers.controlLayer) vers",
+        "newInpaintMask": "Nouveau $t(controlLayers.inpaintMask)",
+        "newRasterLayer": "Nouveau $t(controlLayers.rasterLayer)",
+        "canvasAsRasterLayer": "$t(controlLayers.canvas) en tant que $t(controlLayers.rasterLayer)"
     },
     "upscaling": {
         "exceedsMaxSizeDetails": "La limite maximale d'agrandissement est de {{maxUpscaleDimension}}x{{maxUpscaleDimension}} pixels. Veuillez essayer une image plus petite ou réduire votre sélection d'échelle.",
@@ -2048,7 +2116,7 @@
             "config": "Configuration",
             "canvas": "Toile",
             "generation": "Génération",
-            "workflows": "Processus",
+            "workflows": "Workflows",
             "system": "Système",
             "models": "Modèles",
             "logNamespaces": "Journalisation des espaces de noms",
@@ -2071,9 +2139,9 @@
     "newUserExperience": {
         "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",
+        "noModelsInstalled": "Il semble qu'aucun modèle ne soit installé",
         "downloadStarterModels": "Télécharger les modèles de démarrage",
-        "importModels": "Importer Modèles",
+        "importModels": "Importer des 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": {

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

@@ -92,7 +92,9 @@
         "none": "Niente",
         "new": "Nuovo",
         "view": "Vista",
-        "close": "Chiudi"
+        "close": "Chiudi",
+        "clipboard": "Appunti",
+        "ok": "Ok"
     },
     "gallery": {
         "galleryImageSize": "Dimensione dell'immagine",
@@ -542,7 +544,6 @@
         "defaultSettingsSaved": "Impostazioni predefinite salvate",
         "defaultSettings": "Impostazioni predefinite",
         "metadata": "Metadati",
-        "useDefaultSettings": "Usa le impostazioni predefinite",
         "triggerPhrases": "Frasi Trigger",
         "deleteModelImage": "Elimina l'immagine del modello",
         "localOnly": "solo locale",
@@ -588,7 +589,15 @@
         "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."
+        "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.",
+        "noDefaultSettings": "Nessuna impostazione predefinita configurata per questo modello. Visita Gestione Modelli per aggiungere impostazioni predefinite.",
+        "defaultSettingsOutOfSync": "Alcune impostazioni non corrispondono a quelle predefinite del modello:",
+        "restoreDefaultSettings": "Fare clic per utilizzare le impostazioni predefinite del modello.",
+        "usingDefaultSettings": "Utilizzo delle impostazioni predefinite del modello",
+        "huggingFace": "HuggingFace",
+        "huggingFaceRepoID": "HuggingFace Repository ID",
+        "clipEmbed": "CLIP Embed",
+        "t5Encoder": "T5 Encoder"
     },
     "parameters": {
         "images": "Immagini",
@@ -689,7 +698,8 @@
         "boxBlur": "Sfocatura Box",
         "staged": "Maschera espansa",
         "optimizedImageToImage": "Immagine-a-immagine ottimizzata",
-        "sendToCanvas": "Invia alla Tela"
+        "sendToCanvas": "Invia alla Tela",
+        "coherenceMinDenoise": "Riduzione minima del rumore"
     },
     "settings": {
         "models": "Modelli",
@@ -724,7 +734,10 @@
         "reloadingIn": "Ricaricando in",
         "informationalPopoversDisabled": "Testo informativo a comparsa disabilitato",
         "informationalPopoversDisabledDesc": "I testi informativi a comparsa sono disabilitati. Attivali nelle impostazioni.",
-        "confirmOnNewSession": "Conferma su nuova sessione"
+        "confirmOnNewSession": "Conferma su nuova sessione",
+        "enableModelDescriptions": "Abilita le descrizioni dei modelli nei menu a discesa",
+        "modelDescriptionsDisabled": "Descrizioni dei modelli nei menu a discesa disabilitate",
+        "modelDescriptionsDisabledDesc": "Le descrizioni dei modelli nei menu a discesa sono state disabilitate. Abilitale nelle Impostazioni."
     },
     "toast": {
         "uploadFailed": "Caricamento fallito",
@@ -1076,7 +1089,8 @@
         "noLoRAsInstalled": "Nessun LoRA installato",
         "addLora": "Aggiungi LoRA",
         "defaultVAE": "VAE predefinito",
-        "concepts": "Concetti"
+        "concepts": "Concetti",
+        "lora": "LoRA"
     },
     "invocationCache": {
         "disable": "Disabilita",
@@ -1133,7 +1147,8 @@
             "paragraphs": [
                 "Scegli quanti livelli del modello CLIP saltare.",
                 "Alcuni modelli funzionano meglio con determinate impostazioni di CLIP Skip."
-            ]
+            ],
+            "heading": "CLIP Skip"
         },
         "compositingCoherencePass": {
             "heading": "Passaggio di Coerenza",
@@ -1492,6 +1507,42 @@
                 "Controlla quanto il prompt influenza il processo di generazione.",
                 "Valori di guida elevati possono causare sovrasaturazione e una guida elevata o bassa può causare risultati di generazione distorti. La guida si applica solo ai modelli FLUX DEV."
             ]
+        },
+        "regionalReferenceImage": {
+            "paragraphs": [
+                "Pennello per applicare un'immagine di riferimento ad aree specifiche."
+            ],
+            "heading": "Immagine di riferimento Regionale"
+        },
+        "rasterLayer": {
+            "paragraphs": [
+                "Contenuto basato sui pixel della tua tela, utilizzato durante la generazione dell'immagine."
+            ],
+            "heading": "Livello Raster"
+        },
+        "regionalGuidance": {
+            "heading": "Guida Regionale",
+            "paragraphs": [
+                "Pennello per guidare la posizione in cui devono apparire gli elementi dei prompt globali."
+            ]
+        },
+        "regionalGuidanceAndReferenceImage": {
+            "heading": "Guida regionale e immagine di riferimento regionale",
+            "paragraphs": [
+                "Per la Guida Regionale, utilizzare il pennello per indicare dove devono apparire gli elementi dei prompt globali.",
+                "Per l'immagine di riferimento regionale, utilizzare il pennello per applicare un'immagine di riferimento ad aree specifiche."
+            ]
+        },
+        "globalReferenceImage": {
+            "heading": "Immagine di riferimento Globale",
+            "paragraphs": [
+                "Applica un'immagine di riferimento per influenzare l'intera generazione."
+            ]
+        },
+        "inpainting": {
+            "paragraphs": [
+                "Controlla quale area viene modificata, in base all'intensità di riduzione del rumore."
+            ]
         }
     },
     "sdxl": {
@@ -1513,7 +1564,6 @@
         "refinerSteps": "Passi Affinamento"
     },
     "metadata": {
-        "seamless": "Senza giunture",
         "positivePrompt": "Prompt positivo",
         "negativePrompt": "Prompt negativo",
         "generationMode": "Modalità generazione",
@@ -1541,7 +1591,10 @@
         "parsingFailed": "Analisi non riuscita",
         "recallParameter": "Richiama {{label}}",
         "canvasV2Metadata": "Tela",
-        "guidance": "Guida"
+        "guidance": "Guida",
+        "seamlessXAxis": "Asse X senza giunte",
+        "seamlessYAxis": "Asse Y senza giunte",
+        "vae": "VAE"
     },
     "hrf": {
         "enableHrf": "Abilita Correzione Alta Risoluzione",
@@ -1638,11 +1691,11 @@
         "regionalGuidance": "Guida regionale",
         "opacity": "Opacità",
         "mergeVisible": "Fondi il visibile",
-        "mergeVisibleOk": "Livelli visibili uniti",
+        "mergeVisibleOk": "Livelli uniti",
         "deleteReferenceImage": "Elimina l'immagine di riferimento",
         "referenceImage": "Immagine di riferimento",
         "fitBboxToLayers": "Adatta il riquadro di delimitazione ai livelli",
-        "mergeVisibleError": "Errore durante l'unione dei livelli visibili",
+        "mergeVisibleError": "Errore durante l'unione dei livelli",
         "regionalReferenceImage": "Immagine di riferimento Regionale",
         "newLayerFromImage": "Nuovo livello da immagine",
         "newCanvasFromImage": "Nuova tela da immagine",
@@ -1734,7 +1787,7 @@
             "composition": "Solo Composizione",
             "ipAdapterMethod": "Metodo Adattatore IP"
         },
-        "showingType": "Mostrare {{type}}",
+        "showingType": "Mostra {{type}}",
         "dynamicGrid": "Griglia dinamica",
         "tool": {
             "view": "Muovi",
@@ -1862,8 +1915,6 @@
         "layer_withCount_one": "Livello ({{count}})",
         "layer_withCount_many": "Livelli ({{count}})",
         "layer_withCount_other": "Livelli ({{count}})",
-        "convertToControlLayer": "Converti in livello di controllo",
-        "convertToRasterLayer": "Converti in livello raster",
         "unlocked": "Sbloccato",
         "enableTransparencyEffect": "Abilita l'effetto trasparenza",
         "replaceLayer": "Sostituisci livello",
@@ -1876,9 +1927,7 @@
         "newCanvasSession": "Nuova sessione Tela",
         "deleteSelected": "Elimina selezione",
         "settings": {
-            "isolatedFilteringPreview": "Anteprima del filtraggio isolata",
             "isolatedStagingPreview": "Anteprima di generazione isolata",
-            "isolatedTransformingPreview": "Anteprima di trasformazione isolata",
             "isolatedPreview": "Anteprima isolata",
             "invertBrushSizeScrollDirection": "Inverti scorrimento per dimensione pennello",
             "snapToGrid": {
@@ -1890,7 +1939,9 @@
             "preserveMask": {
                 "alert": "Preservare la regione mascherata",
                 "label": "Preserva la regione mascherata"
-            }
+            },
+            "isolatedLayerPreview": "Anteprima livello isolato",
+            "isolatedLayerPreviewDesc": "Se visualizzare solo questo livello quando si eseguono operazioni come il filtraggio o la trasformazione."
         },
         "transform": {
             "reset": "Reimposta",
@@ -1935,9 +1986,46 @@
             "canvasGroup": "Tela",
             "newRasterLayer": "Nuovo Livello Raster",
             "saveCanvasToGallery": "Salva la Tela nella Galleria",
-            "saveToGalleryGroup": "Salva nella Galleria"
+            "saveToGalleryGroup": "Salva nella Galleria",
+            "newInpaintMask": "Nuova maschera Inpaint",
+            "newRegionalGuidance": "Nuova Guida Regionale"
         },
-        "newImg2ImgCanvasFromImage": "Nuova Immagine da immagine"
+        "newImg2ImgCanvasFromImage": "Nuova Immagine da immagine",
+        "copyRasterLayerTo": "Copia $t(controlLayers.rasterLayer) in",
+        "copyControlLayerTo": "Copia $t(controlLayers.controlLayer) in",
+        "copyInpaintMaskTo": "Copia $t(controlLayers.inpaintMask) in",
+        "selectObject": {
+            "dragToMove": "Trascina un punto per spostarlo",
+            "clickToAdd": "Fare clic sul livello per aggiungere un punto",
+            "clickToRemove": "Clicca su un punto per rimuoverlo",
+            "help3": "Inverte la selezione per selezionare tutto tranne l'oggetto di destinazione.",
+            "pointType": "Tipo punto",
+            "apply": "Applica",
+            "reset": "Reimposta",
+            "cancel": "Annulla",
+            "selectObject": "Seleziona oggetto",
+            "invertSelection": "Inverti selezione",
+            "exclude": "Escludi",
+            "include": "Includi",
+            "neutral": "Neutro",
+            "saveAs": "Salva come",
+            "process": "Elabora",
+            "help1": "Seleziona un singolo oggetto di destinazione. Aggiungi i punti <Bold>Includi</Bold> e <Bold>Escludi</Bold> per indicare quali parti del livello fanno parte dell'oggetto di destinazione.",
+            "help2": "Inizia con un punto <Bold>Include</Bold> all'interno dell'oggetto di destinazione. Aggiungi altri punti per perfezionare la selezione. Meno punti in genere producono risultati migliori."
+        },
+        "convertControlLayerTo": "Converti $t(controlLayers.controlLayer) in",
+        "newRasterLayer": "Nuovo $t(controlLayers.rasterLayer)",
+        "newRegionalGuidance": "Nuova $t(controlLayers.regionalGuidance)",
+        "canvasAsRasterLayer": "$t(controlLayers.canvas) come $t(controlLayers.rasterLayer)",
+        "canvasAsControlLayer": "$t(controlLayers.canvas) come $t(controlLayers.controlLayer)",
+        "convertInpaintMaskTo": "Converti $t(controlLayers.inpaintMask) in",
+        "copyRegionalGuidanceTo": "Copia $t(controlLayers.regionalGuidance) in",
+        "convertRasterLayerTo": "Converti $t(controlLayers.rasterLayer) in",
+        "convertRegionalGuidanceTo": "Converti $t(controlLayers.regionalGuidance) in",
+        "newControlLayer": "Nuovo $t(controlLayers.controlLayer)",
+        "newInpaintMask": "Nuova $t(controlLayers.inpaintMask)",
+        "replaceCurrent": "Sostituisci corrente",
+        "mergeDown": "Unire in basso"
     },
     "ui": {
         "tabs": {
@@ -2030,15 +2118,13 @@
         "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": {
-            "readReleaseNotes": "Leggi le Note di Rilascio",
-            "fluxSupport": "Supporto per la famiglia di modelli Flux",
-            "newCanvas": "Una nuova potente tela di controllo",
-            "watchReleaseVideo": "Guarda il video di rilascio",
-            "watchUiUpdatesOverview": "Guarda le novità dell'interfaccia",
-            "newLayerTypes": "Nuovi tipi di livello per un miglior controllo"
-        },
-        "whatsNewInInvoke": "Novità in Invoke"
+        "whatsNewInInvoke": "Novità in Invoke",
+        "line2": "Supporto Flux esteso, ora con immagini di riferimento globali",
+        "line3": "Tooltip e menu contestuali migliorati",
+        "readReleaseNotes": "Leggi le note di rilascio",
+        "watchRecentReleaseVideos": "Guarda i video su questa versione",
+        "line1": "Strumento <ItalicComponent>Seleziona oggetto</ItalicComponent> per la selezione e la modifica precise degli oggetti",
+        "watchUiUpdatesOverview": "Guarda le novità dell'interfaccia"
     },
     "system": {
         "logLevel": {

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

@@ -229,7 +229,6 @@
         "submitSupportTicket": "サポート依頼を送信する"
     },
     "metadata": {
-        "seamless": "シームレス",
         "Threshold": "ノイズ閾値",
         "seed": "シード",
         "width": "幅",

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

@@ -155,7 +155,6 @@
         "path": "Pad",
         "triggerPhrases": "Triggerzinnen",
         "typePhraseHere": "Typ zin hier in",
-        "useDefaultSettings": "Gebruik standaardinstellingen",
         "modelImageDeleteFailed": "Fout bij verwijderen modelafbeelding",
         "modelImageUpdated": "Modelafbeelding bijgewerkt",
         "modelImageUpdateFailed": "Fout bij bijwerken modelafbeelding",
@@ -666,7 +665,6 @@
         }
     },
     "metadata": {
-        "seamless": "Naadloos",
         "positivePrompt": "Positieve prompt",
         "negativePrompt": "Negatieve prompt",
         "generationMode": "Genereermodus",

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

@@ -544,7 +544,6 @@
         "scanResults": "Результаты сканирования",
         "source": "Источник",
         "triggerPhrases": "Триггерные фразы",
-        "useDefaultSettings": "Использовать стандартные настройки",
         "modelName": "Название модели",
         "modelSettings": "Настройки модели",
         "upcastAttention": "Внимание",
@@ -573,7 +572,6 @@
         "simpleModelPlaceholder": "URL или путь к локальному файлу или папке diffusers",
         "urlOrLocalPath": "URL или локальный путь",
         "urlOrLocalPathHelper": "URL-адреса должны указывать на один файл. Локальные пути могут указывать на один файл или папку для одной модели диффузоров.",
-        "hfToken": "Токен HuggingFace",
         "starterModels": "Стартовые модели",
         "textualInversions": "Текстовые инверсии",
         "loraModels": "LoRAs",
@@ -1402,7 +1400,6 @@
         }
     },
     "metadata": {
-        "seamless": "Бесшовность",
         "positivePrompt": "Запрос",
         "negativePrompt": "Негативный запрос",
         "generationMode": "Режим генерации",
@@ -1836,14 +1833,12 @@
         },
         "settings": {
             "isolatedPreview": "Изолированный предпросмотр",
-            "isolatedTransformingPreview": "Изолированный предпросмотр преобразования",
             "invertBrushSizeScrollDirection": "Инвертировать прокрутку для размера кисти",
             "snapToGrid": {
                 "label": "Привязка к сетке",
                 "on": "Вкл",
                 "off": "Выкл"
             },
-            "isolatedFilteringPreview": "Изолированный предпросмотр фильтрации",
             "pressureSensitivity": "Чувствительность к давлению",
             "isolatedStagingPreview": "Изолированный предпросмотр на промежуточной стадии",
             "preserveMask": {
@@ -1865,7 +1860,6 @@
         "enableAutoNegative": "Включить авто негатив",
         "maskFill": "Заполнение маски",
         "viewProgressInViewer": "Просматривайте прогресс и результаты в <Btn>Просмотрщике изображений</Btn>.",
-        "convertToRasterLayer": "Конвертировать в растровый слой",
         "tool": {
             "move": "Двигать",
             "bbox": "Ограничительная рамка",
@@ -1933,7 +1927,6 @@
         "newGallerySession": "Новая сессия галереи",
         "sendToCanvasDesc": "Нажатие кнопки Invoke отображает вашу текущую работу на холсте.",
         "globalReferenceImages_withCount_hidden": "Глобальные эталонные изображения ({{count}} скрыто)",
-        "convertToControlLayer": "Конвертировать в контрольный слой",
         "layer_withCount_one": "Слой ({{count}})",
         "layer_withCount_few": "Слои ({{count}})",
         "layer_withCount_many": "Слои ({{count}})",
@@ -2063,14 +2056,6 @@
         }
     },
     "whatsNew": {
-        "canvasV2Announcement": {
-            "newLayerTypes": "Новые типы слоев для еще большего контроля",
-            "readReleaseNotes": "Прочитать информацию о выпуске",
-            "watchReleaseVideo": "Смотреть видео о выпуске",
-            "fluxSupport": "Поддержка семейства моделей Flux",
-            "newCanvas": "Новый мощный холст управления",
-            "watchUiUpdatesOverview": "Обзор обновлений пользовательского интерфейса"
-        },
         "whatsNewInInvoke": "Что нового в Invoke"
     },
     "newUserExperience": {

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

@@ -82,7 +82,21 @@
         "dontShowMeThese": "请勿显示这些内容",
         "beta": "测试版",
         "toResolve": "解决",
-        "tab": "标签页"
+        "tab": "标签页",
+        "apply": "应用",
+        "edit": "编辑",
+        "off": "关",
+        "loadingImage": "正在加载图片",
+        "ok": "确定",
+        "placeholderSelectAModel": "选择一个模型",
+        "close": "关闭",
+        "reset": "重设",
+        "none": "无",
+        "new": "新建",
+        "view": "视图",
+        "alpha": "透明度通道",
+        "openInViewer": "在查看器中打开",
+        "clipboard": "剪贴板"
     },
     "gallery": {
         "galleryImageSize": "预览大小",
@@ -124,7 +138,7 @@
         "selectAllOnPage": "选择本页全部",
         "swapImages": "交换图像",
         "exitBoardSearch": "退出面板搜索",
-        "exitSearch": "退出搜索",
+        "exitSearch": "退出图像搜索",
         "oldestFirst": "最旧在前",
         "sortDirection": "排序方向",
         "showStarredImagesFirst": "优先显示收藏的图片",
@@ -135,17 +149,333 @@
         "searchImages": "按元数据搜索",
         "jump": "跳过",
         "compareHelp2": "按 <Kbd>M</Kbd> 键切换不同的比较模式。",
-        "displayBoardSearch": "显示面板搜索",
-        "displaySearch": "显示搜索",
+        "displayBoardSearch": "板块搜索",
+        "displaySearch": "图像搜索",
         "stretchToFit": "拉伸以适应",
         "exitCompare": "退出对比",
         "compareHelp1": "在点击图库中的图片或使用箭头键切换比较图片时，请按住<Kbd>Alt</Kbd> 键。",
-        "go": "运行"
+        "go": "运行",
+        "boardsSettings": "画板设置",
+        "imagesSettings": "画廊图片设置",
+        "gallery": "画廊",
+        "move": "移动",
+        "imagesTab": "您在Invoke中创建和保存的图片。",
+        "openViewer": "打开查看器",
+        "closeViewer": "关闭查看器",
+        "assetsTab": "您已上传用于项目的文件。"
     },
     "hotkeys": {
         "searchHotkeys": "检索快捷键",
         "noHotkeysFound": "未找到快捷键",
-        "clearSearch": "清除检索项"
+        "clearSearch": "清除检索项",
+        "app": {
+            "cancelQueueItem": {
+                "title": "取消",
+                "desc": "取消当前正在处理的队列项目。"
+            },
+            "selectQueueTab": {
+                "title": "选择队列标签",
+                "desc": "选择队列标签。"
+            },
+            "toggleLeftPanel": {
+                "desc": "显示或隐藏左侧面板。",
+                "title": "开关左侧面板"
+            },
+            "resetPanelLayout": {
+                "title": "重设面板布局",
+                "desc": "将左侧和右侧面板重置为默认大小和布局。"
+            },
+            "togglePanels": {
+                "title": "开关面板",
+                "desc": "同时显示或隐藏左右两侧的面板。"
+            },
+            "selectWorkflowsTab": {
+                "title": "选择工作流标签",
+                "desc": "选择工作流标签。"
+            },
+            "selectModelsTab": {
+                "title": "选择模型标签",
+                "desc": "选择模型标签。"
+            },
+            "toggleRightPanel": {
+                "title": "开关右侧面板",
+                "desc": "显示或隐藏右侧面板。"
+            },
+            "clearQueue": {
+                "title": "清除队列",
+                "desc": "取消并清除所有队列条目。"
+            },
+            "selectCanvasTab": {
+                "title": "选择画布标签",
+                "desc": "选择画布标签。"
+            },
+            "invokeFront": {
+                "desc": "将生成请求排队，添加到队列的前面。",
+                "title": "调用（前台）"
+            },
+            "selectUpscalingTab": {
+                "title": "选择放大选项卡",
+                "desc": "选择高清放大选项卡。"
+            },
+            "focusPrompt": {
+                "title": "聚焦提示",
+                "desc": "将光标焦点移动到正向提示。"
+            },
+            "title": "应用程序",
+            "invoke": {
+                "title": "调用",
+                "desc": "将生成请求排队，添加到队列的末尾。"
+            }
+        },
+        "canvas": {
+            "selectBrushTool": {
+                "title": "画笔工具",
+                "desc": "选择画笔工具。"
+            },
+            "selectEraserTool": {
+                "title": "橡皮擦工具",
+                "desc": "选择橡皮擦工具。"
+            },
+            "title": "画布",
+            "selectColorPickerTool": {
+                "title": "拾色器工具",
+                "desc": "选择拾色器工具。"
+            },
+            "fitBboxToCanvas": {
+                "title": "使边界框适应画布",
+                "desc": "缩放并调整视图以适应边界框。"
+            },
+            "setZoomTo400Percent": {
+                "title": "缩放到400%",
+                "desc": "将画布的缩放设置为400%。"
+            },
+            "setZoomTo800Percent": {
+                "desc": "将画布的缩放设置为800%。",
+                "title": "缩放到800%"
+            },
+            "redo": {
+                "desc": "重做上一次画布操作。",
+                "title": "重做"
+            },
+            "nextEntity": {
+                "title": "下一层",
+                "desc": "在列表中选择下一层。"
+            },
+            "selectRectTool": {
+                "title": "矩形工具",
+                "desc": "选择矩形工具。"
+            },
+            "selectViewTool": {
+                "title": "视图工具",
+                "desc": "选择视图工具。"
+            },
+            "prevEntity": {
+                "desc": "在列表中选择上一层。",
+                "title": "上一层"
+            },
+            "transformSelected": {
+                "desc": "变换所选图层。",
+                "title": "变换"
+            },
+            "selectBboxTool": {
+                "title": "边界框工具",
+                "desc": "选择边界框工具。"
+            },
+            "setZoomTo200Percent": {
+                "title": "缩放到200%",
+                "desc": "将画布的缩放设置为200%。"
+            },
+            "applyFilter": {
+                "title": "应用过滤器",
+                "desc": "将待处理的过滤器应用于所选图层。"
+            },
+            "filterSelected": {
+                "title": "过滤器",
+                "desc": "对所选图层进行过滤。仅适用于栅格层和控制层。"
+            },
+            "cancelFilter": {
+                "title": "取消过滤器",
+                "desc": "取消待处理的过滤器。"
+            },
+            "incrementToolWidth": {
+                "title": "增加工具宽度",
+                "desc": "增加所选的画笔或橡皮擦工具的宽度。"
+            },
+            "decrementToolWidth": {
+                "desc": "减少所选的画笔或橡皮擦工具的宽度。",
+                "title": "减少工具宽度"
+            },
+            "selectMoveTool": {
+                "title": "移动工具",
+                "desc": "选择移动工具。"
+            },
+            "setFillToWhite": {
+                "title": "将颜色设置为白色",
+                "desc": "将当前工具的颜色设置为白色。"
+            },
+            "cancelTransform": {
+                "desc": "取消待处理的变换。",
+                "title": "取消变换"
+            },
+            "applyTransform": {
+                "title": "应用变换",
+                "desc": "将待处理的变换应用于所选图层。"
+            },
+            "setZoomTo100Percent": {
+                "title": "缩放到100%",
+                "desc": "将画布的缩放设置为100%。"
+            },
+            "resetSelected": {
+                "title": "重置图层",
+                "desc": "重置选定的图层。仅适用于修复蒙版和区域指导。"
+            },
+            "undo": {
+                "title": "撤消",
+                "desc": "撤消上一次画布操作。"
+            },
+            "quickSwitch": {
+                "title": "图层快速切换",
+                "desc": "在最后两个选定的图层之间切换。如果某个图层被书签标记，则始终在该图层和最后一个未标记的图层之间切换。"
+            },
+            "fitLayersToCanvas": {
+                "title": "使图层适应画布",
+                "desc": "缩放并调整视图以适应所有可见图层。"
+            },
+            "deleteSelected": {
+                "title": "删除图层",
+                "desc": "删除选定的图层。"
+            }
+        },
+        "hotkeys": "快捷键",
+        "workflows": {
+            "pasteSelection": {
+                "title": "粘贴",
+                "desc": "粘贴复制的节点和边。"
+            },
+            "title": "工作流",
+            "addNode": {
+                "title": "添加节点",
+                "desc": "打开添加节点菜单。"
+            },
+            "copySelection": {
+                "desc": "复制选定的节点和边。",
+                "title": "复制"
+            },
+            "pasteSelectionWithEdges": {
+                "title": "带边缘的粘贴",
+                "desc": "粘贴复制的节点、边，以及与复制的节点连接的所有边。"
+            },
+            "selectAll": {
+                "title": "全选",
+                "desc": "选择所有节点和边。"
+            },
+            "deleteSelection": {
+                "title": "删除",
+                "desc": "删除选定的节点和边。"
+            },
+            "undo": {
+                "title": "撤销",
+                "desc": "撤销上一个工作流操作。"
+            },
+            "redo": {
+                "desc": "重做上一个工作流操作。",
+                "title": "重做"
+            }
+        },
+        "gallery": {
+            "title": "画廊",
+            "galleryNavUp": {
+                "title": "向上导航",
+                "desc": "在图库网格中向上导航，选择该图像。如果在页面顶部，则转到上一页。"
+            },
+            "galleryNavUpAlt": {
+                "title": "向上导航（比较图像）",
+                "desc": "与向上导航相同，但选择比较图像，如果比较模式尚未打开，则将其打开。"
+            },
+            "selectAllOnPage": {
+                "desc": "选择当前页面上的所有图像。",
+                "title": "选页面上的所有内容"
+            },
+            "galleryNavDownAlt": {
+                "title": "向下导航（比较图像）",
+                "desc": "与向下导航相同，但选择比较图像，如果比较模式尚未打开，则将其打开。"
+            },
+            "galleryNavLeftAlt": {
+                "title": "向左导航（比较图像）",
+                "desc": "与向左导航相同，但选择比较图像，如果比较模式尚未打开，则将其打开。"
+            },
+            "clearSelection": {
+                "title": "清除选择",
+                "desc": "清除当前的选择（如果有的话）。"
+            },
+            "deleteSelection": {
+                "title": "删除",
+                "desc": "删除所有选定的图像。默认情况下，系统会提示您确认删除。如果这些图像当前在应用中使用，系统将发出警告。"
+            },
+            "galleryNavLeft": {
+                "title": "向左导航",
+                "desc": "在图库网格中向左导航，选择该图像。如果处于行的第一张图像，转到上一行。如果处于页面的第一张图像，转到上一页。"
+            },
+            "galleryNavRight": {
+                "title": "向右导航",
+                "desc": "在图库网格中向右导航，选择该图像。如果在行的最后一张图像，转到下一行。如果在页面的最后一张图像，转到下一页。"
+            },
+            "galleryNavDown": {
+                "desc": "在图库网格中向下导航，选择该图像。如果在页面底部，则转到下一页。",
+                "title": "向下导航"
+            },
+            "galleryNavRightAlt": {
+                "title": "向右导航（比较图像）",
+                "desc": "与向右导航相同，但选择比较图像，如果比较模式尚未打开，则将其打开。"
+            }
+        },
+        "viewer": {
+            "toggleMetadata": {
+                "desc": "显示或隐藏当前图像的元数据覆盖。",
+                "title": "显示/隐藏元数据"
+            },
+            "recallPrompts": {
+                "desc": "召回当前图像的正面和负面提示。",
+                "title": "召回提示"
+            },
+            "toggleViewer": {
+                "title": "显示/隐藏图像查看器",
+                "desc": "显示或隐藏图像查看器。仅在画布选项卡上可用。"
+            },
+            "recallAll": {
+                "desc": "召回当前图像的所有元数据。",
+                "title": "召回所有元数据"
+            },
+            "recallSeed": {
+                "title": "召回种子",
+                "desc": "召回当前图像的种子。"
+            },
+            "swapImages": {
+                "title": "交换比较图像",
+                "desc": "交换正在比较的图像。"
+            },
+            "nextComparisonMode": {
+                "title": "下一个比较模式",
+                "desc": "环浏览比较模式。"
+            },
+            "loadWorkflow": {
+                "title": "加载工作流",
+                "desc": "加载当前图像的保存工作流程（如果有的话）。"
+            },
+            "title": "图像查看器",
+            "remix": {
+                "title": "混合",
+                "desc": "召回当前图像的所有元数据，除了种子。"
+            },
+            "useSize": {
+                "title": "使用尺寸",
+                "desc": "使用当前图像的尺寸作为边界框尺寸。"
+            },
+            "runPostprocessing": {
+                "title": "行后处理",
+                "desc": "对当前图像运行所选的后处理。"
+            }
+        }
     },
     "modelManager": {
         "modelManager": "模型管理器",
@@ -210,7 +540,6 @@
         "noModelsInstalled": "无已安装的模型",
         "urlOrLocalPathHelper": "链接应该指向单个文件.本地路径可以指向单个文件,或者对于单个扩散模型(diffusers model),可以指向一个文件夹.",
         "modelSettings": "模型设置",
-        "useDefaultSettings": "使用默认设置",
         "scanPlaceholder": "本地文件夹路径",
         "installRepo": "安装仓库",
         "modelImageDeleted": "模型图像已删除",
@@ -249,7 +578,16 @@
         "loraTriggerPhrases": "LoRA 触发词",
         "ipAdapters": "IP适配器",
         "spandrelImageToImage": "图生图(Spandrel)",
-        "starterModelsInModelManager": "您可以在模型管理器中找到初始模型"
+        "starterModelsInModelManager": "您可以在模型管理器中找到初始模型",
+        "noDefaultSettings": "此模型没有配置默认设置。请访问模型管理器添加默认设置。",
+        "clipEmbed": "CLIP 嵌入",
+        "defaultSettingsOutOfSync": "某些设置与模型的默认值不匹配：",
+        "restoreDefaultSettings": "点击以使用模型的默认设置。",
+        "usingDefaultSettings": "使用模型的默认设置",
+        "huggingFace": "HuggingFace",
+        "hfTokenInvalid": "HF 令牌无效或缺失",
+        "hfTokenLabel": "HuggingFace 令牌（某些模型所需）",
+        "hfTokenHelperText": "使用某些模型需要 HF 令牌。点击这里创建或获取你的令牌。"
     },
     "parameters": {
         "images": "图像",
@@ -367,7 +705,7 @@
         "uploadFailed": "上传失败",
         "imageCopied": "图像已复制",
         "parametersNotSet": "参数未恢复",
-        "uploadFailedInvalidUploadDesc": "必须是单张的 PNG 或 JPEG 图片",
+        "uploadFailedInvalidUploadDesc": "必须是单个 PNG 或 JPEG 图像。",
         "connected": "服务器连接",
         "parameterSet": "参数已恢复",
         "parameterNotSet": "参数未恢复",
@@ -379,7 +717,7 @@
         "setControlImage": "设为控制图像",
         "setNodeField": "设为节点字段",
         "imageUploaded": "图像已上传",
-        "addedToBoard": "已添加到面板",
+        "addedToBoard": "添加到{{name}}的资产中",
         "workflowLoaded": "工作流已加载",
         "imageUploadFailed": "图像上传失败",
         "baseModelChangedCleared_other": "已清除或禁用{{count}}个不兼容的子模型",
@@ -416,7 +754,9 @@
         "createIssue": "创建问题",
         "about": "关于",
         "submitSupportTicket": "提交支持工单",
-        "toggleRightPanel": "切换右侧面板(G)"
+        "toggleRightPanel": "切换右侧面板(G)",
+        "uploadImages": "上传图片",
+        "toggleLeftPanel": "开关左侧面板(T)"
     },
     "nodes": {
         "zoomInNodes": "放大",
@@ -569,7 +909,7 @@
         "cancelSucceeded": "项目已取消",
         "queue": "队列",
         "batch": "批处理",
-        "clearQueueAlertDialog": "清除队列时会立即取消所有处理中的项目并且会完全清除队列。",
+        "clearQueueAlertDialog": "清空队列将立即取消所有正在处理的项目，并完全清空队列。待处理的过滤器将被取消。",
         "pending": "待定",
         "completedIn": "完成于",
         "resumeFailed": "恢复处理器时出现问题",
@@ -610,7 +950,15 @@
         "openQueue": "打开队列",
         "prompts_other": "提示词",
         "iterations_other": "迭代",
-        "generations_other": "生成"
+        "generations_other": "生成",
+        "canvas": "画布",
+        "workflows": "工作流",
+        "generation": "生成",
+        "other": "其他",
+        "gallery": "画廊",
+        "destination": "目标存储",
+        "upscaling": "高清放大",
+        "origin": "来源"
     },
     "sdxl": {
         "refinerStart": "Refiner 开始作用时机",
@@ -649,7 +997,6 @@
         "workflow": "工作流",
         "steps": "步数",
         "scheduler": "调度器",
-        "seamless": "无缝",
         "recallParameters": "召回参数",
         "noRecallParameters": "未找到要召回的参数",
         "vae": "VAE",
@@ -658,7 +1005,11 @@
         "parsingFailed": "解析失败",
         "recallParameter": "调用{{label}}",
         "imageDimensions": "图像尺寸",
-        "parameterSet": "已设置参数{{parameter}}"
+        "parameterSet": "已设置参数{{parameter}}",
+        "guidance": "指导",
+        "seamlessXAxis": "无缝 X 轴",
+        "seamlessYAxis": "无缝 Y 轴",
+        "canvasV2Metadata": "画布"
     },
     "models": {
         "noMatchingModels": "无相匹配的模型",
@@ -709,7 +1060,8 @@
         "shared": "共享面板",
         "archiveBoard": "归档面板",
         "archived": "已归档",
-        "assetsWithCount_other": "{{count}}项资源"
+        "assetsWithCount_other": "{{count}}项资源",
+        "updateBoardError": "更新画板出错"
     },
     "dynamicPrompts": {
         "seedBehaviour": {
@@ -1175,7 +1527,8 @@
     },
     "prompt": {
         "addPromptTrigger": "添加提示词触发器",
-        "noMatchingTriggers": "没有匹配的触发器"
+        "noMatchingTriggers": "没有匹配的触发器",
+        "compatibleEmbeddings": "兼容的嵌入"
     },
     "controlLayers": {
         "autoNegative": "自动反向",
@@ -1186,8 +1539,8 @@
         "moveToFront": "移动到前面",
         "addLayer": "添加层",
         "deletePrompt": "删除提示词",
-        "addPositivePrompt": "添加 $t(common.positivePrompt)",
-        "addNegativePrompt": "添加 $t(common.negativePrompt)",
+        "addPositivePrompt": "添加 $t(controlLayers.prompt)",
+        "addNegativePrompt": "添加 $t(controlLayers.negativePrompt)",
         "rectangle": "矩形",
         "opacity": "透明度"
     },

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

@@ -58,7 +58,6 @@
         "model": "模型",
         "seed": "種子",
         "vae": "VAE",
-        "seamless": "無縫",
         "metadata": "元數據",
         "width": "寬度",
         "height": "高度"

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

@@ -8,10 +8,8 @@ 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';
-import ImageUploadOverlay from 'common/components/ImageUploadOverlay';
 import { useFocusRegionWatcher } from 'common/hooks/focus';
 import { useClearStorage } from 'common/hooks/useClearStorage';
-import { useFullscreenDropzone } from 'common/hooks/useFullscreenDropzone';
 import { useGlobalHotkeys } from 'common/hooks/useGlobalHotkeys';
 import ChangeBoardModal from 'features/changeBoardModal/components/ChangeBoardModal';
 import {
@@ -19,6 +17,7 @@ import {
   NewGallerySessionDialog,
 } from 'features/controlLayers/components/NewSessionConfirmationAlertDialog';
 import DeleteImageModal from 'features/deleteImageModal/components/DeleteImageModal';
+import { FullscreenDropzone } from 'features/dnd/FullscreenDropzone';
 import { DynamicPromptsModal } from 'features/dynamicPrompts/components/DynamicPromptsPreviewModal';
 import DeleteBoardModal from 'features/gallery/components/Boards/DeleteBoardModal';
 import { ImageContextMenu } from 'features/gallery/components/ImageContextMenu/ImageContextMenu';
@@ -62,8 +61,6 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
   useGetOpenAPISchemaQuery();
   useSyncLoggingConfig();
 
-  const { dropzone, isHandlingUpload, setIsHandlingUpload } = useFullscreenDropzone();
-
   const handleReset = useCallback(() => {
     clearStorage();
     location.reload();
@@ -92,19 +89,8 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
 
   return (
     <ErrorBoundary onReset={handleReset} FallbackComponent={AppErrorBoundaryFallback}>
-      <Box
-        id="invoke-app-wrapper"
-        w="100dvw"
-        h="100dvh"
-        position="relative"
-        overflow="hidden"
-        {...dropzone.getRootProps()}
-      >
-        <input {...dropzone.getInputProps()} />
+      <Box id="invoke-app-wrapper" w="100dvw" h="100dvh" position="relative" overflow="hidden">
         <AppContent />
-        {dropzone.isDragActive && isHandlingUpload && (
-          <ImageUploadOverlay dropzone={dropzone} setIsHandlingUpload={setIsHandlingUpload} />
-        )}
       </Box>
       <DeleteImageModal />
       <ChangeBoardModal />
@@ -121,6 +107,7 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
       <NewGallerySessionDialog />
       <NewCanvasSessionDialog />
       <ImageContextMenu />
+      <FullscreenDropzone />
     </ErrorBoundary>
   );
 };

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

@@ -1,4 +1,3 @@
-import { skipToken } from '@reduxjs/toolkit/query';
 import { useAppSelector } from 'app/store/storeHooks';
 import { useIsRegionFocused } from 'common/hooks/focus';
 import { useAssertSingleton } from 'common/hooks/useAssertSingleton';
@@ -8,13 +7,11 @@ import { selectLastSelectedImage } from 'features/gallery/store/gallerySelectors
 import { useRegisteredHotkeys } from 'features/system/components/HotkeysModal/useHotkeyData';
 import { useFeatureStatus } from 'features/system/hooks/useFeatureStatus';
 import { memo } from 'react';
-import { useGetImageDTOQuery } from 'services/api/endpoints/images';
 import type { ImageDTO } from 'services/api/types';
 
 export const GlobalImageHotkeys = memo(() => {
   useAssertSingleton('GlobalImageHotkeys');
-  const lastSelectedImage = useAppSelector(selectLastSelectedImage);
-  const { currentData: imageDTO } = useGetImageDTOQuery(lastSelectedImage?.image_name ?? skipToken);
+  const imageDTO = useAppSelector(selectLastSelectedImage);
 
   if (!imageDTO) {
     return null;

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

@@ -19,7 +19,6 @@ import { $workflowCategories } from 'app/store/nanostores/workflowCategories';
 import { createStore } from 'app/store/store';
 import type { PartialAppConfig } from 'app/types/invokeai';
 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, useLayoutEffect, useMemo } from 'react';
@@ -237,9 +236,7 @@ const InvokeAIUI = ({
       <Provider store={store}>
         <React.Suspense fallback={<Loading />}>
           <ThemeLocaleProvider>
-            <AppDndContext>
-              <App config={config} studioInitAction={studioInitAction} />
-            </AppDndContext>
+            <App config={config} studioInitAction={studioInitAction} />
           </ThemeLocaleProvider>
         </React.Suspense>
       </Provider>

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

@@ -17,6 +17,7 @@ const $logger = atom<Logger>(Roarr.child(BASE_CONTEXT));
 export const zLogNamespace = z.enum([
   'canvas',
   'config',
+  'dnd',
   'events',
   'gallery',
   'generation',

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

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

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/index.ts

@@ -16,7 +16,6 @@ import { addGalleryOffsetChangedListener } from 'app/store/middleware/listenerMi
 import { addGetOpenAPISchemaListener } from 'app/store/middleware/listenerMiddleware/listeners/getOpenAPISchema';
 import { addImageAddedToBoardFulfilledListener } from 'app/store/middleware/listenerMiddleware/listeners/imageAddedToBoard';
 import { addImageDeletionListeners } from 'app/store/middleware/listenerMiddleware/listeners/imageDeletionListeners';
-import { addImageDroppedListener } from 'app/store/middleware/listenerMiddleware/listeners/imageDropped';
 import { addImageRemovedFromBoardFulfilledListener } from 'app/store/middleware/listenerMiddleware/listeners/imageRemovedFromBoard';
 import { addImagesStarredListener } from 'app/store/middleware/listenerMiddleware/listeners/imagesStarred';
 import { addImagesUnstarredListener } from 'app/store/middleware/listenerMiddleware/listeners/imagesUnstarred';
@@ -93,9 +92,6 @@ addGetOpenAPISchemaListener(startAppListening);
 addWorkflowLoadRequestedListener(startAppListening);
 addUpdateAllNodesRequestedListener(startAppListening);
 
-// DND
-addImageDroppedListener(startAppListening);
-
 // Models
 addModelSelectedListener(startAppListening);
 

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

@@ -1,12 +1,12 @@
 import { createAction } from '@reduxjs/toolkit';
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import type { SerializableObject } from 'common/types';
 import { buildAdHocPostProcessingGraph } from 'features/nodes/util/graph/buildAdHocPostProcessingGraph';
 import { toast } from 'features/toast/toast';
 import { t } from 'i18next';
 import { queueApi } from 'services/api/endpoints/queue';
 import type { BatchConfig, ImageDTO } from 'services/api/types';
+import type { JsonObject } from 'type-fest';
 
 const log = logger('queue');
 
@@ -39,9 +39,9 @@ export const addAdHocPostProcessingRequestedListener = (startAppListening: AppSt
 
         const enqueueResult = await req.unwrap();
         req.reset();
-        log.debug({ enqueueResult } as SerializableObject, t('queue.graphQueued'));
+        log.debug({ enqueueResult } as JsonObject, t('queue.graphQueued'));
       } catch (error) {
-        log.error({ enqueueBatchArg } as SerializableObject, t('queue.graphFailedToQueue'));
+        log.error({ enqueueBatchArg } as JsonObject, t('queue.graphFailedToQueue'));
 
         if (error instanceof Object && 'status' in error && error.status === 403) {
           return;

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

@@ -1,12 +1,12 @@
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import type { SerializableObject } from 'common/types';
 import { zPydanticValidationError } from 'features/system/store/zodSchemas';
 import { toast } from 'features/toast/toast';
 import { t } from 'i18next';
 import { truncate, upperFirst } from 'lodash-es';
 import { serializeError } from 'serialize-error';
 import { queueApi } from 'services/api/endpoints/queue';
+import type { JsonObject } from 'type-fest';
 
 const log = logger('queue');
 
@@ -17,7 +17,7 @@ export const addBatchEnqueuedListener = (startAppListening: AppStartListening) =
     effect: (action) => {
       const enqueueResult = action.payload;
       const arg = action.meta.arg.originalArgs;
-      log.debug({ enqueueResult } as SerializableObject, 'Batch enqueued');
+      log.debug({ enqueueResult } as JsonObject, 'Batch enqueued');
 
       toast({
         id: 'QUEUE_BATCH_SUCCEEDED',
@@ -45,7 +45,7 @@ export const addBatchEnqueuedListener = (startAppListening: AppStartListening) =
           status: 'error',
           description: t('common.unknownError'),
         });
-        log.error({ batchConfig } as SerializableObject, t('queue.batchFailedToQueue'));
+        log.error({ batchConfig } as JsonObject, t('queue.batchFailedToQueue'));
         return;
       }
 
@@ -71,7 +71,7 @@ export const addBatchEnqueuedListener = (startAppListening: AppStartListening) =
           description: t('common.unknownError'),
         });
       }
-      log.error({ batchConfig, error: serializeError(response) } as SerializableObject, t('queue.batchFailedToQueue'));
+      log.error({ batchConfig, error: serializeError(response) } as JsonObject, t('queue.batchFailedToQueue'));
     },
   });
 };

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

@@ -1,19 +1,22 @@
 import { logger } from 'app/logging/logger';
 import { enqueueRequested } from 'app/store/actions';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import type { SerializableObject } from 'common/types';
+import { extractMessageFromAssertionError } from 'common/util/extractMessageFromAssertionError';
 import type { Result } from 'common/util/result';
 import { withResult, withResultAsync } from 'common/util/result';
 import { $canvasManager } from 'features/controlLayers/store/ephemeral';
 import { prepareLinearUIBatch } from 'features/nodes/util/graph/buildLinearBatchConfig';
 import { buildFLUXGraph } from 'features/nodes/util/graph/generation/buildFLUXGraph';
 import { buildSD1Graph } from 'features/nodes/util/graph/generation/buildSD1Graph';
+import { buildSD3Graph } from 'features/nodes/util/graph/generation/buildSD3Graph';
 import { buildSDXLGraph } from 'features/nodes/util/graph/generation/buildSDXLGraph';
 import type { Graph } from 'features/nodes/util/graph/generation/Graph';
+import { toast } from 'features/toast/toast';
 import { serializeError } from 'serialize-error';
 import { queueApi } from 'services/api/endpoints/queue';
 import type { Invocation } from 'services/api/types';
-import { assert } from 'tsafe';
+import { assert, AssertionError } from 'tsafe';
+import type { JsonObject } from 'type-fest';
 
 const log = logger('generation');
 
@@ -32,8 +35,8 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
       let buildGraphResult: Result<
         {
           g: Graph;
-          noise: Invocation<'noise' | 'flux_denoise'>;
-          posCond: Invocation<'compel' | 'sdxl_compel_prompt' | 'flux_text_encoder'>;
+          noise: Invocation<'noise' | 'flux_denoise' | 'sd3_denoise'>;
+          posCond: Invocation<'compel' | 'sdxl_compel_prompt' | 'flux_text_encoder' | 'sd3_text_encoder'>;
         },
         Error
       >;
@@ -49,6 +52,9 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
         case `sd-2`:
           buildGraphResult = await withResultAsync(() => buildSD1Graph(state, manager));
           break;
+        case `sd-3`:
+          buildGraphResult = await withResultAsync(() => buildSD3Graph(state, manager));
+          break;
         case `flux`:
           buildGraphResult = await withResultAsync(() => buildFLUXGraph(state, manager));
           break;
@@ -57,7 +63,17 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
       }
 
       if (buildGraphResult.isErr()) {
-        log.error({ error: serializeError(buildGraphResult.error) }, 'Failed to build graph');
+        let description: string | null = null;
+        if (buildGraphResult.error instanceof AssertionError) {
+          description = extractMessageFromAssertionError(buildGraphResult.error);
+        }
+        const error = serializeError(buildGraphResult.error);
+        log.error({ error }, 'Failed to build graph');
+        toast({
+          status: 'error',
+          title: 'Failed to build graph',
+          description,
+        });
         return;
       }
 
@@ -88,7 +104,7 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
         return;
       }
 
-      log.debug({ batchConfig: prepareBatchResult.value } as SerializableObject, 'Enqueued batch');
+      log.debug({ batchConfig: prepareBatchResult.value } as JsonObject, 'Enqueued batch');
     },
   });
 };

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

@@ -1,12 +1,12 @@
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import type { SerializableObject } from 'common/types';
 import { parseify } from 'common/util/serialize';
 import { $templates } from 'features/nodes/store/nodesSlice';
 import { parseSchema } from 'features/nodes/util/schema/parseSchema';
 import { size } from 'lodash-es';
 import { serializeError } from 'serialize-error';
 import { appInfoApi } from 'services/api/endpoints/appInfo';
+import type { JsonObject } from 'type-fest';
 
 const log = logger('system');
 
@@ -16,12 +16,12 @@ export const addGetOpenAPISchemaListener = (startAppListening: AppStartListening
     effect: (action, { getState }) => {
       const schemaJSON = action.payload;
 
-      log.debug({ schemaJSON: parseify(schemaJSON) } as SerializableObject, 'Received OpenAPI schema');
+      log.debug({ schemaJSON: parseify(schemaJSON) } as JsonObject, 'Received OpenAPI schema');
       const { nodesAllowlist, nodesDenylist } = getState().config;
 
       const nodeTemplates = parseSchema(schemaJSON, nodesAllowlist, nodesDenylist);
 
-      log.debug({ nodeTemplates } as SerializableObject, `Built ${size(nodeTemplates)} node templates`);
+      log.debug({ nodeTemplates } as JsonObject, `Built ${size(nodeTemplates)} node templates`);
 
       $templates.set(nodeTemplates);
     },

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

@@ -1,292 +0,0 @@
-import { createAction } from '@reduxjs/toolkit';
-import { logger } from 'app/logging/logger';
-import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import { deepClone } from 'common/util/deepClone';
-import { selectDefaultControlAdapter, selectDefaultIPAdapter } from 'features/controlLayers/hooks/addLayerHooks';
-import { getPrefixedId } from 'features/controlLayers/konva/util';
-import {
-  controlLayerAdded,
-  entityRasterized,
-  entitySelected,
-  rasterLayerAdded,
-  referenceImageAdded,
-  referenceImageIPAdapterImageChanged,
-  rgAdded,
-  rgIPAdapterImageChanged,
-} from 'features/controlLayers/store/canvasSlice';
-import { selectCanvasSlice } from 'features/controlLayers/store/selectors';
-import type {
-  CanvasControlLayerState,
-  CanvasRasterLayerState,
-  CanvasReferenceImageState,
-  CanvasRegionalGuidanceState,
-} from 'features/controlLayers/store/types';
-import { imageDTOToImageObject, imageDTOToImageWithDims } from 'features/controlLayers/store/util';
-import type { TypesafeDraggableData, TypesafeDroppableData } from 'features/dnd/types';
-import { isValidDrop } from 'features/dnd/util/isValidDrop';
-import { imageToCompareChanged, selectionChanged } from 'features/gallery/store/gallerySlice';
-import { fieldImageValueChanged } from 'features/nodes/store/nodesSlice';
-import { upscaleInitialImageChanged } from 'features/parameters/store/upscaleSlice';
-import { imagesApi } from 'services/api/endpoints/images';
-
-export const dndDropped = createAction<{
-  overData: TypesafeDroppableData;
-  activeData: TypesafeDraggableData;
-}>('dnd/dndDropped');
-
-const log = logger('system');
-
-export const addImageDroppedListener = (startAppListening: AppStartListening) => {
-  startAppListening({
-    actionCreator: dndDropped,
-    effect: (action, { dispatch, getState }) => {
-      const { activeData, overData } = action.payload;
-      if (!isValidDrop(overData, activeData)) {
-        return;
-      }
-
-      if (activeData.payloadType === 'IMAGE_DTO') {
-        log.debug({ activeData, overData }, 'Image dropped');
-      } else if (activeData.payloadType === 'GALLERY_SELECTION') {
-        log.debug({ activeData, overData }, `Images (${getState().gallery.selection.length}) dropped`);
-      } else if (activeData.payloadType === 'NODE_FIELD') {
-        log.debug({ activeData, overData }, 'Node field dropped');
-      } else {
-        log.debug({ activeData, overData }, `Unknown payload dropped`);
-      }
-
-      /**
-       * Image dropped on IP Adapter Layer
-       */
-      if (
-        overData.actionType === 'SET_IPA_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { id } = overData.context;
-        dispatch(
-          referenceImageIPAdapterImageChanged({
-            entityIdentifier: { id, type: 'reference_image' },
-            imageDTO: activeData.payload.imageDTO,
-          })
-        );
-        return;
-      }
-
-      /**
-       * Image dropped on RG Layer IP Adapter
-       */
-      if (
-        overData.actionType === 'SET_RG_IP_ADAPTER_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { id, referenceImageId } = overData.context;
-        dispatch(
-          rgIPAdapterImageChanged({
-            entityIdentifier: { id, type: 'regional_guidance' },
-            referenceImageId,
-            imageDTO: activeData.payload.imageDTO,
-          })
-        );
-        return;
-      }
-
-      /**
-       * Image dropped on Raster layer
-       */
-      if (
-        overData.actionType === 'ADD_RASTER_LAYER_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
-        const { x, y } = selectCanvasSlice(getState()).bbox.rect;
-        const overrides: Partial<CanvasRasterLayerState> = {
-          objects: [imageObject],
-          position: { x, y },
-        };
-        dispatch(rasterLayerAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      /**
-       * Image dropped on Raster layer
-       */
-      if (
-        overData.actionType === 'ADD_CONTROL_LAYER_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const state = getState();
-        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
-        const { x, y } = selectCanvasSlice(state).bbox.rect;
-        const defaultControlAdapter = selectDefaultControlAdapter(state);
-        const overrides: Partial<CanvasControlLayerState> = {
-          objects: [imageObject],
-          position: { x, y },
-          controlAdapter: defaultControlAdapter,
-        };
-        dispatch(controlLayerAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      if (
-        overData.actionType === 'ADD_REGIONAL_REFERENCE_IMAGE_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const state = getState();
-        const ipAdapter = deepClone(selectDefaultIPAdapter(state));
-        ipAdapter.image = imageDTOToImageWithDims(activeData.payload.imageDTO);
-        const overrides: Partial<CanvasRegionalGuidanceState> = {
-          referenceImages: [{ id: getPrefixedId('regional_guidance_reference_image'), ipAdapter }],
-        };
-        dispatch(rgAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      if (
-        overData.actionType === 'ADD_GLOBAL_REFERENCE_IMAGE_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const state = getState();
-        const ipAdapter = deepClone(selectDefaultIPAdapter(state));
-        ipAdapter.image = imageDTOToImageWithDims(activeData.payload.imageDTO);
-        const overrides: Partial<CanvasReferenceImageState> = {
-          ipAdapter,
-        };
-        dispatch(referenceImageAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      /**
-       * Image dropped on Raster layer
-       */
-      if (overData.actionType === 'REPLACE_LAYER_WITH_IMAGE' && activeData.payloadType === 'IMAGE_DTO') {
-        const state = getState();
-        const { entityIdentifier } = overData.context;
-        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
-        const { x, y } = selectCanvasSlice(state).bbox.rect;
-        dispatch(entityRasterized({ entityIdentifier, imageObject, position: { x, y }, replaceObjects: true }));
-        dispatch(entitySelected({ entityIdentifier }));
-        return;
-      }
-
-      /**
-       * Image dropped on node image field
-       */
-      if (
-        overData.actionType === 'SET_NODES_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { fieldName, nodeId } = overData.context;
-        dispatch(
-          fieldImageValueChanged({
-            nodeId,
-            fieldName,
-            value: activeData.payload.imageDTO,
-          })
-        );
-        return;
-      }
-
-      /**
-       * Image selected for compare
-       */
-      if (
-        overData.actionType === 'SELECT_FOR_COMPARE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { imageDTO } = activeData.payload;
-        dispatch(imageToCompareChanged(imageDTO));
-        return;
-      }
-
-      /**
-       * Image dropped on user board
-       */
-      if (
-        overData.actionType === 'ADD_TO_BOARD' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { imageDTO } = activeData.payload;
-        const { boardId } = overData.context;
-        dispatch(
-          imagesApi.endpoints.addImageToBoard.initiate({
-            imageDTO,
-            board_id: boardId,
-          })
-        );
-        dispatch(selectionChanged([]));
-        return;
-      }
-
-      /**
-       * Image dropped on 'none' board
-       */
-      if (
-        overData.actionType === 'REMOVE_FROM_BOARD' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { imageDTO } = activeData.payload;
-        dispatch(
-          imagesApi.endpoints.removeImageFromBoard.initiate({
-            imageDTO,
-          })
-        );
-        dispatch(selectionChanged([]));
-        return;
-      }
-
-      /**
-       * Image dropped on upscale initial image
-       */
-      if (
-        overData.actionType === 'SET_UPSCALE_INITIAL_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { imageDTO } = activeData.payload;
-
-        dispatch(upscaleInitialImageChanged(imageDTO));
-        return;
-      }
-
-      /**
-       * Multiple images dropped on user board
-       */
-      if (overData.actionType === 'ADD_TO_BOARD' && activeData.payloadType === 'GALLERY_SELECTION') {
-        const imageDTOs = getState().gallery.selection;
-        const { boardId } = overData.context;
-        dispatch(
-          imagesApi.endpoints.addImagesToBoard.initiate({
-            imageDTOs,
-            board_id: boardId,
-          })
-        );
-        dispatch(selectionChanged([]));
-        return;
-      }
-
-      /**
-       * Multiple images dropped on 'none' board
-       */
-      if (overData.actionType === 'REMOVE_FROM_BOARD' && activeData.payloadType === 'GALLERY_SELECTION') {
-        const imageDTOs = getState().gallery.selection;
-        dispatch(
-          imagesApi.endpoints.removeImagesFromBoard.initiate({
-            imageDTOs,
-          })
-        );
-        dispatch(selectionChanged([]));
-        return;
-      }
-    },
-  });
-};

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

@@ -1,18 +1,8 @@
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
 import type { RootState } from 'app/store/store';
-import {
-  entityRasterized,
-  entitySelected,
-  referenceImageIPAdapterImageChanged,
-  rgIPAdapterImageChanged,
-} from 'features/controlLayers/store/canvasSlice';
-import { selectCanvasSlice } from 'features/controlLayers/store/selectors';
-import { imageDTOToImageObject } from 'features/controlLayers/store/util';
 import { selectListBoardsQueryArgs } from 'features/gallery/store/gallerySelectors';
 import { boardIdSelected, galleryViewChanged } from 'features/gallery/store/gallerySlice';
-import { fieldImageValueChanged } from 'features/nodes/store/nodesSlice';
-import { upscaleInitialImageChanged } from 'features/parameters/store/upscaleSlice';
 import { toast } from 'features/toast/toast';
 import { t } from 'i18next';
 import { omit } from 'lodash-es';
@@ -51,12 +41,14 @@ export const addImageUploadedFulfilledListener = (startAppListening: AppStartLis
 
       log.debug({ imageDTO }, 'Image uploaded');
 
-      const { postUploadAction } = action.meta.arg.originalArgs;
-
-      if (!postUploadAction) {
+      if (action.meta.arg.originalArgs.silent || imageDTO.is_intermediate) {
+        // When a "silent" upload is requested, or the image is intermediate, we can skip all post-upload actions,
+        // like toasts and switching the gallery view
         return;
       }
 
+      const boardId = imageDTO.board_id ?? 'none';
+
       const DEFAULT_UPLOADED_TOAST = {
         id: 'IMAGE_UPLOADED',
         title: t('toast.imageUploaded'),
@@ -64,80 +56,34 @@ export const addImageUploadedFulfilledListener = (startAppListening: AppStartLis
       } as const;
 
       // default action - just upload and alert user
-      if (postUploadAction.type === 'TOAST') {
-        const boardId = imageDTO.board_id ?? 'none';
-        if (lastUploadedToastTimeout !== null) {
-          window.clearTimeout(lastUploadedToastTimeout);
-        }
-        const toastApi = toast({
-          ...DEFAULT_UPLOADED_TOAST,
-          title: postUploadAction.title || DEFAULT_UPLOADED_TOAST.title,
-          description: getUploadedToastDescription(boardId, state),
-          duration: null, // we will close the toast manually
-        });
-        lastUploadedToastTimeout = window.setTimeout(() => {
-          toastApi.close();
-        }, 3000);
-        /**
-         * We only want to change the board and view if this is the first upload of a batch, else we end up hijacking
-         * the user's gallery board and view selection:
-         * - User uploads multiple images
-         * - A couple uploads finish, but others are pending still
-         * - User changes the board selection
-         * - Pending uploads finish and change the board back to the original board
-         * - User is confused as to why the board changed
-         *
-         * Default to true to not require _all_ image upload handlers to set this value
-         */
-        const isFirstUploadOfBatch = action.meta.arg.originalArgs.isFirstUploadOfBatch ?? true;
-        if (isFirstUploadOfBatch) {
-          dispatch(boardIdSelected({ boardId }));
-          dispatch(galleryViewChanged('assets'));
-        }
-        return;
+      if (lastUploadedToastTimeout !== null) {
+        window.clearTimeout(lastUploadedToastTimeout);
       }
+      const toastApi = toast({
+        ...DEFAULT_UPLOADED_TOAST,
+        title: DEFAULT_UPLOADED_TOAST.title,
+        description: getUploadedToastDescription(boardId, state),
+        duration: null, // we will close the toast manually
+      });
+      lastUploadedToastTimeout = window.setTimeout(() => {
+        toastApi.close();
+      }, 3000);
 
-      if (postUploadAction.type === 'SET_UPSCALE_INITIAL_IMAGE') {
-        dispatch(upscaleInitialImageChanged(imageDTO));
-        toast({
-          ...DEFAULT_UPLOADED_TOAST,
-          description: 'set as upscale initial image',
-        });
-        return;
-      }
-
-      if (postUploadAction.type === 'SET_IPA_IMAGE') {
-        const { id } = postUploadAction;
-        dispatch(referenceImageIPAdapterImageChanged({ entityIdentifier: { id, type: 'reference_image' }, imageDTO }));
-        toast({ ...DEFAULT_UPLOADED_TOAST, description: t('toast.setControlImage') });
-        return;
-      }
-
-      if (postUploadAction.type === 'SET_RG_IP_ADAPTER_IMAGE') {
-        const { id, referenceImageId } = postUploadAction;
-        dispatch(
-          rgIPAdapterImageChanged({ entityIdentifier: { id, type: 'regional_guidance' }, referenceImageId, imageDTO })
-        );
-        toast({ ...DEFAULT_UPLOADED_TOAST, description: t('toast.setControlImage') });
-        return;
-      }
-
-      if (postUploadAction.type === 'SET_NODES_IMAGE') {
-        const { nodeId, fieldName } = postUploadAction;
-        dispatch(fieldImageValueChanged({ nodeId, fieldName, value: imageDTO }));
-        toast({ ...DEFAULT_UPLOADED_TOAST, description: `${t('toast.setNodeField')} ${fieldName}` });
-        return;
-      }
-
-      if (postUploadAction.type === 'REPLACE_LAYER_WITH_IMAGE') {
-        const { entityIdentifier } = postUploadAction;
-
-        const state = getState();
-        const imageObject = imageDTOToImageObject(imageDTO);
-        const { x, y } = selectCanvasSlice(state).bbox.rect;
-        dispatch(entityRasterized({ entityIdentifier, imageObject, position: { x, y }, replaceObjects: true }));
-        dispatch(entitySelected({ entityIdentifier }));
-        return;
+      /**
+       * We only want to change the board and view if this is the first upload of a batch, else we end up hijacking
+       * the user's gallery board and view selection:
+       * - User uploads multiple images
+       * - A couple uploads finish, but others are pending still
+       * - User changes the board selection
+       * - Pending uploads finish and change the board back to the original board
+       * - User is confused as to why the board changed
+       *
+       * Default to true to not require _all_ image upload handlers to set this value
+       */
+      const isFirstUploadOfBatch = action.meta.arg.originalArgs.isFirstUploadOfBatch ?? true;
+      if (isFirstUploadOfBatch) {
+        dispatch(boardIdSelected({ boardId }));
+        dispatch(galleryViewChanged('assets'));
       }
     },
   });

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

@@ -1,7 +1,6 @@
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
 import type { AppDispatch, RootState } from 'app/store/store';
-import type { SerializableObject } from 'common/types';
 import {
   controlLayerModelChanged,
   referenceImageIPAdapterModelChanged,
@@ -41,6 +40,7 @@ import {
   isSpandrelImageToImageModelConfig,
   isT5EncoderModelConfig,
 } from 'services/api/types';
+import type { JsonObject } from 'type-fest';
 
 const log = logger('models');
 
@@ -85,7 +85,7 @@ type ModelHandler = (
   models: AnyModelConfig[],
   state: RootState,
   dispatch: AppDispatch,
-  log: Logger<SerializableObject>
+  log: Logger<JsonObject>
 ) => undefined;
 
 const handleMainModels: ModelHandler = (models, state, dispatch, log) => {
@@ -164,7 +164,7 @@ const handleVAEModels: ModelHandler = (models, state, dispatch, log) => {
   // We have a VAE selected, need to check if it is available
 
   // Grab just the VAE models
-  const vaeModels = models.filter(isNonFluxVAEModelConfig);
+  const vaeModels = models.filter((m) => isNonFluxVAEModelConfig(m));
 
   // If the current VAE model is available, we don't need to do anything
   if (vaeModels.some((m) => m.key === selectedVAEModel.key)) {
@@ -297,7 +297,7 @@ const handleUpscaleModel: ModelHandler = (models, state, dispatch, log) => {
 
 const handleT5EncoderModels: ModelHandler = (models, state, dispatch, log) => {
   const selectedT5EncoderModel = state.params.t5EncoderModel;
-  const t5EncoderModels = models.filter(isT5EncoderModelConfig);
+  const t5EncoderModels = models.filter((m) => isT5EncoderModelConfig(m));
 
   // If the currently selected model is available, we don't need to do anything
   if (selectedT5EncoderModel && t5EncoderModels.some((m) => m.key === selectedT5EncoderModel.key)) {
@@ -325,7 +325,7 @@ const handleT5EncoderModels: ModelHandler = (models, state, dispatch, log) => {
 
 const handleCLIPEmbedModels: ModelHandler = (models, state, dispatch, log) => {
   const selectedCLIPEmbedModel = state.params.clipEmbedModel;
-  const CLIPEmbedModels = models.filter(isCLIPEmbedModelConfig);
+  const CLIPEmbedModels = models.filter((m) => isCLIPEmbedModelConfig(m));
 
   // If the currently selected model is available, we don't need to do anything
   if (selectedCLIPEmbedModel && CLIPEmbedModels.some((m) => m.key === selectedCLIPEmbedModel.key)) {
@@ -353,7 +353,7 @@ const handleCLIPEmbedModels: ModelHandler = (models, state, dispatch, log) => {
 
 const handleFLUXVAEModels: ModelHandler = (models, state, dispatch, log) => {
   const selectedFLUXVAEModel = state.params.fluxVAE;
-  const fluxVAEModels = models.filter(isFluxVAEModelConfig);
+  const fluxVAEModels = models.filter((m) => isFluxVAEModelConfig(m));
 
   // If the currently selected model is available, we don't need to do anything
   if (selectedFLUXVAEModel && fluxVAEModels.some((m) => m.key === selectedFLUXVAEModel.key)) {

invokeai/frontend/web/src/app/store/nanostores/util.ts

@@ -4,6 +4,8 @@ import { atom } from 'nanostores';
 /**
  * A fallback non-writable atom that always returns `false`, used when a nanostores atom is only conditionally available
  * in a hook or component.
+ *
+ * @knipignore
  */
 export const $false: ReadableAtom<boolean> = atom(false);
 /**

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

@@ -3,7 +3,6 @@ import { autoBatchEnhancer, combineReducers, configureStore } from '@reduxjs/too
 import { logger } from 'app/logging/logger';
 import { idbKeyValDriver } from 'app/store/enhancers/reduxRemember/driver';
 import { errorHandler } from 'app/store/enhancers/reduxRemember/errors';
-import type { SerializableObject } from 'common/types';
 import { deepClone } from 'common/util/deepClone';
 import { changeBoardModalSlice } from 'features/changeBoardModal/store/slice';
 import { canvasSettingsPersistConfig, canvasSettingsSlice } from 'features/controlLayers/store/canvasSettingsSlice';
@@ -37,6 +36,7 @@ import undoable from 'redux-undo';
 import { serializeError } from 'serialize-error';
 import { api } from 'services/api';
 import { authToastMiddleware } from 'services/api/authToastMiddleware';
+import type { JsonObject } from 'type-fest';
 
 import { STORAGE_PREFIX } from './constants';
 import { actionSanitizer } from './middleware/devtools/actionSanitizer';
@@ -139,7 +139,7 @@ const unserialize: UnserializeFunction = (data, key) => {
       {
         persistedData: parsed,
         rehydratedData: transformed,
-        diff: diff(parsed, transformed) as SerializableObject, // this is always serializable
+        diff: diff(parsed, transformed) as JsonObject, // this is always serializable
       },
       `Rehydrated slice "${key}"`
     );

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

@@ -25,7 +25,8 @@ export type AppFeature =
   | 'invocationCache'
   | 'bulkDownload'
   | 'starterModels'
-  | 'hfToken';
+  | 'hfToken'
+  | 'invocationProgressAlert';
 
 /**
  * A disable-able Stable Diffusion feature

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

@@ -1,251 +0,0 @@
-import type { ChakraProps, FlexProps, SystemStyleObject } from '@invoke-ai/ui-library';
-import { Flex, Icon, Image } from '@invoke-ai/ui-library';
-import { IAILoadingImageFallback, IAINoContentFallback } from 'common/components/IAIImageFallback';
-import ImageMetadataOverlay from 'common/components/ImageMetadataOverlay';
-import { useImageUploadButton } from 'common/hooks/useImageUploadButton';
-import type { TypesafeDraggableData, TypesafeDroppableData } from 'features/dnd/types';
-import { useImageContextMenu } from 'features/gallery/components/ImageContextMenu/ImageContextMenu';
-import type { MouseEvent, ReactElement, ReactNode, SyntheticEvent } from 'react';
-import { memo, useCallback, useMemo, useRef } from 'react';
-import { PiImageBold, PiUploadSimpleBold } from 'react-icons/pi';
-import type { ImageDTO, PostUploadAction } from 'services/api/types';
-
-import IAIDraggable from './IAIDraggable';
-import IAIDroppable from './IAIDroppable';
-
-const defaultUploadElement = <Icon as={PiUploadSimpleBold} boxSize={16} />;
-
-const defaultNoContentFallback = <IAINoContentFallback icon={PiImageBold} />;
-
-const baseStyles: SystemStyleObject = {
-  touchAction: 'none',
-  userSelect: 'none',
-  webkitUserSelect: 'none',
-};
-
-const sx: SystemStyleObject = {
-  ...baseStyles,
-  '.gallery-image-container::before': {
-    content: '""',
-    display: 'inline-block',
-    position: 'absolute',
-    top: 0,
-    left: 0,
-    right: 0,
-    bottom: 0,
-    pointerEvents: 'none',
-    borderRadius: 'base',
-  },
-  '&[data-selected="selected"]>.gallery-image-container::before': {
-    boxShadow:
-      'inset 0px 0px 0px 3px var(--invoke-colors-invokeBlue-500), inset 0px 0px 0px 4px var(--invoke-colors-invokeBlue-800)',
-  },
-  '&[data-selected="selectedForCompare"]>.gallery-image-container::before': {
-    boxShadow:
-      'inset 0px 0px 0px 3px var(--invoke-colors-invokeGreen-300), inset 0px 0px 0px 4px var(--invoke-colors-invokeGreen-800)',
-  },
-  '&:hover>.gallery-image-container::before': {
-    boxShadow:
-      'inset 0px 0px 0px 2px var(--invoke-colors-invokeBlue-300), inset 0px 0px 0px 3px var(--invoke-colors-invokeBlue-800)',
-  },
-  '&:hover[data-selected="selected"]>.gallery-image-container::before': {
-    boxShadow:
-      'inset 0px 0px 0px 3px var(--invoke-colors-invokeBlue-400), inset 0px 0px 0px 4px var(--invoke-colors-invokeBlue-800)',
-  },
-  '&:hover[data-selected="selectedForCompare"]>.gallery-image-container::before': {
-    boxShadow:
-      'inset 0px 0px 0px 3px var(--invoke-colors-invokeGreen-200), inset 0px 0px 0px 4px var(--invoke-colors-invokeGreen-800)',
-  },
-};
-
-type IAIDndImageProps = FlexProps & {
-  imageDTO: ImageDTO | undefined;
-  onError?: (event: SyntheticEvent<HTMLImageElement>) => void;
-  onLoad?: (event: SyntheticEvent<HTMLImageElement>) => void;
-  onClick?: (event: MouseEvent<HTMLDivElement>) => void;
-  withMetadataOverlay?: boolean;
-  isDragDisabled?: boolean;
-  isDropDisabled?: boolean;
-  isUploadDisabled?: boolean;
-  minSize?: number;
-  postUploadAction?: PostUploadAction;
-  imageSx?: ChakraProps['sx'];
-  fitContainer?: boolean;
-  droppableData?: TypesafeDroppableData;
-  draggableData?: TypesafeDraggableData;
-  dropLabel?: string;
-  isSelected?: boolean;
-  isSelectedForCompare?: boolean;
-  thumbnail?: boolean;
-  noContentFallback?: ReactElement;
-  useThumbailFallback?: boolean;
-  withHoverOverlay?: boolean;
-  children?: JSX.Element;
-  uploadElement?: ReactNode;
-  dataTestId?: string;
-};
-
-const IAIDndImage = (props: IAIDndImageProps) => {
-  const {
-    imageDTO,
-    onError,
-    onClick,
-    withMetadataOverlay = false,
-    isDropDisabled = false,
-    isDragDisabled = false,
-    isUploadDisabled = false,
-    minSize = 24,
-    postUploadAction,
-    imageSx,
-    fitContainer = false,
-    droppableData,
-    draggableData,
-    dropLabel,
-    isSelected = false,
-    isSelectedForCompare = false,
-    thumbnail = false,
-    noContentFallback = defaultNoContentFallback,
-    uploadElement = defaultUploadElement,
-    useThumbailFallback,
-    withHoverOverlay = false,
-    children,
-    dataTestId,
-    ...rest
-  } = props;
-
-  const openInNewTab = useCallback(
-    (e: MouseEvent) => {
-      if (!imageDTO) {
-        return;
-      }
-      if (e.button !== 1) {
-        return;
-      }
-      window.open(imageDTO.image_url, '_blank');
-    },
-    [imageDTO]
-  );
-
-  const ref = useRef<HTMLDivElement>(null);
-  useImageContextMenu(imageDTO, ref);
-
-  return (
-    <Flex
-      ref={ref}
-      width="full"
-      height="full"
-      alignItems="center"
-      justifyContent="center"
-      position="relative"
-      minW={minSize ? minSize : undefined}
-      minH={minSize ? minSize : undefined}
-      userSelect="none"
-      cursor={isDragDisabled || !imageDTO ? 'default' : 'pointer'}
-      sx={withHoverOverlay ? sx : baseStyles}
-      data-selected={isSelectedForCompare ? 'selectedForCompare' : isSelected ? 'selected' : undefined}
-      {...rest}
-    >
-      {imageDTO && (
-        <Flex
-          className="gallery-image-container"
-          w="full"
-          h="full"
-          position={fitContainer ? 'absolute' : 'relative'}
-          alignItems="center"
-          justifyContent="center"
-        >
-          <Image
-            src={thumbnail ? imageDTO.thumbnail_url : imageDTO.image_url}
-            fallbackStrategy="beforeLoadOrError"
-            fallbackSrc={useThumbailFallback ? imageDTO.thumbnail_url : undefined}
-            fallback={useThumbailFallback ? undefined : <IAILoadingImageFallback image={imageDTO} />}
-            onError={onError}
-            draggable={false}
-            w={imageDTO.width}
-            objectFit="contain"
-            maxW="full"
-            maxH="full"
-            borderRadius="base"
-            sx={imageSx}
-            data-testid={dataTestId}
-          />
-          {withMetadataOverlay && <ImageMetadataOverlay imageDTO={imageDTO} />}
-        </Flex>
-      )}
-      {!imageDTO && !isUploadDisabled && (
-        <UploadButton
-          isUploadDisabled={isUploadDisabled}
-          postUploadAction={postUploadAction}
-          uploadElement={uploadElement}
-          minSize={minSize}
-        />
-      )}
-      {!imageDTO && isUploadDisabled && noContentFallback}
-      {imageDTO && !isDragDisabled && (
-        <IAIDraggable
-          data={draggableData}
-          disabled={isDragDisabled || !imageDTO}
-          onClick={onClick}
-          onAuxClick={openInNewTab}
-        />
-      )}
-      {children}
-      {!isDropDisabled && <IAIDroppable data={droppableData} disabled={isDropDisabled} dropLabel={dropLabel} />}
-    </Flex>
-  );
-};
-
-export default memo(IAIDndImage);
-
-const UploadButton = memo(
-  ({
-    isUploadDisabled,
-    postUploadAction,
-    uploadElement,
-    minSize,
-  }: {
-    isUploadDisabled: boolean;
-    postUploadAction?: PostUploadAction;
-    uploadElement: ReactNode;
-    minSize: number;
-  }) => {
-    const { getUploadButtonProps, getUploadInputProps } = useImageUploadButton({
-      postUploadAction,
-      isDisabled: isUploadDisabled,
-    });
-
-    const uploadButtonStyles = useMemo<SystemStyleObject>(() => {
-      const styles: SystemStyleObject = {
-        minH: minSize,
-        w: 'full',
-        h: 'full',
-        alignItems: 'center',
-        justifyContent: 'center',
-        borderRadius: 'base',
-        transitionProperty: 'common',
-        transitionDuration: '0.1s',
-        color: 'base.500',
-      };
-      if (!isUploadDisabled) {
-        Object.assign(styles, {
-          cursor: 'pointer',
-          bg: 'base.700',
-          _hover: {
-            bg: 'base.650',
-            color: 'base.300',
-          },
-        });
-      }
-      return styles;
-    }, [isUploadDisabled, minSize]);
-
-    return (
-      <Flex sx={uploadButtonStyles} {...getUploadButtonProps()}>
-        <input {...getUploadInputProps()} />
-        {uploadElement}
-      </Flex>
-    );
-  }
-);
-
-UploadButton.displayName = 'UploadButton';

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

@@ -1,38 +0,0 @@
-import type { BoxProps } from '@invoke-ai/ui-library';
-import { Box } from '@invoke-ai/ui-library';
-import { useDraggableTypesafe } from 'features/dnd/hooks/typesafeHooks';
-import type { TypesafeDraggableData } from 'features/dnd/types';
-import { memo, useRef } from 'react';
-import { v4 as uuidv4 } from 'uuid';
-
-type IAIDraggableProps = BoxProps & {
-  disabled?: boolean;
-  data?: TypesafeDraggableData;
-};
-
-const IAIDraggable = (props: IAIDraggableProps) => {
-  const { data, disabled, ...rest } = props;
-  const dndId = useRef(uuidv4());
-
-  const { attributes, listeners, setNodeRef } = useDraggableTypesafe({
-    id: dndId.current,
-    disabled,
-    data,
-  });
-
-  return (
-    <Box
-      ref={setNodeRef}
-      position="absolute"
-      w="full"
-      h="full"
-      top={0}
-      insetInlineStart={0}
-      {...attributes}
-      {...listeners}
-      {...rest}
-    />
-  );
-};
-
-export default memo(IAIDraggable);

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

@@ -1,64 +0,0 @@
-import { Flex, Text } from '@invoke-ai/ui-library';
-import { memo } from 'react';
-
-type Props = {
-  isOver: boolean;
-  label?: string;
-  withBackdrop?: boolean;
-};
-
-const IAIDropOverlay = (props: Props) => {
-  const { isOver, label, withBackdrop = true } = props;
-  return (
-    <Flex position="absolute" top={0} right={0} bottom={0} left={0}>
-      <Flex
-        position="absolute"
-        top={0}
-        right={0}
-        bottom={0}
-        left={0}
-        w="full"
-        h="full"
-        bg={withBackdrop ? 'base.900' : 'transparent'}
-        opacity={0.7}
-        borderRadius="base"
-        alignItems="center"
-        justifyContent="center"
-        transitionProperty="common"
-        transitionDuration="0.1s"
-      />
-
-      <Flex
-        position="absolute"
-        top={0.5}
-        right={0.5}
-        bottom={0.5}
-        left={0.5}
-        opacity={1}
-        borderWidth={1.5}
-        borderColor={isOver ? 'invokeYellow.300' : 'base.500'}
-        borderRadius="base"
-        borderStyle="dashed"
-        transitionProperty="common"
-        transitionDuration="0.1s"
-        alignItems="center"
-        justifyContent="center"
-      >
-        {label && (
-          <Text
-            fontSize="lg"
-            fontWeight="semibold"
-            color={isOver ? 'invokeYellow.300' : 'base.500'}
-            transitionProperty="common"
-            transitionDuration="0.1s"
-            textAlign="center"
-          >
-            {label}
-          </Text>
-        )}
-      </Flex>
-    </Flex>
-  );
-};
-
-export default memo(IAIDropOverlay);

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

@@ -1,46 +0,0 @@
-import { Box } from '@invoke-ai/ui-library';
-import { useDroppableTypesafe } from 'features/dnd/hooks/typesafeHooks';
-import type { TypesafeDroppableData } from 'features/dnd/types';
-import { isValidDrop } from 'features/dnd/util/isValidDrop';
-import { AnimatePresence } from 'framer-motion';
-import { memo, useRef } from 'react';
-import { v4 as uuidv4 } from 'uuid';
-
-import IAIDropOverlay from './IAIDropOverlay';
-
-type IAIDroppableProps = {
-  dropLabel?: string;
-  disabled?: boolean;
-  data?: TypesafeDroppableData;
-};
-
-const IAIDroppable = (props: IAIDroppableProps) => {
-  const { dropLabel, data, disabled } = props;
-  const dndId = useRef(uuidv4());
-
-  const { isOver, setNodeRef, active } = useDroppableTypesafe({
-    id: dndId.current,
-    disabled,
-    data,
-  });
-
-  return (
-    <Box
-      ref={setNodeRef}
-      position="absolute"
-      top={0}
-      right={0}
-      bottom={0}
-      left={0}
-      w="full"
-      h="full"
-      pointerEvents={active ? 'auto' : 'none'}
-    >
-      <AnimatePresence>
-        {isValidDrop(data, active?.data.current) && <IAIDropOverlay isOver={isOver} label={dropLabel} />}
-      </AnimatePresence>
-    </Box>
-  );
-};
-
-export default memo(IAIDroppable);

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

@@ -1,24 +0,0 @@
-import type { SystemStyleObject } from '@invoke-ai/ui-library';
-import { Box, Skeleton } from '@invoke-ai/ui-library';
-import { memo } from 'react';
-
-const skeletonStyles: SystemStyleObject = {
-  position: 'relative',
-  height: 'full',
-  width: 'full',
-  '::before': {
-    content: "''",
-    display: 'block',
-    pt: '100%',
-  },
-};
-
-const IAIFillSkeleton = () => {
-  return (
-    <Skeleton sx={skeletonStyles}>
-      <Box position="absolute" top={0} insetInlineStart={0} height="full" width="full" />
-    </Skeleton>
-  );
-};
-
-export default memo(IAIFillSkeleton);

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

@@ -6,7 +6,7 @@ import type { ImageDTO } from 'services/api/types';
 
 type Props = { image: ImageDTO | undefined };
 
-export const IAILoadingImageFallback = memo((props: Props) => {
+const IAILoadingImageFallback = memo((props: Props) => {
   if (props.image) {
     return (
       <Skeleton

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/ImageMetadataOverlay.tsx

@@ -1,28 +0,0 @@
-import { Badge, Flex } from '@invoke-ai/ui-library';
-import { memo } from 'react';
-import type { ImageDTO } from 'services/api/types';
-
-type ImageMetadataOverlayProps = {
-  imageDTO: ImageDTO;
-};
-
-const ImageMetadataOverlay = ({ imageDTO }: ImageMetadataOverlayProps) => {
-  return (
-    <Flex
-      pointerEvents="none"
-      flexDirection="column"
-      position="absolute"
-      top={0}
-      insetInlineStart={0}
-      p={2}
-      alignItems="flex-start"
-      gap={2}
-    >
-      <Badge variant="solid" colorScheme="base">
-        {imageDTO.width} × {imageDTO.height}
-      </Badge>
-    </Flex>
-  );
-};
-
-export default memo(ImageMetadataOverlay);

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

@@ -1,89 +0,0 @@
-import { Box, Flex, Heading } from '@invoke-ai/ui-library';
-import { useAppSelector } from 'app/store/storeHooks';
-import { selectSelectedBoardId } from 'features/gallery/store/gallerySelectors';
-import { selectMaxImageUploadCount } from 'features/system/store/configSlice';
-import { memo } from 'react';
-import type { DropzoneState } from 'react-dropzone';
-import { useHotkeys } from 'react-hotkeys-hook';
-import { useTranslation } from 'react-i18next';
-import { useBoardName } from 'services/api/hooks/useBoardName';
-
-type ImageUploadOverlayProps = {
-  dropzone: DropzoneState;
-  setIsHandlingUpload: (isHandlingUpload: boolean) => void;
-};
-
-const ImageUploadOverlay = (props: ImageUploadOverlayProps) => {
-  const { dropzone, setIsHandlingUpload } = props;
-
-  useHotkeys(
-    'esc',
-    () => {
-      setIsHandlingUpload(false);
-    },
-    [setIsHandlingUpload]
-  );
-
-  return (
-    <Box position="absolute" top={0} right={0} bottom={0} left={0} zIndex={999} backdropFilter="blur(20px)">
-      <Flex position="absolute" top={0} right={0} bottom={0} left={0} bg="base.900" opacity={0.7} />
-      <Flex
-        position="absolute"
-        flexDir="column"
-        gap={4}
-        top={2}
-        right={2}
-        bottom={2}
-        left={2}
-        opacity={1}
-        borderWidth={2}
-        borderColor={dropzone.isDragAccept ? 'invokeYellow.300' : 'error.500'}
-        borderRadius="base"
-        borderStyle="dashed"
-        transitionProperty="common"
-        transitionDuration="0.1s"
-        alignItems="center"
-        justifyContent="center"
-        color={dropzone.isDragReject ? 'error.300' : undefined}
-      >
-        {dropzone.isDragAccept && <DragAcceptMessage />}
-        {!dropzone.isDragAccept && <DragRejectMessage />}
-      </Flex>
-    </Box>
-  );
-};
-export default memo(ImageUploadOverlay);
-
-const DragAcceptMessage = () => {
-  const { t } = useTranslation();
-  const selectedBoardId = useAppSelector(selectSelectedBoardId);
-  const boardName = useBoardName(selectedBoardId);
-
-  return (
-    <>
-      <Heading size="lg">{t('gallery.dropToUpload')}</Heading>
-      <Heading size="md">{t('toast.imagesWillBeAddedTo', { boardName })}</Heading>
-    </>
-  );
-};
-
-const DragRejectMessage = () => {
-  const { t } = useTranslation();
-  const maxImageUploadCount = useAppSelector(selectMaxImageUploadCount);
-
-  if (maxImageUploadCount === undefined) {
-    return (
-      <>
-        <Heading size="lg">{t('toast.invalidUpload')}</Heading>
-        <Heading size="md">{t('toast.uploadFailedInvalidUploadDesc')}</Heading>
-      </>
-    );
-  }
-
-  return (
-    <>
-      <Heading size="lg">{t('toast.invalidUpload')}</Heading>
-      <Heading size="md">{t('toast.uploadFailedInvalidUploadDesc_withCount', { count: maxImageUploadCount })}</Heading>
-    </>
-  );
-};

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

@@ -1,5 +1,6 @@
 import type { PopoverProps } from '@invoke-ai/ui-library';
 import commercialLicenseBg from 'public/assets/images/commercial-license-bg.png';
+import denoisingStrength from 'public/assets/images/denoising-strength.png';
 
 export type Feature =
   | 'clipSkip'
@@ -23,8 +24,10 @@ export type Feature =
   | 'dynamicPrompts'
   | 'dynamicPromptsMaxPrompts'
   | 'dynamicPromptsSeedBehaviour'
+  | 'globalReferenceImage'
   | 'imageFit'
   | 'infillMethod'
+  | 'inpainting'
   | 'ipAdapterMethod'
   | 'lora'
   | 'loraWeight'
@@ -46,6 +49,7 @@ export type Feature =
   | 'paramVAEPrecision'
   | 'paramWidth'
   | 'patchmatchDownScaleSize'
+  | 'rasterLayer'
   | 'refinerModel'
   | 'refinerNegativeAestheticScore'
   | 'refinerPositiveAestheticScore'
@@ -53,6 +57,9 @@ export type Feature =
   | 'refinerStart'
   | 'refinerSteps'
   | 'refinerCfgScale'
+  | 'regionalGuidance'
+  | 'regionalGuidanceAndReferenceImage'
+  | 'regionalReferenceImage'
   | 'scaleBeforeProcessing'
   | 'seamlessTilingXAxis'
   | 'seamlessTilingYAxis'
@@ -76,6 +83,24 @@ 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',
   },
@@ -101,7 +126,7 @@ export const POPOVER_DATA: { [key in Feature]?: PopoverData } = {
     href: 'https://support.invoke.ai/support/solutions/articles/151000158838-compositing-settings',
   },
   infillMethod: {
-    href: 'https://support.invoke.ai/support/solutions/articles/151000158841-infill-and-scaling',
+    href: 'https://support.invoke.ai/support/solutions/articles/151000158838-compositing-settings',
   },
   scaleBeforeProcessing: {
     href: 'https://support.invoke.ai/support/solutions/articles/151000158841',
@@ -114,6 +139,7 @@ export const POPOVER_DATA: { [key in Feature]?: PopoverData } = {
   },
   paramDenoisingStrength: {
     href: 'https://support.invoke.ai/support/solutions/articles/151000094998-image-to-image',
+    image: denoisingStrength,
   },
   paramHrf: {
     href: 'https://support.invoke.ai/support/solutions/articles/151000096700-how-can-i-get-larger-images-what-does-upscaling-do-',

invokeai/frontend/web/src/common/components/OverlayScrollbars/ScrollableContent.tsx

@@ -1,9 +1,13 @@
+import { combine } from '@atlaskit/pragmatic-drag-and-drop/combine';
+import { autoScrollForElements } from '@atlaskit/pragmatic-drag-and-drop-auto-scroll/element';
+import { autoScrollForExternal } from '@atlaskit/pragmatic-drag-and-drop-auto-scroll/external';
 import type { ChakraProps } from '@invoke-ai/ui-library';
 import { Box, Flex } from '@invoke-ai/ui-library';
 import { getOverlayScrollbarsParams } from 'common/components/OverlayScrollbars/constants';
+import type { OverlayScrollbarsComponentRef } from 'overlayscrollbars-react';
 import { OverlayScrollbarsComponent } from 'overlayscrollbars-react';
 import type { CSSProperties, PropsWithChildren } from 'react';
-import { memo, useMemo } from 'react';
+import { memo, useEffect, useMemo, useState } from 'react';
 
 type Props = PropsWithChildren & {
   maxHeight?: ChakraProps['maxHeight'];
@@ -11,17 +15,38 @@ type Props = PropsWithChildren & {
   overflowY?: 'hidden' | 'scroll';
 };
 
-const styles: CSSProperties = { height: '100%', width: '100%' };
+const styles: CSSProperties = { position: 'absolute', top: 0, left: 0, right: 0, bottom: 0 };
 
 const ScrollableContent = ({ children, maxHeight, overflowX = 'hidden', overflowY = 'scroll' }: Props) => {
   const overlayscrollbarsOptions = useMemo(
     () => getOverlayScrollbarsParams(overflowX, overflowY).options,
     [overflowX, overflowY]
   );
+  const [os, osRef] = useState<OverlayScrollbarsComponentRef | null>(null);
+  useEffect(() => {
+    const osInstance = os?.osInstance();
+
+    if (!osInstance) {
+      return;
+    }
+
+    const element = osInstance.elements().viewport;
+
+    // `pragmatic-drag-and-drop-auto-scroll` requires the element to have `overflow-y: scroll` or `overflow-y: auto`
+    // else it logs an ugly warning. In our case, using a custom scrollbar library, it will be 'hidden' by default.
+    // To prevent the erroneous warning, we temporarily set the overflow-y to 'scroll' and then revert it back.
+    const overflowY = element.style.overflowY; // starts 'hidden'
+    element.style.setProperty('overflow-y', 'scroll', 'important');
+    const cleanup = combine(autoScrollForElements({ element }), autoScrollForExternal({ element }));
+    element.style.setProperty('overflow-y', overflowY);
+
+    return cleanup;
+  }, [os]);
+
   return (
     <Flex w="full" h="full" maxHeight={maxHeight} position="relative">
       <Box position="absolute" top={0} left={0} right={0} bottom={0}>
-        <OverlayScrollbarsComponent defer style={styles} options={overlayscrollbarsOptions}>
+        <OverlayScrollbarsComponent ref={osRef} style={styles} options={overlayscrollbarsOptions}>
           {children}
         </OverlayScrollbarsComponent>
       </Box>

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

@@ -0,0 +1,57 @@
+type Props = {
+  /**
+   * The amplitude of the wave. 0 is a straight line, higher values create more pronounced waves.
+   */
+  amplitude: number;
+  /**
+   * The number of segments in the line. More segments create a smoother wave.
+   */
+  segments?: number;
+  /**
+   * The color of the wave.
+   */
+  stroke: string;
+  /**
+   * The width of the wave.
+   */
+  strokeWidth: number;
+  /**
+   * The width of the SVG.
+   */
+  width: number;
+  /**
+   * The height of the SVG.
+   */
+  height: number;
+};
+
+const WavyLine = ({ amplitude, stroke, strokeWidth, width, height, segments = 5 }: Props) => {
+  // Calculate the path dynamically based on waviness
+  const generatePath = () => {
+    if (amplitude === 0) {
+      // If waviness is 0, return a straight line
+      return `M0,${height / 2} L${width},${height / 2}`;
+    }
+
+    const clampedAmplitude = Math.min(height / 2, amplitude); // Cap amplitude to half the height
+    const segmentWidth = width / segments;
+    let path = `M0,${height / 2}`; // Start in the middle of the left edge
+
+    // Loop through each segment and alternate the y position to create waves
+    for (let i = 1; i <= segments; i++) {
+      const x = i * segmentWidth;
+      const y = height / 2 + (i % 2 === 0 ? clampedAmplitude : -clampedAmplitude);
+      path += ` Q${x - segmentWidth / 2},${y} ${x},${height / 2}`;
+    }
+
+    return path;
+  };
+
+  return (
+    <svg width={width} height={height} viewBox={`0 0 ${width} ${height}`} xmlns="http://www.w3.org/2000/svg">
+      <path d={generatePath()} fill="none" stroke={stroke} strokeWidth={strokeWidth} />
+    </svg>
+  );
+};
+
+export default WavyLine;

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);